将数据成 训练数据和测试数据,并计算正确率(评价)
X_train,X_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
from sklearn.metrics import accuracy_score
from sklearn import datasets#引入数据集,sklearn包含众多数据集
from sklearn.model_selection import train_test_split#将数据分为测试集和训练集
from sklearn.neighbors import KNeighborsClassifier#利用邻近点方式训练数据
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
###引入数据###
iris=datasets.load_iris()#引入iris鸢尾花数据,iris数据包含4个特征变量
# print(iris.keys())
# print(iris.DESCR)
iris_X=iris.data#特征变量
iris_y=iris.target#目标值
shuffle_indexes=np.random.permutation(len(iris_X))
print(shuffle_indexes)
test_ratio=0.2
test_size=int(len(iris_X)*test_ratio)
# print(test_size)
# test_indexex=shuffle_indexes[:test_size]
# train_indexex=shuffle_indexes[test_size:]
# print(test_indexex)
# print(train_indexex)
# X_train=iris_X[train_indexex]
# y_train=iris_y[train_indexex]
#