codefarmer-cyk/recsyscode

Automatically exported from code.google.com/p/recsyscode

recsyscode's Issues

support the change of upper and lower limit of the score(support the kddcup dataset)

support the change of  upper and lower limit of the score to make our project 
support the kddcup dataset.


目前数据集不支持kddcup的数据集，打分的上下限不可调，需��
�调整支持kddcup的数据集

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:28

lack of temporal model

The temporal model need to be implemented.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:23

modularize the calculation of similiarity of KNN model

We just use the pearson similiarity in the KNN model. But friends may want to 
use other similiarities. So We should modularize the calculation of similiarity 
of KNN model.


KNN算法目前相似度的计算采用person相关系数，需要把这个相��
�度的计算模块化，可以替换

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:26

make the code to an Object-oriented one

The code is a Process-Oriented one. I want to make the code become an 
Object-oriented  one.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:33

reduce the length of some functions

There are some functions which are too long. We should reduce the length of 
these functions.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:31

make the code compatible with google-code-style

What steps will reproduce the problem?
1. change the code format
2. test the code with 
[http://google-styleguide.googlecode.com/svn/trunk/cpplint/cpplint.py 
cpplint.py](a tool to assist with style guide compliance)
3. if the code passes the test,then done; else go to step 1.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:19

svdBase里的user character Matrix和item character Matrix是轮流更新的吧

我看代码里怎么同时更新了？
for( k=1; k< K_NUM+1; ++k) {
                        //double tempPu = p[u][k];
                        p[u][k] += alpha2 * (eui*q[itemI][k] - beta2*p[u][k]);
                        q[itemI][k] += alpha2 * (eui*p[u][k] - beta2*q[itemI][k]);
                    }

不是应该固定p，更新q，然后固定q，更新p么？

Original issue reported on code.google.com by [email protected] on 24 May 2012 at 6:22

lack of RBM model

The RBM model need be implemented.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:22

add formula as comment for each method in the corresponding cpp file

add formulas so that the codes would be easier to be understand. 

Original issue reported on code.google.com by [email protected] on 8 Jun 2011 at 5:18

add unit test code

The unit test is the foundation of  refactoring. We should add the test unit 
before all our refactoring.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:35

Python version of the code

It's quite a while since I read C++ code last time. I do not understand them 
quite well now. 

Can somebody translate this great package into Python so that other users like 
me could be able to tailor the code accordingly.

Thanks.

Happy New Year

Original issue reported on code.google.com by [email protected] on 21 Jan 2012 at 11:24

test

test

Original issue reported on code.google.com by [email protected] on 19 May 2011 at 6:13

fix the bug with svd++ model

There are bugs with svd++ model. 
When I used the netflix dataset to test the model, it generated nan error. I am 
fixing the bug now.

Original issue reported on code.google.com by honglianglv on 19 May 2011 at 5:21