это мой code.it читает обзоры из файла Excel (столбец rev) и составляет список списка.
xp похож на это
["['intrepid', 'bumbling', 'duo', 'deliver', 'good', 'one'],['better', 'offering', 'considerable', 'cv', 'freshly', 'qualified', 'private', 'investigator', 'thrust', 'murder', 'investigation', 'invisible'],[ 'man', 'alone', 'tell', 'fun', 'flow', 'decent', 'clip', 'need', 'say', 'sequence', 'comedy', 'gold', 'like', 'scene', 'restaurant', 'excellent', 'costello', 'pretending', 'work', 'ball', 'gym', 'final', 'reel']"]
, но когда используется список длямодель, это дает мне ошибку «TypeError: объект« float »не повторяется». Я не знаю, где моя проблема.Спасибо.
xp=[]
import gensim
import logging
import pandas as pd
file = r'FileNamelast.xlsx'
df = pd.read_excel(file,sheet_name='FileNamex')
pages = [i for i in range(0,1000)]
for page in pages:
text =df.loc[page,["rev"]]
xp.append(text[0])
model = gensim.models.Word2Vec (xp, size=150, window=10, min_count=2,
workers=10)
model.train(xp,total_examples=len(xp),epochs=10)
это то, что я получил. Тип ошибки: объект 'float' не повторяется
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-32-aa34c0e432bf> in <module>()
14
15
---> 16 model = gensim.models.Word2Vec (xp, size=150, window=10, min_count=2, workers=10)
17 model.train(xp,total_examples=len(xp),epochs=10)
C:\ProgramData\Anaconda3\lib\site-packages\gensim\models\word2vec.py in __init__(self, sentences, corpus_file, size, alpha, window, min_count, max_vocab_size, sample, seed, workers, min_alpha, sg, hs, negative, ns_exponent, cbow_mean, hashfxn, iter, null_word, trim_rule, sorted_vocab, batch_words, compute_loss, callbacks, max_final_vocab)
765 callbacks=callbacks, batch_words=batch_words, trim_rule=trim_rule, sg=sg, alpha=alpha, window=window,
766 seed=seed, hs=hs, negative=negative, cbow_mean=cbow_mean, min_alpha=min_alpha, compute_loss=compute_loss,
--> 767 fast_version=FAST_VERSION)
768
769 def _do_train_epoch(self, corpus_file, thread_id, offset, cython_vocab, thread_private_mem, cur_epoch,
C:\ProgramData\Anaconda3\lib\site-packages\gensim\models\base_any2vec.py in __init__(self, sentences, corpus_file, workers, vector_size, epochs, callbacks, batch_words, trim_rule, sg, alpha, window, seed, hs, negative, ns_exponent, cbow_mean, min_alpha, compute_loss, fast_version, **kwargs)
757 raise TypeError("You can't pass a generator as the sentences argument. Try an iterator.")
758
--> 759 self.build_vocab(sentences=sentences, corpus_file=corpus_file, trim_rule=trim_rule)
760 self.train(
761 sentences=sentences, corpus_file=corpus_file, total_examples=self.corpus_count,
C:\ProgramData\Anaconda3\lib\site-packages\gensim\models\base_any2vec.py in build_vocab(self, sentences, corpus_file, update, progress_per, keep_raw_vocab, trim_rule, **kwargs)
934 """
935 total_words, corpus_count = self.vocabulary.scan_vocab(
--> 936 sentences=sentences, corpus_file=corpus_file, progress_per=progress_per, trim_rule=trim_rule)
937 self.corpus_count = corpus_count
938 self.corpus_total_words = total_words
C:\ProgramData\Anaconda3\lib\site-packages\gensim\models\word2vec.py in scan_vocab(self, sentences, corpus_file, progress_per, workers, trim_rule)
1569 sentences = LineSentence(corpus_file)
1570
-> 1571 total_words, corpus_count = self._scan_vocab(sentences, progress_per, trim_rule)
1572
1573 logger.info(
C:\ProgramData\Anaconda3\lib\site-packages\gensim\models\word2vec.py in _scan_vocab(self, sentences, progress_per, trim_rule)
1552 sentence_no, total_words, len(vocab)
1553 )
-> 1554 for word in sentence:
1555 vocab[word] += 1
1556 total_words += len(sentence)
TypeError: 'float' object is not iterable