sklearn中模型抽取

特征抽取sklearn.feature_extraction 模块提供了从原始数据如文本，图像等众抽取能够被机器学习算法直接处理的特征向量。

1.特征抽取方法之 Loading Features from Dicts

measurements=[
    {'city':'Dubai','temperature':33.},
    {'city':'London','temperature':12.},
    {'city':'San Fransisco','temperature':18.},
]

from sklearn.feature_extraction import DictVectorizer
vec=DictVectorizer()
print(vec.fit_transform(measurements).toarray())
print(vec.get_feature_names())

#[[  1.   0.   0.  33.]
 #[  0.   1.   0.  12.]
 #[  0.   0.   1.  18.]]

#['city=Dubai', 'city=London', 'city=San Fransisco', 'temperature']

2.特征抽取方法之 Features hashing

3.特征抽取方法之 Text Feature Extraction

词袋模型 the bag of words represenatation

#词袋模型
from sklearn.feature_extraction.text import CountVectorizer
#查看默认的参数
vectorizer=CountVectorizer(min_df=1)
print(vectorizer)

"""
CountVectorizer(analyzer='word', binary=False, decode_error='strict',
        dtype=<class 'numpy.int64'>, encoding='utf-8', input='content',
        lowercase=True, max_df=1.0, max_features=None, min_df=1,
        ngram_range=(1, 1), preprocessor=None, stop_words=None,
        strip_accents=None, token_pattern='(?u)\b\w\w+\b',
        tokenizer=None, vocabulary=None)

"""

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)

"""
(0, 1)    1
  (0, 2)    1
  (0, 6)    1
  (0, 3)    1
  (0, 8)    1
  (1, 5)    2
  (1, 1)    1
  (1, 6)    1
  (1, 3)    1
  (1, 8)    1
  (2, 4)    1
  (2, 7)    1
  (2, 0)    1
  (2, 6)    1
  (3, 1)    1
  (3, 2)    1
  (3, 6)    1
  (3, 3)    1
  (3, 8)    1
"""

 默认是可以识别的字符串至少为2个字符

analyze=vectorizer.build_analyzer()
print(analyze("this is a document to anzlyze.")==
　　　　(["this","is","document","to","anzlyze"]))

#True

在fit阶段被analyser发现的每一个词语都会被分配一个独特的整形索引，该索引对应于特征向量矩阵中的一列

print(vectorizer.get_feature_names()==(
    ["and","document","first","is","one","second","the","third","this"]
))
#True
print(x.toarray())
"""
[[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]]
"""

获取属性

print(vectorizer.vocabulary_.get('document'))
#1

对于一些没有出现过的字或者字符，则会显示为0

vectorizer.transform(["somthing completely new."]).toarray()
"""
[[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]]
"""

在上边的语料库中，第一个和最后一个单词是一模一样的，只是顺序不一样，他们会被编码成相同的特征向量，所以词袋表示法会丢失了单词顺序的前后相关性信息，为了保持某些局部的顺序性，可以抽取2个词和一个词    

bigram_vectorizer=CountVectorizer(ngram_range=(1,2),token_pattern=r"w+",min_df=1)
analyze=bigram_vectorizer.build_analyzer()
print(analyze("Bi-grams are cool!")==(['Bi','grams','are','cool','Bi grams',
                                 'grams are','are cool']))

#True
x_2=bigram_vectorizer.fit_transform(corpus).toarray()
print(x_2)

"""
[[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]]
"""