《python机器学习基础教程》代码实现K近邻

《python机器学习基础教程》代码实现K近邻

KNeighborsClassifier

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
import matplotlib.pyplot as plt
cancer = load_breast_cancer()
X_train,X_test,y_train,y_test = train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=0)
training_accuracy = []
test_accuracy = []
neighbors_settings = range(1,11)

for neighbors in neighbors_settings:
    clf=KNeighborsClassifier(n_neighbors=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.xlabel("Accuracy")
plt.ylabel("n_neighbors")
plt.legend()
plt.show()

KNeighborsRegressor

from sklearn.neighbors import KNeighborsRegressor
from sklearn.model_selection import train_test_split
import mglearn
import numpy as np
import matplotlib.pyplot as plt
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)
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("{}nrighbor(s)n train 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(["Nodel predictions","Training data/target","Test data/target"],loc='best')
plt.show()