concordia
/
sshoc-skosmapping
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Upload files to ''

This commit is contained in:
Cesare Concordia 2021-02-04 12:52:25 +01:00
parent b64401eaec
commit be065bb270
1 changed files with 561 additions and 97 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

658
Progetto_Lett.ipynb
View File

@ -9,7 +9,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 1,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -25,7 +25,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -34,7 +34,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -43,7 +43,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -52,7 +52,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -61,7 +61,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -74,7 +74,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -87,7 +87,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -148,7 +148,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 269, "execution_count": 36,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -270,17 +270,38 @@
" iris = []\n", " iris = []\n",
" i=0\n", " i=0\n",
" for div in self.soup.body.find_all(\"div1\"):\n", " for div in self.soup.body.find_all(\"div1\"):\n",
" islm1=False;\n",
" for verso in div.find_all('l'):\n", " for verso in div.find_all('l'):\n",
" i=i+1;\n", " i=i+1;\n",
" lm1_text=[];\n",
" verso_text=elem_to_text(verso).strip();\n", " verso_text=elem_to_text(verso).strip();\n",
" for child in verso.children: #Manage <LM1> elements\n",
" if (child.name=='lm1'):\n",
" islm1=True;\n",
" lm1_text.append(elem_to_text(child).strip());\n",
" # print (lm1_text);\n",
" \n",
" if(islm1):\n",
" islm1=False;\n",
" for lm1str in lm1_text:\n",
" replace_str=lm1str.partition(' ')[0];\n",
" verso_text=verso_text.replace(lm1str, replace_str);\n",
" \n",
" for vparent in verso.parents:\n", " for vparent in verso.parents:\n",
" if (vparent.name=='div1'):\n", " if (vparent.name=='div1'):\n",
" canto = vparent.contents[0];\n", " canto = vparent.contents[0];\n",
" #\" \".join(verso_text.split())).strip()\n",
" verso_text=verso_text.replace(\" ,\", \",\");\n",
" verso_text=verso_text.replace(\" .\", \".\");\n",
" verso_text=verso_text.replace(\" !\", \"!\");\n",
" verso_text=verso_text.replace(\" ?\", \"?\");\n",
" verso_text=verso_text.replace(\"l' \", \"l'\");\n",
" iri_verso=\"http://hdn.dantenetwork.it/resource/work/commedia/cantica/\"+str(self.idres)+\"/\"+\"/\".join(canto.lower().split())+\"/verso/\"+str(i);\n", " iri_verso=\"http://hdn.dantenetwork.it/resource/work/commedia/cantica/\"+str(self.idres)+\"/\"+\"/\".join(canto.lower().split())+\"/verso/\"+str(i);\n",
" iri_verso=iri_verso+'\\n a efrbroo:F2_Expression ,\\n rdfs:Resource ; \\nhttp://erlangen-crm.org/current/P190_has_symbolic_content \"';\n", " iri_verso=iri_verso+'\\n a efrbroo:F2_Expression ,\\n rdfs:Resource ; \\nhttp://erlangen-crm.org/current/P190_has_symbolic_content \"';\n",
" iri_verso=iri_verso+(\" \".join(verso_text.split())).strip()+ '\\\"^^xsd:string ;\\n http://erlangen-crm.org/current/P3_has_note';\n", " iri_verso=iri_verso+verso_text.strip()+ '\"^^xsd:string ;\\n http://erlangen-crm.org/current/P3_has_note';\n",
" iri_verso=iri_verso+' \"'+str(i)+'\"^^xsd:int ;\\n http://hdn.dantenetwork.it/resource/has_number \"'+str(i)+'\"^^xsd:int .'\n", " iri_verso=iri_verso+' \"'+str(i)+'\"^^xsd:int ;\\n http://hdn.dantenetwork.it/resource/has_number \"'+str(i)+'\"^^xsd:int .'\n",
" iris.append((i, \" \".join(verso_text.split()), iri_verso));\n", " \n",
" iris.append((i, verso_text.strip(), iri_verso));\n",
" \n", " \n",
" \n", " \n",
" return iris\n", " return iris\n",
@ -328,7 +349,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 235, "execution_count": 29,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -349,7 +370,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 219, "execution_count": 30,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -400,13 +421,13 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Carico il testo *inferno.xml* e creo una tabella\n", "### Elaboro il file *inferno.xml*\n",
"Eseguo il parsing del testo presente nel file e creo una tabella con le seguenti colonne: *forma flessa, categoria, lemma, canto, verso, pposizione forma flessa nel verso*" "Eseguo il parsing del testo presente nel file e creo una tabella con le seguenti colonne: *forma flessa, categoria, lemma, canto, verso, pposizione forma flessa nel verso*"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 270, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -423,7 +444,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 271, "execution_count": 13,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -438,7 +459,7 @@
"dtype: int64" "dtype: int64"
] ]
}, },
"execution_count": 271, "execution_count": 13,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -453,7 +474,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 272, "execution_count": 14,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -594,7 +615,7 @@
"9 per [epskpl] [per] Canto 1 2 3" "9 per [epskpl] [per] Canto 1 2 3"
] ]
}, },
"execution_count": 272, "execution_count": 14,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -607,7 +628,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Generiamo una tabella con gli IRI dei versi per la cantica *Inferno*\n", "#### Creo una tabella con gli IRI dei versi per la cantica *Inferno*\n",
"\n", "\n",
"La abella contiene il numero del verso, il verso e l'IRI del verso. \n", "La abella contiene il numero del verso, il verso e l'IRI del verso. \n",
"Per l'IRI del verso mi son basato su quanto riportato nel file *Commedia.rdf*, un esempio è il seguente: \n", "Per l'IRI del verso mi son basato su quanto riportato nel file *Commedia.rdf*, un esempio è il seguente: \n",
@ -625,7 +646,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 280, "execution_count": 15,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -637,7 +658,7 @@
"dtype: int64" "dtype: int64"
] ]
}, },
"execution_count": 280, "execution_count": 15,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -651,21 +672,21 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 282, "execution_count": 16,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/html": [ "text/html": [
"<style type=\"text/css\" >\n", "<style type=\"text/css\" >\n",
"#T_07283f2a_66d2_11eb_8bb0_60f81dca6224row0_col2,#T_07283f2a_66d2_11eb_8bb0_60f81dca6224row1_col2,#T_07283f2a_66d2_11eb_8bb0_60f81dca6224row2_col2,#T_07283f2a_66d2_11eb_8bb0_60f81dca6224row3_col2,#T_07283f2a_66d2_11eb_8bb0_60f81dca6224row4_col2{\n", "#T_a736dc4a_66de_11eb_b4ac_60f81dca6224row0_col2,#T_a736dc4a_66de_11eb_b4ac_60f81dca6224row1_col2,#T_a736dc4a_66de_11eb_b4ac_60f81dca6224row2_col2,#T_a736dc4a_66de_11eb_b4ac_60f81dca6224row3_col2,#T_a736dc4a_66de_11eb_b4ac_60f81dca6224row4_col2{\n",
" width: 400px;\n", " width: 400px;\n",
" }</style><table id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >NumeroVerso</th> <th class=\"col_heading level0 col1\" >Verso</th> <th class=\"col_heading level0 col2\" >IRIVerso</th> </tr></thead><tbody>\n", " }</style><table id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >NumeroVerso</th> <th class=\"col_heading level0 col1\" >Verso</th> <th class=\"col_heading level0 col2\" >IRIVerso</th> </tr></thead><tbody>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224level0_row0\" class=\"row_heading level0 row0\" >0</th>\n", " <th id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row0_col0\" class=\"data row0 col0\" >1</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row0_col0\" class=\"data row0 col0\" >1</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row0_col1\" class=\"data row0 col1\" >Nel mezzo del cammin di nostra vita</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row0_col1\" class=\"data row0 col1\" >Nel mezzo del cammin di nostra vita</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row0_col2\" class=\"data row0 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/1\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row0_col2\" class=\"data row0 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/1\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"Nel mezzo del cammin di nostra vita\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"Nel mezzo del cammin di nostra vita\"^^xsd:string ;\n",
@ -673,10 +694,10 @@
" http://hdn.dantenetwork.it/resource/has_number \"1\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"1\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224level0_row1\" class=\"row_heading level0 row1\" >1</th>\n", " <th id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row1_col0\" class=\"data row1 col0\" >2</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row1_col0\" class=\"data row1 col0\" >2</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row1_col1\" class=\"data row1 col1\" >mi ritrovai per una selva oscura</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row1_col1\" class=\"data row1 col1\" >mi ritrovai per una selva oscura</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row1_col2\" class=\"data row1 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/2\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row1_col2\" class=\"data row1 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/2\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"mi ritrovai per una selva oscura\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"mi ritrovai per una selva oscura\"^^xsd:string ;\n",
@ -684,21 +705,21 @@
" http://hdn.dantenetwork.it/resource/has_number \"2\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"2\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224level0_row2\" class=\"row_heading level0 row2\" >2</th>\n", " <th id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row2_col0\" class=\"data row2 col0\" >3</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row2_col0\" class=\"data row2 col0\" >3</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row2_col1\" class=\"data row2 col1\" >ché la diritta via era smarrita .</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row2_col1\" class=\"data row2 col1\" >ché la diritta via era smarrita.</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row2_col2\" class=\"data row2 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/3\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row2_col2\" class=\"data row2 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/3\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"ché la diritta via era smarrita .\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"ché la diritta via era smarrita.\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"3\"^^xsd:int ;\n", " http://erlangen-crm.org/current/P3_has_note \"3\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"3\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"3\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224level0_row3\" class=\"row_heading level0 row3\" >3</th>\n", " <th id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row3_col0\" class=\"data row3 col0\" >4</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row3_col0\" class=\"data row3 col0\" >4</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row3_col1\" class=\"data row3 col1\" >Ahi quanto a dir qual era è cosa dura</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row3_col1\" class=\"data row3 col1\" >Ahi quanto a dir qual era è cosa dura</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row3_col2\" class=\"data row3 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/4\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row3_col2\" class=\"data row3 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/4\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"Ahi quanto a dir qual era è cosa dura\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"Ahi quanto a dir qual era è cosa dura\"^^xsd:string ;\n",
@ -706,10 +727,10 @@
" http://hdn.dantenetwork.it/resource/has_number \"4\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"4\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224level0_row4\" class=\"row_heading level0 row4\" >4</th>\n", " <th id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row4_col0\" class=\"data row4 col0\" >5</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row4_col0\" class=\"data row4 col0\" >5</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row4_col1\" class=\"data row4 col1\" >esta selva selvaggia e aspra e forte</td>\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row4_col1\" class=\"data row4 col1\" >esta selva selvaggia e aspra e forte</td>\n",
" <td id=\"T_07283f2a_66d2_11eb_8bb0_60f81dca6224row4_col2\" class=\"data row4 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/5\n", " <td id=\"T_a736dc4a_66de_11eb_b4ac_60f81dca6224row4_col2\" class=\"data row4 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/1/canto/1/verso/5\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"esta selva selvaggia e aspra e forte\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"esta selva selvaggia e aspra e forte\"^^xsd:string ;\n",
@ -719,10 +740,10 @@
" </tbody></table>" " </tbody></table>"
], ],
"text/plain": [ "text/plain": [
"<pandas.io.formats.style.Styler at 0x14efc2a10>" "<pandas.io.formats.style.Styler at 0x107109d10>"
] ]
}, },
"execution_count": 282, "execution_count": 16,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -735,17 +756,17 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### File *purgatorio.xml*\n", "### Elaborazione del file *purgatorio.xml*\n",
"\n", "Eseguo il parsing del testo presente nel file e creo una tabella simile alla precedente"
"Test, ignorare.\n"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 276, "execution_count": 17,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"#TEST IGNORARE\n",
"#tei_purgatorio = TEIFile('/Users/cesare/Projects/hdn/triple/DanteTriple/xml/DanteSearch/grammaticale/purgatorio.xml', 2)\n", "#tei_purgatorio = TEIFile('/Users/cesare/Projects/hdn/triple/DanteTriple/xml/DanteSearch/grammaticale/purgatorio.xml', 2)\n",
"#bbs_pu=tei_purgatorio.IRIverso\n", "#bbs_pu=tei_purgatorio.IRIverso\n",
"#for repu in bbs_pu:\n", "#for repu in bbs_pu:\n",
@ -755,18 +776,9 @@
"# break" "# break"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Carico il testo *purgatorio.xml* e creo una tabella\n",
"Eseguo il parsing del testo presente nel file e creo una tabella simile alla precedente\n",
"\\<LM1\\> forma flessa con due lemmi, gestire nel parser"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 277, "execution_count": 18,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -783,7 +795,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 278, "execution_count": 19,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -798,14 +810,12 @@
"dtype: int64" "dtype: int64"
] ]
}, },
"execution_count": 278, "execution_count": 19,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"source": [ "source": [
"#DA COMPLETARE CON IRI CORRETTO!\n",
"\n",
"data_purgatorio = [parsed_purgatorio[0]]\n", "data_purgatorio = [parsed_purgatorio[0]]\n",
"#dfObj_purgatorio = pd.DataFrame(data_purgatorio[0]) \n", "#dfObj_purgatorio = pd.DataFrame(data_purgatorio[0]) \n",
"testo_purgatorio_tabella=pd.DataFrame(data_purgatorio[0], columns = ['FormaFlessa' , 'Categoria', 'Lemma', 'Canto', 'Verso', 'PosizioneFFNelVerso']) \n", "testo_purgatorio_tabella=pd.DataFrame(data_purgatorio[0], columns = ['FormaFlessa' , 'Categoria', 'Lemma', 'Canto', 'Verso', 'PosizioneFFNelVerso']) \n",
@ -814,7 +824,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 279, "execution_count": 20,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -912,7 +922,7 @@
"33244 7 " "33244 7 "
] ]
}, },
"execution_count": 279, "execution_count": 20,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -925,14 +935,14 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Generiamo una tabella con gli IRI dei versi per la cantica *Purgatorio*\n", "#### Creazione di una tabella con gli IRI dei versi per la cantica *Purgatorio*\n",
"\n", "\n",
"La tabella contiene il numero del verso, il verso e l'IRI del verso. " "La tabella contiene il numero del verso, il verso e l'IRI del verso. "
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 284, "execution_count": 21,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -944,7 +954,7 @@
"dtype: int64" "dtype: int64"
] ]
}, },
"execution_count": 284, "execution_count": 21,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -958,21 +968,21 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 285, "execution_count": 22,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/html": [ "text/html": [
"<style type=\"text/css\" >\n", "<style type=\"text/css\" >\n",
"#T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row0_col2,#T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row1_col2,#T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row2_col2,#T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row3_col2,#T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row4_col2{\n", "#T_c1fe4676_66de_11eb_b4ac_60f81dca6224row0_col2,#T_c1fe4676_66de_11eb_b4ac_60f81dca6224row1_col2,#T_c1fe4676_66de_11eb_b4ac_60f81dca6224row2_col2,#T_c1fe4676_66de_11eb_b4ac_60f81dca6224row3_col2,#T_c1fe4676_66de_11eb_b4ac_60f81dca6224row4_col2{\n",
" width: 400px;\n", " width: 400px;\n",
" }</style><table id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >NumeroVerso</th> <th class=\"col_heading level0 col1\" >Verso</th> <th class=\"col_heading level0 col2\" >IRIVerso</th> </tr></thead><tbody>\n", " }</style><table id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >NumeroVerso</th> <th class=\"col_heading level0 col1\" >Verso</th> <th class=\"col_heading level0 col2\" >IRIVerso</th> </tr></thead><tbody>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224level0_row0\" class=\"row_heading level0 row0\" >0</th>\n", " <th id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row0_col0\" class=\"data row0 col0\" >1</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row0_col0\" class=\"data row0 col0\" >1</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row0_col1\" class=\"data row0 col1\" >Per correr miglior acque alza le vele</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row0_col1\" class=\"data row0 col1\" >Per correr miglior acque alza le vele</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row0_col2\" class=\"data row0 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/1\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row0_col2\" class=\"data row0 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/1\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"Per correr miglior acque alza le vele\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"Per correr miglior acque alza le vele\"^^xsd:string ;\n",
@ -980,21 +990,21 @@
" http://hdn.dantenetwork.it/resource/has_number \"1\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"1\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224level0_row1\" class=\"row_heading level0 row1\" >1</th>\n", " <th id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row1_col0\" class=\"data row1 col0\" >2</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row1_col0\" class=\"data row1 col0\" >2</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row1_col1\" class=\"data row1 col1\" >omai la navicella del del mio ingegno ,</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row1_col1\" class=\"data row1 col1\" >omai la navicella del mio ingegno,</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row1_col2\" class=\"data row1 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/2\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row1_col2\" class=\"data row1 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/2\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"omai la navicella del del mio ingegno ,\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"omai la navicella del mio ingegno,\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"2\"^^xsd:int ;\n", " http://erlangen-crm.org/current/P3_has_note \"2\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"2\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"2\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224level0_row2\" class=\"row_heading level0 row2\" >2</th>\n", " <th id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row2_col0\" class=\"data row2 col0\" >3</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row2_col0\" class=\"data row2 col0\" >3</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row2_col1\" class=\"data row2 col1\" >che lascia dietro a sé mar sì crudele;</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row2_col1\" class=\"data row2 col1\" >che lascia dietro a sé mar sì crudele;</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row2_col2\" class=\"data row2 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/3\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row2_col2\" class=\"data row2 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/3\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"che lascia dietro a sé mar sì crudele;\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"che lascia dietro a sé mar sì crudele;\"^^xsd:string ;\n",
@ -1002,10 +1012,10 @@
" http://hdn.dantenetwork.it/resource/has_number \"3\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"3\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224level0_row3\" class=\"row_heading level0 row3\" >3</th>\n", " <th id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row3_col0\" class=\"data row3 col0\" >4</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row3_col0\" class=\"data row3 col0\" >4</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row3_col1\" class=\"data row3 col1\" >e canterò di quel secondo regno</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row3_col1\" class=\"data row3 col1\" >e canterò di quel secondo regno</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row3_col2\" class=\"data row3 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/4\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row3_col2\" class=\"data row3 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/4\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"e canterò di quel secondo regno\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"e canterò di quel secondo regno\"^^xsd:string ;\n",
@ -1013,10 +1023,10 @@
" http://hdn.dantenetwork.it/resource/has_number \"4\"^^xsd:int .</td>\n", " http://hdn.dantenetwork.it/resource/has_number \"4\"^^xsd:int .</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224level0_row4\" class=\"row_heading level0 row4\" >4</th>\n", " <th id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row4_col0\" class=\"data row4 col0\" >5</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row4_col0\" class=\"data row4 col0\" >5</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row4_col1\" class=\"data row4 col1\" >dove l' umano spirito si purga</td>\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row4_col1\" class=\"data row4 col1\" >dove l' umano spirito si purga</td>\n",
" <td id=\"T_b043fcfc_66d2_11eb_8bb0_60f81dca6224row4_col2\" class=\"data row4 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/5\n", " <td id=\"T_c1fe4676_66de_11eb_b4ac_60f81dca6224row4_col2\" class=\"data row4 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/2/canto/1/verso/5\n",
" a efrbroo:F2_Expression ,\n", " a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n", " rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"dove l' umano spirito si purga\"^^xsd:string ;\n", "http://erlangen-crm.org/current/P190_has_symbolic_content \"dove l' umano spirito si purga\"^^xsd:string ;\n",
@ -1026,10 +1036,10 @@
" </tbody></table>" " </tbody></table>"
], ],
"text/plain": [ "text/plain": [
"<pandas.io.formats.style.Styler at 0x14cdefe10>" "<pandas.io.formats.style.Styler at 0x107109950>"
] ]
}, },
"execution_count": 285, "execution_count": 22,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1038,6 +1048,460 @@
"df_IRI_versi_pur.head().style.set_properties(subset=['IRIVerso'], **{'width': '400px'})" "df_IRI_versi_pur.head().style.set_properties(subset=['IRIVerso'], **{'width': '400px'})"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Elaborazione del file paradiso.xml\n",
"Eseguo il parsing del testo presente nel file e creo una tabella simile alle precedenti"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Handled /Users/cesare/Projects/hdn/triple/DanteTriple/xml/DanteSearch/grammaticale/paradiso.xml\n"
]
}
],
"source": [
"parsed_paradiso=tei_to_csv_entry('/Users/cesare/Projects/hdn/triple/DanteTriple/xml/DanteSearch/grammaticale/paradiso.xml', 3)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"FormaFlessa 32747\n",
"Categoria 32747\n",
"Lemma 32747\n",
"Canto 32747\n",
"Verso 32747\n",
"PosizioneFFNelVerso 32747\n",
"dtype: int64"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_paradiso = [parsed_paradiso[0]]\n",
"testo_paradiso_tabella=pd.DataFrame(data_paradiso[0], columns = ['FormaFlessa' , 'Categoria', 'Lemma', 'Canto', 'Verso', 'PosizioneFFNelVerso']) \n",
"testo_paradiso_tabella.count()"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>FormaFlessa</th>\n",
" <th>Categoria</th>\n",
" <th>Lemma</th>\n",
" <th>Canto</th>\n",
" <th>Verso</th>\n",
" <th>PosizioneFFNelVerso</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>La</td>\n",
" <td>[rdfs]</td>\n",
" <td>[la]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>gloria</td>\n",
" <td>[sf1fs]</td>\n",
" <td>[gloria]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>di</td>\n",
" <td>[epskg]</td>\n",
" <td>[di]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>colui</td>\n",
" <td>[pdms]</td>\n",
" <td>[colui]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>che</td>\n",
" <td>[pr]</td>\n",
" <td>[che]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>tutto</td>\n",
" <td>[pi1ms]</td>\n",
" <td>[tutto]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>move</td>\n",
" <td>[vta2ips3]</td>\n",
" <td>[muovere]</td>\n",
" <td>Canto 1</td>\n",
" <td>1</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>per</td>\n",
" <td>[epskpl]</td>\n",
" <td>[per]</td>\n",
" <td>Canto 1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>l'</td>\n",
" <td>[rdms]</td>\n",
" <td>[lo]</td>\n",
" <td>Canto 1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>universo</td>\n",
" <td>[sm2ms]</td>\n",
" <td>[universo]</td>\n",
" <td>Canto 1</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>penetra</td>\n",
" <td>[vi1ips3]</td>\n",
" <td>[penetrare]</td>\n",
" <td>Canto 1</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>e</td>\n",
" <td>[cscc]</td>\n",
" <td>[e]</td>\n",
" <td>Canto 1</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>risplende</td>\n",
" <td>[vi2ips3]</td>\n",
" <td>[risplendere]</td>\n",
" <td>Canto 1</td>\n",
" <td>2</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>in</td>\n",
" <td>[epsksl]</td>\n",
" <td>[in]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>una</td>\n",
" <td>[rifs]</td>\n",
" <td>[una]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>parte</td>\n",
" <td>[sf3fs]</td>\n",
" <td>[parte]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>più</td>\n",
" <td>[b]</td>\n",
" <td>[più]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>e</td>\n",
" <td>[cscc]</td>\n",
" <td>[e]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>meno</td>\n",
" <td>[b]</td>\n",
" <td>[meno]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>altrove</td>\n",
" <td>[b]</td>\n",
" <td>[altrove]</td>\n",
" <td>Canto 1</td>\n",
" <td>3</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Nel</td>\n",
" <td>[epaksl, rdms]</td>\n",
" <td>[in, il]</td>\n",
" <td>Canto 1</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" FormaFlessa Categoria Lemma Canto Verso \\\n",
"0 La [rdfs] [la] Canto 1 1 \n",
"1 gloria [sf1fs] [gloria] Canto 1 1 \n",
"2 di [epskg] [di] Canto 1 1 \n",
"3 colui [pdms] [colui] Canto 1 1 \n",
"4 che [pr] [che] Canto 1 1 \n",
"5 tutto [pi1ms] [tutto] Canto 1 1 \n",
"6 move [vta2ips3] [muovere] Canto 1 1 \n",
"7 per [epskpl] [per] Canto 1 2 \n",
"8 l' [rdms] [lo] Canto 1 2 \n",
"9 universo [sm2ms] [universo] Canto 1 2 \n",
"10 penetra [vi1ips3] [penetrare] Canto 1 2 \n",
"11 e [cscc] [e] Canto 1 2 \n",
"12 risplende [vi2ips3] [risplendere] Canto 1 2 \n",
"13 in [epsksl] [in] Canto 1 3 \n",
"14 una [rifs] [una] Canto 1 3 \n",
"15 parte [sf3fs] [parte] Canto 1 3 \n",
"16 più [b] [più] Canto 1 3 \n",
"17 e [cscc] [e] Canto 1 3 \n",
"18 meno [b] [meno] Canto 1 3 \n",
"19 altrove [b] [altrove] Canto 1 3 \n",
"20 Nel [epaksl, rdms] [in, il] Canto 1 4 \n",
"\n",
" PosizioneFFNelVerso \n",
"0 1 \n",
"1 2 \n",
"2 3 \n",
"3 4 \n",
"4 5 \n",
"5 6 \n",
"6 7 \n",
"7 1 \n",
"8 2 \n",
"9 3 \n",
"10 4 \n",
"11 5 \n",
"12 6 \n",
"13 1 \n",
"14 2 \n",
"15 3 \n",
"16 4 \n",
"17 5 \n",
"18 6 \n",
"19 7 \n",
"20 1 "
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"testo_paradiso_tabella.head(21)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Creazione di una tabella con gli IRI dei versi per la cantica Paradiso\n",
"La tabella contiene il numero del verso, il verso e l'IRI del verso."
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"NumeroVerso 4757\n",
"Verso 4757\n",
"IRIVerso 4757\n",
"dtype: int64"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_IRI_versi_par = [parsed_paradiso[1]]\n",
"#data_IRI_versi\n",
"df_IRI_versi_par=pd.DataFrame(data_IRI_versi_par[0], columns = ['NumeroVerso', 'Verso' , 'IRIVerso']) \n",
"df_IRI_versi_par.count()"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_5658186a_66df_11eb_b4ac_60f81dca6224row0_col2,#T_5658186a_66df_11eb_b4ac_60f81dca6224row1_col2,#T_5658186a_66df_11eb_b4ac_60f81dca6224row2_col2,#T_5658186a_66df_11eb_b4ac_60f81dca6224row3_col2,#T_5658186a_66df_11eb_b4ac_60f81dca6224row4_col2{\n",
" width: 400px;\n",
" }</style><table id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >NumeroVerso</th> <th class=\"col_heading level0 col1\" >Verso</th> <th class=\"col_heading level0 col2\" >IRIVerso</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row0_col0\" class=\"data row0 col0\" >1</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row0_col1\" class=\"data row0 col1\" >La gloria di colui che tutto move</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row0_col2\" class=\"data row0 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/3/canto/1/verso/1\n",
" a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"La gloria di colui che tutto move\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"1\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"1\"^^xsd:int .</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row1_col0\" class=\"data row1 col0\" >2</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row1_col1\" class=\"data row1 col1\" >per l'universo penetra, e risplende</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row1_col2\" class=\"data row1 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/3/canto/1/verso/2\n",
" a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"per l'universo penetra, e risplende\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"2\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"2\"^^xsd:int .</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row2_col0\" class=\"data row2 col0\" >3</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row2_col1\" class=\"data row2 col1\" >in una parte più e meno altrove.</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row2_col2\" class=\"data row2 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/3/canto/1/verso/3\n",
" a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"in una parte più e meno altrove.\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"3\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"3\"^^xsd:int .</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row3_col0\" class=\"data row3 col0\" >4</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row3_col1\" class=\"data row3 col1\" >Nel ciel che più de la sua luce prende</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row3_col2\" class=\"data row3 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/3/canto/1/verso/4\n",
" a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"Nel ciel che più de la sua luce prende\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"4\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"4\"^^xsd:int .</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row4_col0\" class=\"data row4 col0\" >5</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row4_col1\" class=\"data row4 col1\" >fu' io, e vidi cose che ridire</td>\n",
" <td id=\"T_5658186a_66df_11eb_b4ac_60f81dca6224row4_col2\" class=\"data row4 col2\" >http://hdn.dantenetwork.it/resource/work/commedia/cantica/3/canto/1/verso/5\n",
" a efrbroo:F2_Expression ,\n",
" rdfs:Resource ; \n",
"http://erlangen-crm.org/current/P190_has_symbolic_content \"fu' io, e vidi cose che ridire\"^^xsd:string ;\n",
" http://erlangen-crm.org/current/P3_has_note \"5\"^^xsd:int ;\n",
" http://hdn.dantenetwork.it/resource/has_number \"5\"^^xsd:int .</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x121a4ce10>"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_IRI_versi_par.head().style.set_properties(subset=['IRIVerso'], **{'width': '400px'})"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,