Python 第五章 数据预处理

#缺失值填充
import pandas as pd
import numpy as np
data=pd.read_excel('missing.xlsx')                        #数据框data
c=np.array([[1,2,3,4],[4,5,6,np.nan],[5,6,7,8],[9,4,np.nan,8]])   #数组c
C=pd.DataFrame(c)                                    #数据框C

# 1.均值填充策略
from sklearn.preprocessing import Imputer 
fC=C 
imp = Imputer(missing_values='NaN', strategy='mean', axis=0)
imp.fit(fC)
fC=imp.transform(fC)
print(fC)

[[1.         2.         3.         4.        ]
 [4.         5.         6.         6.66666667]
 [5.         6.         7.         8.        ]
 [9.         4.         5.33333333 8.        ]]

# 2.中位数填充策略
imp = Imputer(missing_values='NaN', strategy='median', axis=1)
fc=c
imp.fit(fc)
fc=imp.transform(fc)
print(fc)

[[1. 2. 3. 4.]
 [4. 5. 6. 5.]
 [5. 6. 7. 8.]
 [9. 4. 8. 8.]]

# 3.最频繁值填充策略
fD=data[['a','c']]
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)
imp.fit(fD)
fD=imp.transform(fD)
print(fD)

[[2. 4.]
 [2. 6.]
 [2. 5.]
 [5. 6.]
 [6. 6.]]

#规范化处理
data=np.load('data.npy')
data=data[:,1:]
print(data)

[[  17.           66.17647059   32.         1614.96618125   13.15625   ]
 [   8.           68.6875       36.          143.56458056    3.80555556]
 [  16.           65.84375      43.         1344.13137674   12.69767442]
 ...
 [  10.           67.95         24.          115.87417083    2.79166667]
 [  21.           66.5          41.          538.71289268   20.31707317]
 [  11.           78.27272727    9.           62.98323333    9.44444444]]

imp = Imputer(missing_values='NaN', strategy='mean', axis=0)
imp.fit(data)
data=imp.transform(data)
print(data)

[[  17.           66.17647059   32.         1614.96618125   13.15625   ]
 [   8.           68.6875       36.          143.56458056    3.80555556]
 [  16.           65.84375      43.         1344.13137674   12.69767442]
 ...
 [  10.           67.95         24.          115.87417083    2.79166667]
 [  21.           66.5          41.          538.71289268   20.31707317]
 [  11.           78.27272727    9.           62.98323333    9.44444444]]

#标准化（均值0，标准差1）
from sklearn.preprocessing import StandardScaler
X=data
scaler = StandardScaler()
scaler.fit(X) 
X=scaler.transform(X)
print(X)

[[ 0.20025842 -0.82760637  0.05554634  2.84353829  0.76954149]
 [-0.68918721 -0.09224269  0.20662516 -0.18554119 -0.65156099]
 [ 0.10143112 -0.92504475  0.47101308  2.28598816  0.69984796]
 ...
 [-0.49153262 -0.30822213 -0.24661129 -0.24254565 -0.80565008]
 [ 0.59556758 -0.73285966  0.39547367  0.62792513  1.85783108]
 [-0.39270533  2.71482439 -0.81315684 -0.35142881  0.20542766]]

#归一化处理，【0,1】
from sklearn.preprocessing import MinMaxScaler   
X1=data
min_max_scaler = MinMaxScaler()
min_max_scaler.fit(X1)
X1=min_max_scaler.transform(X1)
print(X1)

[[0.38095238 0.04406273 0.2519685  0.33941778 0.1381392 ]
 [0.16666667 0.17158327 0.28346457 0.03015525 0.03188131]
 [0.35714286 0.0271658  0.33858268 0.28249311 0.13292812]
 ...
 [0.21428571 0.13412995 0.18897638 0.02433521 0.02035985]
 [0.47619048 0.06049291 0.32283465 0.11320842 0.2195122 ]
 [0.23809524 0.65836106 0.07086614 0.01321848 0.0959596 ]]

本节内容参考Python金融数据分析与挖掘实战，黄恒秋，人民邮电出版社的内容