sklearn中实现标准化、归一化

这里记录下标准化，归一化等内容：

from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.preprocessing import MinMaxScaler, StandardScaler, Imputer
from sklearn.feature_selection import VarianceThreshold
from sklearn.decomposition import PCA
import numpy as np

def dictvec():
    # sparse默认是True，是为了节省内存
    dict1 = DictVectorizer(sparse=False)
    data1 = dict1.fit_transform([{'city': '北京','temperature':100},{'city': '上海','temperature':60},{'city': '深圳','temperature':30}])
    print(data1)
    
    print("===============================")
    print("sparse默认为True，返回如下：")
    
    dict2 = DictVectorizer(sparse=True)
    data2 = dict2.fit_transform([{'city': '北京','temperature':100},{'city': '上海','temperature':60},{'city': '深圳','temperature':30}])
    print(data2)
    
    print("===============================")
    print("字典类别数据：")
    print(dict2.get_feature_names())
    
    return None

def countvec():
    cv = CountVectorizer()
    data = cv.fit_transform(["life is short,i like python life","life is too long,i dislike python"])
    print("===============================")
    print("sparse默认为True，返回如下：")
    print(data)
    
    print("===============================")
    print("CountVectorizer没有sparse参数，按照如下方式操作：")
    print(data.toarray())
    
    print("===============================")
    print("获得类别名：")
    print(cv.get_feature_names())
    
    return None

# 归一化
def mm():
    # feature_range改变归一化范围，默认0-1
#     mm = MinMaxScaler(feat ure_range=(2,3))
    mm = MinMaxScaler()
    data = mm.fit_transform([[90, 2, 10, 40], [60, 4, 15, 45], [75, 3, 13, 46]])
    print("===============================")
    print("归一化，返回如下：")
    print(data)
    
    return None

# 标准化
def ss():
    std = StandardScaler()
    data = std.fit_transform([[ 1., -1., 3.],[ 2., 4., 2.],[ 4., 6., -1.]])
    print("===============================")
    print("标准化，返回如下：")
    print(data)
    
    return None
    
# 缺失值
def im():
    im = Imputer(missing_values='NaN', strategy='mean', axis=0) # 按列
    data = im.fit_transform([[1, 2], [np.nan, 3], [7, 6]])
    print("===============================")
    print("缺失值处理，返回如下：")
    print(data)
    
    return None
 
    
# 降维
def var():
    """
    特征选择-删除低方差的特征
    """
    var = VarianceThreshold(threshold=0)
    data = var.fit_transform([[0, 2, 0, 3], [0, 1, 4, 3],[0, 1, 1, 3]])
    print("===============================")
    print("删除低方差降维，返回如下：")
    print(data)
    
    return None

# 主成分分析PCA
def pca():
    """
    主成分分析进行降维
    """
    # 信息保留90%
    pca = PCA(n_components=0.9)
    data = pca.fit_transform([[2,8,4,5],[6,3,0,8],[5,4,9,1]])
    print("===============================")
    print("主成分分析降维，返回如下：")
    print(data)
    
    return None


if __name__ == "__main__":
#     dictvec()
    countvec()
#     mm()
#     ss()
#     im()
#     var()
#     pca()