Rapid antibiotic susceptibility testing and species identification for mixed samples by Praneeth Karempudi (13721170)

“…This experiment as mulitple directories containing data (data directory), dbscan-python (cloned code for paralled-dbscan implementation, compile for your own architectures), narsil2 (our pipeline code for all the analysis done in the paper, you will have to install this package in an environment using anaconda from .yml files provided), notebooks (notebooks for running various tasks and some sample notebooks), saved_models (directory containing all the models applied in the paper). …”

Map Matching on Low Sampling Rate Trajectories Through Deep Inverse Reinforcement Learning and Multi Intention Modeling by Reza Safarzadeh (18072472)

“…</p><p>---------</p><p dir="ltr">Sample data are provided in the "Data" folder to show how the code works.</p><p dir="ltr">This repository contains the following Python codes:</p><p><br></p><p dir="ltr"><br></p><ul><li>`environmnet.py`: Contains the implementation of the environment used for IRL. …”

Algoritmo de clasificación de expresiones de odio por intensidades en español (Algorithm for classifying hate expressions by intensities in Spanish) by Xiomara Blanco (18598099)

“…</li></ul><h2>Métricas de Evaluación</h2><p dir="ltr">El modelo se evalúa utilizando:</p><ul><li>Macro recall, precision, and F1-score</li><li>One-vs-Rest AUC</li><li>Accuracy</li><li>Métricas por clase</li><li>Matriz de confusión</li></ul><h2>Requerimientos</h2><p dir="ltr">Se requiere los siguientes paquetes de Python (consulte requirements.txt para ver la lista completa):</p><ul><li>TensorFlow</li><li>Transformers</li><li>scikit-learn</li><li>pandas</li><li>datasets</li><li>matplotlib</li><li>seaborn</li></ul><h2>Uso</h2><p dir="ltr">El modelo espera datos de entrada con las siguientes especificaciones:</p><ol><li><b>Formato de datos</b>:</li><li><ul><li>Archivo CSV o DataFrame de Pandas</li><li>Nombre de columna obligatorio: <code>text</code> (tipo cadena)</li><li>Nombre de columna opcional: <code>label</code> (tipo entero, 0, 1, 2 o 3) si está disponible para la evaluación</li></ul></li><li><b>Preprocesamiento de texto</b>:</li><li><ul><li>El texto se convertirá automáticamente a minúsculas durante el procesamiento</li><li>Longitud máxima: 128 tokens (los textos más largos se truncarán)</li><li>Los caracteres especiales, las URL y los emojis deben permanecer en el texto (el tokenizador los gestiona)</li></ul></li><li><b>Codificación de etiquetas</b>:</li><li><ul><li><code>0</code> = Intensidad 1 : Odio asociado a mensajes incívico</li><li><code>1</code> = Intensidad 2 : Odio asociado a mensajes mal intencionados o con expresiones abusivas</li><li><code>2</code> = Intensidad 3 : Odio asociado a insultos</li><li><code>3</code> = Intensidad 4 : Odio asociado a amenazas veladas o explícitas</li></ul></li></ol><p dir="ltr">El proceso de creación de este algoritmo se expone en el informe técnico localizado en: Blanco-Valencia, X., De Gregorio-Vicente, O., Ruiz Iniesta, A., & Said-Hung, E. (2025). …”

Global Aridity Index and Potential Evapotranspiration (ET0) Database: Version 3.1 by Robert Zomer (12796235)

“…</p><p dir="ltr">The Python programming source code used to run the calculation of ET0 and AI is provided and available online on Figshare at:</p><p dir="ltr">https://figshare.com/articles/software/Global_Aridity_Index_and_Potential_Evapotranspiration_Climate_Database_v3_-_Algorithm_Code_Python_/20005589</p><p dir="ltr">Peer-Review Reference and Proper Citation:</p><p dir="ltr">Zomer, R.J.; Xu, J.; Trabuco, A. 2022. …”

Neural-Signal Tokenization and Real-Time Contextual Foundation Modelling for Sovereign-Scale AGI Systems by Lakshit Mathur (20894549)

“…</p><p dir="ltr"><b>Availability</b> — The repository includes LaTeX sources, trained model checkpoints, Python/PyTorch code, and synthetic datasets. Data are released under a Creative Commons Attribution-NonCommercial-4.0 (CC BY-NC 4.0) license; code under MIT License.…”

Cycle data for "Growth and arrest of topological cycles in small physical networks" by Tim Sirk (8817251)

“…</div><div><br></div><div>The vitroid code for cycle counting: <a href="https://github.com/vitroid/CountRings">https://github.com/vitroid/CountRings</a></div><br><div>LAMMPS was used for molecular dynamics simulations: <a href="https://lammps.sandia.gov/">https://lammps.sandia.gov/</a></div><div><br><div>The python library SciPy was used for numerical fits of a Guassian to this data: <a href="https://www.scipy.org/">https://www.scipy.org/</a></div></div><div><div><div> </div></div></div></div>…”

Numerical analysis and modeling of water quality indicators in the Ribeirão João Leite reservoir (Goiás, Brazil) by Amanda Bueno de Moraes (22559249)

“…The code implements a statistical–computational workflow for parameter selection (VIF, Bartlett and KMO tests, PCA and FA with <i>varimax</i>) and then trains and evaluates machine-learning models to predict three key physico-chemical indicators: turbidity, true color, and total iron. …”

Missing Value Imputation in Relational Data Using Variational Inference by Simon Fontaine (7046618)

“…Additional results, implementation details, a Python implementation, and the code reproducing the results are available online. …”

Data from: Circadian activity predicts breeding phenology in the Asian burying beetle <i>Nicrophorus nepalensis</i> by Hao Chen (20313552)

“…</p><p dir="ltr">The dataset includes:</p><ol><li>Raw locomotor activity measurements (.txt files) with 1-minute resolution</li><li>Breeding experiment data (Pair_breeding.csv) documenting nest IDs, population sources, photoperiod treatments, and breeding success</li><li>Activity measurement metadata (Loc_metadataset.csv) containing detailed experimental parameters and daily activity metrics extracted using tsfresh</li></ol><p dir="ltr">The repository also includes complete analysis pipelines implemented in both Python (3.8.8) and R (4.3.1), featuring:</p><ul><li>Data preprocessing and machine learning model development</li><li>Statistical analyses</li><li>Visualization scripts for generating Shapley plots, activity pattern plots, and other figures</li></ul><p></p>…”

Probabilistic-QSR-GeoQA by Mohammad Kazemi (19442467)

“…<p dir="ltr">The code and data are related to the paper Mohammad Kazemi Beydokhti, Matt Duckham, Amy L. …”

EGERL by Eric Liu (19428442)

“…<pre>The source codes that support the paper <b>'</b><b>Synthesizing event semantics for geographical entity representation'</b><br><br>This program provides the implementation of our EGERL as described in our paper.…”

<i>PyRates</i> software structure. by Richard Gast (8129451)

“…<p><b>(A)</b> Depiction of the user interface: <i>PyRates</i> models are implemented via different templates that can be defined via a <i>YAML</i> or <i>Python</i> interface. …”

Void-Center Galaxies and the Gravity of Probability Framework: Pre-DESI Consistency with VGS 12 and NGC 6789 by Jordan Waters (21620558)

“…<br><br><br><b>ORCID ID: https://orcid.org/0009-0009-0793-8089</b><br></p><p dir="ltr"><b>Code Availability:</b></p><p dir="ltr"><b>All Python tools used for GoP simulations and predictions are available at:</b></p><p dir="ltr"><b>https://github.com/Jwaters290/GoP-Probabilistic-Curvature</b><br><br>The Gravity of Probability framework is implemented in this public Python codebase that reproduces all published GoP predictions from preexisting DESI data, using a single fixed set of global parameters. …”

Spelling tree for the kernel (ha). by Tyler J. Gray (6162674)

“…We note that Mill has written a more recent paper based largely on this earlier work specialized for Python [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0232938#pone.0232938.ref039" target="_blank">39</a>], and an implementation for it as well [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0232938#pone.0232938.ref040" target="_blank">40</a>], but they both contain algorithmic bugs (detailed in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0232938#pone.0232938.s003" target="_blank">S3 Appendix</a>).…”

Examples of advanced and upcoming CRIMSON features. by Christopher J. Arthurs (10777046)

“…<p><b>A:</b> Custom aortic valve model implementation using the NEBCT and Python Control Systems Framework. …”

Genosophus: A Dynamical-Systems Diagnostic Engine for Neural Representation Analysis by Alan Glanz (22109698)

“…</p><h2><b>Included Files</b></h2><h3><b>1. </b><code><strong>GenosophusV2.py</strong></code></h3><p dir="ltr">Executable Python implementation of the Genosophus Engine.…”

Algoritmo de clasificación de expresiones de odio por tipos en español (Algorithm for classifying hate expressions by type in Spanish) by Daniel Pérez Palau (11097348)

“…</li></ul><p dir="ltr"><b>File Structure</b></p><p dir="ltr">The code generates and saves:</p><ul><li>Weights of the trained model (.h5)</li><li>Configured tokenizer</li><li>Training history in CSV</li><li>Requirements file</li></ul><p dir="ltr"><b>Important Notes</b></p><ul><li>The model excludes category 2 during training</li><li>Implements transfer learning from a pre-trained model for binary hate detection</li><li>Includes early stopping callbacks to prevent overfitting</li><li>Uses class weighting to handle category imbalances</li></ul><p dir="ltr">The process of creating this algorithm is explained in the technical report located at: Blanco-Valencia, X., De Gregorio-Vicente, O., Ruiz Iniesta, A., & Said-Hung, E. (2025). …”

Workflow from B-mode ultrasound image acquisition and processing to machine-learning (ML) model training and real-time muscle length tracking. by Luis G. Rosa (2080873)

“…D-E) Images in each frame are cropped and down-sampled using Python code to implement open-source functions. F) A machine learning (ML) model is trained using outputs from C and E. …”

Algoritmo de detección de odio en español (Algorithm for detection of hate speech in Spanish) by Elias Said-Hung (10790310)

“…</li></ul><h2>Training Process</h2><h3>Pre-entrenamiento</h3><ul><li>Batch size: 16</li><li>Epochs: 5</li><li>Learning rate: 2e-5 with 10% warmup steps</li><li>Early stopping with patience=2</li></ul><h3>Fine-tuning</h3><ul><li>Batch size: 128</li><li>Epochs: 5</li><li>Learning rate: 2e-5 with 10% warmup steps</li><li>Early stopping with patience=2</li><li>Métricas personalizadas:</li><li><ul><li>Recall for non-hate class</li><li>Precision for hate class</li><li>F1-score (weighted)</li><li>AUC-PR</li><li>Recall at precision=0.9 (non-hate)</li><li>Precision at recall=0.9 (hate)</li></ul></li></ul><h2>Métricas de Evaluación</h2><p dir="ltr">El modelo se evalúa utilizando:</p><ul><li>Macro recall, precision, and F1-score</li><li>One-vs-Rest AUC</li><li>Accuracy</li><li>Métricas por clase</li><li>Matriz de confusión</li></ul><h2>Requerimientos</h2><p dir="ltr">Se requiere los siguientes paquetes de Python (consulte requirements.txt para ver la lista completa):</p><ul><li>TensorFlow</li><li>Transformers</li><li>scikit-learn</li><li>pandas</li><li>datasets</li><li>matplotlib</li><li>seaborn</li></ul><h2>Uso</h2><p dir="ltr">El modelo espera datos de entrada con las siguientes especificaciones:</p><ol><li><b>Formato de datos</b>:</li></ol><ul><li>Archivo CSV o DataFrame de Pandas</li><li>Nombre de columna obligatorio: <code>text</code> (tipo cadena)</li><li>Nombre de columna opcional: <code>label</code> (tipo entero, 0 o 1) si está disponible para la evaluación</li></ul><ol><li><b>Preprocesamiento de texto</b>:</li></ol><ul><li>El texto se convertirá automáticamente a minúsculas durante el procesamiento</li><li>Longitud máxima: 128 tokens (los textos más largos se truncarán)</li><li>Los caracteres especiales, las URL y los emojis deben permanecer en el texto (el tokenizador los gestiona)</li></ul><ol><li><b>Codificación de etiquetas</b>:</li></ol><ul><li><code>0</code> = Sin contenido de odio (incluido contenido neutral/positivo)</li><li><code>1</code> = Incitación al odio</li></ul><p dir="ltr">El proceso de creación de este algoritmo se expone en el informe técnico localizado en: Blanco-Valencia, X., De Gregorio-Vicente, O., Ruiz Iniesta, A., & Said-Hung, E. (2025). …”

CAR-1SDM-published by Juan Escamilla-Molgora (11974253)

“…<p>This repository contains the code and data to reproduce the results published in the paper: [[doi:<a href="https://doi.org/10.1101/2021.06.28.450233" rel="nofollow">https://doi.org/10.1101/2021.06.28.450233</a> ] entitled: "A joint distribution framework to improve presence-only species distribution models by exploiting opportunistic surveys" (Escamilla Mólgora et. al, 2022).…”