数据预处理
1. 导入库
import numpy as np
import pandas as pd
2. 导入数据集
dataset = pd.read_csv('datasets/Data.csv')#读取csv文件
X = dataset.iloc[ : , :-1].values #.iloc[行，列]
Y = dataset.iloc[ : , 3].values # : 全部行 or 列；[a]第a行 or 列
# [a,b,c]第 a,b,c 行 or 列
print('X:' + str(X))
print('Y:' + str(Y))
X:[['France' 44.0 72000.0]
['Spain' 27.0 48000.0]
['Germany' 30.0 54000.0]
['Spain' 38.0 61000.0]
['Germany' 40.0 nan]
['France' 35.0 58000.0]
['Spain' nan 52000.0]
['France' 48.0 79000.0]
['Germany' 50.0 83000.0]
['France' 37.0 67000.0]]
Y:['No' 'Yes' 'No' 'No' 'Yes' 'Yes' 'No' 'Yes' 'No' 'Yes']
3. 处理丢失数据
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0)
imputer = imputer.fit(X[ : , 1:3])
X[ : , 1:3] = imputer.transform(X[ : , 1:3])
4. 解析分类数据
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])
创建虚拟变量
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
5. 拆分数据集为训练集合和测试集合
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split( X , Y , test_size = 0.2, random_state = 0)
6. 特征量化
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
