AabidMK/SafeBite_Infosys_Internship_Oct2024
Nov 2024 – Nov 2024
1 Month active
Languages Used
Jupyter NotebookPython
Technical Skills
API DevelopmentData AnalysisData ScienceFlaskMachine LearningModel Deployment
sudhanshu0182
PROFILE
Sudhanshu0182
Aabid MK developed an AI model validation workflow for SafeBite, focusing on reproducibility and seamless integration between development and production. In the AabidMK/SafeBite_Infosys_Internship_Oct2024 repository, Aabid introduced a Jupyter Notebook that loads trained models and encoders using pickle, updates file paths for Flask API compatibility, and demonstrates an end-to-end prediction pipeline on sample data. The workflow exports prediction results to CSV, supporting rapid validation and reporting. Leveraging Python, Pandas, and Scikit-learn, Aabid’s work addressed the need for reliable model testing artifacts and improved the handoff process by aligning notebook outputs with the deployed API environment.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
1Total
Bugs
0
Commits
1
Features
1
Lines of code
1,122
Activity Months1
Your Network
7 peopleSame Organization
@rcciit.org.in1
Work History
November 2024
1 Commits • 1 Features
Nov 1, 2024November 2024 (Month: 2024-11) — Delivered a focused AI-model validation workflow for SafeBite. Key feature introduced: AI Model Testing Notebook with Pickle-based Model/Encoder Loading. The notebook demonstrates an end-to-end prediction flow on sample data, loads the trained model and encoder via pickle with updated file paths in the Flask API, and saves prediction results to a CSV for quick validation and reporting. This work enhances model validation, improves reproducibility, and tightens the dev-prod handoff by aligning testing artifacts with the API integration. Related work is in repo AabidMK/SafeBite_Infosys_Internship_Oct2024. Commits include: 4840b16f0a48b3a5b737e2e946bac01366401c9e ("Added model testing file").
1 Commits • 1 Features
Nov 1, 2024November 2024 (Month: 2024-11) — Delivered a focused AI-model validation workflow for SafeBite. Key feature introduced: AI Model Testing Notebook with Pickle-based Model/Encoder Loading. The notebook demonstrates an end-to-end prediction flow on sample data, loads the trained model and encoder via pickle with updated file paths in the Flask API, and saves prediction results to a CSV for quick validation and reporting. This work enhances model validation, improves reproducibility, and tightens the dev-prod handoff by aligning testing artifacts with the API integration. Related work is in repo AabidMK/SafeBite_Infosys_Internship_Oct2024. Commits include: 4840b16f0a48b3a5b737e2e946bac01366401c9e ("Added model testing file").
November 2024
Activity
Loading activity data...
Quality Metrics
Correctness80.0%
Maintainability80.0%
Architecture80.0%
Performance80.0%
AI Usage80.0%
Skills & Technologies
Programming Languages
Jupyter NotebookPython
Technical Skills
API DevelopmentData AnalysisData ScienceFlaskMachine LearningModel DeploymentPandasPythonScikit-learn
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline