基于sklearn package 的KNN实现

#将数据分为测试集和训练集
from sklearn.model_selection import train_test_split
X,y=mglearn.datasets.make_forge()
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
#拟合
from sklearn.neighbors import KNeighborsClassifier
clf=KNeighborsClassifier(n_neighbors=3)
clf.fit(X_t​#将数据分为测试集和训练集
from sklearn.model_selection import train_test_split
X,y=mglearn.datasets.make_forge()
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)
#拟合
from sklearn.neighbors import KNeighborsClassifier
clf=KNeighborsClassifier(n_neighbors=3)
clf.fit(X_train,y_train)
#预测
print("Test set predictions:{}".format(clf.predict(X_test)))
#评估泛化能力
print("Test set accuracy:{:.2f}".format(clf.score(X_test,y_test)))
#查看决策边界
fig,axes=plt.subplots(1,3,figsize=(10,3))
for n_neighbors,ax in zip([1,3,9],axes):
    #fit方法返回对象本身，所以我们可以将实例化和拟合放在一行代码里
    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],y,ax=ax)
    ax.set_title("{}neighbors".format(n_neighbors))
    ax.set_xlabel("feature 0")
    ax.set_ylabel("feature 1")
axes[0].legend(loc=3)rain,y_train)
#预测
print("Test set predictions:{}".format(clf.predict(X_test)))
#评估泛化能力
print("Test set accuracy:{:.2f}".format(clf.score(X_test,y_test)))
#查看决策边界
fig,axes=plt.subplots(1,3,figsize=(10,3))
for n_neighbors,ax in zip([1,3,9],axes):
    #fit方法返回对象本身，所以我们可以将实例化和拟合放在一行代码里
    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],y,ax=ax)
    ax.set_title("{}neighbors".format(n_neighbors))
    ax.set_xlabel("feature 0")
    ax.set_ylabel("feature 1")
axes[0].legend(loc=3)