From 2bd47f08413a63db3ae3002bea65edea21b2853e Mon Sep 17 00:00:00 2001
From: Alex Moreo <alejandro.moreo@isti.cnr.it>
Date: Mon, 6 Dec 2021 18:25:47 +0100
Subject: [PATCH] updating the documentation

---
 docs/build/html/genindex.html   |  14 +-
 docs/build/html/objects.inv     | Bin 2717 -> 2703 bytes
 docs/build/html/quapy.data.html | 767 +++++++++++++++++++++++++++-----
 docs/build/html/quapy.html      |  87 +++-
 docs/build/html/searchindex.js  |   2 +-
 quapy/data/base.py              | 306 +++++++++++--
 quapy/data/datasets.py          |  93 +++-
 quapy/data/preprocessing.py     | 116 +++--
 quapy/data/reader.py            |  30 +-
 9 files changed, 1197 insertions(+), 218 deletions(-)

diff --git a/docs/build/html/genindex.html b/docs/build/html/genindex.html
index a446bfe..faa4cf5 100644
--- a/docs/build/html/genindex.html
+++ b/docs/build/html/genindex.html
@@ -255,12 +255,8 @@
         <li><a href="quapy.method.html#quapy.method.neural.QuaNetModule.device">(quapy.method.neural.QuaNetModule property)</a>
 </li>
       </ul></li>
-      <li><a href="quapy.data.html#quapy.data.datasets.df_replace">df_replace() (in module quapy.data.datasets)</a>
-</li>
       <li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.dimensions">dimensions() (quapy.classification.neural.TextClassifierNet method)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="quapy.classification.html#quapy.classification.neural.CNNnet.document_embedding">document_embedding() (quapy.classification.neural.CNNnet method)</a>
 
       <ul>
@@ -269,6 +265,8 @@
         <li><a href="quapy.classification.html#quapy.classification.neural.TextClassifierNet.document_embedding">(quapy.classification.neural.TextClassifierNet method)</a>
 </li>
       </ul></li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="quapy.html#quapy.util.download_file">download_file() (in module quapy.util)</a>
 </li>
       <li><a href="quapy.html#quapy.util.download_file_if_not_exists">download_file_if_not_exists() (in module quapy.util)</a>
@@ -462,19 +460,15 @@
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="quapy.data.html#quapy.data.preprocessing.index">index() (in module quapy.data.preprocessing)</a>
-
-      <ul>
-        <li><a href="quapy.data.html#quapy.data.preprocessing.IndexTransformer.index">(quapy.data.preprocessing.IndexTransformer method)</a>
 </li>
-      </ul></li>
       <li><a href="quapy.data.html#quapy.data.preprocessing.IndexTransformer">IndexTransformer (class in quapy.data.preprocessing)</a>
 </li>
       <li><a href="quapy.method.html#quapy.method.neural.QuaNetModule.init_hidden">init_hidden() (quapy.method.neural.QuaNetModule method)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="quapy.method.html#quapy.method.base.isaggregative">isaggregative() (in module quapy.method.base)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="quapy.html#quapy.isbinary">isbinary() (in module quapy)</a>
 
       <ul>
diff --git a/docs/build/html/objects.inv b/docs/build/html/objects.inv
index 012fec8af06cd9d60b80b7fe755113a95859a5c7..6216f98ce5cfd03d3232594af5482c24ed92b46f 100644
GIT binary patch
delta 2610
zcmV-23eEMM6^|8=cz-q$fbV_^rLtGEGE=pe+#Fj;Tq}9xk>kytP!QRYuqFWpfNU$L
zyhdJcpJW04i4-B4_~9I8Mnj^%2AYlT2Ke*G0q4hAe*7_G$svW=53@h?k!UZo^!xJI
z^*?6USLM+-#X^uRiLoS%8pOH{Mp2>+<enuWEG=5Fx38GKEPvRJ2ub3vu;ZZGmAx)x
zW}gPsxbveek;PbwhEplofkZjxI1|(B$~hz?mfuVf$~oKM>D7sEXhX>{6<fwLUsV(i
z9H)UMO9_i^A08-3&xz4tMG1=!8BmEJ+dz^Kx(hS#njg;pyWCe6<IN$({D=hk6Es|T
zV-8#%z3_|m(|<CUjVsu6My?eEw{i`h%FGYNKeyF6;7=SA3OtP2FTkS&UP(Op7((Qg
z4>Sb7+?Nyu$|&Qsgh?kK=u&ZB8IOJ|1B!2@C~)42p5R@cv^<20h&^nS5EU79>J?M<
ze7f-4SEa7N8|KMm{NOXcuVRYX*w->uV(Dvo$FJ%aI)6|Sa(XZx@9(h0BG}Am5hE=0
zuax1W%!xid7O$By>o!m&TG68Q^RlLTjQxzJGIUIIEI``>jhm&b|KJ-10dn&>GEj~@
z$A-%s=j2zMk_4qp2q@TCN=`Nh2_x}|a!rFb>BAR%s5rGzp6w_WU7Tqr=>f55ou@>u
zRf?24Du0-w^El3iP!+I@v1%Nk=sXDIfq41(_Sty=I-)oWQ&e@|qxV8$DV%#SCTR?l
z7I*_`3dt=~e>V}v#;5v(==Wogo<x{y|BMMvk-(YqS-L|zP}Lolj9VLRqyj<{cn_<_
zd72nlF*{HPk1>#(CXRvQG=~fvpXp@6VX5ngiGMt&N1woLR3cTW323=Q_odZ64aq`V
z&a!goL9yY8I?*BFp6N_Xr;u#`RTVf2d1cO-j;18y6tkMr^Fz_3OiRL{s;NbzEy#F}
ze!IPIl{of2IAP2Q&Y7sDB!M^K#gK1A%5oj!z);I+%OR*ZqQYscH}oqfv%5AO`RHCd
z)PGaGyJFg+9M_Q^D8fmC-Wa!<q#q#7%Nq|G8roNK<xasgl!k8PCV)6PT%?wRhZs=I
z(nCgt4@pH{nqZz(<8j4Ec$c5$mLyv{3WsL<!EOSTf@K+K-S<kk$h5I|br%+D^(;J;
zYqL2?b0~|WREOg64gj1pKKc%S(K^B#p?};=0&0YNs!UoU9LEkKVA0y5?e>#xU$&oY
z@cLp>oLPvxq{;Zknax-;z!bS&wL+Lfs*1Z;aHrUfj@mWnR@M*}jqN&O)emo*+KfYF
zjLH3|_G&qFxby_ig|N_wv={rQl@+RXD=*cB7kh9K$0Sp!E(lCzEykrKs`?3*Vt;Do
z8pJI1!gw;4lYI@O@y4ys8=qb=yWL47`c*AIRMi3ej_CSjT+(RC<K({wAt6EP43(W{
z*lZ|92Wzi9Enxbl8`YSc5h?}3xw<UxBy;H)Rply9RaJz#+Z{HDL)IQt%raeR$@&(m
z1*t_TvgAO;G9FUgH{6hvNCF-#b$^{y1!rv>A-RTFO4Zv4{=U*|NDw8iia;C8;4Z{j
z+iG#spP=Q53-h!(iFZ2=yCUWJ6QY~j+y0`s4f#mA`M+t|W(BHlTpfKm=5@3cLKPCa
zpeUl5e)zzPSH;BY#`f`sCbxQD+<f<LJofZ^RZm*|IOJm$c}<%g0pU^3)PJBjVZ0wR
zoGmp%>j%#_gw@qLZrtY&sjbSG$B73ucxT#0QD}c_^)*an8AMk>G{}{0;RkOOhhT?u
zlor`Ha2lbz=^QRf0rTp?)6iBPzQN}S4?Nd{Pj9c9AXG`<pUDGf-1%bZVHPDF#x5EZ
zA_i!Vr-A3oM<0tUAJrdE{eRJXwZ30`dGNiqinP4>9o;|8zXm{sxzGyae}Tf4O!M~~
zVp*(JmsqW!$)CmVZUNw9xOcVKiiun>A(n(H1)^D`dtiUPJ9;>&k`8k<HOTX7_I79f
z<7pb@@gAmGuDygKmP_qKfaIQo*t0b8G0t-R*{eIBL-$9`I!xDZ0DrmfRXUMAd!oKj
zcosKl>S3uG5oT62w1LOY>|tTb?=H?W+cq%I7|?LS)YT1cg5~^)9d04rFhi8k4J=I6
zyz<*iTLs%pTZP(9TLsuoTlpC!m`wtVr0vEN?do-O1ZJ<Fmp5~dYoX--wYc*GJa`ix
z{lvd|nc(T4Kln)3b$`W|veLljN7(&%VWx{29kVRgH`up1pAIhZCY`YFa*DotMiw(P
zY(45z=}Y~ds(wIs4{3hkVbDR?h1ZA1+^i}d@%>5t<-E~sAo%V7nt-nLtBK`azM5zb
zzG=d^*PAAqXGv&6x>kfHmhc>G;S8P*d&cndFe1)8-hTcL-+$pABi_5{b`<pwb_^m~
zG@4iSxxLnC?k-vFk-CUhJ6A5EE03{K0a=xTEu6L^8$I7F?(fj*%i{j_e!g}nT)Q|N
z#|Mt%Bg$DyV(Te>2J?yiU6kvb>{8t0eV3DnAogi6sEGOX#(?mnI;5d4z&!zVIi9KK
z3?_LHo4Y2jE`LP?GLc{hw~GZ8;b$C6#$BUVaiyDGs3S_$r7B{_r6=|Vkr%(^H70RX
z-*-@H_yOdyl(&nE2Ex#{jI3FgKU!jqQZ>Frdy*tTy>J)52W5@$2#ptT`YHT)5AjR!
zIB1Ar_MpmNc@Qw<EZzqpIRsxLN6*Yw`b3~&sC}@xh<|pAT}GU1KsCaIZ{IQu#Wy<~
zq8Fpc|B25tN>tpxJ!A{=0x8)umaLj*XXpBoy6j9j>F}B0PWoJCf|DW-e|FO6?C?(7
zTxJAIAVmUNZ#Iv5J>g6)`h}BZ4VcG!!&dOH&bDl{QNarp4GcrD;0$`O1;^}}7JxyI
zv)~MPl79t7So9`OnH=p8x^cDeLK}jG`fJ>~6FtFQs%p&CRx}}aSHE8~PL8t|pc~AQ
zIOH5My^h@|4kueV8dAJ|W+kS|<?-(T>Bi9<^YpluEdOv`70qJ~SOOwjM43eJuB!C0
z{i<b^gTSd^8YP*qH>$tlg0>_DH>pmS#b}0}Uw_4a(Vk`FRcAOaCPJD*I$FqHfW$8;
zB#47ryzzK^_XJjToPJ%}&Y%*qT+Mv=;H}QP`YRhkCO;-Do?U;M)yIlfs?GfLrev$t
z>1f^Vo(idq(rej1UbkIVpF3|gs}7Yd9=q?SRp+jjI-p&zn;g{^@180##lcx~@M@)|
zs(;ik47CL7V|CYdK+De*=r+YmTe?+!v}{#;A>r!OtU|R~{2S6(d!b}{EUV-H{`y<Y
z>ThKhgZl1D&2odL{CHiTXa=DJM5(ik3?0K&hswsq^}T8_K7g-|%CfYpqhPc(oSdfo
zIm>bUf_Gs4AbwBK@Ws2C`BVBGZ1E|)9xJSQyMNaHU|vVCN@hLLR^2n}zUWnniy}96
UEmj^Yh05GHTj{p{2T=nY!9r~ob^rhX

delta 2624
zcmV-G3cvM_6`d83cz?JNfbV_^r8ZZycBU$qy*aja*A>a589C18go4PHgqQ@l0AyQx
z+SkbI<w*kYPoxM@#1H2%Ga3^8HGUf14G`q-2b>>g`SGWWC5IGdKhA#FSE9Yl(jUre
zw||}8-jrA46bnJNB*v03Y7pxd7)6OPkb9Phu(W8w-oIh`x_@9hA|#2w!H$C}SJt|a
znSB~i<Iaz^L>6r+3QnbD2NLC&<4jDiE9a1qSbjG}DCca0r&lMwV;@S6sn{}}`KqFD
z;5ZF5SxQ)R|MWybdQOZED@s^=$bd=&*#?q?&|R2@*Zgqy-{ros7;g?K=0_yRAE4pN
z8gt<C=!IXbpMRIZ`nZBk*U7bl;JsXfr|RaX;-CBK9`I+52?ZXe+b_VQ1l~wIc^g8+
zl`9&85BDWSfg;K{En&jR6<x~DtIng}s{_UNQWQ9DMbGddPg<TrdBh$zN{I4|I`oRE
zYCfI&?W<BF@Q!&h89(^U@2i+%Hukkl6<GS3KJc6Rg?|o|gq$9X$NL8?u?RLZTEqwo
z{VQcSDPy8fjm2B0x^){U6Rl{``ej*DJ=%UoQxQ5Q+83bhfyT|!)xYtLf&j7k92qD^
zo@2vBj&t%GPDz4NCIl30EF~wKgM^XzM46_+n)KxhHdNf&D9d&fi!RQzlk|XCw9Zo^
z*D6Fx?SB<a-gz8nL#T3CMqf1!P*ffS@<6=)eE;Iy0PRtng(<44?@@apu@ufV7!x#x
zNejGzG==1zslOW!V`Ec&LiF1)NKGQlwSC3}r%2#T*(}|m9jNRMOUA7`ZKMK16Zi<L
z#(A0;STQ?L2a7R~oF<Ne<1~j19G~fA!eOcNh<}MJr$?W_Y*Zjsp$TZYME9lDH4Vu^
zTh6kw=|QpKh&s?A;U4KsOedFZ096?{3OO?8OvkPy;^ecM)bpxnQidhrkk!<pQL;rG
z@)VawZ?8Mrf{gd*pZAZg9LWb`j*!koHKz%@3onLzCsLLRAqR$9k6SiDIU?ncWBo*+
zvVT&$!R^RLkJ=)i>+KoS9_P4<^gt0#67<fv)hxe)G_Q|5XlQ6-%9U$9$*=IHsG}iQ
zbt5;8bu{2etxpdzpqQnHj0zu;3I#O5JgM5_ijnXkKg%siwssT_&3=g8ge(Qiywtkx
zm2eUIWAWxLEYxydcqrH1<|NIb%+^xv+JDCz0C3Lu=pzS3=?HIxGBXLN5$>rnX^C(g
zJBWZqX^XPkPqua0ezL*q!K65|5P40L@r5&+wq}4Savilom_w?v%{OqT*tL$@73WsH
zAuI~pRm7?u-hFD*4v{e?_oK?I_1WRlk)jK3p%H2CKAe_%sM<cglxJS7!9^UCOn-&C
zATSlR7?+l)>L*x=siky~ZmC!5ld+uo*FYNIx%GYHaT>GPokXHv)pAB<9l#%m&R@m_
zjg~x4{&Nr#5~S`>**R2aLopgydns%I(@z1Z#^j7pDG<)puzZlrrD9a2t2k9z5$f*0
z*dPvByHPRAbfzWiXSx=o7Nv-i1AiIIcu4Ueb3;-h33#y7IH?TIx^sl&8e%C`?`!zm
zO0z>kl(<R)Z7_q|B4=f*#Z7;LmNzcU)9NPP?Ktd;kmpZ`?(XmVi|jV!nsoDj)3VJ9
zR6R*M`f|+caw~*NBy>Vicr$$(!i!h=#Og`=@s1|<dZXU_IB`7o^m|oLT7P{$^K0dK
zO`9hH;Ze?1qc~x_?=zfxYJ}D+2QI?uYF#%zcnGPjikQcV8#VZ-+(l7ndu!D-jAt1{
zS57p@$hPo<&#ptT!x>78?CUs<(A{(f7o~uCbrLpoFAqO)^n?eV>%phDS56QrCGd~r
zfg|pGvGnK`B^{<;G$@1*(0?4y4xTT+`t->1tNP=qKbo)BkBcu)zGJIM%e&vu<MaGm
z092TPRv`ZY3YRj?KXQm=u~uDTwSp#p6u-L(fKSJLsKr)H<bnyYBvdI7%_7|c`|HEe
z!$_5Mn9<ZA&(ZAd&ivc6Ym~)%bj@<@B^<F_Y9j(9_Z-BYrHN1HEPvOZy{hv$bbZvU
z!*u-)ko%6(iS*eM^@YNVxJy%yo~jXHW<^6AI0t7B3zL3#ah}n(fqD9Xh7%^QZg3MU
z=TGc#3+aX#B86^XVY23x-(K1(*k;-))Na};z;@couTz5cNr0BL&3K|+y^fB+?Dfm?
zZtgJ_O8y^<2S31*H-F))pZGVgE_nXik3Q0MUh$>OG_d(hy&o^kbTOl2mgV{Z`!?s(
z!6n|L6V_c$QFl+zVupszM}0DVsb8GcCx-Ws<`)i^4#F<H&ot&?RdMF{@9Hn-jb;PE
zZ~xZ>bj@E)Ecf))M02oB6UIH?G|@a$LKD(8BQ&vuXJZRv@P9PeGlrjq5pibm_Vai6
z3HKQB-k{r2)IZqKiD=PiUghWZTBEtUWVJ`?B3kWSxrnYj+DZjvRS32)+Kz1Wa<_PV
zK&vl{$NR_m+97f6;&2=vIF64fXDNxTr}!Dn$M<(pu5+?WargIKP9lQzPlG{)&#yNI
zgdf!*40QqS0e`5=@eDm@Fv)}Txohz1QbeFG671kMSWppu#<67F)q52q-RwdgQKE*b
z@Ew;<><uC>eq3x!;HW-0p~CPJ$Ym*S=NAoxp^qzBvo3!{#Tun@e2MlXNq~CcE`FfO
z8sXs@FW~ek{CE%XYjGSjL^FF(Wv@I47;+ZxgOD7YuYZxFXJ#vWB2Yfm-q~D4yZJ67
z&efqBVZyg=8HVB`A`ae*QRIK(^NbP|&u<Ueg1kaX_KYQ~=IrcT52?$}l#>ph3GSrN
zWhOW&@~~$oea;5&q|IeUumn;hp!KHosMizD<f30VN!EaQyf<tG59@5pMjPe4P*K3p
z1Pjif1%F#`%$8{Z7_>MG&VVIZP=rNo@|4NZ_Mi(_3oo=GSg60oy*tqp+@&hVOl?II
zf_L@%HRI$sdj-0|9En5DA=B&FjpA^!m7^iW>t|MCDqSA`4v;P!%`s1pYsvDf^QtHw
zbHEZ1*&@m$f)ACYkF8fNs|*BA3DYRaguPS!S$`R{B`LT`b*d~zGxYo_{)_f38?QRU
zc`*^v6w=W`_5vh+O(8)X)Z&fD<EtmI%H#Cw(smsxA<NawhbwP&KGdK65Hk5GVe#zt
z)2zN$lu~8pr#B^ArA}Ata*tF<)hWG_?dx^fW%d2_R<Y_*S>kK={j}=d%~CtG+jSG8
z+JEBRTP3ErIBPE6tkhJM`h}sEV12Ew+74*>nF3v=cxg+Qs;`!%iZ3MGoQhSbR*8Q>
z8fz<*Ot)oq{NJDd6|?%|okgSma-(LsK~sLbt#34q&<>*1S$c*}$5ofg!o~RBv=~?5
ztE1{!+SO4o+8RzqQ~sRgIDW-DFn^)HCpl>N1mDd3ZT}9o_%>e;*1X+6Yk$G7BUlBq
io@guYnRQ?Es>DSR8@oMLUMq#l*g0G2vi}Ey?@?XFK`?0m

diff --git a/docs/build/html/quapy.data.html b/docs/build/html/quapy.data.html
index 355bc52..3f7df30 100644
--- a/docs/build/html/quapy.data.html
+++ b/docs/build/html/quapy.data.html
@@ -63,45 +63,144 @@
 <dt class="sig sig-object py" id="quapy.data.base.Dataset">
 <em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">Dataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">quapy.data.base.LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">test</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">quapy.data.base.LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">vocabulary</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">dict</span><span class="p"><span class="pre">]</span></span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset" title="Permalink to this definition">¶</a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
+<p>Abstraction of training and test <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> objects.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>training</strong> – a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> instance</p></li>
+<li><p><strong>test</strong> – a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> instance</p></li>
+<li><p><strong>vocabulary</strong> – if indicated, is a dictionary of the terms used in this textual dataset</p></li>
+<li><p><strong>name</strong> – a string representing the name of the dataset</p></li>
+</ul>
+</dd>
+</dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.SplitStratified">
 <em class="property"><span class="pre">classmethod</span> </em><span class="sig-name descname"><span class="pre">SplitStratified</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">collection</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">quapy.data.base.LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">train_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.SplitStratified" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Generates a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> from a stratified split of a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> instance.
+See <a class="reference internal" href="#quapy.data.base.LabelledCollection.split_stratified" title="quapy.data.base.LabelledCollection.split_stratified"><code class="xref py py-meth docutils literal notranslate"><span class="pre">LabelledCollection.split_stratified()</span></code></a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>collection</strong> – <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a></p></li>
+<li><p><strong>train_size</strong> – the proportion of training documents (the rest conforms the test split)</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an instance of <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.binary">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">binary</span></span><a class="headerlink" href="#quapy.data.base.Dataset.binary" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns True if the training collection is labelled according to two classes</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>boolean</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.classes_">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">classes_</span></span><a class="headerlink" href="#quapy.data.base.Dataset.classes_" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>The classes according to which the training collection is labelled</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>The classes according to which the training collection is labelled</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.kFCV">
 <em class="property"><span class="pre">classmethod</span> </em><span class="sig-name descname"><span class="pre">kFCV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">quapy.data.base.LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">nfolds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nrepeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.kFCV" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Generator of stratified folds to be used in k-fold cross validation. This function is only a wrapper around
+<a class="reference internal" href="#quapy.data.base.LabelledCollection.kFCV" title="quapy.data.base.LabelledCollection.kFCV"><code class="xref py py-meth docutils literal notranslate"><span class="pre">LabelledCollection.kFCV()</span></code></a> that returns <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> instances made of training and test folds.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>nfolds</strong> – integer (default 5), the number of folds to generate</p></li>
+<li><p><strong>nrepeats</strong> – integer (default 1), the number of rounds of k-fold cross validation to run</p></li>
+<li><p><strong>random_state</strong> – integer (default 0), guarantees that the folds generated are reproducible</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>yields <cite>nfolds * nrepeats</cite> folds for k-fold cross validation as instances of <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.load">
-<em class="property"><span class="pre">classmethod</span> </em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">callable</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.load" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<em class="property"><span class="pre">classmethod</span> </em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">loader_kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.load" title="Permalink to this definition">¶</a></dt>
+<dd><p>Loads a training and a test labelled set of data and convert it into a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> instance.
+The function in charge of reading the instances must be specified. This function can be a custom one, or any of
+the reading functions defined in <a class="reference internal" href="#module-quapy.data.reader" title="quapy.data.reader"><code class="xref py py-mod docutils literal notranslate"><span class="pre">quapy.data.reader</span></code></a> module.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>train_path</strong> – string, the path to the file containing the training instances</p></li>
+<li><p><strong>test_path</strong> – string, the path to the file containing the test instances</p></li>
+<li><p><strong>loader_func</strong> – a custom function that implements the data loader and returns a tuple with instances and
+labels</p></li>
+<li><p><strong>classes</strong> – array-like, the classes according to which the instances are labelled</p></li>
+<li><p><strong>loader_kwargs</strong> – any argument that the <cite>loader_func</cite> function needs in order to read the instances.
+See <a class="reference internal" href="#quapy.data.base.LabelledCollection.load" title="quapy.data.base.LabelledCollection.load"><code class="xref py py-meth docutils literal notranslate"><span class="pre">LabelledCollection.load()</span></code></a> for further details.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> object</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.n_classes">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">n_classes</span></span><a class="headerlink" href="#quapy.data.base.Dataset.n_classes" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>The number of classes according to which the training collection is labelled</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>integer</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.stats">
-<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.stats" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">show</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.Dataset.stats" title="Permalink to this definition">¶</a></dt>
+<dd><p>Returns (and eventually prints) a dictionary with some stats of this dataset. E.g.,:</p>
+<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">&#39;kindle&#39;</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">data</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">Dataset</span><span class="o">=</span><span class="n">kindle</span> <span class="c1">#tr-instances=3821, #te-instances=21591, type=&lt;class &#39;scipy.sparse.csr.csr_matrix&#39;&gt;, #features=4403, #classes=[0 1], tr-prevs=[0.081, 0.919], te-prevs=[0.063, 0.937]</span>
+</pre></div>
+</div>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>show</strong> – if set to True (default), prints the stats in standard output</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a dictionary containing some stats of this collection for the training and test collections. The keys
+are <cite>train</cite> and <cite>test</cite>, and point to dedicated dictionaries of stats, for each collection, with keys
+<cite>#instances</cite> (the number of instances), <cite>type</cite> (the type representing the instances),
+<cite>#features</cite> (the number of features, if the instances are in array-like format), <cite>#classes</cite> (the classes of
+the collection), <cite>prevs</cite> (the prevalence values for each class)</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.Dataset.vocabulary_size">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">vocabulary_size</span></span><a class="headerlink" href="#quapy.data.base.Dataset.vocabulary_size" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>If the dataset is textual, and the vocabulary was indicated, returns the size of the vocabulary</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>integer</p>
+</dd>
+</dl>
+</dd></dl>
 
 </dd></dl>
 
@@ -109,161 +208,480 @@
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection">
 <em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">LabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">instances</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes_</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection" title="Permalink to this definition">¶</a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
-<p>A LabelledCollection is a set of objects each with a label associated to it.</p>
+<p>A LabelledCollection is a set of objects each with a label associated to it. This class implements many sampling
+routines.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>instances</strong> – array-like (np.ndarray, list, or csr_matrix are supported)</p></li>
+<li><p><strong>labels</strong> – array-like with the same length of instances</p></li>
+<li><p><strong>classes</strong> – optional, list of classes from which labels are taken. If not specified, the classes are inferred
+from the labels. The classes must be indicated in cases in which some of the labels might have no examples
+(i.e., a prevalence of 0)</p></li>
+</ul>
+</dd>
+</dl>
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.Xy">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">Xy</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.Xy" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Gets the instances and labels. This is useful when working with <cite>sklearn</cite> estimators, e.g.:</p>
+<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">svm</span> <span class="o">=</span> <span class="n">LinearSVC</span><span class="p">()</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="o">*</span><span class="n">my_collection</span><span class="o">.</span><span class="n">Xy</span><span class="p">)</span>
+</pre></div>
+</div>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>a tuple <cite>(instances, labels)</cite> from this collection</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.artificial_sampling_generator">
 <span class="sig-name descname"><span class="pre">artificial_sampling_generator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_prevalences</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">101</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.artificial_sampling_generator" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>A generator of samples that implements the artificial prevalence protocol (APP). The APP consists of exploring
+a grid of prevalence values (e.g., [0, 0.05, 0.1, 0.15, …, 1]), and generating all valid combinations of
+prevalence values for all classes (e.g., for 3 classes, samples with [0, 0, 1], [0, 0.05, 0.95], …,
+[1, 0, 0] prevalence values of size <cite>sample_size</cite> will be yielded). The number of samples for each valid
+combination of prevalence values is indicated by <cite>repeats</cite></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>sample_size</strong> – the number of instances in each sample</p></li>
+<li><p><strong>n_prevalences</strong> – the number of prevalence points to be taken from the [0,1] interval (including the
+limits {0,1}). E.g., if <cite>n_prevalences=11</cite>, then the prevalence points to take are [0, 0.1, 0.2, …, 1]</p></li>
+<li><p><strong>repeats</strong> – the number of samples to generate for each valid combination of prevalence values (default 1)</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>yield samples generated at artificially controlled prevalence values</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.artificial_sampling_index_generator">
 <span class="sig-name descname"><span class="pre">artificial_sampling_index_generator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_prevalences</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">101</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.artificial_sampling_index_generator" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>A generator of sample indexes implementing the artificial prevalence protocol (APP).
+The APP consists of exploring
+a grid of prevalence values (e.g., [0, 0.05, 0.1, 0.15, …, 1]), and generating all valid combinations of
+prevalence values for all classes (e.g., for 3 classes, samples with [0, 0, 1], [0, 0.05, 0.95], …,
+[1, 0, 0] prevalence values of size <cite>sample_size</cite> will be yielded). The number of sample indexes for each valid
+combination of prevalence values is indicated by <cite>repeats</cite></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>sample_size</strong> – the number of instances in each sample (i.e., length of each index)</p></li>
+<li><p><strong>n_prevalences</strong> – the number of prevalence points to be taken from the [0,1] interval (including the
+limits {0,1}). E.g., if <cite>n_prevalences=11</cite>, then the prevalence points to take are [0, 0.1, 0.2, …, 1]</p></li>
+<li><p><strong>repeats</strong> – the number of samples to generate for each valid combination of prevalence values (default 1)</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>yield the indexes that generate the samples according to APP</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.binary">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">binary</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.binary" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns True if the number of classes is 2</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>boolean</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.counts">
 <span class="sig-name descname"><span class="pre">counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.counts" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns the number of instances for each of the classes of interest.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>a np.ndarray of shape <cite>(n_classes)</cite> with the number of instances of each class, in the same order
+as listed by <cite>self.classes_</cite></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.kFCV">
 <span class="sig-name descname"><span class="pre">kFCV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nfolds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nrepeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.kFCV" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Generator of stratified folds to be used in k-fold cross validation.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>nfolds</strong> – integer (default 5), the number of folds to generate</p></li>
+<li><p><strong>nrepeats</strong> – integer (default 1), the number of rounds of k-fold cross validation to run</p></li>
+<li><p><strong>random_state</strong> – integer (default 0), guarantees that the folds generated are reproducible</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>yields <cite>nfolds * nrepeats</cite> folds for k-fold cross validation</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.load">
-<em class="property"><span class="pre">classmethod</span> </em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.load" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<em class="property"><span class="pre">classmethod</span> </em><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loader_func</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">callable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">loader_kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.load" title="Permalink to this definition">¶</a></dt>
+<dd><p>Loads a labelled set of data and convert it into a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> instance. The function in charge
+of reading the instances must be specified. This function can be a custom one, or any of the reading functions
+defined in <a class="reference internal" href="#module-quapy.data.reader" title="quapy.data.reader"><code class="xref py py-mod docutils literal notranslate"><span class="pre">quapy.data.reader</span></code></a> module.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>path</strong> – string, the path to the file containing the labelled instances</p></li>
+<li><p><strong>loader_func</strong> – a custom function that implements the data loader and returns a tuple with instances and
+labels</p></li>
+<li><p><strong>classes</strong> – array-like, the classes according to which the instances are labelled</p></li>
+<li><p><strong>loader_kwargs</strong> – any argument that the <cite>loader_func</cite> function needs in order to read the instances, i.e.,
+these arguments are used to call <cite>loader_func(path, **loader_kwargs)</cite></p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> object</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py property">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.n_classes">
 <em class="property"><span class="pre">property</span> </em><span class="sig-name descname"><span class="pre">n_classes</span></span><a class="headerlink" href="#quapy.data.base.LabelledCollection.n_classes" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>The number of classes</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>integer</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.natural_sampling_generator">
 <span class="sig-name descname"><span class="pre">natural_sampling_generator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.natural_sampling_generator" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>A generator of samples that implements the natural prevalence protocol (NPP). The NPP consists of drawing
+samples uniformly at random, therefore approximately preserving the natural prevalence of the collection.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>sample_size</strong> – integer, the number of instances in each sample</p></li>
+<li><p><strong>repeats</strong> – the number of samples to generate</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>yield instances of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.natural_sampling_index_generator">
 <span class="sig-name descname"><span class="pre">natural_sampling_index_generator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.natural_sampling_index_generator" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>A generator of sample indexes according to the natural prevalence protocol (NPP). The NPP consists of drawing
+samples uniformly at random, therefore approximately preserving the natural prevalence of the collection.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>sample_size</strong> – integer, the number of instances in each sample (i.e., the length of each index)</p></li>
+<li><p><strong>repeats</strong> – the number of indexes to generate</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>yield <cite>repeats</cite> instances of np.ndarray with shape <cite>(sample_size,)</cite></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.prevalence">
 <span class="sig-name descname"><span class="pre">prevalence</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.prevalence" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns the prevalence, or relative frequency, of the classes of interest.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>a np.ndarray of shape <cite>(n_classes)</cite> with the relative frequencies of each class, in the same order
+as listed by <cite>self.classes_</cite></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling">
 <span class="sig-name descname"><span class="pre">sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Return a random sample (an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a>) of desired size and desired prevalence
+values. For each class, the sampling is drawn without replacement if the requested prevalence is larger than
+the actual prevalence of the class, or with replacement otherwise.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>size</strong> – integer, the requested size</p></li>
+<li><p><strong>prevs</strong> – the prevalence for each class; the prevalence value for the last class can be lead empty since
+it is constrained. E.g., for binary collections, only the prevalence <cite>p</cite> for the first class (as listed in
+<cite>self.classes_</cite> can be specified, while the other class takes prevalence value <cite>1-p</cite></p></li>
+<li><p><strong>shuffle</strong> – if set to True (default), shuffles the index before returning it</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> with length == <cite>size</cite> and prevalence close to <cite>prevs</cite> (or
+prevalence == <cite>prevs</cite> if the exact prevalence values can be met as proportions of instances)</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling_from_index">
 <span class="sig-name descname"><span class="pre">sampling_from_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling_from_index" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> whose elements are sampled from this collection using the
+index.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>index</strong> – np.ndarray</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.sampling_index">
 <span class="sig-name descname"><span class="pre">sampling_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.sampling_index" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns an index to be used to extract a random sample of desired size and desired prevalence values. If the
+prevalence values are not specified, then returns the index of a uniform sampling.
+For each class, the sampling is drawn without replacement if the requested prevalence is larger than
+the actual prevalence of the class, or with replacement otherwise.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>size</strong> – integer, the requested size</p></li>
+<li><p><strong>prevs</strong> – the prevalence for each class; the prevalence value for the last class can be lead empty since
+it is constrained. E.g., for binary collections, only the prevalence <cite>p</cite> for the first class (as listed in
+<cite>self.classes_</cite> can be specified, while the other class takes prevalence value <cite>1-p</cite></p></li>
+<li><p><strong>shuffle</strong> – if set to True (default), shuffles the index before returning it</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a np.ndarray of shape <cite>(size)</cite> with the indexes</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.split_stratified">
 <span class="sig-name descname"><span class="pre">split_stratified</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">train_prop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.split_stratified" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns two instances of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> split with stratification from this collection, at desired
+proportion.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>train_prop</strong> – the proportion of elements to include in the left-most returned collection (typically used
+as the training collection). The rest of elements are included in the right-most returned collection
+(typically used as a test collection).</p></li>
+<li><p><strong>random_state</strong> – if specified, guarantees reproducibility of the split.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>two instances of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a>, the first one with <cite>train_prop</cite> elements, and the
+second one with <cite>1-train_prop</cite> elements</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.stats">
 <span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">show</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.stats" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns (and eventually prints) a dictionary with some stats of this collection. E.g.,:</p>
+<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">data</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_reviews</span><span class="p">(</span><span class="s1">&#39;kindle&#39;</span><span class="p">,</span> <span class="n">tfidf</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">data</span><span class="o">.</span><span class="n">training</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="c1">#instances=3821, type=&lt;class &#39;scipy.sparse.csr.csr_matrix&#39;&gt;, #features=4403, #classes=[0 1], prevs=[0.081, 0.919]</span>
+</pre></div>
+</div>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>show</strong> – if set to True (default), prints the stats in standard output</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a dictionary containing some stats of this collection. Keys include <cite>#instances</cite> (the number of
+instances), <cite>type</cite> (the type representing the instances), <cite>#features</cite> (the number of features, if the
+instances are in array-like format), <cite>#classes</cite> (the classes of the collection), <cite>prevs</cite> (the prevalence
+values for each class)</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.uniform_sampling">
 <span class="sig-name descname"><span class="pre">uniform_sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.uniform_sampling" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns a uniform sample (an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a>) of desired size. The sampling is drawn
+without replacement if the requested size is greater than the number of instances, or with replacement
+otherwise.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>size</strong> – integer, the requested size</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> with length == <cite>size</cite></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.base.LabelledCollection.uniform_sampling_index">
 <span class="sig-name descname"><span class="pre">uniform_sampling_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.LabelledCollection.uniform_sampling_index" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns an index to be used to extract a uniform sample of desired size. The sampling is drawn
+without replacement if the requested size is greater than the number of instances, or with replacement
+otherwise.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>size</strong> – integer, the size of the uniform sample</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a np.ndarray of shape <cite>(size)</cite> with the indexes</p>
+</dd>
+</dl>
+</dd></dl>
 
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.base.isbinary">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.base.</span></span><span class="sig-name descname"><span class="pre">isbinary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.base.isbinary" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Returns True if <cite>data</cite> is either a binary <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> or a binary <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>data</strong> – a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a> or a <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">LabelledCollection</span></code></a> object</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>True if labelled according to two classes</p>
+</dd>
+</dl>
+</dd></dl>
 
 </section>
 <section id="module-quapy.data.datasets">
 <span id="quapy-data-datasets-module"></span><h2>quapy.data.datasets module<a class="headerlink" href="#module-quapy.data.datasets" title="Permalink to this headline">¶</a></h2>
-<dl class="py function">
-<dt class="sig sig-object py" id="quapy.data.datasets.df_replace">
-<span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">df_replace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="pre">df</span></em>, <em class="sig-param"><span class="pre">col</span></em>, <em class="sig-param"><span class="pre">repl={'no':</span> <span class="pre">0</span></em>, <em class="sig-param"><span class="pre">'yes':</span> <span class="pre">1}</span></em>, <em class="sig-param"><span class="pre">astype=&lt;class</span> <span class="pre">'float'&gt;</span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.datasets.df_replace" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
-
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCIDataset">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCIDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_split</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_UCIDataset" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Loads a UCI dataset as an instance of <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a>, as used in
+<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253516300628">Pérez-Gállego, P., Quevedo, J. R., &amp; del Coz, J. J. (2017).
+Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
+Information Fusion, 34, 87-100.</a>
+and
+<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego, P., Castano, A., Quevedo, J. R., &amp; del Coz, J. J. (2019).
+Dynamic ensemble selection for quantification tasks.
+Information Fusion, 45, 1-15.</a>.
+The datasets do not come with a predefined train-test split (see <a class="reference internal" href="#quapy.data.datasets.fetch_UCILabelledCollection" title="quapy.data.datasets.fetch_UCILabelledCollection"><code class="xref py py-meth docutils literal notranslate"><span class="pre">fetch_UCILabelledCollection()</span></code></a> for further
+information on how to use these collections), and so a train-test split is generated at desired proportion.
+The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI_DATASETS</cite></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset_name</strong> – a dataset name</p></li>
+<li><p><strong>data_home</strong> – specify the quapy home directory where collections will be dumped (leave empty to use the default
+~/quay_data/ directory)</p></li>
+<li><p><strong>test_split</strong> – proportion of documents to be included in the test set. The rest conforms the training set</p></li>
+<li><p><strong>verbose</strong> – set to True (default is False) to get information (from the UCI ML repository) about the datasets</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.datasets.fetch_UCILabelledCollection">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_UCILabelledCollection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_UCILabelledCollection" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Loads a UCI collection as an instance of <a class="reference internal" href="#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.LabelledCollection</span></code></a>, as used in
+<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253516300628">Pérez-Gállego, P., Quevedo, J. R., &amp; del Coz, J. J. (2017).
+Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
+Information Fusion, 34, 87-100.</a>
+and
+<a class="reference external" href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego, P., Castano, A., Quevedo, J. R., &amp; del Coz, J. J. (2019).
+Dynamic ensemble selection for quantification tasks.
+Information Fusion, 45, 1-15.</a>.
+The datasets do not come with a predefined train-test split, and so Pérez-Gállego et al. adopted a 5FCVx2 evaluation
+protocol, meaning that each collection was used to generate two rounds (hence the x2) of 5 fold cross validation.
+This can be reproduced by using <a class="reference internal" href="#quapy.data.base.Dataset.kFCV" title="quapy.data.base.Dataset.kFCV"><code class="xref py py-meth docutils literal notranslate"><span class="pre">quapy.data.base.Dataset.kFCV()</span></code></a>, e.g.:</p>
+<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">quapy</span> <span class="k">as</span> <span class="nn">qp</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">collection</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">fetch_UCILabelledCollection</span><span class="p">(</span><span class="s2">&quot;yeast&quot;</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">qp</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">Dataset</span><span class="o">.</span><span class="n">kFCV</span><span class="p">(</span><span class="n">collection</span><span class="p">,</span> <span class="n">nfolds</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">nrepeats</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
+<span class="gp">&gt;&gt;&gt; </span>    <span class="o">...</span>
+</pre></div>
+</div>
+<p>The list of valid dataset names can be accessed in <cite>quapy.data.datasets.UCI_DATASETS</cite></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset_name</strong> – a dataset name</p></li>
+<li><p><strong>data_home</strong> – specify the quapy home directory where collections will be dumped (leave empty to use the default
+~/quay_data/ directory)</p></li>
+<li><p><strong>test_split</strong> – proportion of documents to be included in the test set. The rest conforms the training set</p></li>
+<li><p><strong>verbose</strong> – set to True (default is False) to get information (from the UCI ML repository) about the datasets</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.datasets.fetch_reviews">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_reviews</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tfidf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_reviews" title="Permalink to this definition">¶</a></dt>
-<dd><p>Load a Reviews dataset as a Dataset instance, as used in:
-Esuli, A., Moreo, A., and Sebastiani, F. “A recurrent neural network for sentiment quantification.”
-Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018.
-:param dataset_name: the name of the dataset: valid ones are ‘hp’, ‘kindle’, ‘imdb’
-:param tfidf: set to True to transform the raw documents into tfidf weighted matrices
-:param min_df: minimun number of documents that should contain a term in order for the term to be
-kept (ignored if tfidf==False)
-:param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
-~/quay_data/ directory)
-:param pickle: set to True to pickle the Dataset object the first time it is generated, in order to allow for
-faster subsequent invokations
-:return: a Dataset instance</p>
+<dd><p>Loads a Reviews dataset as a Dataset instance, as used in
+<a class="reference external" href="https://dl.acm.org/doi/abs/10.1145/3269206.3269287">Esuli, A., Moreo, A., and Sebastiani, F. “A recurrent neural network for sentiment quantification.”
+Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018.</a>.
+The list of valid dataset names can be accessed in <cite>quapy.data.datasets.REVIEWS_SENTIMENT_DATASETS</cite></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset_name</strong> – the name of the dataset: valid ones are ‘hp’, ‘kindle’, ‘imdb’</p></li>
+<li><p><strong>tfidf</strong> – set to True to transform the raw documents into tfidf weighted matrices</p></li>
+<li><p><strong>min_df</strong> – minimun number of documents that should contain a term in order for the term to be
+kept (ignored if tfidf==False)</p></li>
+<li><p><strong>data_home</strong> – specify the quapy home directory where collections will be dumped (leave empty to use the default
+~/quay_data/ directory)</p></li>
+<li><p><strong>pickle</strong> – set to True to pickle the Dataset object the first time it is generated, in order to allow for
+faster subsequent invokations</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance</p>
+</dd>
+</dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.datasets.fetch_twitter">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.datasets.</span></span><span class="sig-name descname"><span class="pre">fetch_twitter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_model_selection</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_home</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></span><a class="headerlink" href="#quapy.data.datasets.fetch_twitter" title="Permalink to this definition">¶</a></dt>
-<dd><p>Load a Twitter dataset as a Dataset instance, as used in:
-Gao, W., Sebastiani, F.: From classification to quantification in tweet sentiment analysis.
-Social Network Analysis and Mining6(19), 1–22 (2016)
-The datasets ‘semeval13’, ‘semeval14’, ‘semeval15’ share the same training set.</p>
+<dd><p>Loads a Twitter dataset as a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance, as used in:
+<a class="reference external" href="https://link.springer.com/content/pdf/10.1007/s13278-016-0327-z.pdf">Gao, W., Sebastiani, F.: From classification to quantification in tweet sentiment analysis.
+Social Network Analysis and Mining6(19), 1–22 (2016)</a>
+Note that the datasets ‘semeval13’, ‘semeval14’, ‘semeval15’ share the same training set.
+The list of valid dataset names corresponding to training sets can be accessed in
+<cite>quapy.data.datasets.TWITTER_SENTIMENT_DATASETS_TRAIN</cite>, while the test sets can be accessed in
+<cite>quapy.data.datasets.TWITTER_SENTIMENT_DATASETS_TEST</cite></p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>dataset_name</strong> – the name of the dataset: valid ones are ‘gasp’, ‘hcr’, ‘omd’, ‘sanders’, ‘semeval13’,</p>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset_name</strong> – the name of the dataset: valid ones are ‘gasp’, ‘hcr’, ‘omd’, ‘sanders’, ‘semeval13’,
+‘semeval14’, ‘semeval15’, ‘semeval16’, ‘sst’, ‘wa’, ‘wb’</p></li>
+<li><p><strong>for_model_selection</strong> – if True, then returns the train split as the training set and the devel split
+as the test set; if False, then returns the train+devel split as the training set and the test set as the
+test set</p></li>
+<li><p><strong>min_df</strong> – minimun number of documents that should contain a term in order for the term to be kept</p></li>
+<li><p><strong>data_home</strong> – specify the quapy home directory where collections will be dumped (leave empty to use the default
+~/quay_data/ directory)</p></li>
+<li><p><strong>pickle</strong> – set to True to pickle the Dataset object the first time it is generated, in order to allow for
+faster subsequent invokations</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> instance</p>
 </dd>
 </dl>
-<p>‘semeval14’, ‘semeval15’, ‘semeval16’, ‘sst’, ‘wa’, ‘wb’
-:param for_model_selection: if True, then returns the train split as the training set and the devel split
-as the test set; if False, then returns the train+devel split as the training set and the test set as the
-test set
-:param min_df: minimun number of documents that should contain a term in order for the term to be kept
-:param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
-~/quay_data/ directory)
-:param pickle: set to True to pickle the Dataset object the first time it is generated, in order to allow for
-faster subsequent invokations
-:return: a Dataset instance</p>
 </dd></dl>
 
 <dl class="py function">
@@ -278,15 +696,41 @@ faster subsequent invokations
 <dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer">
 <em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">IndexTransformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer" title="Permalink to this definition">¶</a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
+<p>This class implements a sklearn’s-style transformer that indexes text as numerical ids for the tokens it
+contains, and that would be generated by sklearn’s
+<a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html">CountVectorizer</a></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>kwargs</strong> – <p>keyworded arguments from <a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html">CountVectorizer</a></p>
+</p>
+</dd>
+</dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.add_word">
 <span class="sig-name descname"><span class="pre">add_word</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">word</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nogaps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.add_word" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Adds a new token (regardless of whether it has been found in the text or not), with dedicated id.
+Useful to define special tokens for codifying unknown words, or padding tokens.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>word</strong> – string, surface form of the token</p></li>
+<li><p><strong>id</strong> – integer, numerical value to assign to the token (leave as None for indicating the next valid id,
+default)</p></li>
+<li><p><strong>nogaps</strong> – if set to True (default) asserts that the id indicated leads to no numerical gaps with
+precedent ids stored so far</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>integer, the numerical id for the new token</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.fit">
 <span class="sig-name descname"><span class="pre">fit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.fit" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="field-list simple">
+<dd><p>Fits the transformer, i.e., decides on the vocabulary, given a list of strings.</p>
+<dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><p><strong>X</strong> – a list of strings</p>
 </dd>
@@ -299,66 +743,139 @@ faster subsequent invokations
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.fit_transform">
 <span class="sig-name descname"><span class="pre">fit_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-</span> <span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.fit_transform" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
-
-<dl class="py method">
-<dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.index">
-<span class="sig-name descname"><span class="pre">index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">documents</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.index" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Fits the transform on <cite>X</cite> and transforms it.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>X</strong> – a list of strings</p></li>
+<li><p><strong>n_jobs</strong> – the number of parallel workers to carry out this task</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <cite>np.ndarray</cite> of numerical ids</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.transform">
 <span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-</span> <span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.transform" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Transforms the strings in <cite>X</cite> as lists of numerical ids</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>X</strong> – a list of strings</p></li>
+<li><p><strong>n_jobs</strong> – the number of parallel workers to carry out this task</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a <cite>np.ndarray</cite> of numerical ids</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.IndexTransformer.vocabulary_size">
 <span class="sig-name descname"><span class="pre">vocabulary_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.IndexTransformer.vocabulary_size" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Gets the length of the vocabulary according to which the document tokens have been indexed</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p>integer</p>
+</dd>
+</dl>
+</dd></dl>
 
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.index">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.index" title="Permalink to this definition">¶</a></dt>
-<dd><p>Indexes a dataset of strings. To index a document means to replace each different token by a unique numerical index.
-Rare words (i.e., words occurring less than _min_df_ times) are replaced by a special token UNK
-:param dataset: a Dataset where the instances are lists of str
-:param min_df: minimum number of instances below which the term is replaced by a UNK index
-:param inplace: whether or not to apply the transformation inplace, or to a new copy
-:param kwargs: the rest of parameters of the transformation (as for sklearn.feature_extraction.text.CountVectorizer)
-:return: a new Dataset (if inplace=False) or a reference to the current Dataset (inplace=True)
-consisting of lists of integer values representing indices.</p>
+<dd><p>Indexes the tokens of a textual <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> of string documents.
+To index a document means to replace each different token by a unique numerical index.
+Rare words (i.e., words occurring less than <cite>min_df</cite> times) are replaced by a special token <cite>UNK</cite></p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset</strong> – a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> object where the instances of training and test documents
+are lists of str</p></li>
+<li><p><strong>min_df</strong> – minimum number of occurrences below which the term is replaced by a <cite>UNK</cite> index</p></li>
+<li><p><strong>inplace</strong> – whether or not to apply the transformation inplace (True), or to a new copy (False, default)</p></li>
+<li><p><strong>kwargs</strong> – the rest of parameters of the transformation (as for sklearn’s</p></li>
+</ul>
+</dd>
+</dl>
+<p><cite>CountVectorizer &lt;https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html&gt;_</cite>)
+:return: a new <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> (if inplace=False) or a reference to the current</p>
+<blockquote>
+<div><p><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> (inplace=True) consisting of lists of integer values representing indices.</p>
+</div></blockquote>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.reduce_columns">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">reduce_columns</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.reduce_columns" title="Permalink to this definition">¶</a></dt>
-<dd><p>Reduces the dimensionality of the csr_matrix by removing the columns of words which are not present in at least
-_min_df_ instances
-:param dataset: a Dataset in sparse format (any subtype of scipy.sparse.spmatrix)
-:param min_df: minimum number of instances below which the columns are removed
-:param inplace: whether or not to apply the transformation inplace, or to a new copy
-:return: a new Dataset (if inplace=False) or a reference to the current Dataset (inplace=True)
-where the dimensions corresponding to infrequent instances have been removed</p>
+<dd><p>Reduces the dimensionality of the instances, represented as a <cite>csr_matrix</cite> (or any subtype of
+<cite>scipy.sparse.spmatrix</cite>), of training and test documents by removing the columns of words which are not present
+in at least <cite>min_df</cite> instances in the training set</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset</strong> – a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> in which instances are represented in sparse format (any
+subtype of scipy.sparse.spmatrix)</p></li>
+<li><p><strong>min_df</strong> – integer, minimum number of instances below which the columns are removed</p></li>
+<li><p><strong>inplace</strong> – whether or not to apply the transformation inplace (True), or to a new copy (False, default)</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a new <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> (if inplace=False) or a reference to the current
+<a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> (inplace=True) where the dimensions corresponding to infrequent terms
+in the training set have been removed</p>
+</dd>
+</dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.standardize">
-<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">standardize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.standardize" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">standardize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.standardize" title="Permalink to this definition">¶</a></dt>
+<dd><p>Standardizes the real-valued columns of a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a>.
+Standardization, aka z-scoring, of a variable <cite>X</cite> comes down to subtracting the average and normalizing by the
+standard deviation.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset</strong> – a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> object</p></li>
+<li><p><strong>inplace</strong> – set to True if the transformation is to be applied inplace, or to False (default) if a new
+<a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> is to be returned</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.preprocessing.text2tfidf">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.preprocessing.</span></span><span class="sig-name descname"><span class="pre">text2tfidf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><span class="pre">quapy.data.base.Dataset</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sublinear_tf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.preprocessing.text2tfidf" title="Permalink to this definition">¶</a></dt>
-<dd><p>Transforms a Dataset of textual instances into a Dataset of tfidf weighted sparse vectors
-:param dataset: a Dataset where the instances are lists of str
-:param min_df: minimum number of occurrences for a word to be considered as part of the vocabulary
-:param sublinear_tf: whether or not to apply the log scalling to the tf counters
-:param inplace: whether or not to apply the transformation inplace, or to a new copy
-:param kwargs: the rest of parameters of the transformation (as for sklearn.feature_extraction.text.TfidfVectorizer)
-:return: a new Dataset in csr_matrix format (if inplace=False) or a reference to the current Dataset (inplace=True)
-where the instances are stored in a csr_matrix of real-valued tfidf scores</p>
+<dd><p>Transforms a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> of textual instances into a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> of
+tfidf weighted sparse vectors</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dataset</strong> – a <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> where the instances of training and test collections are
+lists of str</p></li>
+<li><p><strong>min_df</strong> – minimum number of occurrences for a word to be considered as part of the vocabulary (default 3)</p></li>
+<li><p><strong>sublinear_tf</strong> – whether or not to apply the log scalling to the tf counters (default True)</p></li>
+<li><p><strong>inplace</strong> – whether or not to apply the transformation inplace (True), or to a new copy (False, default)</p></li>
+<li><p><strong>kwargs</strong> – the rest of parameters of the transformation (as for sklearn’s
+<a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html">TfidfVectorizer</a>)</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a new <a class="reference internal" href="#quapy.data.base.Dataset" title="quapy.data.base.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">quapy.data.base.Dataset</span></code></a> in <cite>csr_matrix</cite> format (if inplace=False) or a reference to the
+current Dataset (if inplace=True) where the instances are stored in a <cite>csr_matrix</cite> of real-valued tfidf scores</p>
+</dd>
+</dl>
 </dd></dl>
 
 </section>
@@ -367,7 +884,24 @@ where the instances are stored in a csr_matrix of real-valued tfidf scores</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.reader.binarize">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">binarize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_class</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.binarize" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Binarizes a categorical array-like collection of labels towards the positive class <cite>pos_class</cite>. E.g.,:</p>
+<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">binarize</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">pos_class</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">array</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span>
+</pre></div>
+</div>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>y</strong> – array-like of labels</p></li>
+<li><p><strong>pos_class</strong> – integer, the positive class</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a binary np.ndarray, in which values 1 corresponds to positions in whcih <cite>y</cite> had <cite>pos_class</cite> labels, and
+0 otherwise</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.data.reader.from_csv">
@@ -376,10 +910,13 @@ where the instances are stored in a csr_matrix of real-valued tfidf scores</p>
 File format &lt;label&gt;,&lt;feat1&gt;,&lt;feat2&gt;,…,&lt;featn&gt;</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>path</strong> – path to the csv file</p>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>path</strong> – path to the csv file</p></li>
+<li><p><strong>encoding</strong> – the text encoding used to open the file</p></li>
+</ul>
 </dd>
 <dt class="field-even">Returns</dt>
-<dd class="field-even"><p>a ndarray for the labels and a ndarray (float) for the covariates</p>
+<dd class="field-even"><p>a np.ndarray for the labels and a ndarray (float) for the covariates</p>
 </dd>
 </dl>
 </dd></dl>
@@ -394,7 +931,7 @@ File format &lt;-1 or 0 or 1&gt;[s col(int):val(float)]</p>
 <dd class="field-odd"><p><strong>path</strong> – path to the labelled collection</p>
 </dd>
 <dt class="field-even">Returns</dt>
-<dd class="field-even"><p>a csr_matrix containing the instances (rows), and a ndarray containing the labels</p>
+<dd class="field-even"><p>a <cite>csr_matrix</cite> containing the instances (rows), and a ndarray containing the labels</p>
 </dd>
 </dl>
 </dd></dl>
@@ -406,7 +943,11 @@ File format &lt;-1 or 0 or 1&gt;[s col(int):val(float)]</p>
 File fomart &lt;0 or 1&gt;        &lt;document&gt;</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>path</strong> – path to the labelled collection</p>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>path</strong> – path to the labelled collection</p></li>
+<li><p><strong>encoding</strong> – the text encoding used to open the file</p></li>
+<li><p><strong>verbose</strong> – if &gt;0 (default) shows some progress information in standard output</p></li>
+</ul>
 </dd>
 <dt class="field-even">Returns</dt>
 <dd class="field-even"><p>a list of sentences, and a list of labels</p>
@@ -418,9 +959,19 @@ File fomart &lt;0 or 1&gt;        &lt;document&gt;</p>
 <dt class="sig sig-object py" id="quapy.data.reader.reindex_labels">
 <span class="sig-prename descclassname"><span class="pre">quapy.data.reader.</span></span><span class="sig-name descname"><span class="pre">reindex_labels</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.data.reader.reindex_labels" title="Permalink to this definition">¶</a></dt>
 <dd><p>Re-indexes a list of labels as a list of indexes, and returns the classnames corresponding to the indexes.
-E.g., y=[‘B’, ‘B’, ‘A’, ‘C’] -&gt; [1,1,0,2], [‘A’,’B’,’C’]
-:param y: the list or array of original labels
-:return: a ndarray (int) of class indexes, and a ndarray of classnames corresponding to the indexes.</p>
+E.g.:</p>
+<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">reindex_labels</span><span class="p">([</span><span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;A&#39;</span><span class="p">,</span> <span class="s1">&#39;C&#39;</span><span class="p">])</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="p">(</span><span class="n">array</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">]),</span> <span class="n">array</span><span class="p">([</span><span class="s1">&#39;A&#39;</span><span class="p">,</span> <span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;C&#39;</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;&lt;U1&#39;</span><span class="p">))</span>
+</pre></div>
+</div>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><p><strong>y</strong> – the list or array of original labels</p>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>a ndarray (int) of class indexes, and a ndarray of classnames corresponding to the indexes.</p>
+</dd>
+</dl>
 </dd></dl>
 
 </section>
diff --git a/docs/build/html/quapy.html b/docs/build/html/quapy.html
index fc4066f..32f7f57 100644
--- a/docs/build/html/quapy.html
+++ b/docs/build/html/quapy.html
@@ -515,14 +515,20 @@ will be taken from the environment variable <cite>SAMPLE_SIZE</cite> (which has
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.evaluation.artificial_prevalence_prediction">
 <span class="sig-prename descclassname"><span class="pre">quapy.evaluation.</span></span><span class="sig-name descname"><span class="pre">artificial_prevalence_prediction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="quapy.method.html#quapy.method.base.BaseQuantifier" title="quapy.method.base.BaseQuantifier"><span class="pre">quapy.method.base.BaseQuantifier</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">test</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="quapy.data.html#quapy.data.base.LabelledCollection" title="quapy.data.base.LabelledCollection"><span class="pre">quapy.data.base.LabelledCollection</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">sample_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_prevpoints</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">210</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_repetitions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eval_budget</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span> <span class="o"><span class="pre">=</span></span> <span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">42</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.evaluation.artificial_prevalence_prediction" title="Permalink to this definition">¶</a></dt>
-<dd><p>Performs the predictions for all samples generated according to the artificial sampling protocol.
-:param model: the model in charge of generating the class prevalence estimations
-:param test: the test set on which to perform arificial sampling
-:param sample_size: the size of the samples
-:param n_prevpoints: the number of different prevalences to sample (or set to None if eval_budget is specified)
-:param n_repetitions: the number of repetitions for each prevalence
-:param eval_budget: if specified, sets a ceil on the number of evaluations to perform. For example, if there are 3
-classes, n_repetitions=1 and eval_budget=20, then n_prevpoints will be set to 5, since this will generate 15
+<dd><p>Performs the predictions for all samples generated according to the artificial sampling protocol.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>model</strong> – the model in charge of generating the class prevalence estimations</p></li>
+<li><p><strong>test</strong> – the test set on which to perform arificial sampling</p></li>
+<li><p><strong>sample_size</strong> – the size of the samples</p></li>
+<li><p><strong>n_prevpoints</strong> – the number of different prevalences to sample (or set to None if eval_budget is specified)</p></li>
+<li><p><strong>n_repetitions</strong> – the number of repetitions for each prevalence</p></li>
+<li><p><strong>eval_budget</strong> – if specified, sets a ceil on the number of evaluations to perform. For example, if there are 3</p></li>
+</ul>
+</dd>
+</dl>
+<p>classes, n_repetitions=1 and eval_budget=20, then n_prevpoints will be set to 5, since this will generate 15
 different prevalences ([0, 0, 1], [0, 0.25, 0.75], [0, 0.5, 0.5] … [1, 0, 0]) and since setting it n_prevpoints
 to 6 would produce more than 20 evaluations.
 :param n_jobs: number of jobs to be run in parallel
@@ -601,7 +607,31 @@ contains the the prevalence estimations</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.functional.artificial_prevalence_sampling">
 <span class="sig-prename descclassname"><span class="pre">quapy.functional.</span></span><span class="sig-name descname"><span class="pre">artificial_prevalence_sampling</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dimensions</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_prevalences</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">21</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeat</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_constrained_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.functional.artificial_prevalence_sampling" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<dd><p>Generates vectors of prevalence values artificially drawn from an exhaustive grid of prevalence values. The
+number of prevalence values explored for each dimension depends on <cite>n_prevalences</cite>, so that, if, for example,
+<cite>n_prevalences=11</cite> then the prevalence values of the grid are taken from [0, 0.1, 0.2, …, 0.9, 1]. Only
+valid prevalence distributions are returned, i.e., vectors of prevalence values that sum up to 1. For each
+valid vector of prevalence values, <cite>repeat</cite> copies are returned. The vector of prevalence values can be
+implicit (by setting <cite>return_constrained_dim=False</cite>), meaning that the last dimension (which is constrained
+to 1 - sum of the rest) is not returned (note that, quite obviously, in this case the vector does not sum up to 1).</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dimensions</strong> – the number of classes</p></li>
+<li><p><strong>n_prevalences</strong> – the number of equidistant prevalence points to extract from the [0,1] interval for the grid
+(default is 21)</p></li>
+<li><p><strong>repeat</strong> – number of copies for each valid prevalence vector (default is 1)</p></li>
+<li><p><strong>return_constrained_dim</strong> – set to True to return all dimensions, or to False (default) for ommitting the
+constrained dimension</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an ndarray of shape <cite>(n, dimensions)</cite> if <cite>return_constrained_dim=True</cite> or of shape <cite>(n, dimensions-1)</cite>
+if <cite>return_constrained_dim=False</cite>, where <cite>n</cite> is the number of valid combinations found in the grid multiplied
+by <cite>repeat</cite></p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.functional.get_nprevpoints_approximation">
@@ -634,8 +664,21 @@ number of possible combinations are 5, i.e.: [0,1], [0.25,0.75], [0.50,0.50], [0
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.functional.prevalence_from_labels">
-<span class="sig-prename descclassname"><span class="pre">quapy.functional.</span></span><span class="sig-name descname"><span class="pre">prevalence_from_labels</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes_</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.functional.prevalence_from_labels" title="Permalink to this definition">¶</a></dt>
-<dd></dd></dl>
+<span class="sig-prename descclassname"><span class="pre">quapy.functional.</span></span><span class="sig-name descname"><span class="pre">prevalence_from_labels</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">classes</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.functional.prevalence_from_labels" title="Permalink to this definition">¶</a></dt>
+<dd><p>Computed the prevalence values from a vector of labels.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>labels</strong> – array-like of shape <cite>(n_instances)</cite> with the label for each instance</p></li>
+<li><p><strong>classes</strong> – the class labels. This is needed in order to correctly compute the prevalence vector even when
+some classes have no examples.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an ndarray of shape <cite>(len(classes))</cite> with the class prevalence values</p>
+</dd>
+</dl>
+</dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.functional.prevalence_from_probabilities">
@@ -645,13 +688,21 @@ number of possible combinations are 5, i.e.: [0,1], [0.25,0.75], [0.50,0.50], [0
 <dl class="py function">
 <dt class="sig sig-object py" id="quapy.functional.prevalence_linspace">
 <span class="sig-prename descclassname"><span class="pre">quapy.functional.</span></span><span class="sig-name descname"><span class="pre">prevalence_linspace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_prevalences</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">21</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeat</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">smooth_limits_epsilon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quapy.functional.prevalence_linspace" title="Permalink to this definition">¶</a></dt>
-<dd><p>Produces a uniformly separated values of prevalence. By default, produces an array 21 prevalences, with step 0.05
-and with the limits smoothed, i.e.:
-[0.01, 0.05, 0.10, 0.15, …, 0.90, 0.95, 0.99]
-:param n_prevalences: the number of prevalence values to sample from the [0,1] interval (default 21)
-:param repeat: number of times each prevalence is to be repeated (defaults to 1)
-:param smooth_limits_epsilon: the quantity to add and subtract to the limits 0 and 1
-:return: an array of uniformly separated prevalence values</p>
+<dd><p>Produces a uniformly separated values of prevalence. By default, produces an array of 21 prevalence values, with
+step 0.05 and with the limits smoothed, i.e.:
+[0.01, 0.05, 0.10, 0.15, …, 0.90, 0.95, 0.99]</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>n_prevalences</strong> – the number of prevalence values to sample from the [0,1] interval (default 21)</p></li>
+<li><p><strong>repeat</strong> – number of times each prevalence is to be repeated (defaults to 1)</p></li>
+<li><p><strong>smooth_limits_epsilon</strong> – the quantity to add and subtract to the limits 0 and 1</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p>an array of uniformly separated prevalence values</p>
+</dd>
+</dl>
 </dd></dl>
 
 <dl class="py function">
diff --git a/docs/build/html/searchindex.js b/docs/build/html/searchindex.js
index f92c96d..02ef050 100644
--- a/docs/build/html/searchindex.js
+++ b/docs/build/html/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["Datasets","Evaluation","Installation","Methods","Model-Selection","Plotting","index","modules","quapy","quapy.classification","quapy.data","quapy.method"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,sphinx:56},filenames:["Datasets.md","Evaluation.md","Installation.rst","Methods.md","Model-Selection.md","Plotting.md","index.rst","modules.rst","quapy.rst","quapy.classification.rst","quapy.data.rst","quapy.method.rst"],objects:{"":{quapy:[8,0,0,"-"]},"quapy.classification":{methods:[9,0,0,"-"],neural:[9,0,0,"-"],svmperf:[9,0,0,"-"]},"quapy.classification.methods":{LowRankLogisticRegression:[9,1,1,""]},"quapy.classification.methods.LowRankLogisticRegression":{fit:[9,2,1,""],get_params:[9,2,1,""],predict:[9,2,1,""],predict_proba:[9,2,1,""],set_params:[9,2,1,""],transform:[9,2,1,""]},"quapy.classification.neural":{CNNnet:[9,1,1,""],LSTMnet:[9,1,1,""],NeuralClassifierTrainer:[9,1,1,""],TextClassifierNet:[9,1,1,""],TorchDataset:[9,1,1,""]},"quapy.classification.neural.CNNnet":{document_embedding:[9,2,1,""],get_params:[9,2,1,""],vocabulary_size:[9,3,1,""]},"quapy.classification.neural.LSTMnet":{document_embedding:[9,2,1,""],get_params:[9,2,1,""],vocabulary_size:[9,3,1,""]},"quapy.classification.neural.NeuralClassifierTrainer":{device:[9,3,1,""],fit:[9,2,1,""],get_params:[9,2,1,""],predict:[9,2,1,""],predict_proba:[9,2,1,""],reset_net_params:[9,2,1,""],set_params:[9,2,1,""],transform:[9,2,1,""]},"quapy.classification.neural.TextClassifierNet":{dimensions:[9,2,1,""],document_embedding:[9,2,1,""],forward:[9,2,1,""],get_params:[9,2,1,""],predict_proba:[9,2,1,""],vocabulary_size:[9,3,1,""],xavier_uniform:[9,2,1,""]},"quapy.classification.neural.TorchDataset":{asDataloader:[9,2,1,""]},"quapy.classification.svmperf":{SVMperf:[9,1,1,""]},"quapy.classification.svmperf.SVMperf":{decision_function:[9,2,1,""],fit:[9,2,1,""],predict:[9,2,1,""],set_params:[9,2,1,""],valid_losses:[9,4,1,""]},"quapy.data":{base:[10,0,0,"-"],datasets:[10,0,0,"-"],preprocessing:[10,0,0,"-"],reader:[10,0,0,"-"]},"quapy.data.base":{Dataset:[10,1,1,""],LabelledCollection:[10,1,1,""],isbinary:[10,5,1,""]},"quapy.data.base.Dataset":{SplitStratified:[10,2,1,""],binary:[10,3,1,""],classes_:[10,3,1,""],kFCV:[10,2,1,""],load:[10,2,1,""],n_classes:[10,3,1,""],stats:[10,2,1,""],vocabulary_size:[10,3,1,""]},"quapy.data.base.LabelledCollection":{Xy:[10,3,1,""],artificial_sampling_generator:[10,2,1,""],artificial_sampling_index_generator:[10,2,1,""],binary:[10,3,1,""],counts:[10,2,1,""],kFCV:[10,2,1,""],load:[10,2,1,""],n_classes:[10,3,1,""],natural_sampling_generator:[10,2,1,""],natural_sampling_index_generator:[10,2,1,""],prevalence:[10,2,1,""],sampling:[10,2,1,""],sampling_from_index:[10,2,1,""],sampling_index:[10,2,1,""],split_stratified:[10,2,1,""],stats:[10,2,1,""],uniform_sampling:[10,2,1,""],uniform_sampling_index:[10,2,1,""]},"quapy.data.datasets":{df_replace:[10,5,1,""],fetch_UCIDataset:[10,5,1,""],fetch_UCILabelledCollection:[10,5,1,""],fetch_reviews:[10,5,1,""],fetch_twitter:[10,5,1,""],warn:[10,5,1,""]},"quapy.data.preprocessing":{IndexTransformer:[10,1,1,""],index:[10,5,1,""],reduce_columns:[10,5,1,""],standardize:[10,5,1,""],text2tfidf:[10,5,1,""]},"quapy.data.preprocessing.IndexTransformer":{add_word:[10,2,1,""],fit:[10,2,1,""],fit_transform:[10,2,1,""],index:[10,2,1,""],transform:[10,2,1,""],vocabulary_size:[10,2,1,""]},"quapy.data.reader":{binarize:[10,5,1,""],from_csv:[10,5,1,""],from_sparse:[10,5,1,""],from_text:[10,5,1,""],reindex_labels:[10,5,1,""]},"quapy.error":{absolute_error:[8,5,1,""],acc_error:[8,5,1,""],acce:[8,5,1,""],ae:[8,5,1,""],f1_error:[8,5,1,""],f1e:[8,5,1,""],from_name:[8,5,1,""],kld:[8,5,1,""],mae:[8,5,1,""],mean_absolute_error:[8,5,1,""],mean_relative_absolute_error:[8,5,1,""],mkld:[8,5,1,""],mnkld:[8,5,1,""],mrae:[8,5,1,""],mse:[8,5,1,""],nkld:[8,5,1,""],rae:[8,5,1,""],relative_absolute_error:[8,5,1,""],se:[8,5,1,""],smooth:[8,5,1,""]},"quapy.evaluation":{artificial_prevalence_prediction:[8,5,1,""],artificial_prevalence_protocol:[8,5,1,""],artificial_prevalence_report:[8,5,1,""],evaluate:[8,5,1,""],gen_prevalence_prediction:[8,5,1,""],natural_prevalence_prediction:[8,5,1,""],natural_prevalence_protocol:[8,5,1,""],natural_prevalence_report:[8,5,1,""]},"quapy.functional":{HellingerDistance:[8,5,1,""],adjusted_quantification:[8,5,1,""],artificial_prevalence_sampling:[8,5,1,""],get_nprevpoints_approximation:[8,5,1,""],normalize_prevalence:[8,5,1,""],num_prevalence_combinations:[8,5,1,""],prevalence_from_labels:[8,5,1,""],prevalence_from_probabilities:[8,5,1,""],prevalence_linspace:[8,5,1,""],strprev:[8,5,1,""],uniform_prevalence_sampling:[8,5,1,""],uniform_simplex_sampling:[8,5,1,""]},"quapy.method":{aggregative:[11,0,0,"-"],base:[11,0,0,"-"],meta:[11,0,0,"-"],neural:[11,0,0,"-"],non_aggregative:[11,0,0,"-"]},"quapy.method.aggregative":{ACC:[11,1,1,""],AdjustedClassifyAndCount:[11,4,1,""],AggregativeProbabilisticQuantifier:[11,1,1,""],AggregativeQuantifier:[11,1,1,""],CC:[11,1,1,""],ClassifyAndCount:[11,4,1,""],ELM:[11,1,1,""],EMQ:[11,1,1,""],ExpectationMaximizationQuantifier:[11,4,1,""],ExplicitLossMinimisation:[11,4,1,""],HDy:[11,1,1,""],HellingerDistanceY:[11,4,1,""],MAX:[11,1,1,""],MS2:[11,1,1,""],MS:[11,1,1,""],MedianSweep2:[11,4,1,""],MedianSweep:[11,4,1,""],OneVsAll:[11,1,1,""],PACC:[11,1,1,""],PCC:[11,1,1,""],ProbabilisticAdjustedClassifyAndCount:[11,4,1,""],ProbabilisticClassifyAndCount:[11,4,1,""],SVMAE:[11,1,1,""],SVMKLD:[11,1,1,""],SVMNKLD:[11,1,1,""],SVMQ:[11,1,1,""],SVMRAE:[11,1,1,""],T50:[11,1,1,""],ThresholdOptimization:[11,1,1,""],X:[11,1,1,""],training_helper:[11,5,1,""]},"quapy.method.aggregative.ACC":{aggregate:[11,2,1,""],classify:[11,2,1,""],fit:[11,2,1,""],solve_adjustment:[11,2,1,""]},"quapy.method.aggregative.AggregativeProbabilisticQuantifier":{posterior_probabilities:[11,2,1,""],predict_proba:[11,2,1,""],probabilistic:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.aggregative.AggregativeQuantifier":{aggregate:[11,2,1,""],aggregative:[11,3,1,""],classes_:[11,3,1,""],classify:[11,2,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],learner:[11,3,1,""],n_classes:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.aggregative.CC":{aggregate:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.ELM":{aggregate:[11,2,1,""],classify:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.EMQ":{EM:[11,2,1,""],EPSILON:[11,4,1,""],MAX_ITER:[11,4,1,""],aggregate:[11,2,1,""],fit:[11,2,1,""],predict_proba:[11,2,1,""]},"quapy.method.aggregative.HDy":{aggregate:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.MS":{optimize_threshold:[11,2,1,""]},"quapy.method.aggregative.MS2":{optimize_threshold:[11,2,1,""]},"quapy.method.aggregative.OneVsAll":{aggregate:[11,2,1,""],binary:[11,3,1,""],classes_:[11,3,1,""],classify:[11,2,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],posterior_probabilities:[11,2,1,""],probabilistic:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.aggregative.PACC":{aggregate:[11,2,1,""],classify:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.PCC":{aggregate:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.ThresholdOptimization":{aggregate:[11,2,1,""],compute_fpr:[11,2,1,""],compute_table:[11,2,1,""],compute_tpr:[11,2,1,""],fit:[11,2,1,""],optimize_threshold:[11,2,1,""]},"quapy.method.base":{BaseQuantifier:[11,1,1,""],BinaryQuantifier:[11,1,1,""],isaggregative:[11,5,1,""],isbinary:[11,5,1,""],isprobabilistic:[11,5,1,""]},"quapy.method.base.BaseQuantifier":{aggregative:[11,3,1,""],binary:[11,3,1,""],classes_:[11,3,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],probabilistic:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.base.BinaryQuantifier":{binary:[11,3,1,""]},"quapy.method.meta":{EACC:[11,5,1,""],ECC:[11,5,1,""],EEMQ:[11,5,1,""],EHDy:[11,5,1,""],EPACC:[11,5,1,""],Ensemble:[11,1,1,""],ensembleFactory:[11,5,1,""],get_probability_distribution:[11,5,1,""]},"quapy.method.meta.Ensemble":{VALID_POLICIES:[11,4,1,""],accuracy_policy:[11,2,1,""],aggregative:[11,3,1,""],binary:[11,3,1,""],classes_:[11,3,1,""],ds_policy:[11,2,1,""],ds_policy_get_posteriors:[11,2,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],probabilistic:[11,3,1,""],ptr_policy:[11,2,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""],sout:[11,2,1,""]},"quapy.method.neural":{QuaNetModule:[11,1,1,""],QuaNetTrainer:[11,1,1,""],mae_loss:[11,5,1,""]},"quapy.method.neural.QuaNetModule":{device:[11,3,1,""],forward:[11,2,1,""],init_hidden:[11,2,1,""]},"quapy.method.neural.QuaNetTrainer":{classes_:[11,3,1,""],clean_checkpoint:[11,2,1,""],clean_checkpoint_dir:[11,2,1,""],epoch:[11,2,1,""],fit:[11,2,1,""],get_aggregative_estims:[11,2,1,""],get_params:[11,2,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.non_aggregative":{MaximumLikelihoodPrevalenceEstimation:[11,1,1,""]},"quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation":{classes_:[11,3,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.model_selection":{GridSearchQ:[8,1,1,""]},"quapy.model_selection.GridSearchQ":{best_model:[8,2,1,""],classes_:[8,3,1,""],fit:[8,2,1,""],get_params:[8,2,1,""],quantify:[8,2,1,""],set_params:[8,2,1,""]},"quapy.plot":{binary_bias_bins:[8,5,1,""],binary_bias_global:[8,5,1,""],binary_diagonal:[8,5,1,""],brokenbar_supremacy_by_drift:[8,5,1,""],error_by_drift:[8,5,1,""]},"quapy.util":{EarlyStop:[8,1,1,""],create_if_not_exist:[8,5,1,""],create_parent_dir:[8,5,1,""],download_file:[8,5,1,""],download_file_if_not_exists:[8,5,1,""],get_quapy_home:[8,5,1,""],map_parallel:[8,5,1,""],parallel:[8,5,1,""],pickled_resource:[8,5,1,""],save_text_file:[8,5,1,""],temp_seed:[8,5,1,""]},quapy:{classification:[9,0,0,"-"],data:[10,0,0,"-"],error:[8,0,0,"-"],evaluation:[8,0,0,"-"],functional:[8,0,0,"-"],isbinary:[8,5,1,""],method:[11,0,0,"-"],model_selection:[8,0,0,"-"],plot:[8,0,0,"-"],util:[8,0,0,"-"]}},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","property","Python property"],"4":["py","attribute","Python attribute"],"5":["py","function","Python function"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:property","4":"py:attribute","5":"py:function"},terms:{"0":[0,1,3,4,5,8,9,10,11],"00":[0,1,4,8],"000":1,"0001":[4,11],"000e":1,"001":[4,9,11],"005":8,"009":1,"01":[8,9,11],"017":1,"018":0,"02":1,"021":0,"02552":4,"03":1,"034":1,"035":1,"037":1,"04":1,"041":1,"042":1,"046":1,"048":1,"05":[5,8],"055":1,"063":0,"065":0,"070":1,"073":1,"075":1,"078":0,"081":0,"082":[0,1],"083":0,"086":0,"091":1,"099":0,"1":[0,1,3,4,5,8,9,10,11],"10":[0,1,4,5,8,9,11],"100":[0,1,3,4,5,9,10,11],"1000":[0,4,11],"10000":4,"100000":4,"101":[4,10],"1010":4,"1024":11,"104":0,"108":1,"109":0,"11":[0,1,6],"11338":0,"114":1,"1145":[],"12":9,"120":0,"1215742":0,"1271":0,"13":[0,9],"139":0,"14":[3,11],"142":1,"146":[3,11],"1473":0,"148":0,"1484":0,"15":[3,8,11],"150":0,"153":0,"157":0,"158":0,"159":0,"1593":0,"1594":0,"1599":0,"161":0,"163":[0,1],"164":[0,3,11],"167":0,"17":0,"1771":1,"1775":[0,3],"1778":[0,3],"178":0,"1823":0,"1839":0,"18399":0,"1853":0,"19":[3,10,11],"193":0,"199151":0,"19982":4,"1e":9,"1st":0,"2":[0,1,3,5,8,10,11],"20":[5,8,11],"200":[1,9],"2000":0,"2002":[3,11],"2011":4,"2013":[3,11],"2015":[0,2,3,9,11],"2016":[3,10,11],"2017":[0,3,11],"2018":[0,3,10],"2019":[3,11],"2020":4,"20342":4,"206":0,"207":0,"208":0,"21":[1,3,5,8,11],"210":8,"211":0,"2126":0,"2155":0,"21591":0,"218":[3,11],"2184":0,"219e":1,"22":[0,3,9,10,11],"222":0,"222046":0,"226":0,"229":1,"229399":0,"23":9,"235":1,"238":0,"2390":0,"24":[0,9],"243":0,"248563":0,"24866":4,"24987":4,"25":[0,5,8,9,11],"25000":0,"256":[0,9],"26":9,"261":0,"265":0,"266":0,"267":0,"27":[1,3,9,11],"270":0,"2700406":[],"271":0,"272":0,"274":0,"275":1,"27th":[0,3,10],"28":3,"280":0,"281":0,"282":0,"283":[0,1],"288":0,"289":0,"2971":0,"2nd":0,"2t":[1,8],"2tp":8,"2x5fcv":0,"3":[0,1,3,5,6,8,9,10,11],"30":[0,1,3,11],"300":[0,1,9],"305":0,"306":0,"312":0,"32":[0,6],"33":[0,5],"331":0,"333":0,"335":0,"337":0,"34":[0,3,11],"341":0,"346":1,"347":0,"350":0,"351":0,"357":1,"359":0,"361":0,"366":1,"372":0,"373":0,"376132":0,"3765":0,"3813":0,"3821":0,"383e":1,"387e":1,"392":0,"394":0,"399":0,"3f":[1,6],"3rd":0,"4":[0,1,3,4,5,8,11],"40":[0,3,4,11],"404333":0,"407":0,"41":[3,11],"412":0,"412e":1,"413":0,"414":0,"417":0,"41734":4,"42":[1,8],"421":0,"4259":0,"426e":1,"427":0,"430":0,"434":0,"435":1,"43676":4,"437":0,"44":0,"446":0,"45":[3,5,11],"452":0,"459":1,"4601":0,"461":0,"463":0,"465":0,"466":0,"470":0,"48":[3,11],"481":0,"48135":4,"486":0,"4898":0,"492":0,"496":0,"4960":1,"497":0,"5":[0,1,3,4,5,8,9,10,11],"50":[0,5,8,11],"500":[0,1,4,5,11],"5000":[1,5],"5005":4,"507":0,"508":0,"512":[9,11],"514":0,"515e":1,"530":0,"534":0,"535":0,"535e":1,"5379":4,"539":0,"541":1,"546":0,"5473":0,"54it":4,"55":5,"55it":4,"565":1,"569":0,"57":0,"573":0,"578":1,"583":0,"591":[3,11],"5f":4,"5fcv":11,"6":[0,1,3,5,8,10,11],"60":0,"600":1,"601":0,"604":[3,11],"606":0,"625":0,"627":0,"633e":1,"634":1,"64":[9,11],"640":0,"641":0,"650":0,"653":0,"654":1,"66":[1,11],"665":0,"667":0,"669":0,"67":5,"683":0,"688":0,"691":0,"694582":0,"7":[1,5,8,9],"70":0,"700":0,"701e":1,"711":0,"717":1,"725":1,"730":0,"735":0,"740e":1,"748":0,"75":[0,5,8],"762":0,"774":0,"778":0,"787":0,"794":0,"798":0,"8":[0,1,5,10,11],"8000":0,"830":0,"837":1,"858":1,"861":0,"87":[0,3,11],"8788":0,"889504":0,"8d2fhsgcvn0aaaaa":[],"9":[0,1,3,5,8,11],"90":[5,8],"901":0,"909":1,"914":1,"917":0,"919":0,"922":0,"923":0,"935":0,"936":0,"937":0,"945":1,"95":8,"9533":0,"958":0,"97":0,"979":0,"982":0,"99":8,"abstract":[3,9,11],"boolean":8,"case":[0,1,3,4,5,8,11],"class":[0,1,3,4,5,6,8,9,10,11],"d\u00edez":[3,11],"default":[1,3,8,9,10],"do":[0,1,3,4,8,9],"final":[1,3,5],"float":[0,3,8,9,10,11],"function":[0,1,3,4,5,6,7,9,11],"g\u00e1llego":[0,3,11],"gonz\u00e1lez":[3,11],"import":[0,1,3,4,5,6],"int":[0,5,8,10,11],"long":[4,9],"new":[0,3,10,11],"p\u00e9rez":[0,3,11],"return":[0,1,3,4,5,8,9,10,11],"rodr\u0131":[3,11],"short":9,"static":[3,11],"true":[0,1,3,4,5,6,8,9,10,11],"try":4,"while":[3,5,8,9,11],A:[0,3,8,9,10,11],As:[3,4],By:[1,3,8],For:[0,1,5,6,8,11],If:[3,5,8,11],In:[0,1,2,3,4,5,6,9,11],It:[3,4,5,8],One:[0,1,3,11],That:[1,4],The:[0,1,2,4,5,6,8,9,10,11],Then:3,These:0,To:[5,10],_:5,__:[],__class__:5,__name__:5,_adjust:[],_ae_:[],_classify_:11,_error_name_:11,_fit_learner_:11,_kld_:[],_labelledcollection_:11,_learner_:11,_mean:[],_min_df_:10,_my:[],_nkld_:[],_posterior_probabilities_:11,_q_:[],_rae_:[],_svmperf_:[],ab:[],aboud:3,about:[0,5,8],abov:[0,3,5,8],absolut:[1,3,5,6,8],absolute_error:8,abstractmethod:3,acc:[1,3,5,6,8,11],acc_error:8,accept:3,access:[0,3],accommod:0,accord:[1,3,4,8,9],accordingli:5,accuraci:[1,5,8],accuracy_polici:11,achiev:[1,3,4,5],acm:[0,3,10,11],across:[0,1,4,5,6,8],action:[0,11],acut:0,ad:6,add:[3,4,8],add_word:10,addit:3,addition:[0,11],adjust:[3,6,11],adjusted_quantif:8,adjustedclassifyandcount:11,adopt:[3,4],advanc:[0,6],advantag:3,ae:[1,2,5,8],ae_:1,affect:8,after:8,afterward:11,again:5,against:5,aggreg:[1,4,5,6,7,8],aggregativeprobabilisticquantifi:[3,11],aggregativequantifi:[3,11],aggregg:11,aim:[4,5],al:[0,2,9],alaiz:[3,11],alegr:[3,11],alejandro:4,alia:[3,8,11],all:[0,1,2,3,5,8,11],allia:3,alloc:9,allow:[0,1,2,3,5,8,9,10,11],almost:3,along:[0,3,8,11],alreadi:[3,11],also:[0,1,2,3,5,6,8,9],altern:4,although:[3,4,5,11],alwai:[3,4,5],among:3,amount:8,an:[0,1,2,3,4,5,6,8,9,11],analys:[5,6],analysi:[0,3,6,10,11],analyz:5,ani:[0,1,3,4,5,6,8,9,10,11],anoth:[0,1,3,5],anotherdir:8,anyon:0,api:6,app:8,appeal:1,appear:5,append:5,appli:[2,3,4,5,8,9,10],appropri:4,approxim:[1,5,9,11],ar:[0,1,3,4,5,8,9,10,11],archive_filenam:8,archive_path:[],arg:[8,10,11],args_i:8,argu:4,argument:[0,1,3,5,8],arifici:8,aris:1,around:1,arrai:[1,3,5,8,9,10],articl:[3,4,11],artifici:[0,1,3,4,5,6,8],artificial_prevalence_predict:8,artificial_prevalence_protocol:8,artificial_prevalence_report:8,artificial_prevalence_sampl:8,artificial_sampling_ev:[1,4],artificial_sampling_gener:[0,10],artificial_sampling_index_gener:10,artificial_sampling_predict:[1,5],artificial_sampling_report:1,arxiv:4,asarrai:1,asdataload:9,asonam:0,assess:4,assign:[3,8],associ:[8,10],assum:[1,6,11],assumpt:[1,5,6],astyp:10,attempt:3,attribut:11,august:0,autom:[0,3,6],automat:[0,1],av:[3,11],avail:[0,1,2,3,5,6,9],averag:[1,3,8],avoid:[1,8],axi:[5,8],b:[0,10],balanc:[0,4],band:[5,8],bar:8,barranquero:[2,3,9,11],base:[0,3,6,7,8,9],base_classifi:5,base_estim:3,base_quantifier_class:11,baseestim:[9,11],baselin:6,basequantifi:[3,8,11],basic:[5,11],batch:9,batch_siz:9,batch_size_test:9,been:[0,3,4,5,8,10,11],befor:[3,8,9,11],beforehand:8,behav:[3,5],being:[4,8],belief:1,belong:3,below:[0,2,3,5,8,10],best:[4,8,9,11],best_epoch:8,best_model:8,best_model_:4,best_params_:4,best_scor:8,better:4,between:[4,5,6,8,9],beyond:5,bia:[6,8],bias:5,bidirect:11,bin:[5,8,11],bin_bia:5,bin_diag:5,binar:[8,10],binari:[3,5,6,8,9,10,11],binary_bias_bin:[5,8],binary_bias_glob:[5,8],binary_diagon:[5,8],binary_quantifi:11,binaryquantifi:11,block:0,bool:[8,11],both:5,bound:8,box:[5,8],breast:0,brief:1,broken:[5,8],brokenbar_supremacy_by_drift:8,budg:1,budget:[1,4],build:11,bypass:11,c:[3,4,9,10,11],calibr:3,calibratedclassifi:3,calibratedclassifiercv:3,calibratedcv:11,call:[0,1,5,8,11],callabl:[0,8,10],can:[0,1,2,3,4,5,8],cancer:0,cannot:11,cardiotocographi:0,care:11,carri:3,casa_token:[],castano:[3,11],castro:[3,11],categor:3,categori:[1,8],cc:[3,5,11],ceil:8,center:5,chang:[0,1,3,11],character:[3,6],characteriz:[0,3,11],charg:[0,8],chart:8,check:[3,4],checkpoint:[9,11],checkpointdir:11,checkpointnam:11,checkpointpath:9,choic:4,chosen:[4,8],cl:0,class2int:10,class_weight:4,classes_:[8,10,11],classif:[0,1,3,7,8,10,11],classif_posterior:[3,11],classif_predict:[3,11],classif_predictions_bin:11,classifi:[1,4,5,6,9,11],classifier_net:9,classifiermixin:9,classifyandcount:[3,11],classmethod:[0,10,11],classnam:10,classs:8,clean_checkpoint:11,clean_checkpoint_dir:11,clear:5,clearer:1,clearli:5,clip:8,close:1,closer:1,cm:8,cmc:0,cnn:3,cnnnet:[3,9],code:[0,3,4,5,9],coincid:[0,6],col:[0,10],collect:[0,8,9,10],collet:10,color:[5,8],colormap:8,column:[0,10],com:[],combin:[0,1,4,8],combinatio:8,combinations_budget:8,come:0,commandlin:[],common:11,commonli:6,compar:[5,8,11],comparison:5,compil:[2,3],complet:[3,5],compon:[8,9],compress:0,comput:[1,3,5,8,11],computation:4,compute_fpr:11,compute_t:11,compute_tpr:11,concept:6,concur:11,condit:8,conduct:[0,8],confer:[0,3,10],confid:8,configur:[4,8],consecut:[8,9],consid:[3,5,8,9,10],consist:[0,4,5,9,10],constrain:[1,5],constructor:3,consult:[0,1],contain:[1,2,3,5,8,9,10,11],contanin:8,content:7,context:8,contrast:1,control:[1,4],conv_block:[],conv_lay:[],conveni:8,convert:[1,3,9],convolut:9,copi:10,cornel:[],correct:11,correspond:[5,10],cost:1,costli:4,could:[0,1,3,4,5,6,11],count:[4,5,6,10,11],count_:[],counter:10,countvector:10,covari:10,cover:[1,4,9],coz:[0,3,11],cpu:[1,9],creat:[0,6,8],create_if_not_exist:8,create_parent_dir:8,crisp:3,criteria:4,cross:[3,11],cs:[],csr_matrix:10,csv:10,ctg:0,cuda:[3,9,11],cumbersom:1,cumberson:8,curios:5,current:[3,8,9,10],custom:[3,6,8],customarili:[3,4],cv:[3,4],cyan:5,d_:8,dat:[0,9],data:[1,3,4,5,6,7,8,9,11],data_hom:10,datafram:1,dataload:9,dataset:[1,3,4,5,6,7,8,9,11],dataset_nam:10,deal:0,decaesteck:[3,11],decai:9,decim:1,decis:[3,9],decision_funct:9,decomposit:9,dedic:1,deep:[3,8,11],def:[0,1,3,5,8],defin:[0,3,8,9,11],degre:4,del:[0,3,11],delai:8,deliv:3,dens:0,densiti:8,depend:[0,1,4,5,8],describ:[3,8,11],descript:0,design:4,desir:[0,1],despit:1,destin:8,detail:[0,1,3,6,9,11],determin:[1,4,5],detriment:5,devel:10,develop:[4,6],deviat:[0,1,5,8],devic:[0,3,5,9,11],df:[1,10],df_replac:10,diabet:0,diagon:[6,8],dict:[8,10,11],dictionari:[8,9],differ:[0,1,3,4,5,6,8,10],difficult:5,digit:0,dimens:[8,9,10],dimension:[8,9,10],dir:8,directli:[0,1,3],directori:[2,8,9,10],discard:8,discoveri:[3,11],discuss:5,disjoint:9,disk:8,displai:[1,5,8],displaystyl:8,distanc:11,distant:[1,8],distribut:[0,3,5,8,11],diverg:[1,3,8],divid:8,dl:[],doabl:0,doc_embed:11,doc_embedding_s:11,doc_posterior:11,document:[0,1,3,5,9,10,11],document_embed:9,doe:[0,2,3,8],doi:[],done:3,dot:[5,8],dowload:8,down:5,download:[0,2,3,8],download_fil:8,download_file_if_not_exist:8,drawn:[0,1,4],drift:6,drop:[9,11],drop_p:9,dropout:9,ds:[3,11],ds_polici:11,ds_policy_get_posterior:11,dtype:1,dump:10,dure:[1,5],dynam:[3,9,11],e:[0,1,3,4,5,6,8,9,10,11],eacc:11,each:[0,1,3,4,5,8,9,10,11],earli:[8,9],early_stop:11,earlystop:8,easili:[0,2,5,9],ecc:11,edu:[],eemq:11,effect:3,effici:3,ehdi:11,either:[1,3,8,11],element:3,elm:[3,11],em:11,emb:9,embed:[3,9],embed_s:9,embedding_s:9,empti:10,emq:[5,11],enabl:9,encod:10,end:[4,8],endeavour:6,enough:5,ensembl:[0,6,11],ensemblefactori:11,ensure_probabilist:11,entir:[0,3,4,5],environ:[1,3,4,5,8],ep:[1,8],epacc:11,epoch:[8,9,11],epsilon:[1,8,11],equal:[1,8],equidist:[0,8],equip:[3,5],err:8,err_drift:5,err_nam:8,error:[3,4,6,7,9],error_:[],error_by_drift:[5,8],error_funct:1,error_metr:[1,4,8],error_nam:[5,8,11],especi:8,establish:8,estim:[1,3,5,6,8,9,11],estim_prev:[1,5,8],estim_preval:[3,6],esuli:[0,2,3,9,10,11],et:[0,2,9],etc:6,eval_budget:[4,8],evalu:[0,3,4,5,6,7,9],eventu:9,everi:[3,11],everyth:3,evinc:5,ex:[],exact:0,exactli:0,exampl:[0,1,3,4,5,8,9,11],exce:8,excel:0,except:[3,8],exemplifi:0,exhibit:[4,5],exist:8,exist_ok:8,expand_frame_repr:1,expect:6,expectationmaximizationquantifi:[3,11],experi:[1,2,3,4,5,8],explain:[1,5],explicitlossminim:11,explicitlossminimis:11,explor:[4,8],express:10,ext:2,extend:[2,3,11],extens:[0,2,5],extern:3,extract:[1,8],f1:[1,8,9],f1_error:8,f1e:[1,8],f:[0,1,3,4,5,6,10,11],f_1:8,fabrizio:4,facilit:6,fact:[3,5],factor:8,fals:[1,3,5,8,9,10,11],famili:3,familiar:3,far:[8,9],fare:8,fast:8,faster:[0,10],feat1:10,feat2:10,featn:10,featur:0,feature_extract:10,fetch:[0,6],fetch_review:[0,1,3,4,5,10],fetch_twitt:[0,3,6,10],fetch_ucidataset:[0,3,10],fetch_ucilabelledcollect:[0,10],ff_layer:11,fhe:0,file:[0,5,8,9,10],filenam:8,fin:0,find:[0,4],finish:4,first:[0,1,2,3,5,8,10,11],fit:[1,3,4,5,6,8,9,10,11],fit_learn:[3,11],fit_transform:10,fix:[1,4],flag:8,float64:1,fn:8,fold:[3,11],folder:0,follow:[0,1,3,4,5,6,8],fomart:10,for_model_select:[0,10],form:[0,8],format:[0,5,10],former:[2,11],forward:[9,11],found:[0,3,4,8,9],four:3,fp:[8,11],fpr:8,frac:8,framework:6,frequenc:0,from:[0,1,3,4,5,6,8,10,11],from_csv:10,from_nam:[1,8],from_spars:10,from_text:10,full:[1,8],fulli:0,func:8,further:[0,1,3,9],fusion:[0,3,11],futur:3,g:[0,1,3,4,6,8,10,11],gain:8,gao:[0,3,10,11],gasp:[0,10],gen:8,gen_data:5,gen_fn:8,gen_prevalence_predict:8,gener:[0,1,3,4,5,8,9,10,11],generation_func:8,german:0,get:[0,1,5,8,9],get_aggregative_estim:11,get_nprevpoints_approxim:[1,8],get_param:[3,8,9,11],get_probability_distribut:11,get_quapy_hom:8,github:[],given:[1,3,4,8,9,11],global:8,goe:4,good:[4,5],got:4,govern:1,gpu:9,grant:11,grid:[4,8,11],gridsearchcv:4,gridsearchq:[4,8],group:3,guarante:11,guez:[3,11],gzip:0,ha:[3,4,5,8,9],haberman:[0,3],handl:0,happen:[4,5],hard:3,harder:5,harmon:8,harri:0,hat:8,have:[0,1,2,3,4,5,8,10,11],hcr:[0,3,10],hdy:[6,11],held:[3,4,8,9],helling:11,hellingerdist:8,hellingerdistancei:[3,11],help:5,henc:8,here:1,hidden:[5,9],hidden_s:9,hide:5,high:[5,8],higher:[1,5],highlight:8,hightlight:8,hlt:[],hold:[6,8],home:[8,10],hook:11,how:[0,1,3,4,5,8,11],howev:[0,4,5,11],hp:[0,3,4,10],html:[],http:[],hyper:[4,8,9],hyperparam:4,hyperparamet:[3,8,11],i:[0,1,3,4,5,8,9,10,11],id:[0,3,10],identifi:8,idf:0,ieee:0,ignor:[8,10,11],ii:8,iid:[1,5,6],illustr:[3,4,5],imdb:[0,5,10],implement:[0,1,3,4,5,6,8,9,11],impos:[4,8],improv:[3,8,9],includ:[0,1,3,5,6],inconveni:8,inde:[3,4],independ:8,index:[0,3,6,8,9,10],indextransform:10,indic:[0,1,3,4,5,8,10,11],individu:[1,3],infer:0,inform:[0,1,3,4,8,10,11],infrequ:10,inherit:3,init:3,init_hidden:11,initi:[0,9],inplac:[1,3,10],input:[3,5,8,9],insight:5,inspir:3,instal:[0,3,6,9],instanc:[0,3,4,5,6,8,9,10,11],instanti:[0,1,3,4,9],instead:[1,3,4,11],integ:[3,9,10],integr:6,interest:[1,5,6,8],interestingli:5,interfac:[0,1],intern:[0,3,10],interpret:[5,6],interv:[1,5,8],introduc:1,invok:[0,1,3,8,10],involv:[2,5,8],io:[],ionospher:0,iri:0,irrespect:5,isaggreg:11,isbinari:[8,10,11],isomer:8,isometr:[5,8],isprobabilist:11,isti:[],item:8,iter:[0,8,11],its:[3,4,8,9],itself:[3,8,11],j:[0,3,11],joachim:[3,9],job:[2,8],joblib:2,join:8,just:[1,3],k:[3,6,11],keep:8,kei:8,kept:10,kernel:9,kernel_height:9,kfcv:[0,10,11],kindl:[0,1,3,5,10],kl:8,kld:[1,2,8,9],know:3,knowledg:[0,3,10,11],known:[0,3,4],kullback:[1,3,8],kwarg:[9,10,11],l1:11,label:[0,3,4,5,6,8,9,10,11],labelledcollect:[0,3,4,8,10,11],larg:4,largest:8,last:[1,3,5,8,9],lastli:3,latex:5,latinn:[3,11],latter:11,layer:[3,9],lead:1,learn:[1,2,3,4,6,8,9,11],learner:[3,4,9,11],least:[0,10],leav:10,legend:8,leibler:[1,3,8],length:9,less:[8,10],let:[1,3],level:11,leverag:3,leyend:8,like:[0,1,3,5,8,9],limit:[5,8],line:[1,3,8],linear:5,linear_model:[1,3,4,6,9],linearsvc:[3,5],linspac:5,list:[0,5,8,9,10],listedcolormap:8,literatur:[0,1,4,6],load:[0,3,8,10],loader:0,loader_func:[0,10],local:8,log:[8,10],logist:[1,3,9,11],logisticregress:[1,3,4,6,9],logscal:8,logspac:4,longer:8,longest:9,look:[0,1,3,5],loss:[6,9,11],low:[5,8,9],lower:[5,8],lower_is_bett:8,lowest:5,lowranklogisticregress:9,lr:[1,3,9,11],lstm:[3,9],lstm_class_nlay:9,lstm_hidden_s:11,lstm_nlayer:11,lstmnet:9,m:[3,8,11],machin:[1,4,6],macro:8,made:[0,2,8,11],mae:[1,4,6,8,9,11],mae_loss:11,mai:8,main:5,maintain:[3,11],make:[0,1,3],makedir:8,mammograph:0,manag:[0,3,10],mani:[1,3,4,5,6,8,11],manner:0,manual:0,map:[1,9],map_parallel:8,margin:9,math:[],mathcal:8,matplotlib:[2,8],matric:[0,5,10],matrix:5,max:11,max_it:11,max_sample_s:11,maxim:6,maximum:[1,8,9],maximumlikelihoodprevalenceestim:11,md:[],mean:[0,1,3,4,5,6,8,9,10,11],mean_absolute_error:8,mean_relative_absolute_error:8,measur:[2,3,4,5,6,8,11],mediansweep2:11,mediansweep:11,member:3,memori:9,mention:3,merg:5,meta:[6,7,8],meth:[],method:[0,1,4,5,6,7,8],method_data:5,method_nam:[5,8],method_ord:8,metric:[1,3,4,6,8],might:[1,8],min_df:[1,3,4,5,10],min_po:11,mine:[0,3,11],minim:8,minimum:10,minimun:10,mining6:10,minu:8,miss:8,mixtur:3,mkld:[1,8,11],mnkld:[1,8,11],mock:[8,9],modal:4,model:[0,1,5,6,8,9,11],model_select:[4,7],modifi:[3,8],modul:[0,1,3,5,6,7],moment:[0,3],monitor:8,more:[3,5,8],moreo:[0,3,4,10],most:[0,3,5,6,8,11],movi:0,mrae:[1,6,8,9,11],ms2:11,ms:11,mse:[1,3,6,8,11],msg:11,multiclass:8,multiprocess:8,multivari:[3,9,11],must:3,my:[],my_arrai:8,my_custom_load:0,my_data:0,mycustomloss:3,n:[0,1,8,9],n_bin:[5,8],n_class:[1,3,8,9,10,11],n_compon:9,n_dimens:9,n_epoch:11,n_featur:9,n_instanc:9,n_job:[1,3,4,8,10,11],n_preval:[0,8,10],n_prevpoint:[1,4,5,8],n_repeat:[1,8],n_repetit:[1,4,5,8],n_sampl:[8,9],name:[5,8,9,10],nativ:6,natur:[1,8],natural_prevalence_predict:8,natural_prevalence_protocol:8,natural_prevalence_report:8,natural_sampling_gener:10,natural_sampling_index_gener:10,nbin:[5,8],ndarrai:[1,3,8,10,11],necessarili:11,need:[0,3,11],neg:[0,5,8],nest:[],net:9,network:[0,8,9,10,11],neural:[0,7,8,10],neuralclassifiertrain:[3,9],neutral:0,next:[4,8,9],nfold:[0,10],nkld:[1,2,6,8,9],nn:[9,11],nogap:10,non:[3,11],non_aggreg:[7,8],none:[1,4,8,9,10,11],nonetheless:4,nor:3,normal:[0,1,3,8,11],normalize_preval:8,note:[1,3,4,5],now:5,nowadai:3,np:[1,3,4,5,8],npp:8,nprevpoint:8,nrepeat:[0,10],num_prevalence_combin:[1,8],number:[0,1,3,5,8,9,10,11],numer:[0,1,3,6,10],numpi:[2,4,8,9,11],o_l6x_pcf09mdetq4tu7jk98mxfbgsxp9zso14jkuiyudgfg0:[],object:[0,8,9,10,11],observ:1,obtain:[1,4,8],obtaind:8,occur:[5,10],occurr:10,octob:[0,3],off:9,offer:[3,6],older:2,omd:[0,10],ommit:1,onc:[1,3,5,8],one:[0,1,3,4,5,8,11],ones:[1,3,5,8,10],onevsal:[3,11],onli:[0,3,5,8,9,11],open:[0,6],oper:3,opt:4,optim:[2,3,4,8,9,11],optimize_threshold:11,option:[0,1,3,5,8,10,11],order:[0,2,3,5,8,10,11],order_bi:11,org:[],orient:[3,6,8,11],origin:[0,3,10,11],os:[0,8],other:[1,3,5,6,8],otherwis:[0,3,11],our:[],out:[3,4,5,8,9],outcom:5,outer:8,outlier:8,output:[0,1,3,4,9,11],over:[3,4,8],overal:1,overestim:5,overrid:3,overridden:[3,11],own:4,p:[0,3,8,11],p_hat:8,pacc:[1,3,5,11],packag:[0,2,3,6,7],pad:9,pad_length:9,padding_length:9,page:[0,2,6],pageblock:0,pair:[0,8],panda:[1,2],paper:[0,3,11],parallel:[1,3,8],param:[4,8,9,10,11],param_grid:[4,8,11],param_mod_sel:11,param_model_sel:11,paramet:[1,3,4,8,9,10,11],parent:8,part:[3,10],particular:[0,1,3],particularli:1,pass:[0,1,5,8,9,11],past:1,patch:[2,3,9],path:[0,3,5,8,9,10],patienc:[8,9,11],pattern:[3,11],pca:[],pcalr:[],pcc:[3,4,5,11],pd:1,pdf:5,peopl:[],percentil:8,perf:[6,9],perform:[1,3,4,5,6,8,9,11],perman:8,phonem:0,pick:4,pickl:[3,8,10],pickle_path:8,pickled_resourc:8,pii:[],pip:2,pipelin:[],pkl:8,plai:0,plan:3,pleas:3,plot:[6,7],png:5,point:[0,1,3,8],polici:[3,11],popular:6,portion:4,pos_class:[8,10],posit:[0,3,5,8],possibl:[1,3,8],posterior:[3,8,9,11],posterior_prob:[3,11],postpon:3,potter:0,pp:[0,3],practic:[0,4],pre:[0,3],prec:[0,8],precis:[0,1,8],preclassifi:3,predict:[3,4,5,8,9,11],predict_proba:[3,9,11],predictor:1,prefer:8,prepare_svmperf:[2,3],preprint:4,preprocess:[0,1,3,7,8],present:[0,3,10],preserv:[1,5],pretti:5,prev:[0,1,8,10],prevail:3,preval:[0,1,3,4,5,6,8,10,11],prevalence_estim:8,prevalence_from_label:8,prevalence_from_prob:8,prevalence_linspac:8,prevel:11,previou:3,previous:11,prevs_estim:11,prevs_hat:[1,8],princip:9,print:[0,1,3,4,6,9],prior:[1,3,4,5,6,8],priori:[3,11],probabilist:[3,11],probabilisticadjustedclassifyandcount:11,probabilisticclassifyandcount:11,probabl:[1,3,4,5,6,8,9,11],problem:[0,3,5,8,11],procedur:[3,6,11],proceed:[0,3,10],process:[3,4,8],processor:3,procol:1,produc:[0,1,5,8],product:3,progress:8,properli:0,properti:[3,8,9,10,11],proport:[3,4,8,9,11],propos:[2,3,11],protocl:8,protocol:[0,3,4,5,6,8],provid:[0,3,5,6],ptecondestim:11,ptr:[3,11],ptr_polici:11,purpos:[0,11],python:[0,6],pytorch:2,q:[0,2,3,8,9],qacc:9,qdrop_p:11,qf1:9,qgm:9,qp:[0,1,3,4,5,6,8],quanet:[2,6,9,11],quanetmodul:11,quanettrain:11,quantif:[0,1,6,8,9,10,11],quantifi:[3,4,5,6,8,11],quantification_error:8,quantiti:8,quapi:[0,1,2,3,4,5],quapy_data:0,quay_data:10,quevedo:[0,3,11],quick:[],r:[0,3,11],rac:[],rae:[1,2,8],rais:[3,8],rand:8,random:[1,3,4,5,8],random_se:[1,8],random_st:10,randomli:0,rang:[0,5],rank:[3,9],rare:10,rate:[3,9],rather:[1,4],raw:10,rb:0,re:[3,4,10],read:10,reader:[7,8],readm:[],real:[9,10],reason:[3,5,6],recal:8,receiv:[0,3,5],recip:11,recognit:[3,11],recommend:[1,5],recurr:[0,3,10],red:0,red_siz:[3,11],reduc:[0,10],reduce_column:[0,10],refer:[9,10],refit:[4,8],regard:4,regim:8,region:8,regist:11,regress:9,regressor:[1,3,11],reindex_label:10,reiniti:9,rel:[1,3,8],relative_absolute_error:8,reli:[1,3],reliabl:[3,11],rememb:5,remov:10,repeat:[8,10],repetit:8,repl:10,replac:[0,3,10],replic:[1,4,8],report:1,repositori:0,repr_siz:9,repres:[1,3,5,8,10,11],represent:[0,3,9],request:[0,8,11],requir:[0,1,3,6,9],reset_net_param:9,resourc:8,respect:[0,1,5,8,11],respond:3,rest:[10,11],result:[1,2,3,4,5,6,11],retain:[0,3,9],retrain:4,return_constrained_dim:8,reus:[0,3,8],review:[5,6,10],reviews_sentiment_dataset:0,rewrit:5,right:[4,8],role:0,root:6,roughli:0,routin:8,row:10,run:[0,1,2,3,4,5,8,11],s003132031400291x:[],s:[0,1,3,4,5,8,9,10],saeren:[3,11],sai:11,said:3,same:[0,3,5,8,10],sampl:[0,1,3,4,5,6,8,9,10,11],sample_s:[0,1,3,4,5,8,10,11],sampling_from_index:[0,10],sampling_index:[0,10],sander:[0,10],save:[5,8],save_or_show:[],save_text_fil:8,savepath:[5,8],scale:8,scall:10,scenario:[1,3,4,5,6],scienc:[3,11],sciencedirect:[],scikit:[2,3,4],scipi:[2,10],score:[0,1,4,8,9,10],script:[1,2,3,6],se:[1,8],search:[3,4,6,8,11],sebastiani:[0,3,4,10,11],second:[0,1,3,5,8],secondari:8,section:4,see:[0,1,2,3,4,5,6,8,9],seed:[1,4,8],seem:3,seemingli:5,seen:[5,8],select:[0,3,6,8,11],selector:3,self:[3,8,9,10,11],semeion:0,semev:0,semeval13:[0,10],semeval14:[0,10],semeval15:[0,10],semeval16:[0,6,10],sentenc:10,sentiment:[3,6,10,11],separ:[8,10],seri:0,serv:3,set:[0,1,3,4,5,6,8,9,10,11],set_opt:1,set_param:[3,8,9,11],set_siz:[],sever:0,sh:[2,3],shape:[5,8,9],share:[0,10],shift:[1,4,6,8],shorter:9,shoud:3,should:[0,1,3,4,5,6,9,10,11],show:[0,1,3,4,5,8,9,10],show_dens:8,show_std:[5,8],showcas:5,shown:[1,5,8],shuffl:[9,10],side:8,sign:8,signific:1,significantli:8,silent:[8,11],similar:[8,11],simpl:[0,3,5,11],simplest:3,simplex:[0,8],simpli:[1,2,3,4,5,6,8,11],sinc:[0,1,3,5,8,11],singl:[1,3,6,11],size:[0,1,3,8,9,10,11],sklearn:[1,3,4,5,6,9,10,11],sld:3,slice:8,smooth:[1,8],smooth_limits_epsilon:8,so:[0,1,3,5,8,9,11],social:[0,3,10,11],soft:3,softwar:0,solid:5,solv:4,solve_adjust:11,some:[0,1,3,5,8],some_arrai:8,sometim:1,sonar:0,sourc:[2,3,6,9],sout:11,space:[0,4,8,9],spambas:0,spars:[0,10],special:[0,5,10],specif:[3,4],specifi:[0,1,3,5,8,9,10,11],spectf:0,spectrum:[0,1,4,5,8],speed:3,split:[0,3,4,5,8,9,10,11],split_stratifi:10,splitstratifi:10,spmatrix:10,squar:[1,3,8],sst:[0,10],stabil:1,stand:8,standard:[0,1,5,8,10],start:4,stat:10,state:8,statist:[0,1,8,11],stats_siz:11,std:9,stdout:8,step:[5,8],stop:[8,9],store:[0,9,10],str:[0,8,10],strategi:[3,4],stratifi:[0,3],stride:9,string:[1,8,10],strongli:[4,5],strprev:[0,1,8],structur:3,studi:[0,3,11],subclass:11,subdir:8,subinterv:5,sublinear_tf:10,submit:0,submodul:7,subobject:[],suboptim:4,subpackag:7,subsequ:[10,11],subtract:[0,8],subtyp:10,suffic:5,suffici:11,sum:11,sum_:8,summar:0,supervis:[4,6],support:[3,6,9],surpass:1,svm:[3,5,6,9],svm_light:[],svm_perf:[],svm_perf_classifi:9,svm_perf_learn:9,svm_perf_quantif:[2,3],svmae:[3,11],svmkld:[3,11],svmnkld:[3,11],svmperf:[2,3,7,8],svmperf_bas:[9,11],svmperf_hom:3,svmq:[3,11],svmrae:[3,11],syntax:5,system:4,t50:11,t:[0,1,3,8],tab10:8,tail:8,tail_density_threshold:8,take:[0,3,5,8,11],taken:[3,8,9],target:[3,5,6,8,9,11],task:[3,4,11],temp_se:8,tempor:8,tend:5,tendenc:5,tensor:9,term:[0,1,3,4,5,6,8,9,10,11],test:[0,1,3,4,5,6,8,9,10,11],test_bas:[],test_dataset:[],test_method:[],test_path:[0,10],test_sampl:8,test_split:10,text2tfidf:[0,1,3,10],text:[0,3,8,9,10,11],textclassifiernet:9,textual:[0,6,10],tf:[0,10],tfidf:[0,4,5,10],tfidfvector:10,than:[1,4,5,8,9,10],thei:[0,3],them:[0,3,11],theoret:4,thereaft:1,thi:[0,1,2,3,4,5,6,8,9,11],thing:3,third:[1,5],thorsten:9,those:[1,3,4,5,8,9],though:[3,8],three:[0,5],threshold:8,thresholdoptim:11,through:[3,8],thu:[3,4,5,8,11],tictacto:0,time:[0,1,3,8,10],timeout:8,timeouterror:8,timer:8,titl:8,tj:[],tn:[8,11],token:[0,9,10],tool:[1,6],top:[3,8,11],torch:[3,9,11],torchdataset:9,total:8,toward:5,tp:[8,11],tpr:8,tqdm:2,tr_iter_per_poch:11,tr_prev:[5,8,11],track:8,trade:9,tradition:1,train:[0,1,3,4,5,6,8,9,10,11],train_path:[0,10],train_prev:[5,8],train_prop:10,train_siz:10,train_val_split:11,trainer:9,training_help:11,training_preval:5,training_s:5,transact:[3,11],transform:[0,9,10],transfus:0,trivial:3,true_prev:[1,5,8],true_preval:6,truncatedsvd:9,ttest_alpha:8,turn:4,tweet:[0,3,10,11],twitter:[6,10],twitter_sentiment_datasets_test:0,twitter_sentiment_datasets_train:0,two:[0,1,3,4,5,8],txt:8,type:[0,3,8],typic:[1,4,5,8,9],uci:6,unabl:0,unadjust:5,unalt:9,unbias:5,uncompress:0,under:1,underestim:5,underlin:8,understand:8,unfortun:5,unifi:0,uniform_prevalence_sampl:8,uniform_sampl:10,uniform_sampling_index:10,uniform_simplex_sampl:8,uniformli:8,union:[8,11],uniqu:10,unit:0,unix:0,unk:10,unless:11,unlik:[1,4],unus:[8,9,11],up:[3,4,8,9,11],updat:[],url:8,us:[0,1,3,4,5,6,8,9,10,11],user:[0,1,5],utf:10,util:[7,9],v:[3,11],va_iter_per_poch:11,val:[0,10],val_split:[3,4,8,9,11],valid:[0,1,3,4,5,8,9,10,11],valid_loss:[3,9],valid_polici:11,valu:[0,1,3,8,9,10,11],variabl:[1,3,5,8],varianc:[0,5],variant:[5,6,11],varieti:4,variou:[1,5],vector:[0,8,9,10],verbos:[0,1,4,8,9,10,11],veri:[3,5],versatil:6,version:[2,9],vertic:8,vertical_xtick:8,via:[0,2,3,11],view:5,visual:[5,6],vline:8,vocab_s:9,vocabulari:[9,10],vocabulary_s:[3,9,10],vs:[3,8],w:[0,3,10,11],wa:[0,3,5,8,10,11],wai:[1,11],wait:9,want:[3,4],warn:10,wb:[0,10],wdbc:0,we:[0,1,3,4,5,6],weight:[9,10],weight_decai:9,well:[0,3,4,5],were:0,what:3,when:[0,1,3,4,5,8,9],whenev:[5,8],where:[3,5,8,9,10,11],wherebi:4,whether:[8,9,10,11],which:[0,1,3,4,5,8,9,10,11],white:0,whole:[0,1,3,4,8],why:3,wide:5,wiki:[0,3],wine:0,within:[8,11],without:[1,3,8],word:[1,3,6,9,10],work:[1,3,4,5],worker:[1,8],wors:[4,5,8],would:[0,1,3,5,6,8,11],wrapper:[8,9],written:6,www:[],x:[5,8,9,10,11],x_error:8,xavier:9,xavier_uniform:9,xlrd:[0,2],xy:10,y:[5,8,9,10,11],y_:11,y_error:8,y_pred:8,y_true:8,ye:10,yeast:0,yield:[5,8],yin:[],you:[2,3],your:3,z:0,zero:[0,8],zfthyovrzwxmgfzylqw_y8cagg:[],zip:[0,5]},titles:["Datasets","Evaluation","Installation","Quantification Methods","Model Selection","Plotting","Welcome to QuaPy\u2019s documentation!","quapy","quapy package","quapy.classification package","quapy.data package","quapy.method package"],titleterms:{"function":8,A:6,The:3,ad:0,aggreg:[3,11],base:[10,11],bia:5,classif:[4,9],classifi:3,content:[6,8,9,10,11],count:3,custom:0,data:[0,10],dataset:[0,10],diagon:5,distanc:3,document:6,drift:5,emq:3,ensembl:3,error:[1,5,8],evalu:[1,8],ex:[],exampl:6,expect:3,explicit:3,featur:6,get:[],hdy:3,helling:3,indic:6,instal:2,introduct:6,issu:0,learn:0,loss:[2,3,4],machin:0,maxim:3,measur:1,meta:[3,11],method:[3,9,11],minim:3,model:[3,4],model_select:8,modul:[8,9,10,11],network:3,neural:[3,9,11],non_aggreg:11,orient:[2,4],packag:[8,9,10,11],perf:2,plot:[5,8],preprocess:10,process:0,protocol:1,quanet:3,quantif:[2,3,4,5],quapi:[6,7,8,9,10,11],quick:6,reader:10,readm:[],requir:2,review:0,s:6,select:4,sentiment:0,start:[],submodul:[8,9,10,11],subpackag:8,svm:2,svmperf:9,tabl:6,target:4,test:[],test_bas:[],test_dataset:[],test_method:[],titl:[],twitter:0,uci:0,util:8,variant:3,welcom:6,y:3}})
\ No newline at end of file
+Search.setIndex({docnames:["Datasets","Evaluation","Installation","Methods","Model-Selection","Plotting","index","modules","quapy","quapy.classification","quapy.data","quapy.method"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,sphinx:56},filenames:["Datasets.md","Evaluation.md","Installation.rst","Methods.md","Model-Selection.md","Plotting.md","index.rst","modules.rst","quapy.rst","quapy.classification.rst","quapy.data.rst","quapy.method.rst"],objects:{"":{quapy:[8,0,0,"-"]},"quapy.classification":{methods:[9,0,0,"-"],neural:[9,0,0,"-"],svmperf:[9,0,0,"-"]},"quapy.classification.methods":{LowRankLogisticRegression:[9,1,1,""]},"quapy.classification.methods.LowRankLogisticRegression":{fit:[9,2,1,""],get_params:[9,2,1,""],predict:[9,2,1,""],predict_proba:[9,2,1,""],set_params:[9,2,1,""],transform:[9,2,1,""]},"quapy.classification.neural":{CNNnet:[9,1,1,""],LSTMnet:[9,1,1,""],NeuralClassifierTrainer:[9,1,1,""],TextClassifierNet:[9,1,1,""],TorchDataset:[9,1,1,""]},"quapy.classification.neural.CNNnet":{document_embedding:[9,2,1,""],get_params:[9,2,1,""],vocabulary_size:[9,3,1,""]},"quapy.classification.neural.LSTMnet":{document_embedding:[9,2,1,""],get_params:[9,2,1,""],vocabulary_size:[9,3,1,""]},"quapy.classification.neural.NeuralClassifierTrainer":{device:[9,3,1,""],fit:[9,2,1,""],get_params:[9,2,1,""],predict:[9,2,1,""],predict_proba:[9,2,1,""],reset_net_params:[9,2,1,""],set_params:[9,2,1,""],transform:[9,2,1,""]},"quapy.classification.neural.TextClassifierNet":{dimensions:[9,2,1,""],document_embedding:[9,2,1,""],forward:[9,2,1,""],get_params:[9,2,1,""],predict_proba:[9,2,1,""],vocabulary_size:[9,3,1,""],xavier_uniform:[9,2,1,""]},"quapy.classification.neural.TorchDataset":{asDataloader:[9,2,1,""]},"quapy.classification.svmperf":{SVMperf:[9,1,1,""]},"quapy.classification.svmperf.SVMperf":{decision_function:[9,2,1,""],fit:[9,2,1,""],predict:[9,2,1,""],set_params:[9,2,1,""],valid_losses:[9,4,1,""]},"quapy.data":{base:[10,0,0,"-"],datasets:[10,0,0,"-"],preprocessing:[10,0,0,"-"],reader:[10,0,0,"-"]},"quapy.data.base":{Dataset:[10,1,1,""],LabelledCollection:[10,1,1,""],isbinary:[10,5,1,""]},"quapy.data.base.Dataset":{SplitStratified:[10,2,1,""],binary:[10,3,1,""],classes_:[10,3,1,""],kFCV:[10,2,1,""],load:[10,2,1,""],n_classes:[10,3,1,""],stats:[10,2,1,""],vocabulary_size:[10,3,1,""]},"quapy.data.base.LabelledCollection":{Xy:[10,3,1,""],artificial_sampling_generator:[10,2,1,""],artificial_sampling_index_generator:[10,2,1,""],binary:[10,3,1,""],counts:[10,2,1,""],kFCV:[10,2,1,""],load:[10,2,1,""],n_classes:[10,3,1,""],natural_sampling_generator:[10,2,1,""],natural_sampling_index_generator:[10,2,1,""],prevalence:[10,2,1,""],sampling:[10,2,1,""],sampling_from_index:[10,2,1,""],sampling_index:[10,2,1,""],split_stratified:[10,2,1,""],stats:[10,2,1,""],uniform_sampling:[10,2,1,""],uniform_sampling_index:[10,2,1,""]},"quapy.data.datasets":{fetch_UCIDataset:[10,5,1,""],fetch_UCILabelledCollection:[10,5,1,""],fetch_reviews:[10,5,1,""],fetch_twitter:[10,5,1,""],warn:[10,5,1,""]},"quapy.data.preprocessing":{IndexTransformer:[10,1,1,""],index:[10,5,1,""],reduce_columns:[10,5,1,""],standardize:[10,5,1,""],text2tfidf:[10,5,1,""]},"quapy.data.preprocessing.IndexTransformer":{add_word:[10,2,1,""],fit:[10,2,1,""],fit_transform:[10,2,1,""],transform:[10,2,1,""],vocabulary_size:[10,2,1,""]},"quapy.data.reader":{binarize:[10,5,1,""],from_csv:[10,5,1,""],from_sparse:[10,5,1,""],from_text:[10,5,1,""],reindex_labels:[10,5,1,""]},"quapy.error":{absolute_error:[8,5,1,""],acc_error:[8,5,1,""],acce:[8,5,1,""],ae:[8,5,1,""],f1_error:[8,5,1,""],f1e:[8,5,1,""],from_name:[8,5,1,""],kld:[8,5,1,""],mae:[8,5,1,""],mean_absolute_error:[8,5,1,""],mean_relative_absolute_error:[8,5,1,""],mkld:[8,5,1,""],mnkld:[8,5,1,""],mrae:[8,5,1,""],mse:[8,5,1,""],nkld:[8,5,1,""],rae:[8,5,1,""],relative_absolute_error:[8,5,1,""],se:[8,5,1,""],smooth:[8,5,1,""]},"quapy.evaluation":{artificial_prevalence_prediction:[8,5,1,""],artificial_prevalence_protocol:[8,5,1,""],artificial_prevalence_report:[8,5,1,""],evaluate:[8,5,1,""],gen_prevalence_prediction:[8,5,1,""],natural_prevalence_prediction:[8,5,1,""],natural_prevalence_protocol:[8,5,1,""],natural_prevalence_report:[8,5,1,""]},"quapy.functional":{HellingerDistance:[8,5,1,""],adjusted_quantification:[8,5,1,""],artificial_prevalence_sampling:[8,5,1,""],get_nprevpoints_approximation:[8,5,1,""],normalize_prevalence:[8,5,1,""],num_prevalence_combinations:[8,5,1,""],prevalence_from_labels:[8,5,1,""],prevalence_from_probabilities:[8,5,1,""],prevalence_linspace:[8,5,1,""],strprev:[8,5,1,""],uniform_prevalence_sampling:[8,5,1,""],uniform_simplex_sampling:[8,5,1,""]},"quapy.method":{aggregative:[11,0,0,"-"],base:[11,0,0,"-"],meta:[11,0,0,"-"],neural:[11,0,0,"-"],non_aggregative:[11,0,0,"-"]},"quapy.method.aggregative":{ACC:[11,1,1,""],AdjustedClassifyAndCount:[11,4,1,""],AggregativeProbabilisticQuantifier:[11,1,1,""],AggregativeQuantifier:[11,1,1,""],CC:[11,1,1,""],ClassifyAndCount:[11,4,1,""],ELM:[11,1,1,""],EMQ:[11,1,1,""],ExpectationMaximizationQuantifier:[11,4,1,""],ExplicitLossMinimisation:[11,4,1,""],HDy:[11,1,1,""],HellingerDistanceY:[11,4,1,""],MAX:[11,1,1,""],MS2:[11,1,1,""],MS:[11,1,1,""],MedianSweep2:[11,4,1,""],MedianSweep:[11,4,1,""],OneVsAll:[11,1,1,""],PACC:[11,1,1,""],PCC:[11,1,1,""],ProbabilisticAdjustedClassifyAndCount:[11,4,1,""],ProbabilisticClassifyAndCount:[11,4,1,""],SVMAE:[11,1,1,""],SVMKLD:[11,1,1,""],SVMNKLD:[11,1,1,""],SVMQ:[11,1,1,""],SVMRAE:[11,1,1,""],T50:[11,1,1,""],ThresholdOptimization:[11,1,1,""],X:[11,1,1,""],training_helper:[11,5,1,""]},"quapy.method.aggregative.ACC":{aggregate:[11,2,1,""],classify:[11,2,1,""],fit:[11,2,1,""],solve_adjustment:[11,2,1,""]},"quapy.method.aggregative.AggregativeProbabilisticQuantifier":{posterior_probabilities:[11,2,1,""],predict_proba:[11,2,1,""],probabilistic:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.aggregative.AggregativeQuantifier":{aggregate:[11,2,1,""],aggregative:[11,3,1,""],classes_:[11,3,1,""],classify:[11,2,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],learner:[11,3,1,""],n_classes:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.aggregative.CC":{aggregate:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.ELM":{aggregate:[11,2,1,""],classify:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.EMQ":{EM:[11,2,1,""],EPSILON:[11,4,1,""],MAX_ITER:[11,4,1,""],aggregate:[11,2,1,""],fit:[11,2,1,""],predict_proba:[11,2,1,""]},"quapy.method.aggregative.HDy":{aggregate:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.MS":{optimize_threshold:[11,2,1,""]},"quapy.method.aggregative.MS2":{optimize_threshold:[11,2,1,""]},"quapy.method.aggregative.OneVsAll":{aggregate:[11,2,1,""],binary:[11,3,1,""],classes_:[11,3,1,""],classify:[11,2,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],posterior_probabilities:[11,2,1,""],probabilistic:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.aggregative.PACC":{aggregate:[11,2,1,""],classify:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.PCC":{aggregate:[11,2,1,""],fit:[11,2,1,""]},"quapy.method.aggregative.ThresholdOptimization":{aggregate:[11,2,1,""],compute_fpr:[11,2,1,""],compute_table:[11,2,1,""],compute_tpr:[11,2,1,""],fit:[11,2,1,""],optimize_threshold:[11,2,1,""]},"quapy.method.base":{BaseQuantifier:[11,1,1,""],BinaryQuantifier:[11,1,1,""],isaggregative:[11,5,1,""],isbinary:[11,5,1,""],isprobabilistic:[11,5,1,""]},"quapy.method.base.BaseQuantifier":{aggregative:[11,3,1,""],binary:[11,3,1,""],classes_:[11,3,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],probabilistic:[11,3,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.base.BinaryQuantifier":{binary:[11,3,1,""]},"quapy.method.meta":{EACC:[11,5,1,""],ECC:[11,5,1,""],EEMQ:[11,5,1,""],EHDy:[11,5,1,""],EPACC:[11,5,1,""],Ensemble:[11,1,1,""],ensembleFactory:[11,5,1,""],get_probability_distribution:[11,5,1,""]},"quapy.method.meta.Ensemble":{VALID_POLICIES:[11,4,1,""],accuracy_policy:[11,2,1,""],aggregative:[11,3,1,""],binary:[11,3,1,""],classes_:[11,3,1,""],ds_policy:[11,2,1,""],ds_policy_get_posteriors:[11,2,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],probabilistic:[11,3,1,""],ptr_policy:[11,2,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""],sout:[11,2,1,""]},"quapy.method.neural":{QuaNetModule:[11,1,1,""],QuaNetTrainer:[11,1,1,""],mae_loss:[11,5,1,""]},"quapy.method.neural.QuaNetModule":{device:[11,3,1,""],forward:[11,2,1,""],init_hidden:[11,2,1,""]},"quapy.method.neural.QuaNetTrainer":{classes_:[11,3,1,""],clean_checkpoint:[11,2,1,""],clean_checkpoint_dir:[11,2,1,""],epoch:[11,2,1,""],fit:[11,2,1,""],get_aggregative_estims:[11,2,1,""],get_params:[11,2,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.method.non_aggregative":{MaximumLikelihoodPrevalenceEstimation:[11,1,1,""]},"quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation":{classes_:[11,3,1,""],fit:[11,2,1,""],get_params:[11,2,1,""],quantify:[11,2,1,""],set_params:[11,2,1,""]},"quapy.model_selection":{GridSearchQ:[8,1,1,""]},"quapy.model_selection.GridSearchQ":{best_model:[8,2,1,""],classes_:[8,3,1,""],fit:[8,2,1,""],get_params:[8,2,1,""],quantify:[8,2,1,""],set_params:[8,2,1,""]},"quapy.plot":{binary_bias_bins:[8,5,1,""],binary_bias_global:[8,5,1,""],binary_diagonal:[8,5,1,""],brokenbar_supremacy_by_drift:[8,5,1,""],error_by_drift:[8,5,1,""]},"quapy.util":{EarlyStop:[8,1,1,""],create_if_not_exist:[8,5,1,""],create_parent_dir:[8,5,1,""],download_file:[8,5,1,""],download_file_if_not_exists:[8,5,1,""],get_quapy_home:[8,5,1,""],map_parallel:[8,5,1,""],parallel:[8,5,1,""],pickled_resource:[8,5,1,""],save_text_file:[8,5,1,""],temp_seed:[8,5,1,""]},quapy:{classification:[9,0,0,"-"],data:[10,0,0,"-"],error:[8,0,0,"-"],evaluation:[8,0,0,"-"],functional:[8,0,0,"-"],isbinary:[8,5,1,""],method:[11,0,0,"-"],model_selection:[8,0,0,"-"],plot:[8,0,0,"-"],util:[8,0,0,"-"]}},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","property","Python property"],"4":["py","attribute","Python attribute"],"5":["py","function","Python function"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:property","4":"py:attribute","5":"py:function"},terms:{"0":[0,1,3,4,5,8,9,10,11],"00":[0,1,4,8],"000":1,"0001":[4,11],"000e":1,"001":[4,9,11],"005":8,"009":1,"01":[8,9,11],"017":1,"018":0,"02":1,"021":0,"02552":4,"03":1,"034":1,"035":1,"037":1,"04":1,"041":1,"042":1,"046":1,"048":1,"05":[5,8,10],"055":1,"063":[0,10],"065":0,"070":1,"073":1,"075":1,"078":0,"081":[0,10],"082":[0,1],"083":0,"086":0,"091":1,"099":0,"1":[0,1,3,4,5,8,9,10,11],"10":[0,1,4,5,8,9,11],"100":[0,1,3,4,5,9,10,11],"1000":[0,4,11],"10000":4,"100000":4,"101":[4,10],"1010":4,"1024":11,"104":0,"108":1,"109":0,"11":[0,1,6,8,10],"11338":0,"114":1,"1145":[],"12":9,"120":0,"1215742":0,"1271":0,"13":[0,9],"139":0,"14":[3,11],"142":1,"146":[3,11],"1473":0,"148":0,"1484":0,"15":[3,8,10,11],"150":0,"153":0,"157":0,"158":0,"159":0,"1593":0,"1594":0,"1599":0,"161":0,"163":[0,1],"164":[0,3,11],"167":0,"17":0,"1771":1,"1775":[0,3],"1778":[0,3],"178":0,"1823":0,"1839":0,"18399":0,"1853":0,"19":[3,10,11],"193":0,"199151":0,"19982":4,"1e":9,"1st":0,"2":[0,1,3,5,8,10,11],"20":[5,8,11],"200":[1,9],"2000":0,"2002":[3,11],"2011":4,"2013":[3,11],"2015":[0,2,3,9,11],"2016":[3,10,11],"2017":[0,3,10,11],"2018":[0,3,10],"2019":[3,10,11],"2020":4,"20342":4,"206":0,"207":0,"208":0,"21":[1,3,5,8,11],"210":8,"211":0,"2126":0,"2155":0,"21591":[0,10],"218":[3,11],"2184":0,"219e":1,"22":[0,3,9,10,11],"222":0,"222046":0,"226":0,"229":1,"229399":0,"23":9,"235":1,"238":0,"2390":0,"24":[0,9],"243":0,"248563":0,"24866":4,"24987":4,"25":[0,5,8,9,11],"25000":0,"256":[0,9],"26":9,"261":0,"265":0,"266":0,"267":0,"27":[1,3,9,11],"270":0,"2700406":[],"271":0,"272":0,"274":0,"275":1,"27th":[0,3,10],"28":3,"280":0,"281":0,"282":0,"283":[0,1],"288":0,"289":0,"2971":0,"2nd":0,"2t":[1,8],"2tp":8,"2x5fcv":0,"3":[0,1,3,5,6,8,9,10,11],"30":[0,1,3,11],"300":[0,1,9],"305":0,"306":0,"312":0,"32":[0,6],"3269206":[],"3269287":[],"33":[0,5],"331":0,"333":0,"335":0,"337":0,"34":[0,3,10,11],"341":0,"346":1,"347":0,"350":0,"351":0,"357":1,"359":0,"361":0,"366":1,"372":0,"373":0,"376132":0,"3765":0,"3813":0,"3821":[0,10],"383e":1,"387e":1,"392":0,"394":0,"399":0,"3f":[1,6],"3rd":0,"4":[0,1,3,4,5,8,11],"40":[0,3,4,11],"404333":0,"407":0,"41":[3,11],"412":0,"412e":1,"413":0,"414":0,"417":0,"41734":4,"42":[1,8],"421":0,"4259":0,"426e":1,"427":0,"430":0,"434":0,"435":1,"43676":4,"437":0,"44":0,"4403":10,"446":0,"45":[3,5,10,11],"452":0,"459":1,"4601":0,"461":0,"463":0,"465":0,"466":0,"470":0,"48":[3,11],"481":0,"48135":4,"486":0,"4898":0,"492":0,"496":0,"4960":1,"497":0,"5":[0,1,3,4,5,8,9,10,11],"50":[0,5,8,11],"500":[0,1,4,5,11],"5000":[1,5],"5005":4,"507":0,"508":0,"512":[9,11],"514":0,"515e":1,"530":0,"534":0,"535":0,"535e":1,"5379":4,"539":0,"541":1,"546":0,"5473":0,"54it":4,"55":5,"55it":4,"565":1,"569":0,"57":0,"573":0,"578":1,"583":0,"591":[3,11],"5f":4,"5fcv":11,"5fcvx2":10,"6":[0,1,3,5,8,10,11],"60":0,"600":1,"601":0,"604":[3,11],"606":0,"625":0,"627":0,"633e":1,"634":1,"64":[9,11],"640":0,"641":0,"650":0,"653":0,"654":1,"66":[1,11],"665":0,"667":0,"669":0,"67":5,"683":0,"688":0,"691":0,"694582":0,"7":[1,5,8,9],"70":0,"700":0,"701e":1,"711":0,"717":1,"725":1,"730":0,"735":0,"740e":1,"748":0,"75":[0,5,8],"762":0,"774":0,"778":0,"787":0,"794":0,"798":0,"8":[0,1,5,10,11],"8000":0,"830":0,"837":1,"858":1,"861":0,"87":[0,3,10,11],"8788":0,"889504":0,"8d2fhsgcvn0aaaaa":[],"9":[0,1,3,5,8,11],"90":[5,8],"901":0,"909":1,"914":1,"917":0,"919":[0,10],"922":0,"923":0,"935":0,"936":0,"937":[0,10],"945":1,"95":[8,10],"9533":0,"958":0,"97":0,"979":0,"982":0,"99":8,"abstract":[3,9,10,11],"boolean":[8,10],"case":[0,1,3,4,5,8,10,11],"class":[0,1,3,4,5,6,8,9,10,11],"d\u00edez":[3,11],"default":[1,3,8,9,10],"do":[0,1,3,4,8,9,10],"final":[1,3,5],"float":[0,3,8,9,10,11],"function":[0,1,3,4,5,6,7,9,10,11],"g\u00e1llego":[0,3,10,11],"gonz\u00e1lez":[3,11],"import":[0,1,3,4,5,6,10],"int":[0,5,8,10,11],"long":[4,9],"new":[0,3,10,11],"p\u00e9rez":[0,3,10,11],"return":[0,1,3,4,5,8,9,10,11],"rodr\u0131":[3,11],"short":9,"static":[3,11],"true":[0,1,3,4,5,6,8,9,10,11],"try":4,"while":[3,5,8,9,10,11],A:[0,3,8,9,10,11],As:[3,4],By:[1,3,8],For:[0,1,5,6,8,10,11],If:[3,5,8,10,11],In:[0,1,2,3,4,5,6,9,11],It:[3,4,5,8],One:[0,1,3,11],That:[1,4],The:[0,1,2,4,5,6,8,9,10,11],Then:3,These:0,To:[5,10],_:[5,10],__:[],__class__:5,__name__:5,_adjust:[],_ae_:[],_classify_:11,_error_name_:11,_fit_learner_:11,_kld_:[],_labelledcollection_:11,_learner_:11,_mean:[],_min_df_:[],_my:[],_nkld_:[],_posterior_probabilities_:11,_q_:[],_rae_:[],_svmperf_:[],ab:[],aboud:3,about:[0,5,8,10],abov:[0,3,5,8],absolut:[1,3,5,6,8],absolute_error:8,abstractmethod:3,acc:[1,3,5,6,8,11],acc_error:8,accept:3,access:[0,3,10],accommod:0,accord:[1,3,4,8,9,10],accordingli:5,accuraci:[1,5,8],accuracy_polici:11,achiev:[1,3,4,5],acm:[0,3,10,11],across:[0,1,4,5,6,8],action:[0,11],actual:10,acut:0,ad:6,add:[3,4,8,10],add_word:10,addit:3,addition:[0,11],adjust:[3,6,11],adjusted_quantif:8,adjustedclassifyandcount:11,adopt:[3,4,10],advanc:[0,6],advantag:3,ae:[1,2,5,8],ae_:1,affect:8,after:8,afterward:11,again:5,against:5,aggreg:[1,4,5,6,7,8],aggregativeprobabilisticquantifi:[3,11],aggregativequantifi:[3,11],aggregg:11,aim:[4,5],aka:10,al:[0,2,9,10],alaiz:[3,11],alegr:[3,11],alejandro:4,alia:[3,8,11],all:[0,1,2,3,5,8,10,11],allia:3,alloc:9,allow:[0,1,2,3,5,8,9,10,11],almost:3,along:[0,3,8,11],alreadi:[3,11],also:[0,1,2,3,5,6,8,9],altern:4,although:[3,4,5,11],alwai:[3,4,5],among:3,amount:8,an:[0,1,2,3,4,5,6,8,9,10,11],analys:[5,6],analysi:[0,3,6,10,11],analyz:5,ani:[0,1,3,4,5,6,8,9,10,11],anoth:[0,1,3,5],anotherdir:8,anyon:0,api:6,app:[8,10],appeal:1,appear:5,append:5,appli:[2,3,4,5,8,9,10],appropri:4,approxim:[1,5,9,10,11],ar:[0,1,3,4,5,8,9,10,11],archive_filenam:8,archive_path:[],arg:[8,10,11],args_i:8,argu:4,argument:[0,1,3,5,8,10],arifici:8,aris:1,around:[1,10],arrai:[1,3,5,8,9,10],articl:[3,4,11],artifici:[0,1,3,4,5,6,8,10],artificial_prevalence_predict:8,artificial_prevalence_protocol:8,artificial_prevalence_report:8,artificial_prevalence_sampl:8,artificial_sampling_ev:[1,4],artificial_sampling_gener:[0,10],artificial_sampling_index_gener:10,artificial_sampling_predict:[1,5],artificial_sampling_report:1,arxiv:4,asarrai:1,asdataload:9,asonam:0,assert:10,assess:4,assign:[3,8,10],associ:[8,10],assum:[1,6,11],assumpt:[1,5,6],astyp:[],attempt:3,attribut:11,august:0,autom:[0,3,6],automat:[0,1],av:[3,11],avail:[0,1,2,3,5,6,9],averag:[1,3,8,10],avoid:[1,8],axi:[5,8],b:[0,10],balanc:[0,4],band:[5,8],bar:8,barranquero:[2,3,9,11],base:[0,3,6,7,8,9],base_classifi:5,base_estim:3,base_quantifier_class:11,baseestim:[9,11],baselin:6,basequantifi:[3,8,11],basic:[5,11],batch:9,batch_siz:9,batch_size_test:9,been:[0,3,4,5,8,10,11],befor:[3,8,9,10,11],beforehand:8,behav:[3,5],being:[4,8],belief:1,belong:3,below:[0,2,3,5,8,10],best:[4,8,9,11],best_epoch:8,best_model:8,best_model_:4,best_params_:4,best_scor:8,better:4,between:[4,5,6,8,9],beyond:5,bia:[6,8],bias:5,bidirect:11,bin:[5,8,11],bin_bia:5,bin_diag:5,binar:[8,10],binari:[3,5,6,8,9,10,11],binary_bias_bin:[5,8],binary_bias_glob:[5,8],binary_diagon:[5,8],binary_quantifi:11,binaryquantifi:11,block:0,bool:[8,11],both:5,bound:8,box:[5,8],breast:0,brief:1,broken:[5,8],brokenbar_supremacy_by_drift:8,budg:1,budget:[1,4],build:11,bypass:11,c:[3,4,9,10,11],calibr:3,calibratedclassifi:3,calibratedclassifiercv:3,calibratedcv:11,call:[0,1,5,8,10,11],callabl:[0,8,10],can:[0,1,2,3,4,5,8,10],cancer:0,cannot:11,cardiotocographi:0,care:11,carri:[3,10],casa_token:[],castano:[3,10,11],castro:[3,11],categor:[3,10],categori:[1,8],cc:[3,5,11],ceil:8,center:5,chang:[0,1,3,10,11],character:[3,6],characteriz:[0,3,10,11],charg:[0,8,10],chart:8,check:[3,4],checkpoint:[9,11],checkpointdir:11,checkpointnam:11,checkpointpath:9,choic:4,chosen:[4,8],cl:0,cla:[],class2int:10,class_weight:4,classes_:[8,10,11],classif:[0,1,3,7,8,10,11],classif_posterior:[3,11],classif_predict:[3,11],classif_predictions_bin:11,classifi:[1,4,5,6,9,11],classifier_net:9,classifiermixin:9,classifyandcount:[3,11],classmethod:[0,10,11],classnam:10,classs:8,clean_checkpoint:11,clean_checkpoint_dir:11,clear:5,clearer:1,clearli:5,clip:8,close:[1,10],closer:1,cm:8,cmc:0,cnn:3,cnnnet:[3,9],code:[0,3,4,5,9],codifi:10,coincid:[0,6],col:[0,10],collect:[0,8,9,10],collet:10,color:[5,8],colormap:8,column:[0,10],com:[],combin:[0,1,4,8,10],combinatio:8,combinations_budget:8,come:[0,10],commandlin:[],common:11,commonli:6,compar:[5,8,11],comparison:5,compil:[2,3],complet:[3,5],compon:[8,9],compress:0,comput:[1,3,5,8,11],computation:4,compute_fpr:11,compute_t:11,compute_tpr:11,concept:6,concur:11,condit:8,conduct:[0,8],confer:[0,3,10],confid:8,configur:[4,8],conform:10,consecut:[8,9],consid:[3,5,8,9,10],consist:[0,4,5,9,10],constrain:[1,5,8,10],constructor:3,consult:[0,1],contain:[1,2,3,5,8,9,10,11],contanin:8,content:7,context:8,contrast:1,control:[1,4,10],conv_block:[],conv_lay:[],conveni:8,convert:[1,3,9,10],convolut:9,copi:[8,10],cornel:[],correct:11,correctli:8,correspond:[5,10],cost:1,costli:4,could:[0,1,3,4,5,6,11],count:[4,5,6,10,11],count_:[],counter:10,countvector:10,covari:10,cover:[1,4,9],coz:[0,3,10,11],cpu:[1,9],creat:[0,6,8],create_if_not_exist:8,create_parent_dir:8,crisp:3,criteria:4,cross:[3,10,11],cs:[],csr:10,csr_matrix:10,csv:10,ctg:0,cuda:[3,9,11],cumbersom:1,cumberson:8,curios:5,current:[3,8,9,10],custom:[3,6,8,10],customarili:[3,4],cv:[3,4],cyan:5,d_:8,dat:[0,9],data:[1,3,4,5,6,7,8,9,11],data_hom:10,datafram:1,dataload:9,dataset:[1,3,4,5,6,7,8,9,11],dataset_nam:10,deal:0,decaesteck:[3,11],decai:9,decid:10,decim:1,decis:[3,9],decision_funct:9,decomposit:9,dedic:[1,10],deep:[3,8,11],def:[0,1,3,5,8],defin:[0,3,8,9,10,11],degre:4,del:[0,3,10,11],delai:8,deliv:3,dens:0,densiti:8,depend:[0,1,4,5,8],describ:[3,8,11],descript:0,design:4,desir:[0,1,10],despit:1,destin:8,detail:[0,1,3,6,9,10,11],determin:[1,4,5],detriment:5,devel:10,develop:[4,6],deviat:[0,1,5,8,10],devic:[0,3,5,9,11],df:1,df_replac:[],diabet:0,diagon:[6,8],dict:[8,10,11],dictionari:[8,9,10],differ:[0,1,3,4,5,6,8,10],difficult:5,digit:0,dimens:[8,9,10],dimension:[8,9,10],dir:8,directli:[0,1,3],directori:[2,8,9,10],discard:8,discoveri:[3,11],discuss:5,disjoint:9,disk:8,displai:[1,5,8],displaystyl:8,distanc:11,distant:[1,8],distribut:[0,3,5,8,10,11],diverg:[1,3,8],divid:8,dl:[],doabl:0,doc_embed:11,doc_embedding_s:11,doc_posterior:11,document:[0,1,3,5,9,10,11],document_embed:9,doe:[0,2,3,8],doi:[],done:3,dot:[5,8],dowload:8,down:[5,10],download:[0,2,3,8],download_fil:8,download_file_if_not_exist:8,draw:10,drawn:[0,1,4,8,10],drift:6,drop:[9,11],drop_p:9,dropout:9,ds:[3,11],ds_polici:11,ds_policy_get_posterior:11,dtype:[1,10],dump:10,dure:[1,5],dynam:[3,9,10,11],e:[0,1,3,4,5,6,8,9,10,11],eacc:11,each:[0,1,3,4,5,8,9,10,11],earli:[8,9],early_stop:11,earlystop:8,easili:[0,2,5,9],ecc:11,edu:[],eemq:11,effect:3,effici:3,ehdi:11,either:[1,3,8,10,11],element:[3,10],elm:[3,11],em:11,emb:9,embed:[3,9],embed_s:9,embedding_s:9,empti:10,emq:[5,11],enabl:9,encod:10,end:[4,8],endeavour:6,enough:5,ensembl:[0,6,10,11],ensemblefactori:11,ensure_probabilist:11,entir:[0,3,4,5],environ:[1,3,4,5,8],ep:[1,8],epacc:11,epoch:[8,9,11],epsilon:[1,8,11],equal:[1,8],equidist:[0,8],equip:[3,5],err:8,err_drift:5,err_nam:8,error:[3,4,6,7,9],error_:[],error_by_drift:[5,8],error_funct:1,error_metr:[1,4,8],error_nam:[5,8,11],especi:8,establish:8,estim:[1,3,5,6,8,9,10,11],estim_prev:[1,5,8],estim_preval:[3,6],esuli:[0,2,3,9,10,11],et:[0,2,9,10],etc:6,eval_budget:[4,8],evalu:[0,3,4,5,6,7,9,10],even:8,eventu:[9,10],everi:[3,11],everyth:3,evinc:5,ex:[],exact:[0,10],exactli:0,exampl:[0,1,3,4,5,8,9,10,11],exce:8,excel:0,except:[3,8],exemplifi:0,exhaust:8,exhibit:[4,5],exist:8,exist_ok:8,expand_frame_repr:1,expect:6,expectationmaximizationquantifi:[3,11],experi:[1,2,3,4,5,8],explain:[1,5],explicitlossminim:11,explicitlossminimis:11,explor:[4,8,10],express:10,ext:2,extend:[2,3,11],extens:[0,2,5],extern:3,extract:[1,8,10],f1:[1,8,9],f1_error:8,f1e:[1,8],f:[0,1,3,4,5,6,10,11],f_1:8,fabrizio:4,facilit:6,fact:[3,5],factor:8,fals:[1,3,5,8,9,10,11],famili:3,familiar:3,far:[8,9,10],fare:8,fast:8,faster:[0,10],feat1:10,feat2:10,featn:10,featur:[0,10],feature_extract:10,fetch:[0,6],fetch_review:[0,1,3,4,5,10],fetch_twitt:[0,3,6,10],fetch_ucidataset:[0,3,10],fetch_ucilabelledcollect:[0,10],ff_layer:11,fhe:0,file:[0,5,8,9,10],filenam:8,fin:0,find:[0,4],finish:4,first:[0,1,2,3,5,8,10,11],fit:[1,3,4,5,6,8,9,10,11],fit_learn:[3,11],fit_transform:10,fix:[1,4],flag:8,float64:1,fn:8,fold:[3,10,11],folder:0,follow:[0,1,3,4,5,6,8],fomart:10,for_model_select:[0,10],form:[0,8,10],format:[0,5,10],former:[2,11],forward:[9,11],found:[0,3,4,8,9,10],four:3,fp:[8,11],fpr:8,frac:8,framework:6,frequenc:[0,10],from:[0,1,3,4,5,6,8,10,11],from_csv:10,from_nam:[1,8],from_spars:10,from_text:10,full:[1,8],fulli:0,func:8,further:[0,1,3,9,10],fusion:[0,3,10,11],futur:3,g:[0,1,3,4,6,8,10,11],gain:8,gao:[0,3,10,11],gap:10,gasp:[0,10],gen:8,gen_data:5,gen_fn:8,gen_prevalence_predict:8,gener:[0,1,3,4,5,8,9,10,11],generation_func:8,german:0,get:[0,1,5,8,9,10],get_aggregative_estim:11,get_nprevpoints_approxim:[1,8],get_param:[3,8,9,11],get_probability_distribut:11,get_quapy_hom:8,github:[],given:[1,3,4,8,9,10,11],global:8,goe:4,good:[4,5],got:4,govern:1,gpu:9,grant:11,greater:10,grid:[4,8,10,11],gridsearchcv:4,gridsearchq:[4,8],group:3,guarante:[10,11],guez:[3,11],gzip:0,ha:[3,4,5,8,9,10],haberman:[0,3],had:10,handl:0,happen:[4,5],hard:3,harder:5,harmon:8,harri:0,hat:8,have:[0,1,2,3,4,5,8,10,11],hcr:[0,3,10],hdy:[6,11],held:[3,4,8,9],helling:11,hellingerdist:8,hellingerdistancei:[3,11],help:5,henc:[8,10],here:1,hidden:[5,9],hidden_s:9,hide:5,high:[5,8],higher:[1,5],highlight:8,hightlight:8,hlt:[],hold:[6,8],home:[8,10],hook:11,how:[0,1,3,4,5,8,10,11],howev:[0,4,5,11],hp:[0,3,4,10],html:10,http:10,hyper:[4,8,9],hyperparam:4,hyperparamet:[3,8,11],i:[0,1,3,4,5,8,9,10,11],id:[0,3,10],identifi:8,idf:0,ieee:0,ignor:[8,10,11],ii:8,iid:[1,5,6],illustr:[3,4,5],imdb:[0,5,10],implement:[0,1,3,4,5,6,8,9,10,11],implicit:8,impos:[4,8],improv:[3,8,9],includ:[0,1,3,5,6,10],inconveni:8,inde:[3,4],independ:8,index:[0,3,6,8,9,10],indextransform:10,indic:[0,1,3,4,5,8,10,11],individu:[1,3],infer:[0,10],inform:[0,1,3,4,8,10,11],infrequ:10,inherit:3,init:3,init_hidden:11,initi:[0,9],inplac:[1,3,10],input:[3,5,8,9],insight:5,inspir:3,instal:[0,3,6,9],instanc:[0,3,4,5,6,8,9,10,11],instanti:[0,1,3,4,9],instead:[1,3,4,11],integ:[3,9,10],integr:6,interest:[1,5,6,8,10],interestingli:5,interfac:[0,1],intern:[0,3,10],interpret:[5,6],interv:[1,5,8,10],introduc:1,invok:[0,1,3,8,10],involv:[2,5,8],io:[],ionospher:0,iri:0,irrespect:5,isaggreg:11,isbinari:[8,10,11],isomer:8,isometr:[5,8],isprobabilist:11,isti:[],item:8,iter:[0,8,11],its:[3,4,8,9],itself:[3,8,11],j:[0,3,10,11],joachim:[3,9],job:[2,8],joblib:2,join:8,just:[1,3],k:[3,6,10,11],keep:8,kei:[8,10],kept:10,kernel:9,kernel_height:9,keyword:10,kfcv:[0,10,11],kindl:[0,1,3,5,10],kl:8,kld:[1,2,8,9],know:3,knowledg:[0,3,10,11],known:[0,3,4],kullback:[1,3,8],kwarg:[9,10,11],l1:11,label:[0,3,4,5,6,8,9,10,11],labelledcollect:[0,3,4,8,10,11],larg:4,larger:10,largest:8,last:[1,3,5,8,9,10],lastli:3,latex:5,latinn:[3,11],latter:11,layer:[3,9],lead:[1,10],learn:[1,2,3,4,6,8,9,10,11],learner:[3,4,9,11],least:[0,10],leav:10,left:10,legend:8,leibler:[1,3,8],len:8,length:[9,10],less:[8,10],let:[1,3],level:11,leverag:3,leyend:8,like:[0,1,3,5,8,9,10],limit:[5,8,10],line:[1,3,8],linear:5,linear_model:[1,3,4,6,9],linearsvc:[3,5,10],linspac:5,list:[0,5,8,9,10],listedcolormap:8,literatur:[0,1,4,6],load:[0,3,8,10],loader:[0,10],loader_func:[0,10],loader_kwarg:10,local:8,log:[8,10],logist:[1,3,9,11],logisticregress:[1,3,4,6,9],logscal:8,logspac:4,longer:8,longest:9,look:[0,1,3,5],loss:[6,9,11],low:[5,8,9],lower:[5,8],lower_is_bett:8,lowest:5,lowranklogisticregress:9,lr:[1,3,9,11],lstm:[3,9],lstm_class_nlay:9,lstm_hidden_s:11,lstm_nlayer:11,lstmnet:9,m:[3,8,11],machin:[1,4,6],macro:8,made:[0,2,8,10,11],mae:[1,4,6,8,9,11],mae_loss:11,mai:8,main:5,maintain:[3,11],make:[0,1,3],makedir:8,mammograph:0,manag:[0,3,10],mani:[1,3,4,5,6,8,10,11],manner:0,manual:0,map:[1,9],map_parallel:8,margin:9,math:[],mathcal:8,matplotlib:[2,8],matric:[0,5,10],matrix:5,max:11,max_it:11,max_sample_s:11,maxim:6,maximum:[1,8,9],maximumlikelihoodprevalenceestim:11,md:[],mean:[0,1,3,4,5,6,8,9,10,11],mean_absolute_error:8,mean_relative_absolute_error:8,measur:[2,3,4,5,6,8,11],mediansweep2:11,mediansweep:11,member:3,memori:9,mention:3,merg:5,met:10,meta:[6,7,8],meth:[],method:[0,1,4,5,6,7,8],method_data:5,method_nam:[5,8],method_ord:8,metric:[1,3,4,6,8],might:[1,8,10],min_df:[1,3,4,5,10],min_po:11,mine:[0,3,11],minim:8,minimum:10,minimun:10,mining6:10,minu:8,miss:8,mixtur:3,mkld:[1,8,11],ml:10,mnkld:[1,8,11],mock:[8,9],modal:4,model:[0,1,5,6,8,9,11],model_select:[4,7],modifi:[3,8],modul:[0,1,3,5,6,7],moment:[0,3],monitor:8,more:[3,5,8],moreo:[0,3,4,10],most:[0,3,5,6,8,10,11],movi:0,mrae:[1,6,8,9,11],ms2:11,ms:11,mse:[1,3,6,8,11],msg:11,multiclass:8,multipli:8,multiprocess:8,multivari:[3,9,11],must:[3,10],my:[],my_arrai:8,my_collect:10,my_custom_load:0,my_data:0,mycustomloss:3,n:[0,1,8,9],n_bin:[5,8],n_class:[1,3,8,9,10,11],n_compon:9,n_dimens:9,n_epoch:11,n_featur:9,n_instanc:[8,9],n_job:[1,3,4,8,10,11],n_preval:[0,8,10],n_prevpoint:[1,4,5,8],n_repeat:[1,8],n_repetit:[1,4,5,8],n_sampl:[8,9],name:[5,8,9,10],nativ:6,natur:[1,8,10],natural_prevalence_predict:8,natural_prevalence_protocol:8,natural_prevalence_report:8,natural_sampling_gener:10,natural_sampling_index_gener:10,nbin:[5,8],ndarrai:[1,3,8,10,11],necessarili:11,need:[0,3,8,10,11],neg:[0,5,8],nest:[],net:9,network:[0,8,9,10,11],neural:[0,7,8,10],neuralclassifiertrain:[3,9],neutral:0,next:[4,8,9,10],nfold:[0,10],nkld:[1,2,6,8,9],nn:[9,11],nogap:10,non:[3,11],non_aggreg:[7,8],none:[1,4,8,9,10,11],nonetheless:4,nor:3,normal:[0,1,3,8,10,11],normalize_preval:8,note:[1,3,4,5,8,10],now:5,nowadai:3,np:[1,3,4,5,8,10],npp:[8,10],nprevpoint:8,nrepeat:[0,10],num_prevalence_combin:[1,8],number:[0,1,3,5,8,9,10,11],numer:[0,1,3,6,10],numpi:[2,4,8,9,11],o_l6x_pcf09mdetq4tu7jk98mxfbgsxp9zso14jkuiyudgfg0:[],object:[0,8,9,10,11],observ:1,obtain:[1,4,8],obtaind:8,obvious:8,occur:[5,10],occurr:10,octob:[0,3],off:9,offer:[3,6],older:2,omd:[0,10],ommit:[1,8],onc:[1,3,5,8],one:[0,1,3,4,5,8,10,11],ones:[1,3,5,8,10],onevsal:[3,11],onli:[0,3,5,8,9,10,11],open:[0,6,10],oper:3,opt:4,optim:[2,3,4,8,9,11],optimize_threshold:11,option:[0,1,3,5,8,10,11],order:[0,2,3,5,8,10,11],order_bi:11,org:10,orient:[3,6,8,11],origin:[0,3,10,11],os:[0,8],other:[1,3,5,6,8,10],otherwis:[0,3,10,11],our:[],out:[3,4,5,8,9,10],outcom:5,outer:8,outlier:8,output:[0,1,3,4,9,10,11],over:[3,4,8],overal:1,overestim:5,overrid:3,overridden:[3,11],own:4,p:[0,3,8,10,11],p_hat:8,pacc:[1,3,5,11],packag:[0,2,3,6,7],pad:[9,10],pad_length:9,padding_length:9,page:[0,2,6],pageblock:0,pair:[0,8],panda:[1,2],paper:[0,3,11],parallel:[1,3,8,10],param:[4,8,9,11],param_grid:[4,8,11],param_mod_sel:11,param_model_sel:11,paramet:[1,3,4,8,9,10,11],parent:8,part:[3,10],particular:[0,1,3],particularli:1,pass:[0,1,5,8,9,11],past:1,patch:[2,3,9],path:[0,3,5,8,9,10],patienc:[8,9,11],pattern:[3,11],pca:[],pcalr:[],pcc:[3,4,5,11],pd:1,pdf:5,peopl:[],percentil:8,perf:[6,9],perform:[1,3,4,5,6,8,9,11],perman:8,phonem:0,pick:4,pickl:[3,8,10],pickle_path:8,pickled_resourc:8,pii:[],pip:2,pipelin:[],pkl:8,plai:0,plan:3,pleas:3,plot:[6,7],png:5,point:[0,1,3,8,10],polici:[3,11],popular:6,portion:4,pos_class:[8,10],posit:[0,3,5,8,10],possibl:[1,3,8],posterior:[3,8,9,11],posterior_prob:[3,11],postpon:3,potter:0,pp:[0,3],pprox:[],practic:[0,4],pre:[0,3],prec:[0,8],preced:10,precis:[0,1,8],preclassifi:3,predefin:10,predict:[3,4,5,8,9,11],predict_proba:[3,9,11],predictor:1,prefer:8,prepare_svmperf:[2,3],preprint:4,preprocess:[0,1,3,7,8],present:[0,3,10],preserv:[1,5,10],pretti:5,prev:[0,1,8,10],prevail:3,preval:[0,1,3,4,5,6,8,10,11],prevalence_estim:8,prevalence_from_label:8,prevalence_from_prob:8,prevalence_linspac:8,prevel:11,previou:3,previous:11,prevs_estim:11,prevs_hat:[1,8],princip:9,print:[0,1,3,4,6,9,10],prior:[1,3,4,5,6,8],priori:[3,11],probabilist:[3,11],probabilisticadjustedclassifyandcount:11,probabilisticclassifyandcount:11,probabl:[1,3,4,5,6,8,9,11],problem:[0,3,5,8,10,11],procedur:[3,6,11],proceed:[0,3,10],process:[3,4,8],processor:3,procol:1,produc:[0,1,5,8],product:3,progress:[8,10],properli:0,properti:[3,8,9,10,11],proport:[3,4,8,9,10,11],propos:[2,3,11],protocl:8,protocol:[0,3,4,5,6,8,10],provid:[0,3,5,6],ptecondestim:11,ptr:[3,11],ptr_polici:11,purpos:[0,11],python:[0,6],pytorch:2,q:[0,2,3,8,9],qacc:9,qdrop_p:11,qf1:9,qgm:9,qp:[0,1,3,4,5,6,8,10],quanet:[2,6,9,11],quanetmodul:11,quanettrain:11,quantif:[0,1,6,8,9,10,11],quantifi:[3,4,5,6,8,11],quantification_error:8,quantiti:8,quapi:[0,1,2,3,4,5],quapy_data:0,quay_data:10,quevedo:[0,3,10,11],quick:[],quit:8,r:[0,3,10,11],rac:[],rae:[1,2,8],rais:[3,8],rand:8,random:[1,3,4,5,8,10],random_se:[1,8],random_st:10,randomli:0,rang:[0,5],rank:[3,9],rare:10,rate:[3,9],rather:[1,4],raw:10,rb:0,re:[3,4,10],read:10,reader:[7,8],readm:[],real:[9,10],reason:[3,5,6],recal:8,receiv:[0,3,5],recip:11,recognit:[3,11],recommend:[1,5],recurr:[0,3,10],red:0,red_siz:[3,11],reduc:[0,10],reduce_column:[0,10],refer:[9,10],refit:[4,8],regard:4,regardless:10,regim:8,region:8,regist:11,regress:9,regressor:[1,3,11],reindex_label:10,reiniti:9,rel:[1,3,8,10],relative_absolute_error:8,reli:[1,3],reliabl:[3,11],rememb:5,remov:10,repeat:[8,10],repetit:8,repl:[],replac:[0,3,10],replic:[1,4,8],report:1,repositori:[0,10],repr_siz:9,repres:[1,3,5,8,10,11],represent:[0,3,9],reproduc:10,request:[0,8,10,11],requir:[0,1,3,6,9],reset_net_param:9,resourc:8,respect:[0,1,5,8,11],respond:3,rest:[8,10,11],result:[1,2,3,4,5,6,11],retain:[0,3,9],retrain:4,return_constrained_dim:8,reus:[0,3,8],review:[5,6,10],reviews_sentiment_dataset:[0,10],rewrit:5,right:[4,8,10],role:0,root:6,roughli:0,round:10,routin:[8,10],row:10,run:[0,1,2,3,4,5,8,10,11],s003132031400291x:[],s:[0,1,3,4,5,8,9,10],saeren:[3,11],sai:11,said:3,same:[0,3,5,8,10],sampl:[0,1,3,4,5,6,8,9,10,11],sample_s:[0,1,3,4,5,8,10,11],sampling_from_index:[0,10],sampling_index:[0,10],sander:[0,10],save:[5,8],save_or_show:[],save_text_fil:8,savepath:[5,8],scale:8,scall:10,scenario:[1,3,4,5,6],scienc:[3,11],sciencedirect:[],scikit:[2,3,4,10],scipi:[2,10],score:[0,1,4,8,9,10],script:[1,2,3,6],se:[1,8],search:[3,4,6,8,11],sebastiani:[0,3,4,10,11],second:[0,1,3,5,8,10],secondari:8,section:4,see:[0,1,2,3,4,5,6,8,9,10],seed:[1,4,8],seem:3,seemingli:5,seen:[5,8],select:[0,3,6,8,10,11],selector:3,self:[3,8,9,10,11],semeion:0,semev:0,semeval13:[0,10],semeval14:[0,10],semeval15:[0,10],semeval16:[0,6,10],sentenc:10,sentiment:[3,6,10,11],separ:[8,10],seri:0,serv:3,set:[0,1,3,4,5,6,8,9,10,11],set_opt:1,set_param:[3,8,9,11],set_siz:[],sever:0,sh:[2,3],shape:[5,8,9,10],share:[0,10],shift:[1,4,6,8],shorter:9,shoud:3,should:[0,1,3,4,5,6,9,10,11],show:[0,1,3,4,5,8,9,10],show_dens:8,show_std:[5,8],showcas:5,shown:[1,5,8],shuffl:[9,10],side:8,sign:8,signific:1,significantli:8,silent:[8,11],simeq:[],similar:[8,11],simpl:[0,3,5,11],simplest:3,simplex:[0,8],simpli:[1,2,3,4,5,6,8,11],sinc:[0,1,3,5,8,10,11],singl:[1,3,6,11],size:[0,1,3,8,9,10,11],sklearn:[1,3,4,5,6,9,10,11],sld:3,slice:8,smooth:[1,8],smooth_limits_epsilon:8,so:[0,1,3,5,8,9,10,11],social:[0,3,10,11],soft:3,softwar:0,solid:5,solv:4,solve_adjust:11,some:[0,1,3,5,8,10],some_arrai:8,sometim:1,sonar:0,sourc:[2,3,6,9],sout:11,space:[0,4,8,9],spambas:0,spars:[0,10],special:[0,5,10],specif:[3,4],specifi:[0,1,3,5,8,9,10,11],spectf:0,spectrum:[0,1,4,5,8],speed:3,split:[0,3,4,5,8,9,10,11],split_stratifi:10,splitstratifi:10,spmatrix:10,squar:[1,3,8],sst:[0,10],stabil:1,stabl:10,stand:8,standard:[0,1,5,8,10],start:4,stat:10,state:8,statist:[0,1,8,11],stats_siz:11,std:9,stdout:8,step:[5,8],stop:[8,9],store:[0,9,10],str:[0,8,10],strategi:[3,4],stratif:10,stratifi:[0,3,10],stride:9,string:[1,8,10],strongli:[4,5],strprev:[0,1,8],structur:3,studi:[0,3,10,11],style:10,subclass:11,subdir:8,subinterv:5,sublinear_tf:10,submit:0,submodul:7,subobject:[],suboptim:4,subpackag:7,subsequ:[10,11],subtract:[0,8,10],subtyp:10,suffic:5,suffici:11,sum:[8,11],sum_:8,summar:0,supervis:[4,6],support:[3,6,9,10],surfac:10,surpass:1,svm:[3,5,6,9,10],svm_light:[],svm_perf:[],svm_perf_classifi:9,svm_perf_learn:9,svm_perf_quantif:[2,3],svmae:[3,11],svmkld:[3,11],svmnkld:[3,11],svmperf:[2,3,7,8],svmperf_bas:[9,11],svmperf_hom:3,svmq:[3,11],svmrae:[3,11],syntax:5,system:4,t50:11,t:[0,1,3,8],tab10:8,tail:8,tail_density_threshold:8,take:[0,3,5,8,10,11],taken:[3,8,9,10],target:[3,5,6,8,9,11],task:[3,4,10,11],te:10,temp_se:8,tempor:8,tend:5,tendenc:5,tensor:9,term:[0,1,3,4,5,6,8,9,10,11],test:[0,1,3,4,5,6,8,9,10,11],test_bas:[],test_dataset:[],test_method:[],test_path:[0,10],test_sampl:8,test_split:10,text2tfidf:[0,1,3,10],text:[0,3,8,9,10,11],textclassifiernet:9,textual:[0,6,10],tf:[0,10],tfidf:[0,4,5,10],tfidfvector:10,than:[1,4,5,8,9,10],thei:[0,3],them:[0,3,11],theoret:4,thereaft:1,therefor:10,thi:[0,1,2,3,4,5,6,8,9,10,11],thing:3,third:[1,5],thorsten:9,those:[1,3,4,5,8,9],though:[3,8],three:[0,5],threshold:8,thresholdoptim:11,through:[3,8],thu:[3,4,5,8,11],tictacto:0,time:[0,1,3,8,10],timeout:8,timeouterror:8,timer:8,titl:8,tj:[],tn:[8,11],token:[0,9,10],tool:[1,6],top:[3,8,11],torch:[3,9,11],torchdataset:9,total:8,toward:[5,10],tp:[8,11],tpr:8,tqdm:2,tr:10,tr_iter_per_poch:11,tr_prev:[5,8,11],track:8,trade:9,tradition:1,train:[0,1,3,4,5,6,8,9,10,11],train_path:[0,10],train_prev:[5,8],train_prop:10,train_siz:10,train_val_split:11,trainer:9,training_help:11,training_preval:5,training_s:5,transact:[3,11],transform:[0,9,10],transfus:0,trivial:3,true_prev:[1,5,8],true_preval:6,truncatedsvd:9,ttest_alpha:8,tupl:10,turn:4,tweet:[0,3,10,11],twitter:[6,10],twitter_sentiment_datasets_test:[0,10],twitter_sentiment_datasets_train:[0,10],two:[0,1,3,4,5,8,10],txt:8,type:[0,3,8,10],typic:[1,4,5,8,9,10],u1:10,uci:[6,10],uci_dataset:10,unabl:0,unadjust:5,unalt:9,unbias:5,uncompress:0,under:1,underestim:5,underlin:8,understand:8,unfortun:5,unifi:0,uniform:10,uniform_prevalence_sampl:8,uniform_sampl:10,uniform_sampling_index:10,uniform_simplex_sampl:8,uniformli:[8,10],union:[8,11],uniqu:10,unit:0,unix:0,unk:10,unknown:10,unless:11,unlik:[1,4],unus:[8,9,11],up:[3,4,8,9,11],updat:[],url:8,us:[0,1,3,4,5,6,8,9,10,11],user:[0,1,5],utf:10,util:[7,9],v:[3,11],va_iter_per_poch:11,val:[0,10],val_split:[3,4,8,9,11],valid:[0,1,3,4,5,8,9,10,11],valid_loss:[3,9],valid_polici:11,valu:[0,1,3,8,9,10,11],variabl:[1,3,5,8,10],varianc:[0,5],variant:[5,6,11],varieti:4,variou:[1,5],vector:[0,8,9,10],verbos:[0,1,4,8,9,10,11],veri:[3,5],versatil:6,version:[2,9],vertic:8,vertical_xtick:8,via:[0,2,3,11],view:5,visual:[5,6],vline:8,vocab_s:9,vocabulari:[9,10],vocabulary_s:[3,9,10],vs:[3,8],w:[0,3,10,11],wa:[0,3,5,8,10,11],wai:[1,11],wait:9,want:[3,4],warn:10,wb:[0,10],wdbc:0,we:[0,1,3,4,5,6],weight:[9,10],weight_decai:9,well:[0,3,4,5],were:0,what:3,whcih:10,when:[0,1,3,4,5,8,9,10],whenev:[5,8],where:[3,5,8,9,10,11],wherebi:4,whether:[8,9,10,11],which:[0,1,3,4,5,8,9,10,11],white:0,whole:[0,1,3,4,8],whose:10,why:3,wide:5,wiki:[0,3],wine:0,within:[8,11],without:[1,3,8,10],word:[1,3,6,9,10],work:[1,3,4,5,10],worker:[1,8,10],wors:[4,5,8],would:[0,1,3,5,6,8,10,11],wrapper:[8,9,10],written:6,www:[],x2:10,x:[5,8,9,10,11],x_error:8,xavier:9,xavier_uniform:9,xlrd:[0,2],xy:10,y:[5,8,9,10,11],y_:11,y_error:8,y_pred:8,y_true:8,ye:[],yeast:[0,10],yield:[5,8,10],yin:[],you:[2,3],your:3,z:[0,10],zero:[0,8],zfthyovrzwxmgfzylqw_y8cagg:[],zip:[0,5]},titles:["Datasets","Evaluation","Installation","Quantification Methods","Model Selection","Plotting","Welcome to QuaPy\u2019s documentation!","quapy","quapy package","quapy.classification package","quapy.data package","quapy.method package"],titleterms:{"function":8,A:6,The:3,ad:0,aggreg:[3,11],base:[10,11],bia:5,classif:[4,9],classifi:3,content:[6,8,9,10,11],count:3,custom:0,data:[0,10],dataset:[0,10],diagon:5,distanc:3,document:6,drift:5,emq:3,ensembl:3,error:[1,5,8],evalu:[1,8],ex:[],exampl:6,expect:3,explicit:3,featur:6,get:[],hdy:3,helling:3,indic:6,instal:2,introduct:6,issu:0,learn:0,loss:[2,3,4],machin:0,maxim:3,measur:1,meta:[3,11],method:[3,9,11],minim:3,model:[3,4],model_select:8,modul:[8,9,10,11],network:3,neural:[3,9,11],non_aggreg:11,orient:[2,4],packag:[8,9,10,11],perf:2,plot:[5,8],preprocess:10,process:0,protocol:1,quanet:3,quantif:[2,3,4,5],quapi:[6,7,8,9,10,11],quick:6,reader:10,readm:[],requir:2,review:0,s:6,select:4,sentiment:0,start:[],submodul:[8,9,10,11],subpackag:8,svm:2,svmperf:9,tabl:6,target:4,test:[],test_bas:[],test_dataset:[],test_method:[],titl:[],twitter:0,uci:0,util:8,variant:3,welcom:6,y:3}})
\ No newline at end of file
diff --git a/quapy/data/base.py b/quapy/data/base.py
index 3cb2392..8324bc4 100644
--- a/quapy/data/base.py
+++ b/quapy/data/base.py
@@ -1,6 +1,3 @@
-from abc import abstractmethod
-from typing import List, Union
-
 import numpy as np
 from scipy.sparse import issparse
 from scipy.sparse import vstack
@@ -9,18 +6,19 @@ from sklearn.model_selection import train_test_split, RepeatedStratifiedKFold
 from quapy.functional import artificial_prevalence_sampling, strprev
 
 
-
 class LabelledCollection:
-    '''
-    A LabelledCollection is a set of objects each with a label associated to it.
-    '''
+    """
+    A LabelledCollection is a set of objects each with a label associated to it. This class implements many sampling
+    routines.
+
+    :param instances: array-like (np.ndarray, list, or csr_matrix are supported)
+    :param labels: array-like with the same length of instances
+    :param classes_: optional, list of classes from which labels are taken. If not specified, the classes are inferred
+        from the labels. The classes must be indicated in cases in which some of the labels might have no examples
+        (i.e., a prevalence of 0)
+    """
 
     def __init__(self, instances, labels, classes_=None):
-        """
-        :param instances: list of objects
-        :param labels: list of labels, same length of instances
-        :param classes_: optional, list of classes from which labels are taken. When used, must contain the set of values used in labels.
-        """
         if issparse(instances):
             self.instances = instances
         elif isinstance(instances, list) and len(instances) > 0 and isinstance(instances[0], str):
@@ -42,28 +40,81 @@ class LabelledCollection:
 
     @classmethod
     def load(cls, path: str, loader_func: callable, classes=None, **loader_kwargs):
+        """
+        Loads a labelled set of data and convert it into a :class:`LabelledCollection` instance. The function in charge
+        of reading the instances must be specified. This function can be a custom one, or any of the reading functions
+        defined in :mod:`quapy.data.reader` module.
+
+        :param path: string, the path to the file containing the labelled instances
+        :param loader_func: a custom function that implements the data loader and returns a tuple with instances and
+            labels
+        :param classes: array-like, the classes according to which the instances are labelled
+        :param loader_kwargs: any argument that the `loader_func` function needs in order to read the instances, i.e.,
+            these arguments are used to call `loader_func(path, **loader_kwargs)`
+        :return: a :class:`LabelledCollection` object
+        """
         return LabelledCollection(*loader_func(path, **loader_kwargs), classes)
 
     def __len__(self):
+        """
+        Returns the length of this collection (number of labelled instances)
+
+        :return: integer
+        """
         return self.instances.shape[0]
 
     def prevalence(self):
+        """
+        Returns the prevalence, or relative frequency, of the classes of interest.
+
+        :return: a np.ndarray of shape `(n_classes)` with the relative frequencies of each class, in the same order
+            as listed by `self.classes_`
+        """
         return self.counts() / len(self)
 
     def counts(self):
+        """
+        Returns the number of instances for each of the classes of interest.
+
+        :return: a np.ndarray of shape `(n_classes)` with the number of instances of each class, in the same order
+            as listed by `self.classes_`
+        """
         return np.asarray([len(self.index[class_]) for class_ in self.classes_])
 
     @property
     def n_classes(self):
+        """
+        The number of classes
+
+        :return: integer
+        """
         return len(self.classes_)
 
     @property
     def binary(self):
+        """
+        Returns True if the number of classes is 2
+
+        :return: boolean
+        """
         return self.n_classes == 2
 
     def sampling_index(self, size, *prevs, shuffle=True):
+        """
+        Returns an index to be used to extract a random sample of desired size and desired prevalence values. If the
+        prevalence values are not specified, then returns the index of a uniform sampling.
+        For each class, the sampling is drawn without replacement if the requested prevalence is larger than
+        the actual prevalence of the class, or with replacement otherwise.
+
+        :param size: integer, the requested size
+        :param prevs: the prevalence for each class; the prevalence value for the last class can be lead empty since
+            it is constrained. E.g., for binary collections, only the prevalence `p` for the first class (as listed in
+            `self.classes_` can be specified, while the other class takes prevalence value `1-p`
+        :param shuffle: if set to True (default), shuffles the index before returning it
+        :return: a np.ndarray of shape `(size)` with the indexes
+        """
         if len(prevs) == 0:  # no prevalence was indicated; returns an index for uniform sampling
-            return np.random.choice(len(self), size, replace=False)
+            return self.uniform_sampling_index(size)
         if len(prevs) == self.n_classes - 1:
             prevs = prevs + (1 - sum(prevs),)
         assert len(prevs) == self.n_classes, 'unexpected number of prevalences'
@@ -93,47 +144,142 @@ class LabelledCollection:
         return indexes_sample
 
     def uniform_sampling_index(self, size):
+        """
+        Returns an index to be used to extract a uniform sample of desired size. The sampling is drawn
+        without replacement if the requested size is greater than the number of instances, or with replacement
+        otherwise.
+
+        :param size: integer, the size of the uniform sample
+        :return: a np.ndarray of shape `(size)` with the indexes
+        """
         return np.random.choice(len(self), size, replace=False)
 
-    def uniform_sampling(self, size):
-        unif_index = self.uniform_sampling_index(size)
-        return self.sampling_from_index(unif_index)
-
     def sampling(self, size, *prevs, shuffle=True):
+        """
+        Return a random sample (an instance of :class:`LabelledCollection`) of desired size and desired prevalence
+        values. For each class, the sampling is drawn without replacement if the requested prevalence is larger than
+        the actual prevalence of the class, or with replacement otherwise.
+
+        :param size: integer, the requested size
+        :param prevs: the prevalence for each class; the prevalence value for the last class can be lead empty since
+            it is constrained. E.g., for binary collections, only the prevalence `p` for the first class (as listed in
+            `self.classes_` can be specified, while the other class takes prevalence value `1-p`
+        :param shuffle: if set to True (default), shuffles the index before returning it
+        :return: an instance of :class:`LabelledCollection` with length == `size` and prevalence close to `prevs` (or
+            prevalence == `prevs` if the exact prevalence values can be met as proportions of instances)
+        """
         prev_index = self.sampling_index(size, *prevs, shuffle=shuffle)
         return self.sampling_from_index(prev_index)
 
+    def uniform_sampling(self, size):
+        """
+        Returns a uniform sample (an instance of :class:`LabelledCollection`) of desired size. The sampling is drawn
+        without replacement if the requested size is greater than the number of instances, or with replacement
+        otherwise.
+
+        :param size: integer, the requested size
+        :return: an instance of :class:`LabelledCollection` with length == `size`
+        """
+        unif_index = self.uniform_sampling_index(size)
+        return self.sampling_from_index(unif_index)
+
     def sampling_from_index(self, index):
+        """
+        Returns an instance of :class:`LabelledCollection` whose elements are sampled from this collection using the
+        index.
+
+        :param index: np.ndarray
+        :return: an instance of :class:`LabelledCollection`
+        """
         documents = self.instances[index]
         labels = self.labels[index]
         return LabelledCollection(documents, labels, classes_=self.classes_)
 
     def split_stratified(self, train_prop=0.6, random_state=None):
-        # with temp_seed(42):
+        """
+        Returns two instances of :class:`LabelledCollection` split with stratification from this collection, at desired
+        proportion.
+
+        :param train_prop: the proportion of elements to include in the left-most returned collection (typically used
+            as the training collection). The rest of elements are included in the right-most returned collection
+            (typically used as a test collection).
+        :param random_state: if specified, guarantees reproducibility of the split.
+        :return: two instances of :class:`LabelledCollection`, the first one with `train_prop` elements, and the
+            second one with `1-train_prop` elements
+        """
         tr_docs, te_docs, tr_labels, te_labels = \
             train_test_split(self.instances, self.labels, train_size=train_prop, stratify=self.labels,
                              random_state=random_state)
         return LabelledCollection(tr_docs, tr_labels), LabelledCollection(te_docs, te_labels)
 
     def artificial_sampling_generator(self, sample_size, n_prevalences=101, repeats=1):
+        """
+        A generator of samples that implements the artificial prevalence protocol (APP). The APP consists of exploring
+        a grid of prevalence values (e.g., [0, 0.05, 0.1, 0.15, ..., 1]), and generating all valid combinations of
+        prevalence values for all classes (e.g., for 3 classes, samples with [0, 0, 1], [0, 0.05, 0.95], ...,
+        [1, 0, 0] prevalence values of size `sample_size` will be yielded). The number of samples for each valid
+        combination of prevalence values is indicated by `repeats`
+
+        :param sample_size: the number of instances in each sample
+        :param n_prevalences: the number of prevalence points to be taken from the [0,1] interval (including the
+            limits {0,1}). E.g., if `n_prevalences=11`, then the prevalence points to take are [0, 0.1, 0.2, ..., 1]
+        :param repeats: the number of samples to generate for each valid combination of prevalence values (default 1)
+        :return: yield samples generated at artificially controlled prevalence values
+        """
         dimensions = self.n_classes
         for prevs in artificial_prevalence_sampling(dimensions, n_prevalences, repeats):
             yield self.sampling(sample_size, *prevs)
 
     def artificial_sampling_index_generator(self, sample_size, n_prevalences=101, repeats=1):
+        """
+        A generator of sample indexes implementing the artificial prevalence protocol (APP).
+        The APP consists of exploring
+        a grid of prevalence values (e.g., [0, 0.05, 0.1, 0.15, ..., 1]), and generating all valid combinations of
+        prevalence values for all classes (e.g., for 3 classes, samples with [0, 0, 1], [0, 0.05, 0.95], ...,
+        [1, 0, 0] prevalence values of size `sample_size` will be yielded). The number of sample indexes for each valid
+        combination of prevalence values is indicated by `repeats`
+
+        :param sample_size: the number of instances in each sample (i.e., length of each index)
+        :param n_prevalences: the number of prevalence points to be taken from the [0,1] interval (including the
+            limits {0,1}). E.g., if `n_prevalences=11`, then the prevalence points to take are [0, 0.1, 0.2, ..., 1]
+        :param repeats: the number of samples to generate for each valid combination of prevalence values (default 1)
+        :return: yield the indexes that generate the samples according to APP
+        """
         dimensions = self.n_classes
         for prevs in artificial_prevalence_sampling(dimensions, n_prevalences, repeats):
             yield self.sampling_index(sample_size, *prevs)
 
     def natural_sampling_generator(self, sample_size, repeats=100):
+        """
+        A generator of samples that implements the natural prevalence protocol (NPP). The NPP consists of drawing
+        samples uniformly at random, therefore approximately preserving the natural prevalence of the collection.
+
+        :param sample_size: integer, the number of instances in each sample
+        :param repeats: the number of samples to generate
+        :return: yield instances of :class:`LabelledCollection`
+        """
         for _ in range(repeats):
             yield self.uniform_sampling(sample_size)
 
     def natural_sampling_index_generator(self, sample_size, repeats=100):
+        """
+        A generator of sample indexes according to the natural prevalence protocol (NPP). The NPP consists of drawing
+        samples uniformly at random, therefore approximately preserving the natural prevalence of the collection.
+
+        :param sample_size: integer, the number of instances in each sample (i.e., the length of each index)
+        :param repeats: the number of indexes to generate
+        :return: yield `repeats` instances of np.ndarray with shape `(sample_size,)`
+        """
         for _ in range(repeats):
             yield self.uniform_sampling_index(sample_size)
 
     def __add__(self, other):
+        """
+        Returns a new :class:`LabelledCollection` as the union of this collection with another collection
+
+        :param other: another :class:`LabelledCollection`
+        :return: a :class:`LabelledCollection` representing the union of both collections
+        """
         if other is None:
             return self
         elif issparse(self.instances) and issparse(other.instances):
@@ -149,9 +295,29 @@ class LabelledCollection:
 
     @property
     def Xy(self):
+        """
+        Gets the instances and labels. This is useful when working with `sklearn` estimators, e.g.:
+
+        >>> svm = LinearSVC().fit(*my_collection.Xy)
+
+        :return: a tuple `(instances, labels)` from this collection
+        """
         return self.instances, self.labels
 
     def stats(self, show=True):
+        """
+        Returns (and eventually prints) a dictionary with some stats of this collection. E.g.,:
+
+        >>> data = qp.datasets.fetch_reviews('kindle', tfidf=True, min_df=5)
+        >>> data.training.stats()
+        >>> #instances=3821, type=<class 'scipy.sparse.csr.csr_matrix'>, #features=4403, #classes=[0 1], prevs=[0.081, 0.919]
+
+        :param show: if set to True (default), prints the stats in standard output
+        :return: a dictionary containing some stats of this collection. Keys include `#instances` (the number of
+            instances), `type` (the type representing the instances), `#features` (the number of features, if the
+            instances are in array-like format), `#classes` (the classes of the collection), `prevs` (the prevalence
+            values for each class)
+        """
         ninstances = len(self)
         instance_type = type(self.instances[0])
         if instance_type == list:
@@ -171,6 +337,14 @@ class LabelledCollection:
         return stats_
 
     def kFCV(self, nfolds=5, nrepeats=1, random_state=0):
+        """
+        Generator of stratified folds to be used in k-fold cross validation.
+
+        :param nfolds: integer (default 5), the number of folds to generate
+        :param nrepeats: integer (default 1), the number of rounds of k-fold cross validation to run
+        :param random_state: integer (default 0), guarantees that the folds generated are reproducible
+        :return: yields `nfolds * nrepeats` folds for k-fold cross validation
+        """
         kf = RepeatedStratifiedKFold(n_splits=nfolds, n_repeats=nrepeats, random_state=random_state)
         for train_index, test_index in kf.split(*self.Xy):
             train = self.sampling_from_index(train_index)
@@ -178,8 +352,15 @@ class LabelledCollection:
             yield train, test
 
 
-
 class Dataset:
+    """
+    Abstraction of training and test :class:`LabelledCollection` objects.
+
+    :param training: a :class:`LabelledCollection` instance
+    :param test: a :class:`LabelledCollection` instance
+    :param vocabulary: if indicated, is a dictionary of the terms used in this textual dataset
+    :param name: a string representing the name of the dataset
+    """
 
     def __init__(self, training: LabelledCollection, test: LabelledCollection, vocabulary: dict = None, name=''):
         assert set(training.classes_) == set(test.classes_), 'incompatible labels in training and test collections'
@@ -190,45 +371,118 @@ class Dataset:
 
     @classmethod
     def SplitStratified(cls, collection: LabelledCollection, train_size=0.6):
+        """
+        Generates a :class:`Dataset` from a stratified split of a :class:`LabelledCollection` instance.
+        See :meth:`LabelledCollection.split_stratified`
+
+        :param collection: :class:`LabelledCollection`
+        :param train_size: the proportion of training documents (the rest conforms the test split)
+        :return: an instance of :class:`Dataset`
+        """
         return Dataset(*collection.split_stratified(train_prop=train_size))
 
     @property
     def classes_(self):
+        """
+        The classes according to which the training collection is labelled
+
+        :return: The classes according to which the training collection is labelled
+        """
         return self.training.classes_
 
     @property
     def n_classes(self):
+        """
+        The number of classes according to which the training collection is labelled
+
+        :return: integer
+        """
         return self.training.n_classes
 
     @property
     def binary(self):
+        """
+        Returns True if the training collection is labelled according to two classes
+
+        :return: boolean
+        """
         return self.training.binary
 
     @classmethod
-    def load(cls, train_path, test_path, loader_func: callable):
-        training = LabelledCollection.load(train_path, loader_func)
-        test = LabelledCollection.load(test_path, loader_func)
+    def load(cls, train_path, test_path, loader_func: callable, classes=None, **loader_kwargs):
+        """
+        Loads a training and a test labelled set of data and convert it into a :class:`Dataset` instance.
+        The function in charge of reading the instances must be specified. This function can be a custom one, or any of
+        the reading functions defined in :mod:`quapy.data.reader` module.
+
+        :param train_path: string, the path to the file containing the training instances
+        :param test_path: string, the path to the file containing the test instances
+        :param loader_func: a custom function that implements the data loader and returns a tuple with instances and
+            labels
+        :param classes: array-like, the classes according to which the instances are labelled
+        :param loader_kwargs: any argument that the `loader_func` function needs in order to read the instances.
+            See :meth:`LabelledCollection.load` for further details.
+        :return: a :class:`Dataset` object
+        """
+
+        training = LabelledCollection.load(train_path, loader_func, classes, **loader_kwargs)
+        test = LabelledCollection.load(test_path, loader_func, classes, **loader_kwargs)
         return Dataset(training, test)
 
     @property
     def vocabulary_size(self):
+        """
+        If the dataset is textual, and the vocabulary was indicated, returns the size of the vocabulary
+
+        :return: integer
+        """
         return len(self.vocabulary)
 
-    def stats(self):
+    def stats(self, show):
+        """
+        Returns (and eventually prints) a dictionary with some stats of this dataset. E.g.,:
+
+        >>> data = qp.datasets.fetch_reviews('kindle', tfidf=True, min_df=5)
+        >>> data.stats()
+        >>> Dataset=kindle #tr-instances=3821, #te-instances=21591, type=<class 'scipy.sparse.csr.csr_matrix'>, #features=4403, #classes=[0 1], tr-prevs=[0.081, 0.919], te-prevs=[0.063, 0.937]
+
+        :param show: if set to True (default), prints the stats in standard output
+        :return: a dictionary containing some stats of this collection for the training and test collections. The keys
+            are `train` and `test`, and point to dedicated dictionaries of stats, for each collection, with keys
+            `#instances` (the number of instances), `type` (the type representing the instances),
+            `#features` (the number of features, if the instances are in array-like format), `#classes` (the classes of
+            the collection), `prevs` (the prevalence values for each class)
+        """
         tr_stats = self.training.stats(show=False)
         te_stats = self.test.stats(show=False)
-        print(f'Dataset={self.name} #tr-instances={tr_stats["instances"]}, #te-instances={te_stats["instances"]}, '
-              f'type={tr_stats["type"]}, #features={tr_stats["features"]}, #classes={tr_stats["classes"]}, '
-              f'tr-prevs={tr_stats["prevs"]}, te-prevs={te_stats["prevs"]}')
+        if show:
+            print(f'Dataset={self.name} #tr-instances={tr_stats["instances"]}, #te-instances={te_stats["instances"]}, '
+                  f'type={tr_stats["type"]}, #features={tr_stats["features"]}, #classes={tr_stats["classes"]}, '
+                  f'tr-prevs={tr_stats["prevs"]}, te-prevs={te_stats["prevs"]}')
         return {'train': tr_stats, 'test': te_stats}
 
     @classmethod
     def kFCV(cls, data: LabelledCollection, nfolds=5, nrepeats=1, random_state=0):
+        """
+        Generator of stratified folds to be used in k-fold cross validation. This function is only a wrapper around
+        :meth:`LabelledCollection.kFCV` that returns :class:`Dataset` instances made of training and test folds.
+
+        :param nfolds: integer (default 5), the number of folds to generate
+        :param nrepeats: integer (default 1), the number of rounds of k-fold cross validation to run
+        :param random_state: integer (default 0), guarantees that the folds generated are reproducible
+        :return: yields `nfolds * nrepeats` folds for k-fold cross validation as instances of :class:`Dataset`
+        """
         for i, (train, test) in enumerate(data.kFCV(nfolds=nfolds, nrepeats=nrepeats, random_state=random_state)):
             yield Dataset(train, test, name=f'fold {(i % nfolds) + 1}/{nfolds} (round={(i // nfolds) + 1})')
 
 
 def isbinary(data):
+    """
+    Returns True if `data` is either a binary :class:`Dataset` or a binary :class:`LabelledCollection`
+
+    :param data: a :class:`Dataset` or a :class:`LabelledCollection` object
+    :return: True if labelled according to two classes
+    """
     if isinstance(data, Dataset) or isinstance(data, LabelledCollection):
         return data.binary
     return False
diff --git a/quapy/data/datasets.py b/quapy/data/datasets.py
index 575ffca..74e2a3e 100644
--- a/quapy/data/datasets.py
+++ b/quapy/data/datasets.py
@@ -5,9 +5,6 @@ warnings.warn = warn
 import os
 import zipfile
 from os.path import join
-from urllib.error import HTTPError
-from sklearn.model_selection import StratifiedKFold
-
 import pandas as pd
 
 from quapy.data.base import Dataset, LabelledCollection
@@ -49,18 +46,20 @@ UCI_DATASETS = ['acute.a', 'acute.b',
 
 def fetch_reviews(dataset_name, tfidf=False, min_df=None, data_home=None, pickle=False) -> Dataset:
     """
-    Load a Reviews dataset as a Dataset instance, as used in:
-    Esuli, A., Moreo, A., and Sebastiani, F. "A recurrent neural network for sentiment quantification."
-    Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018.
+    Loads a Reviews dataset as a Dataset instance, as used in
+    `Esuli, A., Moreo, A., and Sebastiani, F. "A recurrent neural network for sentiment quantification."
+    Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018. <https://dl.acm.org/doi/abs/10.1145/3269206.3269287>`_.
+    The list of valid dataset names can be accessed in `quapy.data.datasets.REVIEWS_SENTIMENT_DATASETS`
+
     :param dataset_name: the name of the dataset: valid ones are 'hp', 'kindle', 'imdb'
     :param tfidf: set to True to transform the raw documents into tfidf weighted matrices
     :param min_df: minimun number of documents that should contain a term in order for the term to be
-    kept (ignored if tfidf==False)
+        kept (ignored if tfidf==False)
     :param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
-    ~/quay_data/ directory)
+        ~/quay_data/ directory)
     :param pickle: set to True to pickle the Dataset object the first time it is generated, in order to allow for
-    faster subsequent invokations
-    :return: a Dataset instance
+        faster subsequent invokations
+    :return: a :class:`quapy.data.base.Dataset` instance
     """
     assert dataset_name in REVIEWS_SENTIMENT_DATASETS, \
         f'Name {dataset_name} does not match any known dataset for sentiment reviews. ' \
@@ -93,22 +92,25 @@ def fetch_reviews(dataset_name, tfidf=False, min_df=None, data_home=None, pickle
 
 def fetch_twitter(dataset_name, for_model_selection=False, min_df=None, data_home=None, pickle=False) -> Dataset:
     """
-    Load a Twitter dataset as a Dataset instance, as used in:
-    Gao, W., Sebastiani, F.: From classification to quantification in tweet sentiment analysis.
-    Social Network Analysis and Mining6(19), 1–22 (2016)
-    The datasets 'semeval13', 'semeval14', 'semeval15' share the same training set.
+    Loads a Twitter dataset as a :class:`quapy.data.base.Dataset` instance, as used in:
+    `Gao, W., Sebastiani, F.: From classification to quantification in tweet sentiment analysis.
+    Social Network Analysis and Mining6(19), 1–22 (2016) <https://link.springer.com/content/pdf/10.1007/s13278-016-0327-z.pdf>`_
+    Note that the datasets 'semeval13', 'semeval14', 'semeval15' share the same training set.
+    The list of valid dataset names corresponding to training sets can be accessed in
+    `quapy.data.datasets.TWITTER_SENTIMENT_DATASETS_TRAIN`, while the test sets can be accessed in
+    `quapy.data.datasets.TWITTER_SENTIMENT_DATASETS_TEST`
 
     :param dataset_name: the name of the dataset: valid ones are 'gasp', 'hcr', 'omd', 'sanders', 'semeval13',
-    'semeval14', 'semeval15', 'semeval16', 'sst', 'wa', 'wb'
+        'semeval14', 'semeval15', 'semeval16', 'sst', 'wa', 'wb'
     :param for_model_selection: if True, then returns the train split as the training set and the devel split
-    as the test set; if False, then returns the train+devel split as the training set and the test set as the
-    test set
+        as the test set; if False, then returns the train+devel split as the training set and the test set as the
+        test set
     :param min_df: minimun number of documents that should contain a term in order for the term to be kept
     :param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
-    ~/quay_data/ directory)
+        ~/quay_data/ directory)
     :param pickle: set to True to pickle the Dataset object the first time it is generated, in order to allow for
-    faster subsequent invokations
-    :return: a Dataset instance
+        faster subsequent invokations
+    :return: a :class:`quapy.data.base.Dataset` instance
     """
     assert dataset_name in TWITTER_SENTIMENT_DATASETS_TRAIN + TWITTER_SENTIMENT_DATASETS_TEST, \
         f'Name {dataset_name} does not match any known dataset for sentiment twitter. ' \
@@ -163,11 +165,58 @@ def fetch_twitter(dataset_name, for_model_selection=False, min_df=None, data_hom
 
 
 def fetch_UCIDataset(dataset_name, data_home=None, test_split=0.3, verbose=False) -> Dataset:
+    """
+    Loads a UCI dataset as an instance of :class:`quapy.data.base.Dataset`, as used in
+    `Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
+    Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
+    Information Fusion, 34, 87-100. <https://www.sciencedirect.com/science/article/pii/S1566253516300628>`_
+    and
+    `Pérez-Gállego, P., Castano, A., Quevedo, J. R., & del Coz, J. J. (2019).
+    Dynamic ensemble selection for quantification tasks.
+    Information Fusion, 45, 1-15. <https://www.sciencedirect.com/science/article/pii/S1566253517303652>`_.
+    The datasets do not come with a predefined train-test split (see :meth:`fetch_UCILabelledCollection` for further
+    information on how to use these collections), and so a train-test split is generated at desired proportion.
+    The list of valid dataset names can be accessed in `quapy.data.datasets.UCI_DATASETS`
+
+    :param dataset_name: a dataset name
+    :param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
+        ~/quay_data/ directory)
+    :param test_split: proportion of documents to be included in the test set. The rest conforms the training set
+    :param verbose: set to True (default is False) to get information (from the UCI ML repository) about the datasets
+    :return: a :class:`quapy.data.base.Dataset` instance
+    """
     data = fetch_UCILabelledCollection(dataset_name, data_home, verbose)
     return Dataset(*data.split_stratified(1 - test_split, random_state=0))
 
 
 def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) -> Dataset:
+    """
+    Loads a UCI collection as an instance of :class:`quapy.data.base.LabelledCollection`, as used in
+    `Pérez-Gállego, P., Quevedo, J. R., & del Coz, J. J. (2017).
+    Using ensembles for problems with characterizable changes in data distribution: A case study on quantification.
+    Information Fusion, 34, 87-100. <https://www.sciencedirect.com/science/article/pii/S1566253516300628>`_
+    and
+    `Pérez-Gállego, P., Castano, A., Quevedo, J. R., & del Coz, J. J. (2019).
+    Dynamic ensemble selection for quantification tasks.
+    Information Fusion, 45, 1-15. <https://www.sciencedirect.com/science/article/pii/S1566253517303652>`_.
+    The datasets do not come with a predefined train-test split, and so Pérez-Gállego et al. adopted a 5FCVx2 evaluation
+    protocol, meaning that each collection was used to generate two rounds (hence the x2) of 5 fold cross validation.
+    This can be reproduced by using :meth:`quapy.data.base.Dataset.kFCV`, e.g.:
+
+    >>> import quapy as qp
+    >>> collection = qp.datasets.fetch_UCILabelledCollection("yeast")
+    >>> for data in qp.data.Dataset.kFCV(collection, nfolds=5, nrepeats=2):
+    >>>     ...
+
+    The list of valid dataset names can be accessed in `quapy.data.datasets.UCI_DATASETS`
+
+    :param dataset_name: a dataset name
+    :param data_home: specify the quapy home directory where collections will be dumped (leave empty to use the default
+        ~/quay_data/ directory)
+    :param test_split: proportion of documents to be included in the test set. The rest conforms the training set
+    :param verbose: set to True (default is False) to get information (from the UCI ML repository) about the datasets
+    :return: a :class:`quapy.data.base.Dataset` instance
+    """
 
     assert dataset_name in UCI_DATASETS, \
         f'Name {dataset_name} does not match any known dataset from the UCI Machine Learning datasets repository. ' \
@@ -302,7 +351,7 @@ def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) ->
         df = pd.read_csv(data_path, header=None, encoding='utf-16', sep='\t')
 
         df[0] = df[0].apply(lambda x: float(x.replace(',', '.'))).astype(float, copy=False)
-        [df_replace(df, col) for col in range(1, 6)]
+        [_df_replace(df, col) for col in range(1, 6)]
         X = df.loc[:, 0:5].values
         if dataset_name == 'acute.a':
             y = binarize(df[6], pos_class='yes')
@@ -482,5 +531,5 @@ def fetch_UCILabelledCollection(dataset_name, data_home=None, verbose=False) ->
     return data
 
 
-def df_replace(df, col, repl={'yes': 1, 'no':0}, astype=float):
+def _df_replace(df, col, repl={'yes': 1, 'no':0}, astype=float):
     df[col] = df[col].apply(lambda x:repl[x]).astype(astype, copy=False)
\ No newline at end of file
diff --git a/quapy/data/preprocessing.py b/quapy/data/preprocessing.py
index 6e58718..f04f010 100644
--- a/quapy/data/preprocessing.py
+++ b/quapy/data/preprocessing.py
@@ -12,14 +12,18 @@ from .base import LabelledCollection
 
 def text2tfidf(dataset:Dataset, min_df=3, sublinear_tf=True, inplace=False, **kwargs):
     """
-    Transforms a Dataset of textual instances into a Dataset of tfidf weighted sparse vectors
-    :param dataset: a Dataset where the instances are lists of str
-    :param min_df: minimum number of occurrences for a word to be considered as part of the vocabulary
-    :param sublinear_tf: whether or not to apply the log scalling to the tf counters
-    :param inplace: whether or not to apply the transformation inplace, or to a new copy
-    :param kwargs: the rest of parameters of the transformation (as for sklearn.feature_extraction.text.TfidfVectorizer)
-    :return: a new Dataset in csr_matrix format (if inplace=False) or a reference to the current Dataset (inplace=True)
-    where the instances are stored in a csr_matrix of real-valued tfidf scores
+    Transforms a :class:`quapy.data.base.Dataset` of textual instances into a :class:`quapy.data.base.Dataset` of
+    tfidf weighted sparse vectors
+
+    :param dataset: a :class:`quapy.data.base.Dataset` where the instances of training and test collections are
+        lists of str
+    :param min_df: minimum number of occurrences for a word to be considered as part of the vocabulary (default 3)
+    :param sublinear_tf: whether or not to apply the log scalling to the tf counters (default True)
+    :param inplace: whether or not to apply the transformation inplace (True), or to a new copy (False, default)
+    :param kwargs: the rest of parameters of the transformation (as for sklearn's
+        `TfidfVectorizer <https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html>`_)
+    :return: a new :class:`quapy.data.base.Dataset` in `csr_matrix` format (if inplace=False) or a reference to the
+        current Dataset (if inplace=True) where the instances are stored in a `csr_matrix` of real-valued tfidf scores
     """
     __check_type(dataset.training.instances, np.ndarray, str)
     __check_type(dataset.test.instances, np.ndarray, str)
@@ -41,13 +45,17 @@ def text2tfidf(dataset:Dataset, min_df=3, sublinear_tf=True, inplace=False, **kw
 
 def reduce_columns(dataset: Dataset, min_df=5, inplace=False):
     """
-    Reduces the dimensionality of the csr_matrix by removing the columns of words which are not present in at least
-    _min_df_ instances
-    :param dataset: a Dataset in sparse format (any subtype of scipy.sparse.spmatrix)
-    :param min_df: minimum number of instances below which the columns are removed
-    :param inplace: whether or not to apply the transformation inplace, or to a new copy
-    :return: a new Dataset (if inplace=False) or a reference to the current Dataset (inplace=True)
-    where the dimensions corresponding to infrequent instances have been removed
+    Reduces the dimensionality of the instances, represented as a `csr_matrix` (or any subtype of
+    `scipy.sparse.spmatrix`), of training and test documents by removing the columns of words which are not present
+    in at least `min_df` instances in the training set
+
+    :param dataset: a :class:`quapy.data.base.Dataset` in which instances are represented in sparse format (any
+        subtype of scipy.sparse.spmatrix)
+    :param min_df: integer, minimum number of instances below which the columns are removed
+    :param inplace: whether or not to apply the transformation inplace (True), or to a new copy (False, default)
+    :return: a new :class:`quapy.data.base.Dataset` (if inplace=False) or a reference to the current
+        :class:`quapy.data.base.Dataset` (inplace=True) where the dimensions corresponding to infrequent terms
+        in the training set have been removed
     """
     __check_type(dataset.training.instances, spmatrix)
     __check_type(dataset.test.instances, spmatrix)
@@ -71,7 +79,17 @@ def reduce_columns(dataset: Dataset, min_df=5, inplace=False):
         return Dataset(training, test)
 
 
-def standardize(dataset: Dataset, inplace=True):
+def standardize(dataset: Dataset, inplace=False):
+    """
+    Standardizes the real-valued columns of a :class:`quapy.data.base.Dataset`.
+    Standardization, aka z-scoring, of a variable `X` comes down to subtracting the average and normalizing by the
+    standard deviation.
+
+    :param dataset: a :class:`quapy.data.base.Dataset` object
+    :param inplace: set to True if the transformation is to be applied inplace, or to False (default) if a new
+        :class:`quapy.data.base.Dataset` is to be returned
+    :return:
+    """
     s = StandardScaler(copy=not inplace)
     training = s.fit_transform(dataset.training.instances)
     test = s.transform(dataset.test.instances)
@@ -83,14 +101,18 @@ def standardize(dataset: Dataset, inplace=True):
 
 def index(dataset: Dataset, min_df=5, inplace=False, **kwargs):
     """
-    Indexes a dataset of strings. To index a document means to replace each different token by a unique numerical index.
-    Rare words (i.e., words occurring less than _min_df_ times) are replaced by a special token UNK
-    :param dataset: a Dataset where the instances are lists of str
-    :param min_df: minimum number of instances below which the term is replaced by a UNK index
-    :param inplace: whether or not to apply the transformation inplace, or to a new copy
-    :param kwargs: the rest of parameters of the transformation (as for sklearn.feature_extraction.text.CountVectorizer)
-    :return: a new Dataset (if inplace=False) or a reference to the current Dataset (inplace=True)
-    consisting of lists of integer values representing indices.
+    Indexes the tokens of a textual :class:`quapy.data.base.Dataset` of string documents.
+    To index a document means to replace each different token by a unique numerical index.
+    Rare words (i.e., words occurring less than `min_df` times) are replaced by a special token `UNK`
+
+    :param dataset: a :class:`quapy.data.base.Dataset` object where the instances of training and test documents
+        are lists of str
+    :param min_df: minimum number of occurrences below which the term is replaced by a `UNK` index
+    :param inplace: whether or not to apply the transformation inplace (True), or to a new copy (False, default)
+    :param kwargs: the rest of parameters of the transformation (as for sklearn's
+    `CountVectorizer <https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html>_`)
+    :return: a new :class:`quapy.data.base.Dataset` (if inplace=False) or a reference to the current
+        :class:`quapy.data.base.Dataset` (inplace=True) consisting of lists of integer values representing indices.
     """
     __check_type(dataset.training.instances, np.ndarray, str)
     __check_type(dataset.test.instances, np.ndarray, str)
@@ -120,17 +142,23 @@ def __check_type(container, container_type=None, element_type=None):
 
 
 class IndexTransformer:
+    """
+    This class implements a sklearn's-style transformer that indexes text as numerical ids for the tokens it
+    contains, and that would be generated by sklearn's
+    `CountVectorizer <https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html>`_
+
+    :param kwargs: keyworded arguments from `CountVectorizer <https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html>`_
+    """
 
     def __init__(self, **kwargs):
-        """
-        :param kwargs: keyworded arguments from _sklearn.feature_extraction.text.CountVectorizer_
-        """
         self.vect = CountVectorizer(**kwargs)
         self.unk = -1  # a valid index is assigned after fit
         self.pad = -2  # a valid index is assigned after fit
 
     def fit(self, X):
         """
+        Fits the transformer, i.e., decides on the vocabulary, given a list of strings.
+
         :param X: a list of strings
         :return: self
         """
@@ -142,22 +170,52 @@ class IndexTransformer:
         return self
 
     def transform(self, X, n_jobs=-1):
+        """
+        Transforms the strings in `X` as lists of numerical ids
+
+        :param X: a list of strings
+        :param n_jobs: the number of parallel workers to carry out this task
+        :return: a `np.ndarray` of numerical ids
+        """
         # given the number of tasks and the number of jobs, generates the slices for the parallel processes
         assert self.unk != -1, 'transform called before fit'
-        indexed = map_parallel(func=self.index, args=X, n_jobs=n_jobs)
+        indexed = map_parallel(func=self._index, args=X, n_jobs=n_jobs)
         return np.asarray(indexed)
 
-    def index(self, documents):
+    def _index(self, documents):
         vocab = self.vocabulary_.copy()
         return [[vocab.prevalence(word, self.unk) for word in self.analyzer(doc)] for doc in tqdm(documents, 'indexing')]
 
     def fit_transform(self, X, n_jobs=-1):
+        """
+        Fits the transform on `X` and transforms it.
+
+        :param X: a list of strings
+        :param n_jobs: the number of parallel workers to carry out this task
+        :return: a `np.ndarray` of numerical ids
+        """
         return self.fit(X).transform(X, n_jobs=n_jobs)
 
     def vocabulary_size(self):
+        """
+        Gets the length of the vocabulary according to which the document tokens have been indexed
+
+        :return: integer
+        """
         return len(self.vocabulary_)
 
     def add_word(self, word, id=None, nogaps=True):
+        """
+        Adds a new token (regardless of whether it has been found in the text or not), with dedicated id.
+        Useful to define special tokens for codifying unknown words, or padding tokens.
+
+        :param word: string, surface form of the token
+        :param id: integer, numerical value to assign to the token (leave as None for indicating the next valid id,
+            default)
+        :param nogaps: if set to True (default) asserts that the id indicated leads to no numerical gaps with
+            precedent ids stored so far
+        :return: integer, the numerical id for the new token
+        """
         if word in self.vocabulary_:
             raise ValueError(f'word {word} already in dictionary')
         if id is None:
diff --git a/quapy/data/reader.py b/quapy/data/reader.py
index 675b9a1..8f8bc79 100644
--- a/quapy/data/reader.py
+++ b/quapy/data/reader.py
@@ -7,7 +7,10 @@ def from_text(path, encoding='utf-8', verbose=1, class2int=True):
     """
     Reads a labelled colletion of documents.
     File fomart <0 or 1>\t<document>\n
+
     :param path: path to the labelled collection
+    :param encoding: the text encoding used to open the file
+    :param verbose: if >0 (default) shows some progress information in standard output
     :return: a list of sentences, and a list of labels
     """
     all_sentences, all_labels = [], []
@@ -35,8 +38,9 @@ def from_sparse(path):
     """
     Reads a labelled collection of real-valued instances expressed in sparse format
     File format <-1 or 0 or 1>[\s col(int):val(float)]\n
+
     :param path: path to the labelled collection
-    :return: a csr_matrix containing the instances (rows), and a ndarray containing the labels
+    :return: a `csr_matrix` containing the instances (rows), and a ndarray containing the labels
     """
 
     def split_col_val(col_val):
@@ -68,8 +72,10 @@ def from_csv(path, encoding='utf-8'):
     """
     Reads a csv file in which columns are separated by ','.
     File format <label>,<feat1>,<feat2>,...,<featn>\n
+
     :param path: path to the csv file
-    :return: a ndarray for the labels and a ndarray (float) for the covariates
+    :param encoding: the text encoding used to open the file
+    :return: a np.ndarray for the labels and a ndarray (float) for the covariates
     """
 
     X, y = [], []
@@ -85,11 +91,16 @@ def from_csv(path, encoding='utf-8'):
 def reindex_labels(y):
     """
     Re-indexes a list of labels as a list of indexes, and returns the classnames corresponding to the indexes.
-    E.g., y=['B', 'B', 'A', 'C'] -> [1,1,0,2], ['A','B','C']
+    E.g.:
+
+    >>> reindex_labels(['B', 'B', 'A', 'C'])
+    >>> (array([1, 1, 0, 2]), array(['A', 'B', 'C'], dtype='<U1'))
+
     :param y: the list or array of original labels
     :return: a ndarray (int) of class indexes, and a ndarray of classnames corresponding to the indexes.
     """
-    classnames = sorted(np.unique(y))
+    y = np.asarray(y)
+    classnames = np.asarray(sorted(np.unique(y)))
     label2index = {label: index for index, label in enumerate(classnames)}
     indexed = np.empty(y.shape, dtype=np.int)
     for label in classnames:
@@ -98,6 +109,17 @@ def reindex_labels(y):
 
 
 def binarize(y, pos_class):
+    """
+    Binarizes a categorical array-like collection of labels towards the positive class `pos_class`. E.g.,:
+
+    >>> binarize([1, 2, 3, 1, 1, 0], pos_class=2)
+    >>> array([0, 1, 0, 0, 0, 0])
+
+    :param y: array-like of labels
+    :param pos_class: integer, the positive class
+    :return: a binary np.ndarray, in which values 1 corresponds to positions in whcih `y` had `pos_class` labels, and
+        0 otherwise
+    """
     y = np.asarray(y)
     ybin = np.zeros(y.shape, dtype=np.int)
     ybin[y == pos_class] = 1