Learning from Networks Project

Project structure

/data/ -> Folder for the datasets, before(.csv, .tar.gz, etc..) and after (.graphml) preprocessing
/exp_shuffles/ -> Folder for PDA experiment result binaries
/experiment/ -> Folder for main experiment result binaries
/figures/ -> Folder for saved figures of plots
/test_notebooks/ -> Folder for the notebooks used for testing
preprocessing.ipynb -> Preprocessing of the datasets
run_experiment.ipynb -> Compute counts and significance of motifs in the datasets and save the results as binary files.
compare_z_scores.ipynb -> One on one comparison of motifs
read_and_plot.ipynb -> Batch processing and plotting
example.ipynb -> Example experiment on Escherichia Coli dataset
performance_degradation_analysis.ipynb -> Experiment on performance degration of motif_significance() when using speed-up parameters

Hopefully this works:

conda create --name fl-gt --file requirements.txt
conda activate fl-gt
jupyter notebook

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
data		data
test_notebooks		test_notebooks
.gitignore		.gitignore
compare_z_scores.ipynb		compare_z_scores.ipynb
example.ipynb		example.ipynb
performance_degradation.ipynb		performance_degradation.ipynb
preprocessing.ipynb		preprocessing.ipynb
read_and_plot.ipynb		read_and_plot.ipynb
readme.md		readme.md
requirements.txt		requirements.txt
run_experiment.ipynb		run_experiment.ipynb