My internship learning journey for Data Science: Pandas analysis, visualization, Machine Learning and Neural Network projects (weather and disease).
Exploratory Data Analysis on Telecom Customer Churn to uncover key churn drivers, visualize trends, and suggest strategies for customer retention.
End to end NBA Injury Predictor with 4.78M record dataset, XGBoost, Random Forest, TensorFlow Neural Network, & Logistic Regression w/ 69% ROC-AUC. Built w/ serverless AWS Lambda deployment, S3 storage, Tableau dashboards & machine learning pipeline using Python, scikit-learn, TensorFlow, SMOTE class balancing & temporal validation methodology.
End-to-end EDA on a 3,000-row e-commerce dataset — statistical profiling, correlation analysis, hypothesis testing, seasonality discovery, and a 6-panel visualization suite built with Pandas, Scipy & Seaborn.
Data Science & Machine Learning Notebooks || Data Analysis & Visualization || EDA & Feature Engineering & Predictive Modeling.
The Loan Default Analysis project aims to identify key factors contributing to loan defaults by analyzing borrower profiles, financial data, and credit risk indicators. Using statistical methods, visualizations, and predictive modeling, the project provides insights to mitigate risks and improve lending strategies.
An intelligent Retrieval-Augmented Generation assistant that helps cybersecurity analysts search incidents, retrieve Standard Operating Procedures , answer security-related questions, and provide context-aware responses using a locally-hosted Large Language Model and a FAISS vector database. https://part4-ai-cybersecurity-api.onrender.com
Contents: Installation of Python libraries pandas, numpy, matplotlib & seaborn, Importing a library, Reading a file using a library
To associate your repository with the pandas-numpy-matplotlib-seaborn topic, visit your repo's landing page and select "manage topics."