https://github.com/limix/ggp-poisson-example
Example of PoissonGP
https://github.com/limix/ggp-poisson-example
Last synced: 2 months ago
JSON representation
Example of PoissonGP
- Host: GitHub
- URL: https://github.com/limix/ggp-poisson-example
- Owner: limix
- License: mit
- Created: 2017-03-22T11:44:50.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2017-03-23T15:28:23.000Z (about 8 years ago)
- Last Synced: 2025-01-23T08:45:31.302Z (4 months ago)
- Language: Python
- Size: 4.88 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ggp-poisson-example
Example of GLMM for Poisson likelihood.
1. Install limix-inference
```bash
conda install -c conda-forge limix-inference
```
2. Clone this repository
```bash
git clone https://github.com/glimix/ggp-poisson-example.git
```
3. Create and run the example
```bash
cd ggp-poisson-example
python create_example.py
python run_example.py
```
That is it.
You should see something similar to
```
--- Model before optimization ---
LML: -493.26572309
Fixed-effect sizes: [ 0. 0. 0.]
Variances:
covariance0: 1.00000000
covariance1: 1.00000000
covariance2: 1.00000000
Eye : 1.00000000
...
--- Model after optimization ---
LML: -406.67731671
Fixed-effect sizes: [ 0.35329736 0.13210078 0.19191181]
Variances:
covariance0: 0.08680102
covariance1: 0.00266242
covariance2: 0.09787977
Eye : 0.01149269
```
The numbers don't need to match as the example itself
is stochastic.