Code Monkey home page Code Monkey logo

feast's People

Contributors

bieito98 avatar craigacp avatar evgenidubov avatar mellorjc avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

feast's Issues

JMI and DISR generates the same score for selectable and non selectable case.

Hello!

I'm testing the latest feast toolbox with this simple code:

y=[zeros(5,1);ones(5,1)];

X=ones(1,10); %Constant
X=[X' rand(10,1)]; %Random
X=[X y]; %Just a copy of target Y

[sel,score]=feast('jmi',3,X,y)
sel =
3
1
2

score =
1
1
1

And the score of all the variables are the same. Is that the desired result? I'm expecting different scores.

Cannot find the referenced paper

Hey,

I am looking for the following paper you mentioned:

 Information Theoretic Feature Selection for Cost-Sensitive Problems
 A. Pocock, N. Edakunni, M.-J. Zhao, M. Lujan, G. Brown.
 ArXiv

I didn't find it on ArXiv. Can you provide me a link?

Best,

Andreas

Mex file crash

Hi, I tried to use the Matlab toolbox, but I got crash with the mex file.
I attached the log file created by matlab. Thank you.


      Access violation detected at Sun Aug 07 20:39:05 2016

Configuration:
Crash Decoding : Disabled
Crash Mode : continue (default)
Current Graphics Driver: Unknown hardware
Default Encoding : windows-1252
Graphics card 1 : NVIDIA ( 0x10de ) NVIDIA GeForce GTX 560 Ti Version 9.18.13.4788
Graphics card 2 : NVIDIA ( 0x10de ) NVIDIA Tesla M2090 Version 10.18.13.6256
Host Name : ChuongWin8
MATLAB Architecture : win64
MATLAB Root : C:\Program Files\MATLAB\R2016a
MATLAB Version : 9.0.0.341360 (R2016a)
OpenGL : hardware
Operating System : Microsoft Windows 8.1 Pro
Processor ID : x86 Family 6 Model 45 Stepping 6, GenuineIntel
Virtual Machine : Java 1.7.0_60-b19 with Oracle Corporation Java HotSpot(TM) 64-Bit Server VM mixed mode
Window System : Version 6.3 (Build 9600)

Fault Count: 1

Abnormal termination:
Access violation

FEAST Portability

@alecuba16 and @mbq have worked on different R interfaces for FEAST (see #3). This issue is to discuss merging in any changes to the core C library or build system to improve usability for R and other possible ports.

Add pre given feautes to CMIM.

Hello!

As I told you on mloss, I would like to modify the CMIM to accept a set of predefined features by a input , so as a first approach I will work on this code from CMIM.c:

I think that the first loop on lines 80-94 is mandatory because you have to calculate first the max CMIM of whole the features (including pre-selected), is right?

Imagine that I have already received preSelectedFeatures as an array of the positions of the features presents on feature2D and a auxiliary function isApreSelectedFeature as a simply search and check if exists.

CMIM.c lines 104 ->129

for (i = 1; i < k; i++)
{
score = 0.0;
iMinus = i-1;
for (j = 0; j < noOfFeatures; j++)
{
while ((classMI[j] > score) && (lastUsedFeature[j] < i))
{
----------- my code ----------------------------------
if( isApreSelectedFeature(j,preSelectedFeatures)){
outputFeatures[i] = j;
}else{
---------- finish my code ----------------------------
/double calculateConditionalMutualInformation(double *firstVector, double *targetVector, double *conditionVector, int vectorLength);/
currentFeature = (int) outputFeatures[lastUsedFeature[j]];
conditionalInfo = calculateConditionalMutualInformation(feature2D[j],classColumn,feature2D[currentFeature],noOfSamples);
if (classMI[j] > conditionalInfo)
{
classMI[j] = conditionalInfo;
}/reset classMI/
}
/moved due to C indexing from 0 rather than 1/
lastUsedFeature[j] += 1;
}/while partial score greater than score & not reached last feature/
if (classMI[j] > score)
{
score = classMI[j];
outputFeatures[i] = j;
}/if partial score still greater than score/
}/for number of features/
}/*for the number of feature

What do you think?

Feature Score For CMIM

Dear Adam

I need to get a score for each fearure as I need to to know the difference between them. For example, how much important is feature 1 than feature 2?

Can please provide the code for that?

Thanks

Elina

segmentation fault with pyfeast

I compiled this code to use with PyFeast. I ran make x64 and sudo make install. When I tried to run the code that uses FEAST through PyFeast I got a segmentation fault. I determined the segmentation fault was due to the FEAST code.

I didn't find instructions on proper installation with the make file, could the segmentation fault be due to incorrect installation, or are there any suggestions for another reason I got a segmentation fault?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.