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‘]

#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
"""