# -*- coding: utf-8 -*- ''' Created on 2018年1月15日 @author: Jason.F @summary: Scikit-Learn庫K近鄰分類算法 '''from sklearn import datasets import numpy as np from sklearn.cross_validation import train_test_split from sklearn.preprocessing import StandardScaler from matplotlib.colors import ListedColormap import matplotlib.pyplot as plt from sklearn.svm import SVC from sklearn.metrics import accuracy_score from sklearn.neighbors import KNeighborsClassifier #決策邊界函數 def plot_decision_regions(X,y,classifier,test_idx=None,resolution=0.02):# 設置標記點和顏色markers = ('s','x','o','^','v')colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')cmap = ListedColormap(colors[:len(np.unique(y))])# 繪制決策面x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),np.arange(x2_min, x2_max, resolution))Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)Z = Z.reshape(xx1.shape)plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)plt.xlim(xx1.min(), xx1.max())plt.ylim(xx2.min(), xx2.max())#繪制所有樣本X_test,y_test=X[test_idx,:],y[test_idx]for idx,cl in enumerate(np.unique(y)):plt.scatter(x=X[y==cl,0],y=X[y==cl,1],alpha=0.8,c=cmap(idx),marker=markers[idx],label=cl)#高亮預測樣本if test_idx:X_test,y_test =X[test_idx,:],y[test_idx]plt.scatter(X_test[:,0],X_test[:,1],c='',alpha=1.0,linewidths=1,marker='o',s=55,label='test set') #數據導入 iris=datasets.load_iris() X=iris.data[:,[2,3]] y=iris.target print (np.unique(y)) #訓練集和測試集劃分 X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0) #標準化 sc=StandardScaler() sc.fit(X_train)#計算樣本的均值和標準差 X_train_std=sc.transform(X_train) X_test_std=sc.transform(X_test) #惰性學習-實例學習：KNN knn=KNeighborsClassifier(n_neighbors=5,p=2,metric='minkowski')#閔可夫斯基距離 #距離計算參考：http://scikit-learn.org/stable/modules/generated/sklearn.neighbors.DistanceMetric.html knn.fit(X_train_std,y_train) #模型預測 y_pred=knn.predict(X_test_std) print ('Accuracy:%.2f' %accuracy_score(y_test,y_pred))#準確率 #繪制決策邊界 X_combined_std=np.vstack((X_train_std,X_test_std)) y_combined=np.hstack((y_train,y_test)) plot_decision_regions(X=X_combined_std, y=y_combined, classifier=knn, test_idx=range(105,150)) plt.xlabel('petal length[standardized]') plt.ylabel('petal width[standardized]') plt.legend(loc='upper left') plt.show()

結果：

總結

以上是生活随笔為你收集整理的【Python-ML】SKlearn库K近邻(KNN) 使用的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。