Python text.HashingVectorizer方法代码示例

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def transform(self, X_si, high=None, low=None, limit=None):
        """
        Same as HashingVectorizer transform, except allows for 
        interaction list, which is an iterable the same length as X
        filled with True/False. This method adds an empty row to
        docs labelled as False.
        """
        analyzer = self.build_analyzer()

        X = self._get_hasher().transform(
            analyzer(self._deal_with_input(doc)) for doc in X_si)
        
        X.data.fill(1)

        if self.norm is not None:
            X = normalize(X, norm=self.norm, copy=False)

        if low:
            X = self._limit_features(X, low=low)
        return X 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def __init__(self):
        self.vectorizer = HashingVectorizer(ngram_range=(1, 2))
        self.dict_vectorizer = DictVectorizer()

        # These are set dynamically in training
        # but fixed here to match the end feature names
        # in the trained model. If the model is retrained then
        # these may have to change
        self.dict_vectorizer.feature_names_ = [
            'DocumentPositionQuintile0',
            'DocumentPositionQuintile1',
            'DocumentPositionQuintile2',
            'DocumentPositionQuintile3',
            'DocumentPositionQuintile4',
            'DocumentPositionQuintile5',
            'DocumentPositionQuintile6']
        self.dict_vectorizer.vocabulary_ = {k: i for i, k in enumerate(self.dict_vectorizer.feature_names_)}

        self.drugbank = Drugbank() 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_hashed_binary_occurrences():
    # by default multiple occurrences are counted as longs
    test_data = ['aaabc', 'abbde']
    vect = HashingVectorizer(alternate_sign=False, analyzer='char', norm=None)
    X = vect.transform(test_data)
    assert_equal(np.max(X[0:1].data), 3)
    assert_equal(np.max(X[1:2].data), 2)
    assert_equal(X.dtype, np.float64)

    # using boolean features, we can fetch the binary occurrence info
    # instead.
    vect = HashingVectorizer(analyzer='char', alternate_sign=False,
                             binary=True, norm=None)
    X = vect.transform(test_data)
    assert_equal(np.max(X.data), 1)
    assert_equal(X.dtype, np.float64)

    # check the ability to change the dtype
    vect = HashingVectorizer(analyzer='char', alternate_sign=False,
                             binary=True, norm=None, dtype=np.float64)
    X = vect.transform(test_data)
    assert_equal(X.dtype, np.float64) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_vectorizer_unicode():
    # tests that the count vectorizer works with cyrillic.
    document = (
        "Машинное обучение — обширный подраздел искусственного "
        "интеллекта, изучающий методы построения алгоритмов, "
        "способных обучаться."
        )

    vect = CountVectorizer()
    X_counted = vect.fit_transform([document])
    assert_equal(X_counted.shape, (1, 12))

    vect = HashingVectorizer(norm=None, alternate_sign=False)
    X_hashed = vect.transform([document])
    assert_equal(X_hashed.shape, (1, 2 ** 20))

    # No collisions on such a small dataset
    assert_equal(X_counted.nnz, X_hashed.nnz)

    # When norm is None and not alternate_sign, the tokens are counted up to
    # collisions
    assert_array_equal(np.sort(X_counted.data), np.sort(X_hashed.data)) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_vectorizer_stop_words_inconsistent():
    lstr = "['and', 'll', 've']"
    message = ('Your stop_words may be inconsistent with your '
               'preprocessing. Tokenizing the stop words generated '
               'tokens %s not in stop_words.' % lstr)
    for vec in [CountVectorizer(),
                TfidfVectorizer(), HashingVectorizer()]:
        vec.set_params(stop_words=["you've", "you", "you'll", 'AND'])
        assert_warns_message(UserWarning, message, vec.fit_transform,
                             ['hello world'])
        # reset stop word validation
        del vec._stop_words_id
        assert _check_stop_words_consistency(vec) is False

    # Only one warning per stop list
    assert_no_warnings(vec.fit_transform, ['hello world'])
    assert _check_stop_words_consistency(vec) is None

    # Test caching of inconsistency assessment
    vec.set_params(stop_words=["you've", "you", "you'll", 'blah', 'AND'])
    assert_warns_message(UserWarning, message, vec.fit_transform,
                         ['hello world']) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def __init__(self, min_df=1, max_df=0.9, tokenizer=LemmaTokenizer, hash=False):
        """
        `min_df` is set to filter out extremely rare words,
        since we don't want those to dominate the distance metric.

        `max_df` is set to filter out extremely common words,
        since they don't convey much information.
        """

        # Wrap the specified tokenizer
        t = Tokenizer(tokenizer())

        if hash:
            vectr = HashingVectorizer(input='content', stop_words='english', lowercase=True, tokenizer=t)
        else:
            vectr = CountVectorizer(input='content', stop_words='english', lowercase=True, tokenizer=t, min_df=min_df, max_df=max_df)

        args = [
            ('vectorizer', vectr),
            ('tfidf', TfidfTransformer(norm=None, use_idf=True, smooth_idf=True)),
            ('normalizer', Normalizer(copy=False))
        ]

        self.pipeline = Pipeline(args)
        self.trained = False 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def __init__(self,
                 input_columns: Any,
                 output_column: str = None,
                 max_tokens: int = 2 ** 18,
                 tokens: str = 'chars',
                 ngram_range: tuple = None,
                 prefixed_concatenation: bool = True) -> None:

        if ngram_range is None:
            ngram_range = (1, 3) if tokens == 'words' else (1, 5)

        ColumnEncoder.__init__(self, input_columns, output_column, int(max_tokens))

        if tokens == 'words':
            self.vectorizer = HashingVectorizer(n_features=self.output_dim, ngram_range=ngram_range)
        elif tokens == 'chars':
            self.vectorizer = HashingVectorizer(n_features=self.output_dim, ngram_range=ngram_range,
                                                analyzer="char")
        else:
            logger.debug(
                "BowEncoder attribute tokens has to be 'words' or 'chars', defaulting to 'chars'")
            self.vectorizer = HashingVectorizer(n_features=self.output_dim, ngram_range=ngram_range,
                                                analyzer="char")

        self.prefixed_concatenation = prefixed_concatenation 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_cv_pipeline(self):
        pipeline = SKL_Pipeline([
            ('vect', SKL_HashingVectorizer(n_features=20)),
            ('tfidf', SKL_TfidfTransformer(use_idf=False)),
            ('lasso', SKL_Lasso())
        ])
        parameters = {
            'lasso__alpha': (0.001, 0.005, 0.01)
        }
        grid_search = GridSearchCV(self.sc, pipeline, parameters)
        data = [('hi there', 0.0),
                ('what is up', 1.0),
                ('huh', 1.0),
                ('now is the time', 5.0),
                ('for what', 0.0),
                ('the spark was there', 5.0),
                ('and so', 3.0),
                ('were many socks', 0.0),
                ('really', 1.0),
                ('too cool', 2.0)]
        df = self.sql.createDataFrame(data, ["review", "rating"]).toPandas()
        skl_gs = grid_search.fit(df.review.values, df.rating.values)
        assert len(skl_gs.cv_results_['params']) == len(parameters['lasso__alpha']) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_hashed_binary_occurrences():
    # by default multiple occurrences are counted as longs
    test_data = ['aaabc', 'abbde']
    vect = HashingVectorizer(analyzer='char', non_negative=True,
                             norm=None)
    X = vect.transform(test_data)
    assert_equal(np.max(X[0:1].data), 3)
    assert_equal(np.max(X[1:2].data), 2)
    assert_equal(X.dtype, np.float64)

    # using boolean features, we can fetch the binary occurrence info
    # instead.
    vect = HashingVectorizer(analyzer='char', non_negative=True, binary=True,
                             norm=None)
    X = vect.transform(test_data)
    assert_equal(np.max(X.data), 1)
    assert_equal(X.dtype, np.float64)

    # check the ability to change the dtype
    vect = HashingVectorizer(analyzer='char', non_negative=True, binary=True,
                             norm=None, dtype=np.float64)
    X = vect.transform(test_data)
    assert_equal(X.dtype, np.float64) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_pickling_vectorizer():
    instances = [
        HashingVectorizer(),
        HashingVectorizer(norm='l1'),
        HashingVectorizer(binary=True),
        HashingVectorizer(ngram_range=(1, 2)),
        CountVectorizer(),
        CountVectorizer(preprocessor=strip_tags),
        CountVectorizer(analyzer=lazy_analyze),
        CountVectorizer(preprocessor=strip_tags).fit(JUNK_FOOD_DOCS),
        CountVectorizer(strip_accents=strip_eacute).fit(JUNK_FOOD_DOCS),
        TfidfVectorizer(),
        TfidfVectorizer(analyzer=lazy_analyze),
        TfidfVectorizer().fit(JUNK_FOOD_DOCS),
    ]

    for orig in instances:
        s = pickle.dumps(orig)
        copy = pickle.loads(s)
        assert_equal(type(copy), orig.__class__)
        assert_equal(copy.get_params(), orig.get_params())
        assert_array_equal(
            copy.fit_transform(JUNK_FOOD_DOCS).toarray(),
            orig.fit_transform(JUNK_FOOD_DOCS).toarray()) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def get_kmeans_prototypes(X, n_prototypes, hashing_dim=128,
                          ngram_range=(3, 3), sparse=False, sample_weight=None,
                          random_state=None):
    """
    Computes prototypes based on:
      - dimensionality reduction (via hashing n-grams)
      - k-means clustering
      - nearest neighbor
    """
    vectorizer = HashingVectorizer(analyzer='char', norm=None,
                                   alternate_sign=False,
                                   ngram_range=ngram_range,
                                   n_features=hashing_dim)
    projected = vectorizer.transform(X)
    if not sparse:
        projected = projected.toarray()
    kmeans = KMeans(n_clusters=n_prototypes, random_state=random_state)
    kmeans.fit(projected, sample_weight=sample_weight)
    centers = kmeans.cluster_centers_
    neighbors = NearestNeighbors()
    neighbors.fit(projected)
    indexes_prototypes = np.unique(neighbors.kneighbors(centers, 1)[-1])
    if indexes_prototypes.shape[0] < n_prototypes:
        warnings.warn('Final number of unique prototypes is lower than ' +
                      'n_prototypes (expected)')
    return np.sort(X[indexes_prototypes]) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def __init__(self):
        raw_data = np.load(robotreviewer.get_data('pubmed/pubmed_title_hash_2016_07_24.npz'))
        self.vec_ti = csr_matrix((raw_data['data'], raw_data['indices'], raw_data['indptr']), raw_data['shape'])
        self.pmid_ind = np.load(robotreviewer.get_data('pubmed/pubmed_index_2016_07_24.npz'))['pmid_ind']
        self.vectorizer = HashingVectorizer(binary=True, stop_words='english')
        # load database
        self.connection = sqlite3.connect(robotreviewer.get_data('pubmed/pubmed_rcts_2016_07_24.sqlite'))
        self.c = self.connection.cursor() 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def __init__(self):
        
        with open(robotreviewer.get_data(os.path.join('bias_ab', 'bias_prob_clf.pck')), 'rb') as f:
            self.clf = pickle.load(f)

        self.vec = HashingVectorizer(ngram_range=(1, 3), stop_words='english') 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def __init__(self):
        from keras.preprocessing import sequence
        from keras.models import load_model
        from keras.models import Sequential
        from keras.preprocessing import sequence
        from keras.layers import Dense, Dropout, Activation, Lambda, Input, merge, Flatten
        from keras.layers import Embedding
        from keras.layers import Convolution1D, MaxPooling1D
        from keras import backend as K
        from keras.models import Model
        from keras.regularizers import l2
        global sequence, load_model, Sequential, Dense, Dropout, Activation, Lambda, Input, merge, Flatten
        global Embedding, Convolution1D, MaxPooling1D, K, Model, l2
        self.svm_clf = MiniClassifier(os.path.join(robotreviewer.DATA_ROOT, 'rct/rct_svm_weights.npz'))
        cnn_weight_files = glob.glob(os.path.join(robotreviewer.DATA_ROOT, 'rct/*.h5'))
        self.cnn_clfs = [load_model(cnn_weight_file) for cnn_weight_file in cnn_weight_files]
        self.svm_vectorizer = HashingVectorizer(binary=False, ngram_range=(1, 1), stop_words='english')
        self.cnn_vectorizer = KerasVectorizer(vocab_map_file=os.path.join(robotreviewer.DATA_ROOT, 'rct/cnn_vocab_map.pck'), stop_words='english')
        with open(os.path.join(robotreviewer.DATA_ROOT, 'rct/rct_model_calibration.json'), 'r') as f:
            self.constants = json.load(f)

        self.calibration_lr = {}
        with open(os.path.join(robotreviewer.DATA_ROOT, 'rct/svm_cnn_ptyp_calibration.pck'), 'rb') as f:
            self.calibration_lr['svm_cnn_ptyp'] = pickle.load(f)

        with open(os.path.join(robotreviewer.DATA_ROOT, 'rct/svm_cnn_calibration.pck'), 'rb') as f:
            self.calibration_lr['svm_cnn'] = pickle.load(f) 

# 需要导入模块: from sklearn.feature_extraction import text [as 别名]
# 或者: from sklearn.feature_extraction.text import HashingVectorizer [as 别名]
def test_hashing_vectorizer():
    v = HashingVectorizer()
    X = v.transform(ALL_FOOD_DOCS)
    token_nnz = X.nnz
    assert_equal(X.shape, (len(ALL_FOOD_DOCS), v.n_features))
    assert_equal(X.dtype, v.dtype)

    # By default the hashed values receive a random sign and l2 normalization
    # makes the feature values bounded
    assert np.min(X.data) > -1
    assert np.min(X.data) < 0
    assert np.max(X.data) > 0
    assert np.max(X.data) < 1

    # Check that the rows are normalized
    for i in range(X.shape[0]):
        assert_almost_equal(np.linalg.norm(X[0].data, 2), 1.0)

    # Check vectorization with some non-default parameters
    v = HashingVectorizer(ngram_range=(1, 2), norm='l1')
    X = v.transform(ALL_FOOD_DOCS)
    assert_equal(X.shape, (len(ALL_FOOD_DOCS), v.n_features))
    assert_equal(X.dtype, v.dtype)

    # ngrams generate more non zeros
    ngrams_nnz = X.nnz
    assert ngrams_nnz > token_nnz
    assert ngrams_nnz < 2 * token_nnz

    # makes the feature values bounded
    assert np.min(X.data) > -1
    assert np.max(X.data) < 1

    # Check that the rows are normalized
    for i in range(X.shape[0]):
        assert_almost_equal(np.linalg.norm(X[0].data, 1), 1.0)