Comments (1)
Just ran KMeans serial/opencl and GMM serial/opencl, taking the cluster results for the first few thousand gene pairs. The GMM implementations produced very similar results, and they were almost never different by more than one cluster (i.e. serial might find 3 clusters where opencl finds 2 or 4, etc.). So I feel pretty confident that the implementations are consistent.
As for KMeans, serial and opencl got nearly identical results. However, this is mainly because both implementations consistently chose the maximum cluster value, which in this case is 5. So the output logs for each run were just 0's and 5's. This behavior is to be expected with k-means because the model selection criterion for k-means is hopelessly biased towards models with more clusters. So the k-means implementations are consistent, they're just not very good for this problem. But I'll keep the k-means analytic around for now until we can at least see what the produced networks look like.
from kinc.
Related Issues (20)
- Kinc 3D viewer requires that the first column of the amx be labled "Sample" HOT 4
- KINC 3D viewer mangles TTY HOT 1
- Idea to Speed Similarity GMM Step
- Hypergeometric test performs poorly for sub-categories. HOT 3
- Documentation should include uninstall command
- Would be nice if we had a way to see version of kinc
- Need consistency of what files are called HOT 2
- Clarification on --minexpr and --nan values HOT 1
- Consistency of --preout and --postout HOT 1
- Ask for visualization dependencies for KINC HOT 5
- Philosophical thought about the use of "Source" and "Target" labels HOT 4
- install issue
- Need a "version" command HOT 1
- Additional Space prior to every positive correlation value HOT 1
- Post processing with KINC.R changes formatting HOT 1
- KINC 3D viewer attempts to read in p_value as character string
- KINC 3D viewer can not read in non-csGCN KINC network
- Log file print line at start
- Palmetto install broken HOT 2
- How to extract KINC network with container?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kinc.