nikbearbrown/INFO_7390_Art_and_Science_of_Data
Dec 2024 – Dec 2024
1 Month active
Languages Used
Jupyter NotebookMarkdownPythonShell
Technical Skills
API IntegrationBackend DevelopmentCausal InferenceClusteringData AnalysisData Engineering
riteshch123
PROFILE
Riteshch123
Ritesh Choudhary developed three core features for the nikbearbrown/INFO_7390_Art_and_Science_of_Data repository, focusing on reproducible analytics and modular project structure. He delivered a Hepatitis C causal inference notebook using Python, Jupyter Notebook, DoWhy, and EconML, enabling interpretable healthcare analytics through robust data preparation and analysis workflows. Ritesh also created a clustering techniques notebook with clear explanations and visualizations to support experimentation and learning. Additionally, he built a course suggestion chatbot leveraging Retrieval-Augmented Generation, data scraping, embeddings, and a Streamlit interface. His work emphasized maintainability, scientific computing best practices, and scalable repository organization for future subprojects.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
4Total
Bugs
0
Commits
4
Features
3
Lines of code
20,080
Activity Months1
Your Network
15 people
Work History
December 2024
4 Commits • 3 Features
Dec 1, 20242024-12 Monthly Summary for nikbearbrown/INFO_7390_Art_and_Science_of_Data Key focus this month was delivering end-to-end, reproducible analytics and educational notebooks, along with a scalable repo structure to support future subprojects. Features were prioritized to demonstrate robust, interpretable analytics and practical ML workflows in healthcare and education domains. Top achievements: - Hepatitis C Causal Inference Notebook delivered with DoWhy and EconML pipelines, including data preparation, EDA, and interpretable causal analysis to support healthcare decision-making. (Commit: eb95447ed948ef95ef0cb918176fc78cbf3d723a) - Group 2 Clustering Techniques Notebook added, featuring clustering algorithms with explanations, code, and visualizations to accelerate experimentation and learning. (Commit: 1938ec0da77684d12c5a4d53d2c5a8a1dae72dbf) - Course Suggestion Chatbot via Retrieval-Augmented Generation (RAG) introduced, including data scraping, embedding processing, and a Streamlit interface; repository scaffolding updated to register the chatbot subproject. (Commits: 9cac3ea887806cb13abf7799889125240c6cc752, b3fbc2eda35a8cbce10b84e80140beb8e35a2ae1) - Repository scaffolding and project structure improvements implemented to enable modular growth and easier onboarding of new subprojects. Major bugs fixed: - No major bugs fixed this month; notes reflect feature delivery and structural improvements to improve reproducibility and maintainability. Overall impact and accomplishments: - Expanded analytics capabilities in a healthcare context with reproducible notebooks and interpretable causal analyses. - Delivered practical ML workflows (clustering, RAG-based chatbot) that accelerate experimentation, learning, and lightweight product prototyping. - Strengthened software engineering discipline through improved repo scaffolding, documentation, and a modular project layout). Technologies and skills demonstrated: - Python, Jupyter notebooks, DoWhy, EconML for causal inference; data preparation, EDA, and interpretable analytics workflows. - Clustering algorithms and visualizations for Group 2 Notebook. - Retrieval-Augmented Generation (RAG), embeddings, data scraping, and Streamlit interface for the course chatbot. - Repository organization, scientific computing best practices, and Git-based collaboration. Business value: - Enables robust, transparent healthcare analytics to inform prediction and policy decisions. - Provides a scalable framework for experimentation and education, accelerating future feature work and collaborative learning.
4 Commits • 3 Features
Dec 1, 20242024-12 Monthly Summary for nikbearbrown/INFO_7390_Art_and_Science_of_Data Key focus this month was delivering end-to-end, reproducible analytics and educational notebooks, along with a scalable repo structure to support future subprojects. Features were prioritized to demonstrate robust, interpretable analytics and practical ML workflows in healthcare and education domains. Top achievements: - Hepatitis C Causal Inference Notebook delivered with DoWhy and EconML pipelines, including data preparation, EDA, and interpretable causal analysis to support healthcare decision-making. (Commit: eb95447ed948ef95ef0cb918176fc78cbf3d723a) - Group 2 Clustering Techniques Notebook added, featuring clustering algorithms with explanations, code, and visualizations to accelerate experimentation and learning. (Commit: 1938ec0da77684d12c5a4d53d2c5a8a1dae72dbf) - Course Suggestion Chatbot via Retrieval-Augmented Generation (RAG) introduced, including data scraping, embedding processing, and a Streamlit interface; repository scaffolding updated to register the chatbot subproject. (Commits: 9cac3ea887806cb13abf7799889125240c6cc752, b3fbc2eda35a8cbce10b84e80140beb8e35a2ae1) - Repository scaffolding and project structure improvements implemented to enable modular growth and easier onboarding of new subprojects. Major bugs fixed: - No major bugs fixed this month; notes reflect feature delivery and structural improvements to improve reproducibility and maintainability. Overall impact and accomplishments: - Expanded analytics capabilities in a healthcare context with reproducible notebooks and interpretable causal analyses. - Delivered practical ML workflows (clustering, RAG-based chatbot) that accelerate experimentation, learning, and lightweight product prototyping. - Strengthened software engineering discipline through improved repo scaffolding, documentation, and a modular project layout). Technologies and skills demonstrated: - Python, Jupyter notebooks, DoWhy, EconML for causal inference; data preparation, EDA, and interpretable analytics workflows. - Clustering algorithms and visualizations for Group 2 Notebook. - Retrieval-Augmented Generation (RAG), embeddings, data scraping, and Streamlit interface for the course chatbot. - Repository organization, scientific computing best practices, and Git-based collaboration. Business value: - Enables robust, transparent healthcare analytics to inform prediction and policy decisions. - Provides a scalable framework for experimentation and education, accelerating future feature work and collaborative learning.
December 2024
Activity
Loading activity data...
Quality Metrics
Correctness85.0%
Maintainability85.0%
Architecture85.0%
Performance70.0%
AI Usage35.0%
Skills & Technologies
Programming Languages
Jupyter NotebookMarkdownPythonShell
Technical Skills
API IntegrationBackend DevelopmentCausal InferenceClusteringData AnalysisData EngineeringData ScienceDevOpsDoWhyEconMLFrontend DevelopmentJupyter NotebookMachine LearningMatplotlibNatural Language Processing
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline