文本中的特征提取与特征选择

特征提取

Bag of Words

• 分词
• 计算每个词出现的次数

from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer(min_df=1)
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)
 print X.toarray()
输出
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]]...)

提取二元特征

bigram_vectorizer = CountVectorizer(ngram_range=(1, 2),
                  token_pattern=r'\b\w+\b', min_df=1)
X_2 = bigram_vectorizer.fit_transform(corpus).toarray()
print X_2
输出
array([[0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0],
       [0, 0, 1, 0, 0, 1, 1, 0, 0, 2, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0],
       [1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0],
       [0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1]]...)

Tf-idf

用每个词的tf-idf值作为特征

from sklearn.feature_extraction.text import TfidfTransformer
counts = [[3, 0, 1],
           [2, 0, 0],
           [3, 0, 0],
           [4, 0, 0],
           [3, 2, 0],
           [3, 0, 2]]
transformer = TfidfTransformer()
print transformer.fit_transform(counts).toarray()
输出
array([[ 0.85151335,  0.        ,  0.52433293],
       [ 1.        ,  0.        ,  0.        ],
       [ 1.        ,  0.        ,  0.        ],
       [ 1.        ,  0.        ,  0.        ],
       [ 0.55422893,  0.83236428,  0.        ],
       [ 0.63035731,  0.        ,  0.77630514]])

TfidfVectorizer 将 CountVectorizer 与 TfidfTransformer 合为一体，

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(min_df=1)
print vectorizer.fit_transform(corpus).toarray()
输出：
array([[ 0.        ,  0.43877674,  0.54197657,  0.43877674,  0.        ,
         0.        ,  0.35872874,  0.        ,  0.43877674],
       [ 0.        ,  0.27230147,  0.        ,  0.27230147,  0.        ,
         0.85322574,  0.22262429,  0.        ,  0.27230147],
       [ 0.55280532,  0.        ,  0.        ,  0.        ,  0.55280532,
         0.        ,  0.28847675,  0.55280532,  0.        ],
       [ 0.        ,  0.43877674,  0.54197657,  0.43877674,  0.        ,
         0.        ,  0.35872874,  0.        ,  0.43877674]])

对于CountVectorizer 与 TfidfTransformer的参数，例如一元或二元等，用交叉验证进行选择。

from __future__ import print_function

from pprint import pprint
from time import time
import logging

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline

print(__doc__)

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s %(levelname)s %(message)s')
Load some categories from the training set
categories = [
    'alt.atheism',
    'talk.religion.misc',
]
# Uncomment the following to do the analysis on all the categories
#categories = None

print("Loading 20 newsgroups dataset for categories:")
print(categories)

data = fetch_20newsgroups(subset='train', categories=categories)
print("%d documents" % len(data.filenames))
print("%d categories" % len(data.target_names))
print()
define a pipeline combining a text feature extractor with a simple classifier
pipeline = Pipeline([
    ('vect', CountVectorizer()),
    ('tfidf', TfidfTransformer()),
    ('clf', SGDClassifier()),
])

# uncommenting more parameters will give better exploring power but will
# increase processing time in a combinatorial way
parameters = {
    'vect__max_df': (0.5, 0.75, 1.0),
    #'vect__max_features': (None, 5000, 10000, 50000),
    'vect__ngram_range': ((1, 1), (1, 2)),  # unigrams or bigrams
    #'tfidf__use_idf': (True, False),
    #'tfidf__norm': ('l1', 'l2'),
    'clf__alpha': (0.00001, 0.000001),
    'clf__penalty': ('l2', 'elasticnet'),
    #'clf__n_iter': (10, 50, 80),
}

if __name__ == "__main__":
    # multiprocessing requires the fork to happen in a __main__ protected
    # block

    # find the best parameters for both the feature extraction and the
    # classifier
    grid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1)

    print("Performing grid search...")
    print("pipeline:", [name for name, _ in pipeline.steps])
    print("parameters:")
    pprint(parameters)
    t0 = time()
    grid_search.fit(data.data, data.target)
    print("done in %0.3fs" % (time() - t0))
    print()

    print("Best score: %0.3f" % grid_search.best_score_)
    print("Best parameters set:")
    best_parameters = grid_search.best_estimator_.get_params()
    for param_name in sorted(parameters.keys()):
        print("\t%s: %r" % (param_name, best_parameters[param_name]))

特征选择

将文本用特征表示之后，我们可以进行特征选择，选出比较好的特征。选择的标准有协方差，互信息等。

from sklearn.datasets import load_iris
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
iris = load_iris()
X, y = iris.data, iris.target
pritn X.shape
X_new = SelectKBest(chi2, k=2).fit_transform(X, y)
print X_new.shape

输出
(150, 4)
(150, 2)