#導(dǎo)入相應(yīng)的庫（對(duì)數(shù)據(jù)庫進(jìn)行切分需要用到的庫是sklearn.model_selection 中的 train_test_split）
import numpy as np
from sklearn.model_selection import train_test_split
 #首先，讀取.CSV文件成矩陣的形式。
my_matrix = np.loadtxt(open("xxxxxx.csv"),delimiter=",",skiprows=0)
 #對(duì)于矩陣而言，將矩陣倒數(shù)第一列之前的數(shù)值給了X（輸入數(shù)據(jù)），將矩陣大最后一列的數(shù)值給了y（標(biāo)簽）
X, y = my_matrix[:,:-1],my_matrix[:,-1]
 #利用train_test_split方法，將X,y隨機(jī)劃分問，訓(xùn)練集（X_train），訓(xùn)練集標(biāo)簽（X_test），測(cè)試卷（y_train），
 測(cè)試集標(biāo)簽（y_test），安訓(xùn)練集：測(cè)試集=7:3的
 概率劃分，到此步驟，可以直接對(duì)數(shù)據(jù)進(jìn)行處理
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
 #此步驟，是為了將訓(xùn)練集與數(shù)據(jù)集的數(shù)據(jù)分別保存為CSV文件
 #np.column_stack將兩個(gè)矩陣進(jìn)行組合連接
train= np.column_stack((X_train,y_train))
 #numpy.savetxt 將txt文件保存為。csv結(jié)尾的文件
numpy.savetxt('train_usual.csv',train, delimiter = ',')
test = np.column_stack((X_test, y_test))
numpy.savetxt('test_usual.csv', test, delimiter = ',')

import numpy as np
from sklearn.model_selection import train_test_split
my_matrix = np.loadtxt(open("xxxxx.csv"),delimiter=",",skiprows=0)
X, y = my_matrix[:,:-1],my_matrix[:,-1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
train= np.column_stack((X_train,y_train))
numpy.savetxt('train_usual.csv',train, delimiter = ',')
test = np.column_stack((X_test, y_test))
numpy.savetxt('test_usual.csv', test, delimiter = ',')