ann 第一节数据预处理

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv(‘Churn_Modelling.csv‘)  #导入该csv文件
X = dataset.iloc[:, 3:13].values              #将该表格的所有列以及3到12行的值取出来。作为一个二维数组
y = dataset.iloc[:, 13].values                #将该表格的所有列以及第十三行取出来。作为一个一维数组。从0开始数

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder   #从sklearn.preprocessing 中导入LabelEncoder，和OneHotEncoder
labelencoder_X_1 = LabelEncoder()                               #新建一个实例labelencoder_X_1 
X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])               #重新赋值X的第一列（0开始）。用labelencoder实例中的fit_transform方法
labelencoder_X_2 = LabelEncoder()                               #同样赋值第二列。fit_transform() 对X【：1】 列进行赋值。0，1，2.。。。
X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])　　　　　　　　　#第二列是性别。0赋值给femal，1赋值给male
onehotencoder = OneHotEncoder(categorical_features = [1])          
X = onehotencoder.fit_transform(X).toarray()
X = X[:, 1:]

# Splitting the dataset into the Training set and Test set
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)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)