1、从sklearn自带的数据集中导入数据
from sklearn.datasets import load_iris from sklearn.neighbors import KNeighborsClassifier from sklearn import cross_validation import numpy as np data = load_iris() X = data.data y = data.target size = np.random.permutation(y.size) X = X[size] y = y[size]
2、通过交叉验证来判断n_neighbors的值,也就是k值,为多少时分类效果最好。
n_range = range(1,31) n_scores = [] for n in n_range: knn = KNeighborsClassifier(n_neighbors=n) score = cross_validation.cross_val_score(knn, X, y, cv=10) n_scores.append(score.mean()) import pandas result = pandas.DataFrame({'n_range':n_range, 'n_scores':n_scores}) zuijia = int(result[result['n_scores']==max(n_scores)]['n_range']) #zuijia就是效果最好的k值 import matplotlib.pyplot as plt plt.plot(n_range, n_scores,'b:+') plt.show()
3、将iris数据分为训练集和测试集,带入最佳的k值,运用knn预测。
X_train = X[:100] y_train = y[:100] X_test = X[100:] y_test = y[100:] KNN = KNeighborsClassifier(n_neighbors=zuijia) KNN.fit(X_train,y_train) plt.plot(KNN.predict(X_test),y_test, 'b:+') plt.show()