vectors = read_record(sc, record_file)
itemIndex = read_index(sc, itemIndex_file, True)
userIndex = read_index(sc, userIndex_file, False)
user_id = read_userID_file(sc, userID_file)
f = open('output.txt','w')
for u in user_id:
uid = userIndex[u]
user = getUserVector(uid, vectors)
otherUser = vectors.filter(lambda (k,v): k != uid)
neighbors = knn2(sc, user, otherUser, K)
#neighbors = knn1(sc, user, otherUser, K)
rlt = getRecommend(neighbors)
tmp = ""
for r in rlt:
if r[0] in itemIndex:
tmp = tmp + itemIndex[r[0]] + ' '
f.write("%s: %s\n" % (u, tmp))
f.close()
# coding: UTF-8
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import knn
import mnist_test
group, labels = knn.createDataSet()
bb = knn.classify0([0,0], group, labels, 3)
print bb
cc = knn.knn2([0,0], group, labels, 3)
# 可视化数据
dataSet, labels = knn.file2matrix('data/datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(dataSet[:,0], dataSet[:,1], s=15.0*labels, c=15.0*labels)
plt.show()
# 测试误判率
reload(knn)
# testRatio为测试集比例，k为邻居个数
knn.knnTest('../data/datingTestSet2.txt',testRatio=0.2, k=3)
# 测试手写数字识别