词袋模型 测试数据使用和训练数据一样的词汇表

def get_features_by_wordbag():
    global max_features
    x_train, x_test, y_train, y_test=load_all_files()

    vectorizer = CountVectorizer(
                                 decode_error='ignore',
                                 strip_accents='ascii',
                                 max_features=max_features,
                                 stop_words='english',
                                 max_df=1.0,
                                 min_df=1 )
    print vectorizer
    x_train=vectorizer.fit_transform(x_train)
    x_train=x_train.toarray()
    vocabulary=vectorizer.vocabulary_

    vectorizer = CountVectorizer(
                                 decode_error='ignore',
                                 strip_accents='ascii',
                                 vocabulary=vocabulary,
                                 stop_words='english',
                                 max_df=1.0,
                                 min_df=1 )
    print vectorizer
    x_test=vectorizer.fit_transform(x_test)
    x_test=x_test.toarray()

    return x_train, x_test, y_train, y_test

 词袋模型示例：

>>> corpus = [
...     'This is the first document.',
...     'This is the second second document.',
...     'And the third one.',
...     'Is this the first document?',
... ]
>>> X = vectorizer.fit_transform(corpus)
>>> X                              
<4x9 sparse matrix of type '<... 'numpy.int64'>'
    with 19 stored elements in Compressed Sparse ... format>

The default configuration tokenizes the string by extracting words of at least 2 letters. The specific function that does this step can be requested explicitly:

>>>

>>> analyze = vectorizer.build_analyzer()
>>> analyze("This is a text document to analyze.") == (
...     ['this', 'is', 'text', 'document', 'to', 'analyze'])
True

Each term found by the analyzer during the fit is assigned a unique integer index corresponding to a column in the resulting matrix. This interpretation of the columns can be retrieved as follows:

>>>

>>> vectorizer.get_feature_names() == (
...     ['and', 'document', 'first', 'is', 'one',
...      'second', 'the', 'third', 'this'])
True

>>> X.toarray()           
array([[0, 1, 1, 1, 0, 0, 1, 0, 1],
       [0, 1, 0, 1, 0, 2, 1, 0, 1],
       [1, 0, 0, 0, 1, 0, 1, 1, 0],
       [0, 1, 1, 1, 0, 0, 1, 0, 1]]...)