监督学习算法2.3.2-K邻近、二分类、回归

全文代码如下：

import matplotlib.pyplot as plt
import mglearn
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

x,y = mglearn.datasets.make_forge()
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state = 0)
clf = KNeighborsClassifier(n_neighbors=3)
clf.fit(x_train,y_train)
print("test set predictions:{}".format(clf.predict(x_test)))
print('test set accuracy:{:.3f}'.format(clf.score(x_test,y_test)))

fig,axes = plt.subplots(1,3,figsize=(10,3))
for n_neighbors,ax in zip([1,3,9],axes):
	clf = KNeighborsClassifier(n_neighbors=n_neighbors).fit(x,y)
	mglearn.plots.plot_2d_separator(clf,x,fill=True,eps=0.5,ax=ax,alpha=.4)
	mglearn.discrete_scatter(x[:,0],x[:,1],ax=ax)
	ax.set_title('{} neighbor(s)'.format(n_neighbors))
	ax.set_xlabel('feature 0')
	ax.set_ylabel('feature 1')
axes[0].legend(loc=3)
plt.show()

from sklearn.datasets import load_breast_cancer
cancer = load_breast_cancer()
x_train,x_test,y_train,y_test = train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=66)

training_accuracy = []
test_accuracy = []
neighbors_settings = range(1,11)

for n_neighbors in neighbors_settings:
	clf = KNeighborsClassifier(n_neighbors=n_neighbors)
	clf.fit(x_train,y_train)
	training_accuracy.append(clf.score(x_train,y_train))
	test_accuracy.append(clf.score(x_test,y_test))
plt.plot(neighbors_settings,training_accuracy,label='training accuracy')
plt.plot(neighbors_settings,test_accuracy,label='test accuracy')
plt.ylabel('accuracy')
plt.xlabel('n_neighbors')
plt.legend()
plt.show()

from sklearn.neighbors import KNeighborsRegressor
x,y = mglearn.datasets.make_wave(n_samples=40)
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=0)
reg = KNeighborsRegressor(n_neighbors=3)
reg.fit(x_train,y_train)

print('test set predictons:{}'.format(reg.predict(x_test)))
print('test set r^2 :{:.2f}'.format(reg.score(x_test,y_test)))

fig,axes = plt.subplots(1,3,figsize=(15,4))
line = np.linspace(-3,3,1000).reshape(-1,1)
for n_neighbors,ax in zip([1,3,9],axes):
	reg = KNeighborsRegressor(n_neighbors=n_neighbors)
	reg.fit(x_train,y_train)
	ax.plot(line,reg.predict(line))
	ax.plot(x_train,y_train,'^',c=mglearn.cm2(0),markersize=8)
	ax.plot(x_test,y_test,'^',c=mglearn.cm2(1),markersize=8)
	ax.set_title('{}neighbor(s) train score:{:.2f} test score:{:.2f}'.format(n_neighbors,reg.score(x_train,y_train),reg.score(x_test,y_test)))
	ax.set_xlabel('feature')
	ax.set_ylabel('target')
axes[0].legend(['model predictiond','training data/target','test data/target'],loc='best')
plt.show()