def useful_words(ls):
"""
this function takes a list of strings and return a list with strings used more than ones
"""
bow_transformer = CountVectorizer().fit(ls)
csr_matrix = bow_transformer.transform([" ".join(ls)])
tfidf_transfrom = TfidfTransformer().fit_transform(csr_matrix)
"""eliminate"""
tmp_list = [] # tmp_list contains the elements to be eliminated
Mc = tfidf_transfrom.tocoo()
for i in Mc.col:
if Mc.data[Mc.col ==
i][0] == Mc.data.min() and Mc.data.min() != Mc.data.max():
tmp_list.append(bow_transformer.get_feature_names()[i])
return list(set(ls) - set(tmp_list))
def get_tfidf(count_by_plz, vocab):
print('building array...')
counts = np.array([[count_by_plz[plz][vocab.get_word(i)] for plz in PLZ]
for i in range(len(vocab))])
counts = counts.transpose()
print('done, shape:', counts.shape)
print('calculating TFIDF...')
tfidf = TfidfTransformer().fit_transform(counts)
print('done, type and shape:', type(tfidf), tfidf.shape)
cx = tfidf.tocoo()
tfidf_by_plz = {plz: defaultdict(int) for plz in PLZ}
for i, j, v in zip(cx.row, cx.col, cx.data):
tfidf_by_plz[PLZ[i]][vocab.get_word(j)] = v
return tfidf_by_plz