reworked unsupervised (aligned) embeddings loader method and class (fastText and MUSE).

new op.arg -t ['MUSE', 'FastText']
uploaded /results/results.csv (on rcv1 ... run0.pickle) obtained on all available setup.
TODO: refactor it also as a standalone class with its own load/weighted sum/extract/reduce methods.

src/FPEC_andrea.py

@@ -17,11 +17,14 @@ parser.add_option("-o", "--output", dest="output",
                   help="Result file", type=str,  default='./results/results.csv')
 
 parser.add_option("-e", "--mode-embed", dest="mode_embed",
-                  help="Set the embedding to be used [none, pretrained, supervised, both]", type=str, default='none')
+                  help="Set the embedding to be used [none, unsupervised, supervised, both]", type=str, default='none')
 
 parser.add_option("-w", "--we-path", dest="we_path",
                   help="Path to the polylingual word embeddings", default='../embeddings/')
 
+parser.add_option('-t', "--we-type", dest="we_type", help="Aligned embeddings to use [FastText, MUSE]", type=str,
+                  default='FastText')
+
 parser.add_option("-s", "--set_c", dest="set_c",type=float,
                   help="Set the C parameter", default=1)
 
@@ -36,7 +39,7 @@ def get_learner(calibrate=False, kernel='linear'):
     return SVC(kernel=kernel, probability=calibrate, cache_size=1000, C=op.set_c, random_state=1, class_weight='balanced')
 
 
-def get_params(dense=False):    # TODO kernel function could be useful for meta-classifier
+def get_params(dense=False):
     if not op.optimc:
         return None
     c_range = [1e4, 1e3, 1e2, 1e1, 1, 1e-1]
@@ -72,30 +75,36 @@ if __name__ == '__main__':
 
     # Embeddings and WCE config
     _available_mode = ['none', 'unsupervised', 'supervised', 'both']
-    assert op.mode_embed in _available_mode , f'{op.mode_embed} not in {_available_mode}'
+    _available_type = ['MUSE', 'FastText']
+    assert op.mode_embed in _available_mode, f'{op.mode_embed} not in {_available_mode}'
+    assert op.we_type in _available_type, f'{op.we_type} not in {_available_type}'
 
     if op.mode_embed == 'none':
         config = {'unsupervised': False,
-                    'supervised': False}
+                  'supervised': False,
+                  'we_type': None}
         _config_id = 'None'
     elif op.mode_embed == 'unsupervised':
         config = {'unsupervised': True,
-                  'supervised': False}
+                  'supervised': False,
+                  'we_type': op.we_type}
         _config_id = 'M'
     elif op.mode_embed == 'supervised':
         config = {'unsupervised': False,
-                  'supervised': True}
+                  'supervised': True,
+                  'we_type': None}
         _config_id = 'F'
     elif op.mode_embed == 'both':
         config = {'unsupervised': True,
-                  'supervised': True}
+                  'supervised': True,
+                  'we_type': op.we_type}
         _config_id = 'M_and_F'
 
     result_id = dataset_file + 'PolyEmbedd_andrea_' + _config_id + ('_optimC' if op.optimc else '')
 
     print(f'### PolyEmbedd_andrea_{_config_id}\n')
-    classifier = AndreaCLF(op.we_path,
+    classifier = AndreaCLF(we_path=op.we_path,
-                           config,
+                           config=config,
                            first_tier_learner=get_learner(calibrate=True),
                            meta_learner=get_learner(calibrate=False, kernel='rbf'),
                            first_tier_parameters=get_params(dense=False),
@@ -114,5 +123,5 @@ if __name__ == '__main__':
         metrics.append([macrof1, microf1, macrok, microk])
         print('Lang %s: macro-F1=%.3f micro-F1=%.3f' % (lang, macrof1, microf1))
         results.add_row(result_id, 'PolyEmbed_andrea', 'svm', _config_id, op.optimc, op.dataset.split('/')[-1],
-                        'not_binary', 'not_ablation', classifier.time, lang, macrof1, microf1, macrok, microk, 'nope')
+                        'not_binary', 'not_ablation', classifier.time, lang, macrof1, microf1, macrok, microk, '')
     print('Averages: MF1, mF1, MK, mK', np.mean(np.array(metrics), axis=0))

src/data/embeddings.py

@@ -147,7 +147,7 @@ class FastTextWikiNews(Vectors):
 
     url_base = 'Cant auto-download MUSE embeddings'
     path = '/storage/andrea/FUNNELING/embeddings/wiki.multi.{}.vec'
-    _name = 'wiki.multi.{}.vec'
+    _name = '/embeddings/wiki.multi.{}.vec'
 
     def __init__(self, cache, language="en", **kwargs):
         url = self.url_base.format(language)
@@ -157,6 +157,30 @@ class FastTextWikiNews(Vectors):
         super(FastTextWikiNews, self).__init__(name, cache=cache, url=url, **kwargs)
 
 
+class EmbeddingsAligned(Vectors):
+
+    def __init__(self, type, path, lang):
+
+        self.name = '/embeddings/wiki.multi.{}.vec' if type == 'MUSE' else '/embeddings_polyFASTTEXT/wiki.{}.align.vec'
+        # todo - rewrite as relative path
+        self.cache_path = '/home/andreapdr/CLESA/embeddings' if type == 'MUSE' else '/home/andreapdr/CLESA/embeddings_polyFASTTEXT'
+        self.path = path + self.name.format(lang)
+        assert os.path.exists(path), f'pre-trained vectors not found in {path}'
+        super(EmbeddingsAligned, self).__init__(self.path, cache=self.cache_path)
+
+    def vocabulary(self):
+        return set(self.stoi.keys())
+
+    def dim(self):
+        return self.dim
+
+    def extract(self, words):
+        source_idx, target_idx = PretrainedEmbeddings.reindex(words, self.stoi)
+        extraction = torch.zeros((len(words), self.dim))
+        extraction[source_idx] = self.vectors[target_idx]
+        return extraction
+
+
 class FastTextMUSE(PretrainedEmbeddings):
 
     def __init__(self, path, lang, limit=None):
@@ -179,12 +203,12 @@ class FastTextMUSE(PretrainedEmbeddings):
         return extraction
 
 
-def embedding_matrix(path, voc, lang):
+def embedding_matrix(type, path, voc, lang):
     vocabulary = np.asarray(list(zip(*sorted(voc.items(), key=lambda x:x[1])))[0])
 
     print('[embedding matrix]')
-    print(f'# [pretrained-matrix: FastTextMUSE {lang}]')
+    print(f'# [pretrained-matrix: {type} {lang}]')
-    pretrained = FastTextMUSE(path, lang)
+    pretrained = EmbeddingsAligned(type, path, lang)
     P = pretrained.extract(vocabulary).numpy()
     del pretrained
     print(f'[embedding matrix done] of shape={P.shape}\n')

src/learning/learners.py

@@ -7,8 +7,6 @@ from sklearn.model_selection import GridSearchCV
 from sklearn.model_selection import KFold
 from joblib import Parallel, delayed
 from sklearn.feature_extraction.text import TfidfVectorizer
-
-from data.supervised import zscores
 from transformers.StandardizeTransformer import StandardizeTransformer
 
 
@@ -444,7 +442,8 @@ class AndreaCLF(FunnellingPolylingualClassifier):
                  first_tier_parameters=None,
                  meta_parameters=None,
                  folded_projections=1,
-                 calmode='cal', n_jobs=-1):
+                 calmode='cal',
+                 n_jobs=-1):
 
         super().__init__(first_tier_learner,
                          meta_learner,
@@ -479,9 +478,8 @@ class AndreaCLF(FunnellingPolylingualClassifier):
             self.languages.append(lang)
             tfidf_vectorizer.fit(lX[lang])
             lX[lang] = tfidf_vectorizer.transform(lX[lang])
-            _sort_if_sparse(lX[lang])
             self.lang_word2idx[lang] = tfidf_vectorizer.vocabulary_
-            self.lang_tfidf[lang] = tfidf_vectorizer # utile in fase di testing
+            self.lang_tfidf[lang] = tfidf_vectorizer
         return self
 
     # @override std class method
@@ -517,15 +515,13 @@ class AndreaCLF(FunnellingPolylingualClassifier):
 
         if unsupervised:
             for lang in languages:
-                # print('Test building embedding matrix FastTextMuse ...')
+                _, M = embedding_matrix(self.config['we_type'], self.we_path, self.lang_word2idx[lang], lang)
-                _, M = embedding_matrix(self.we_path, self.lang_word2idx[lang], lang)
                 self.word_embeddings[lang] = M
                 _r[lang] = lX[lang].dot(M)
 
         if supervised:
             for lang in languages:
                 S = WCE_matrix(lX, ly, lang)
-                # S = np.squeeze(np.asarray(S))   # casting to ndarray to better visualize S while debugging
                 self.supervised_embeddings[lang] = S
                 if unsupervised:
                     _r[lang] = np.hstack((_r[lang], lX[lang].dot(S)))
@@ -562,7 +558,7 @@ class AndreaCLF(FunnellingPolylingualClassifier):
         _vertical_Zy = np.vstack([zy[lang] for lang in self.languages])
 
         self.standardizer = StandardizeTransformer()
-        _vertical_Z  = self.standardizer.fit_predict(_vertical_Z)
+        _vertical_Z = self.standardizer.fit_predict(_vertical_Z)
 
         print('fitting the Z-space of shape={}'.format(_vertical_Z.shape))
         self.model = MonolingualClassifier(base_learner=self.meta_learner, parameters=self.meta_parameters,

src/results/results.csv

@@ -1,7 +1,55 @@
 id	method	learner	embed	optimp	dataset	binary	languages	time	lang	macrof1	microf1	macrok	microk	notes
-jrc_doclist_1958-2005vs2006_all_top300_noparallel_processed_run0.picklePolyEmbedd_andrea_M	PolyEmbed_andrea	svm	M	False	test_datasetname	not_binary	not_ablation	55.56810355186462	da	0.7933333333333333	0.0	0.7933333333333333	0.0	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	it	0.5367684112761455	0.7945344129554656	0.5179685773363333	0.7651326488894972	nope
-jrc_doclist_1958-2005vs2006_all_top300_noparallel_processed_run0.picklePolyEmbedd_andrea_M	PolyEmbed_andrea	svm	M	False	test_datasetname	not_binary	not_ablation	55.56810355186462	en	0.7866666666666666	0.0	0.7927111111111111	-0.0003376325207643527	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	pt	0.6969974938193201	0.878625134264232	0.6967392557377021	0.8466030321042095	nope
-jrc_doclist_1958-2005vs2006_all_top300_noparallel_processed_run0.picklePolyEmbedd_andrea_M	PolyEmbed_andrea	svm	M	False	test_datasetname	not_binary	not_ablation	55.56810355186462	fr	0.7866666666666666	0.0	0.7930666666666667	-0.0001350530083057411	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	sv	0.502213941379271	0.7700107543401444	0.4991078326315248	0.7207899075774371	nope
-jrc_doclist_1958-2005vs2006_all_top300_noparallel_processed_run0.picklePolyEmbedd_andrea_None	PolyEmbed_andrea	svm	None	False	test_datasetname	not_binary	not_ablation	24.031760931015015	da	0.7933333333333333	0.0	0.7933333333333333	0.0	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	es	0.5817849682843411	0.8448214916931778	0.5849433134898768	0.8202407220651875	nope
-jrc_doclist_1958-2005vs2006_all_top300_noparallel_processed_run0.picklePolyEmbedd_andrea_None	PolyEmbed_andrea	svm	None	False	test_datasetname	not_binary	not_ablation	24.031760931015015	en	0.7933333333333333	0.0	0.7931111111111111	-0.00013505300830574107	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	en	0.5284100314545743	0.7625649913344887	0.4968119038332687	0.7152142337789349	nope
-jrc_doclist_1958-2005vs2006_all_top300_noparallel_processed_run0.picklePolyEmbedd_andrea_None	PolyEmbed_andrea	svm	None	False	test_datasetname	not_binary	not_ablation	24.031760931015015	fr	0.7933333333333333	0.0	0.7933333333333333	0.0	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	da	0.4868904596668941	0.7971705872676427	0.4554442856126113	0.741227149968307	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	nl	0.5470546398570723	0.8276762402088773	0.5177281560038681	0.7850292121533595	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	fr	0.4997574965766772	0.7678434382194935	0.4836027981945328	0.7099957841328215	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	161.99278807640076	de	0.4220457399934653	0.7444316119452236	0.4256936056238835	0.7167749374918141	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	it	0.5398437760931379	0.8008933172994331	0.5146465197929204	0.7584451610463148	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	pt	0.6975279233747671	0.8779959377115775	0.6911573032014029	0.8392738059784555	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	sv	0.5179339368901748	0.7752035065748278	0.4962165022301373	0.7133720895906155	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	es	0.5745246656272296	0.8476464247215235	0.5736797442258523	0.8104027280076678	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	en	0.5265892627601801	0.761854398025736	0.4868823643967914	0.7032312369952987	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	da	0.4857267508065667	0.7955911823647295	0.449682467737542	0.7293013090493592	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	nl	0.5461000743929812	0.8304711580801409	0.5139887576564601	0.7790659402231745	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	fr	0.5015991524998897	0.7699748500677114	0.4811739320459739	0.7065159928392686	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	503.81587314605713	de	0.4141396160516795	0.743810005053057	0.4126132681585116	0.7023983497130937	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	it	0.4810224709403544	0.7617194410047762	0.453310215598049	0.6999032557458222	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	pt	0.6693663195289151	0.8619702956806105	0.6657298472047529	0.8182397742327547	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	sv	0.43107388787211537	0.7126933954416902	0.4180735239763325	0.6168407376537499	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	es	0.5087201120140917	0.8249322493224932	0.5032299168859704	0.7835086748116167	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	en	0.3822498549987095	0.6877811094452774	0.3309945723997902	0.5962925522774631	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	da	0.4517051377915163	0.7658914728682171	0.4030339299921389	0.6806166833916132	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	nl	0.4875303727964308	0.7853962600178095	0.4534046979963794	0.7270844266398626	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	fr	0.3750315407356979	0.6999393816932714	0.3628389019101708	0.6136670285424017	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_F_optimC	PolyEmbed_andrea	svm	F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1095.333437204361	de	0.355059356514748	0.7046466085098807	0.33834564366266284	0.6299245108196094	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	it	0.4755443069888554	0.7675079985780305	0.4501140447119437	0.7023435117413848	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	pt	0.673303227450142	0.8655002733734279	0.6702445967772233	0.8193963705153853	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	sv	0.4189470089118392	0.7236711786068009	0.4198491651634073	0.6314272037990425	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	es	0.5178080058189616	0.8268359020852222	0.5104336022388637	0.782714898784318	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	en	0.4115752894185112	0.7001869158878504	0.35164720517285003	0.6091191993104883	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	da	0.4437869429842064	0.7626499739175796	0.39704879178312197	0.6717100410826179	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	nl	0.47635948919429705	0.7874471399955486	0.4589309165206792	0.7292337019755739	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	fr	0.39374621795002507	0.7063947733122155	0.3850407928528449	0.6315594797194366	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.picklePolyEmbedd_andrea_M_and_F_optimC	PolyEmbed_andrea	svm	M_and_F	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run0.pickle	not_binary	not_ablation	1251.0414910316467	de	0.3539890425069821	0.7095981751184418	0.3512802070446796	0.6432196317592322	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	it	0.5791455159341481	0.8060849214309596	0.6034752340075125	0.7869853576681214	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	pt	0.6403974389994276	0.8803876562101505	0.6565213830246649	0.8497743924811387	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	sv	0.5032337014290953	0.7768595041322314	0.4719549200388494	0.7364733997369779	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	es	0.5200567247634353	0.8529964145466963	0.4908726477090496	0.8285929531854332	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	en	0.512424485488998	0.7533647963642719	0.4719843960571978	0.7044441169169227	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	da	0.5861231569852233	0.8040595842200032	0.5393761149602847	0.7381233055764151	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	nl	0.6072184716496147	0.8335123523093448	0.5845309357041368	0.8020267337813639	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	fr	0.4923294612439038	0.7854697603651578	0.4713782273939219	0.7329001302478475	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_None_optimC	PolyEmbed_andrea	svm	None	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	161.2168996334076	de	0.4709904181031267	0.7457793804294378	0.4465581491449931	0.7046844416244138	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	it	0.575387626645539	0.8064243448858833	0.5958411838194531	0.7790018114269683	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	pt	0.653004040098633	0.8791937747161628	0.6559210761775208	0.8482450061614855	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	sv	0.49944915222086167	0.7789179104477612	0.4604673876743342	0.727778938054739	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	es	0.5144474487169811	0.8559087767795439	0.48397711649967695	0.8222692824953204	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	en	0.5160737755179508	0.755674709562109	0.45961112517260677	0.6921096138985132	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	da	0.5875776383868945	0.8015873015873016	0.5367286265015276	0.7288571047461061	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	nl	0.6079883230969934	0.8363004776378636	0.5828217771858487	0.7968282071156207	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	fr	0.4966338770370634	0.7860696517412935	0.46250527724325174	0.7292650668002159	nope
+rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.picklePolyEmbedd_andrea_M_optimC	PolyEmbed_andrea	svm	M	True	rcv1-2_doclist_trByLang1000_teByLang1000_processed_run1.pickle	not_binary	not_ablation	497.6823613643646	de	0.4675732669000923	0.7479187479187479	0.43767984457683634	0.69653035770654	nope

src/transformers/StandardizeTransformer.py

@@ -20,4 +20,4 @@ class StandardizeTransformer:
         return (X - self.mean) / self.std
 
     def fit_predict(self, X):
-        return self.fit(X).predict(X)
+        return self.fit(X).predict(X)