Version submitted for review

.gitignore

@@ -0,0 +1,5 @@
+**/.DS_Store
+.ipynb_checkpoints
+.png
+__pycache__
+**/.nfs*

Dockerfile-jupyter

@@ -0,0 +1,5 @@
+# Start from a core stack version
+FROM jupyter/scipy-notebook:python-3.10.6
+
+COPY requirements.txt /tmp/
+RUN conda install --file /tmp/requirements.txt

README.md

@@ -0,0 +1,55 @@
+[![DOI](https://img.shields.io/badge/DOI-arXiv-red)](https://arxiv.org/abs/2305.06624)
+[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Ejmric/triFastSTMF/HEAD)
+
+# triFastSTMF: Matrix tri-factorization over the tropical semiring
+
+triFastSTMF is a tri-factorization approach for matrix approximation and prediction based on Fast Sparse Tropical Matrix Factorization (FastSTMF).
+
+For details, please refer to Amra Omanović, Polona Oblak, and Tomaž Curk (2023). Matrix tri-factorization over the tropical
+semiring. The preprint is available in [arXiv:2305.06624](https://arxiv.org/abs/2305.06624). If you use this work, please cite:
+```
+@misc{omanovic2023triFastSTMF,
+      title={Matrix tri-factorization over the tropical semiring}, 
+      author={Amra Omanović and Polona Oblak and Tomaž Curk},
+      year={2023},
+      eprint={2305.06624},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+### Real data
+We downloaded the real-world interaction dataset of an ant colony named "insecta-ant-colony3" [[1]](#1) from "Animal Social Networks" data collection on http://networkrepository.com [[2]](#2). Additional preprocessing before running our experiments is explained in the paper.
+
+### Jupyter notebooks
+The notebooks are independent and can be run in any order.
+
+- [preprocessing_real_data.ipynb](https://github.com/Ejmric/triFastSTMF/blob/main/preprocessing_real_data.ipynb): Presents the preprocessing of the real-world interaction dataset of an ant colony.
+- [heatmaps.ipynb](https://github.com/Ejmric/triFastSTMF/blob/main/heatmaps.ipynb): Presents the analysis of ants' behavioral patterns over 41 days.
+- [real_exps.ipynb](https://github.com/Ejmric/triFastSTMF/blob/main/real_exps.ipynb): Presents the experiments on real data.
+- [synthetic_network.ipynb](https://github.com/Ejmric/triFastSTMF/blob/main/synthetic_network.ipynb): Presents the analysis of four-partition network construction.
+
+
+### Use
+```
+import numpy.ma as ma
+import numpy as np
+from triFastSTMF import triFastSTMF
+
+data = ma.array(np.random.rand(100,100), mask=np.zeros((100,100)))
+model = triFastSTMF(rank_1 = 5, rank_2 = 3, initialization="random_vcol", threshold=100)
+model.fit(data)
+approx = model.predict_all()
+```
+
+### References
+
+<a id="1">[1]</a> 
+D. P. Mersch, A. Crespi, and L. Keller (2013). [Tracking individuals shows spatial
+fidelity is a key regulator of ant social organization](https://www.science.org/doi/10.1126/science.1234316). Science, vol. 340, no.
+6136, pp. 1090–1093.
+
+<a id="2">[2]</a> 
+R. A. Rossi and N. K. Ahmed (2015) [The network data repository with
+interactive graph analytics and visualization](http://networkrepository.com). AAAI. [Online].
+Available: http://networkrepository.com

data/approx_errors_pseudo.csv

@@ -0,0 +1,25 @@
+8.886425028750360866e+01
+8.056476518991343028e+01
+8.667987165705456221e+01
+9.063791279901336395e+01
+8.846938459269098587e+01
+8.477399856633218178e+01
+5.864488295943305474e+01
+5.784063584216792719e+01
+9.063438066258521530e+01
+7.527091361422725413e+01
+9.253472336822852640e+01
+9.463728720105470416e+01
+8.333194545710165357e+01
+9.837690220243010231e+01
+7.400474455184459543e+01
+9.884296117057488118e+01
+8.291396623925186304e+01
+8.042784439977856437e+01
+7.798452957697963939e+01
+7.934968391409306321e+01
+8.410075823804683637e+01
+1.007131261748051543e+02
+8.518544151255655095e+01
+8.947631948744191277e+01
+9.010640292522195693e+01

data/approx_errors_random.csv

@@ -0,0 +1,25 @@
+1.571757755175026432e+02
+1.084801383992737414e+02
+9.759804918085848158e+01
+7.500456727017970593e+01
+1.048478402712563167e+02
+8.186838426889237041e+01
+9.549045385641257155e+01
+1.297530262379193857e+02
+1.299447669194628361e+02
+1.074498564150690214e+02
+1.126064502034146244e+02
+1.301354889740836995e+02
+1.025994543764531102e+02
+1.453258467277164243e+02
+1.208473858339098683e+02
+1.107657390718628534e+02
+2.292047788709625706e+02
+1.063278423089237492e+02
+1.174040658589069892e+02
+1.426166265972485121e+02
+9.555865609709759667e+01
+9.312668406186824654e+01
+9.484670206259370673e+01
+1.404329023688364657e+02
+1.243191270191487234e+02