《 Python 机器学习专题手册》笔记 3

数据预处理的几种方法

import numpy as np
from sklearn import preprocessing

data = np.array([[ 3, -1.5,  2, -5.4],
                 [ 0,  4,  -0.3, 2.1],
                 [ 1,  3.3, -1.9, -4.3]])

# 去除均值
data_standardized = preprocessing.scale(data)
print( "\nMean =", data_standardized.mean(axis=0))
print( "Std deviation =", data_standardized.std(axis=0))

# 将特征缩放至特定范围内
data_scaler = preprocessing.MinMaxScaler(feature_range=(0, 1))
data_scaled = data_scaler.fit_transform(data)
print( "\nMin max scaled data:\n", data_scaled)

# 归一化
data_normalized = preprocessing.normalize(data, norm='l1')
print( "\nL1 normalized data:\n", data_normalized)

# 特征二值化 
data_binarized = preprocessing.Binarizer(threshold=1.4).transform(data)
print( "\nBinarized data:\n", data_binarized)

# 分类特征编码
encoder = preprocessin