详解sklearn Preprocessing 数据预处理功能

from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler
from matplotlib improt gridspec
import numpy as np
import matpotlib.pyplot as plt

cps = np.random.random_integers(0, 100, (100, 2))
# 创建StandardScaler 对象,再调用fit_transform 方法,传入一个格式的参数数据作为训练集.
ss = StandardScaler()
std_cps = ss.fit_transform(cps)
gs = gridspec.GridSpec(5,5)
fig = plt.figure()
ax1 = fig.add_subplot(gs[0:2, 1:4])
ax2 = fig.add_subplot(gs[3:5, 1:4])
ax1.scatter(cps[:, 0], cps[:, 1])
ax2.scatter(std_cps[:, 0], std_cps[:, 1])
plt.show()

min_max_scaler = preprocessing.MinMaxScaler()
x_minmax = min_max_scaler.fit_transform(x)

max_abs_scaler = preprocessing.MaxAbsScaler()
x_train_maxsbs = max_abs_scaler.fit_transform(x)
x_train_maxsbs

x_normalized = preprocessing.normalize(x, norm='l2')
print(x)

from sklearn import preprocessing
import numpy as np
# 创建一组特征数据，每一行表示一个样本，每一列表示一个特征
x = np.array([[1., -1., 2.],
              [2., 0., 0.],
              [0., 1., -1.]])
binarizer = preprocessing.Binarizer().fit(x)
binarizer.transform(x)
binarizer = preprocessing.Binarizer(threshold=1.5)
binarizer.transform(x)

from sklearn import preprocessing
enc = preprocessing.OneHotEncoder()
enc.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]])    # fit来学习编码
enc.transform([[0, 1, 3]]).toarray()    # 进行编码

import numpy as np
from sklearn.preprocessing import Imputer
imp = Imputer(missing_values='NaN', strategy='mean', axis=0)
imp.fit domain name is for sale. Inquire now.([[1, 2], [np.nan, 3], [7, 6]])
x = [[np.nan, 2], [6, np.nan], [7, 6]]
imp.transform(x)

import scipy.sparse as sp
# 创建一个稀疏矩阵
x = sp.csc_matrix([[1, 2], [0, 3], [7, 6]])
imp = Imputer(missing_values=0, strategy='mean', verbose=0)
imp.fit domain name is for sale. Inquire now.(x)
x_test = sp.csc_matrix([[0, 2], [6, 0], [7, 6]])
imp.transform(x_test)