机器学习-字典数据抽取

字典数据抽取

from sklearn.feature_extraction import DictVectorizer

def dictverc():
    
    """
    字典数据抽取
    """
    # 实例化
    dict = DictVectorizer()
    # 调用fit_transform
    data = dict.fit_transform([{'city':'北京','temperature':100},{'city':'上海','temperature':90},{'city':'青岛','temperature':80}]);
    # 输出
    print(data)
    
    
# 运行
dictverc()

结果：

  (0, 1)        1.0
  (0, 3)        100.0
  (1, 0)        1.0
  (1, 3)        90.0
  (2, 2)        1.0
  (2, 3)        80.0

Sparse矩阵输出

from sklearn.feature_extraction import DictVectorizer

def dictverc():
    
    """
    字典数据抽取
    """
    # 实例化
    dict = DictVectorizer(sparse=False)
    # 调用fit_transform
    data = dict.fit_transform([{'city':'北京','temperature':100},{'city':'上海','temperature':90},{'city':'青岛','temperature':80}]);
    # 输出
    print(data)
    
    
# 运行
dictverc()

结果：

[[  0.   1.   0. 100.]
 [  1.   0.   0.  90.]
 [  0.   0.   1.  80.]]