sklearn——model_selection——knn手写识别系统+iris分类

X,y划分成训练和验证数据

# 模型选择，可以打乱顺序，按照比例进行划分
from sklearn.model_selection import train_test_split
# test_size = 0.2 ,train_size =0.8;训练：测试 = 4：1
X_train ,X_test ,y_train,y_test = train_test_split(X,y,test_size=0.2)

算法训练和预测（验证）

import numpy as np
from sklearn.neighbors import KNeighborsClassifier
# 模型选择，可以打乱顺序，按照比例进行划分
from sklearn.model_selection import train_test_split
# test_size = 0.2 ,train_size =0.8;训练：测试 = 4：1
X_train ,X_test ,y_train,y_test = train_test_split(X,y,test_size=0.2)
# 数据不符合要求，reshape改变形状，将3维数据变成2维的
X_train = X_train.reshape(4000,-1)
knn = KNeighborsClassifier(n_neighbors=63)# 选择几个关键的邻居
knn.fit(X_train,y_train)
# 使用算法进行预测，保留了1000个数据，算法没见过
# %%time 计时
X_test.reshape(1000,-1)
y_ = knn.predict(X_test)
# 准确率 等效算法，相当于求平均值
(y_==y_test).sum()/1000
(y_==y_test).mean()

knn——iris分类

import  numpy as np
import matplotlib.pylab as pyb
#%matplotlib inline
from sklearn.neighbors import KNeighborsClassifier
from sklearn import datasets
X,y = datasets.load_iris(True)
# 4个属性，4维空间，4维的数据
# print(X.shape)
# （150，4）（样本数量，属性数量）
# 降维，切片
# 训练数据
X = X[:,:2]
# 测试数据 shape (2,2)
print(X.shape)
pyb.scatter(X[:,0],X[:,1],c=y)
# pyb.show()
knn = KNeighborsClassifier(n_neighbors=5)
# 使用150个样本点作为训练数据
knn.fit(X,y)
#获取测试数据：横坐标：4~8；纵坐标：2~4.5
# 背景点取出来，meshgrid
x1 = np.linspace(4,8,100)
y1 = np.linspace(2,4.5,80)
X1,Y1 = np.meshgrid(x1,y1)
print(X1.shape,Y1.shape)
# pyb.scatter(X1,Y1)
# pyb.show()
X1=X1.reshape(-1,1)
Y1=Y1.reshape(-1,1)
X_test = np.concatenate([X1,Y1],axis=1)
# print(X_test.shape) #（8000，2）8000个样本，2个属性
# X1.revel().shape# ravel 平铺，一维化,等价于X1.reshape(-1).shape
# a = np.random.randint(0,30,size=(3,4))#降维
# print(a.ravel())
X_test = np.c_[X1.ravel(),Y1.ravel()]
X_test.shape
# 此时数据已经准备好了
y_ = knn.predict(X_test)
# 指定颜色
from matplotlib.colors import ListedColormap
lc = ListedColormap(['#FFAAAA','#AAFFAA','#AAAAFF'])
lc2 = ListedColormap(['#FF0000','#00FF00','#0000FF'])
pyb.scatter(X_test[:,0],X_test[:,1],c = y_,cmap = lc)
pyb.scatter(X[:,0],X[:,1],c = y,cmap = lc2)
pyb.show()
# 第二种画图方式
# pyb.contour(X1,Y1,y_reshape(80,100),cmap = lc)