test_termDocMatrixFactory.py 文件源码

def test_main(self):
        categories, documents = get_docs_categories()
        clean_function = lambda text: '' if text.startswith('[') else text
        entity_types = set(['GPE'])
        term_doc_mat = (
            TermDocMatrixFactory(
                category_text_iter=zip(categories, documents),
                clean_function=clean_function,
                nlp=_testing_nlp,
                feats_from_spacy_doc=FeatsFromSpacyDoc(entity_types_to_censor=entity_types)
            ).build()
        )
        clf = PassiveAggressiveClassifier(n_iter=5, C=0.5, n_jobs=-1, random_state=0)
        fdc = FeatsFromDoc(term_doc_mat._term_idx_store,
                           clean_function=clean_function,
                           feats_from_spacy_doc=FeatsFromSpacyDoc(
                               entity_types_to_censor=entity_types)).set_nlp(_testing_nlp)
        tfidf = TfidfTransformer(norm='l1')
        X = tfidf.fit_transform(term_doc_mat._X)
        clf.fit(X, term_doc_mat._y)
        X_to_predict = fdc.feats_from_doc('Did sometimes march UNKNOWNWORD')
        pred = clf.predict(tfidf.transform(X_to_predict))
        dec = clf.decision_function(X_to_predict)