Indian Rental Price Predictor (Delhi, Mumbai, Pune)

A small machine learning project that predicts monthly rental prices for properties in three Indian cities using city-specific Random Forest regression models.

This repository includes the data, preprocessing notebook, trained models, and a Streamlit app to make predictions.

Quick start

1. Install dependencies:

   pip install -r requirements.txt

2. Prepare data and train models (required if model files are not present):

   • Open ds_lab_proj_new.ipynb in Jupyter or VS Code and run all cells.
   • This notebook performs cleaning, exploratory analysis, and trains three models. It saves the model files (rf_model_delhi.pkl, rf_model_mumbai.pkl, rf_model_pune.pkl) and a locations CSV used by the app.

3. Run the Streamlit app:

   streamlit run app.py

The app will open in your browser and let you input property features to get a monthly rental price prediction for the selected city.

Files in this repository

• ds_lab_proj_new.ipynb — Data cleaning, EDA, model training pipeline.
• app.py — Streamlit application that loads the trained models and serves predictions.
• requirements.txt — Python dependencies required to run the notebook and app.
• Indian_housing_Delhi_data.csv, Indian_housing_Mumbai_data.csv, Indian_housing_Pune_data.csv — Raw input datasets.
• df_city_locations_and_coords.csv — City location coordinates used by the app (may be generated by the notebook).
• .gitignore — Project ignore rules for Git.

If you ran the notebook, the following files will be created:

• rf_model_delhi.pkl, rf_model_mumbai.pkl, rf_model_pune.pkl — Serialized Random Forest models (one per city).