python中的词汇问题_python – 加载pickled分类器数据：词汇不适合错误

我在这里阅读了所有相关问题,但找不到可行的解决方案：

我的分类器创建：

class StemmedTfidfVectorizer(TfidfVectorizer):

def build_analyzer(self):

analyzer = super(TfidfVectorizer, self).build_analyzer()

return lambda doc: english_stemmer.stemWords(analyzer(doc))

tf = StemmedTfidfVectorizer(analyzer='word', ngram_range=(1,2), min_df = 0, max_features=200000, stop_words = 'english')

def create_tfidf(f):

docs = []

targets = []

with open(f, "r") as sentences_file:

reader = csv.reader(sentences_file, delimiter=';')

reader.next()

for row in reader:

docs.append(row[1])

targets.append(row[0])

tfidf_matrix = tf.fit_transform(docs)

print tfidf_matrix.shape

# print tf.get_feature_names()

return tfidf_matrix, targets

X,y = cre