刚开始学习机器学习不久，这也是我第一次写博客。就先写个简单的，利用sklearn包中的kNN分类器进行分类，分类的数据集为皮马印第安人糖尿病数据集（pima-indians-diabetes.data.csv）。废话不多说，直接上代码，写的不完善的地方，望大家指正。
#coding:utf-8 ''''' Create by Ma Chao August 4th kNN ''''' from sklearn.neighbors import NearestNeighbors, KNeighborsClassifier from sklearn import datasets import numpy as np #加载数据集 def loadDataSet(fileName): input = [] output = [] with open(fileName) as fr: for line in fr.readlines(): lineArr = line.strip().split(',') input.append([float(lineArr[0]), float(lineArr[1]), float(lineArr[2]), float(lineArr[3]), float(lineArr[4]), float(lineArr[5]), float(lineArr[6]), float(lineArr[7])]) output.append(int(lineArr[8])) return input, output if __name__ == "__main__": input, output = loadDataSet('pima-indians-diabetes.data.csv') np.random.seed(0) indices = np.random.permutation(len(input)) input_train = input[:-10] output_train = output[:-10] input_test = input[-10:] output_test = output[-10:] kNN = KNeighborsClassifier() kNN.fit(input_train, output_train) output_predict = kNN.predict(input_test) prob = kNN.predict_proba(input_test) score = kNN.score(input_test, output_test, sample_weight=None) kNeighbor = kNN.kneighbors(input_test[:-1], 4)#找出与测试集中最后一个元素距离最近的4个元素 print 'output_test:', output_test print 'output_predic:', output_predict print '****************' print 'Prob:', prob print '****************' print 'Score:', score代码中所用数据集可在此处下载：http://download.csdn.net/detail/liexian2816/9922400
