sklearn代码3 4-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 需要4维空间才可以 4维数据
# 150代表样本数量
X.shape

(150, 4)

# 降维，最简单的降维操作就是切片
X = X[:,:2]  #切片从2开始一直到最后
X.shape

(150, 2)

pyb.scatter(X[:,0],X[:,1],c = y)  # 横坐标0，纵坐标1 y会分配颜色

<matplotlib.collections.PathCollection at 0x156f7fc22b0>

knn = KNeighborsClassifier(n_neighbors=5)

# 使用150个样本点作为训练数据
knn.fit(X,y)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=5, p=2,
           weights='uniform')

# 训练数据
X.shape
# 测试数据 shape（？，2）    

# 获取测试数据
# 横坐标宽度 4~8 纵坐标2~4.5
# 背景点 取出来 meshgrid
x1 = np.linspace(4,8,100)   # 横坐标4~8，取一百个间隔

y1 = np.linspace(2,4.5,80)

X1,Y1 = np.meshgrid(x1,y1)
# display(X1.shape,Y1.shape)

# X1 = X1.reshape(-1,1)  #-1代表8000样本，1代表横坐标长度
# X1.shape

# Y1 = Y1.reshape(-1,1)

# # X_test = np.concatenate([X1,Y1],axis = 1)
# # X_test.shape
# # 平铺 一维化
X_test = np.c_[X1.ravel(),Y1.ravel()]   #与上述方法都可以实现数据整合

X_test.shape

(8000, 2)

%time  y_ = knn.predict(X_test)  

Wall time: 11.9 ms

from matplotlib.colors import ListedColormap

lc = ListedColormap(['#FFAAAA','#AAFFAA','#AAAAFF'])
lc2 = ListedColormap(['#FF0000','#00FF00','#0000FF'])

%%time
pyb.scatter(X_test[:,0],X_test[:,1],c = y_,cmap=lc)

pyb.scatter(X[:,0],X[:,1],c = y,cmap = lc2)

Wall time: 39.9 ms

%%time
# 轮廓线 等高线
pyb.contourf(X1,Y1,y_.reshape(80,100),cmap=lc)

pyb.scatter(X[:,0],X[:,1],c = y,cmap = lc2)

Wall time: 34.9 ms