You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This repository hosts a project that enables efficient YouTube data extraction, storage, and analysis. It leverages SQL, MongoDB, and Streamlit to develop a user-friendly application for collecting and visualizing data from YouTube channels.
Built an interactive Tableau dashboard to analyze the Airbnb data extracted from MongoDB Atlas. Developed a Streamlit application for trend analysis, pattern recognition, and data insights using EDA. Explored variations in price, location, property type, and seasons through dynamic plots and charts.
Developed a Marathi speech-to-text application using the Hugging Face whisper ASR models. Trained the model with a custom audio dataset and fine-tuned it for optimized performance. Deployed the model on the Hugging Face Model Hub, achieving a WER of 0.74 for the base model.
Build a machine learning model to predict weekly sales with 97.4% accuracy. Integrated Exploratory Data Analysis tools to analyze trends, patterns, and actionable insights. The solution enables detailed sales comparisons, evaluates feature impacts and ranges, and identifies top performers, greatly enhancing decision-making in the retail industries.
Developed a Streamlit application for analyzing transactions and user data from the Pulse dataset. Explored data insights on states, years, quarters, districts, transaction types, and brands through EDA. Visualized trends and patterns using plots and charts to optimize decision-making in the Fintech industry.