In [1]:

    

%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd


    

In [2]:

    

#使用DictVectorizer对特征进行抽取和量化
measurements=[{'city':'Dubai','temperature':33.},
              {'city':'London','temperature':12.},
              {'city':'San Fransisco','temperature':18.}]


    

In [3]:

    

from sklearn.feature_extraction import DictVectorizer


    

In [4]:

    

vec = DictVectorizer()


    

In [5]:

    

print vec.fit_transform(measurements).toarray()


    

    




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

In [6]:

    

print vec.get_feature_names()


    

    




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

In [7]:

    

#从上面可以看出，特征向量化就是将类别的类型作为新的特征处理，数值型的直接作为特征


    

In [ ]: