PranayN23/NFLResourceAnalysis
Oct 2024 – Feb 2026
3 Months active
Languages Used
CSVPythonJSON
Technical Skills
CSV ManipulationData AnalysisData EngineeringData ProcessingPandasData Science
siddarthnachannagari
PROFILE
Siddarthnachannagari
Developed end-to-end data engineering and machine learning features for the PranayN23/NFLResourceAnalysis repository, focusing on NFL running back performance analytics. Built reproducible pipelines in Python and Pandas to process, aggregate, and merge multi-year CSV datasets, enabling consistent trend analysis and team-level insights. Delivered machine learning models using TensorFlow and PyTorch, including RNNs and transformer-based architectures, to predict player outcomes and visualize team correlations. Enhanced model accuracy through feature engineering and stacking techniques, integrating Time2Vec signals with XGBoost. Emphasized maintainability by documenting workflows and ensuring reproducibility, supporting data-driven decision-making for player valuation and strategic team analysis without reported bugs.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
19Total
Bugs
0
Commits
19
Features
5
Lines of code
24,814
Activity Months3
Your Network
128 peopleShared Repositories
10
Work History
February 2026
2 Commits • 2 Features
Feb 1, 2026February 2026 monthly summary for NFLResourceAnalysis. Focused on delivering high-impact ML features with clear documentation and measurable accuracy improvements. No major bugs reported this month; emphasis on performance, reliability, and maintainability.
2 Commits • 2 Features
Feb 1, 2026February 2026 monthly summary for NFLResourceAnalysis. Focused on delivering high-impact ML features with clear documentation and measurable accuracy improvements. No major bugs reported this month; emphasis on performance, reliability, and maintainability.
February 2026
November 2024
13 Commits • 2 Features
Nov 1, 2024November 2024 — NFLResourceAnalysis: Delivered end-to-end, ML-powered prediction and visualization capabilities for NFL running backs and team-level correlations. The work supports data-driven decision-making for player valuation and strategic insights for teams. Key deliverables include R^2-based performance metrics, RNN/MLP visualizations, and robust graphs with reproducible notebooks. Resolved critical RNN graph KeyError and produced barplots comparing predicted vs actual outcomes (PFF, Net EPA). The initiatives strengthened data reliability, analytics speed, and stakeholder confidence in model-driven recommendations.
November 2024
13 Commits • 2 Features
Nov 1, 2024November 2024 — NFLResourceAnalysis: Delivered end-to-end, ML-powered prediction and visualization capabilities for NFL running backs and team-level correlations. The work supports data-driven decision-making for player valuation and strategic insights for teams. Key deliverables include R^2-based performance metrics, RNN/MLP visualizations, and robust graphs with reproducible notebooks. Resolved critical RNN graph KeyError and produced barplots comparing predicted vs actual outcomes (PFF, Net EPA). The initiatives strengthened data reliability, analytics speed, and stakeholder confidence in model-driven recommendations.
October 2024
4 Commits • 1 Features
Oct 1, 2024October 2024: Delivered foundational data engineering work for NFL running back performance analysis in PranayN23/NFLResourceAnalysis. Implemented data processing tooling and datasets for 2018–2022, enabling consistent, auditable analytics and trend assessment. Key deliverables include rb_combine.py for weighted averages and YoY changes, rb_combined_df.py to merge raw CSVs into a single DataFrame, and additional CSVs aggregating data by player and by team for the same period. Four commits completed to create and aggregate the dataset.
4 Commits • 1 Features
Oct 1, 2024October 2024: Delivered foundational data engineering work for NFL running back performance analysis in PranayN23/NFLResourceAnalysis. Implemented data processing tooling and datasets for 2018–2022, enabling consistent, auditable analytics and trend assessment. Key deliverables include rb_combine.py for weighted averages and YoY changes, rb_combined_df.py to merge raw CSVs into a single DataFrame, and additional CSVs aggregating data by player and by team for the same period. Four commits completed to create and aggregate the dataset.
October 2024
Activity
Loading activity data...
Quality Metrics
Correctness87.4%
Maintainability86.4%
Architecture83.2%
Performance84.2%
AI Usage26.2%
Skills & Technologies
Programming Languages
CSVJSONPython
Technical Skills
CSV ManipulationData AnalysisData EngineeringData ProcessingData ScienceData VisualizationDeep LearningFeature EngineeringKerasMachine LearningMatplotlibModel EvaluationModel OptimizationPandasPyTorch
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline