CS_ALearn/ailearning
1
0
Fork 0
mirror of https://github.com/apachecn/ailearning.git synced 2026-02-13 15:26:28 +08:00
Code Issues Projects Releases Wiki Activity

更新 SVD 推荐系统的注释

Browse Source
This commit is contained in:
jiangzhonglian
2017-09-08 20:00:21 +08:00
parent 14345cb4a0
commit 7b743711e3
6 changed files with 44 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/python/14.SVD/svdRecommend.py
View File

@@ -303,15 +303,15 @@ def imgCompress(numSV=3, thresh=0.8):
if __name__ == "__main__":
# # 对矩阵进行SVD分解(用python实现SVD)
Data = loadExData()
print 'Data:', Data
U, Sigma, VT = linalg.svd(Data)
# Data = loadExData()
# print 'Data:', Data
# U, Sigma, VT = linalg.svd(Data)
# # 打印Sigma的结果，因为前3个数值比其他的值大了很多，为9.72140007e+00，5.29397912e+00，6.84226362e-01
# # 后两个值比较小，每台机器输出结果可能有不同可以将这两个值去掉
print 'U:', U
print 'Sigma', Sigma
print 'VT:', VT
print 'VT:', VT.T
# print 'U:', U
# print 'Sigma', Sigma
# print 'VT:', VT
# print 'VT:', VT.T
# # 重构一个3x3的矩阵Sig3
# Sig3 = mat([[Sigma[0], 0, 0], [0, Sigma[1], 0], [0, 0, Sigma[2]]])
@@ -335,15 +335,15 @@ if __name__ == "__main__":
"""
# 计算相似度的方法
# myMat = mat(loadExData2())
myMat = mat(loadExData3())
# print myMat
# 计算相似度的第一种方式
# print recommend(myMat, 1, estMethod=svdEst)
print recommend(myMat, 1, estMethod=svdEst)
# 计算相似度的第二种方式
# print recommend(myMat, 1, estMethod=svdEst, simMeas=pearsSim)
print recommend(myMat, 1, estMethod=svdEst, simMeas=pearsSim)
# 默认推荐（菜馆菜肴推荐示例）
# print recommend(myMat, 2)
print recommend(myMat, 2)
"""
# 利用SVD提高推荐效果