DataWhisper 📊

🔗 Live Demo: : https://datawhisper-elnvwkoaq6og6w2kzwid2n.streamlit.app

A full-stack AI-powered web application built with Streamlit that allows users to upload a CSV file and automatically generates insights, visualizations, and an interactive chat interface for data exploration.

Features

• Exploratory Data Analysis (EDA): Automatic generation of summary statistics, missing value heatmaps, correlation matrices, and distribution/count plots.
• AI-Powered Insights: Get plain-English insights (trends, correlations, anomalies) generated by OpenAI's GPT.
• Chat with Data: An interactive chat interface powered by LangChain's Pandas Dataframe Agent to ask questions directly about your data.
• Recommendations: Actionable preprocessing steps (handling missing values, outliers) suggested by AI.
• Report Export: Generate and download a comprehensive HTML report containing your visualizations and AI insights.

Project Structure

├── app.py                     # Main Streamlit application
├── requirements.txt           # Project dependencies
├── README.md                  # Project documentation
├── sample_data/
│   └── titanic.csv            # Sample dataset for testing
└── src/
    ├── chat.py                # LangChain Pandas Agent integration
    ├── data_loader.py         # CSV file parsing and basic info
    ├── eda.py                 # Matplotlib/Seaborn visualization logic
    ├── llm_insights.py        # LLM integration for dataset insights
    ├── recommendations.py     # LLM integration for data recommendations
    └── report_generator.py    # HTML report generation logic