ebenezer-ohenebeng/Time_estimate

The Accra Commute Estimator is a Flask-based web application that predicts the estimated arrival time for commuters in Accra. # 🕐 Time Estimator — Commute Arrival Predictor > A Flask-based machine learning web app that predicts your estimated arrival time based on departure time, transport mode, and location — built for commuters in Accra, Ghana. 🔗 **Live Demo:** time-estimate.onrender.com --- ## 📌 Overview Time Estimator is an end-to-end machine learning project that takes a commuter's inputs and returns a predicted arrival time. It was built as a **proof-of-concept prototype** to demonstrate a complete ML workflow — from data collection to cloud deployment. > ⚠️ **Note:** The dataset was collected from a small group of volunteers via SurveyCTO, so predictions are experimental rather than production-grade. The primary goal of this project is to showcase the full pipeline: data collection → model training → Flask integration → deployment. --- ## ✨ Features - ⏱ Departure time selection via Flatpickr (24-hour format) - 🚌 Multiple transport modes: Trotro, Taxi, Private Vehicle, Walking - 📍 Dropdowns for home and office locations across Accra - 🤖 ML-powered arrival time prediction - 📱 Responsive UI with persistent form state after submission - ☁️ Deployed and accessible via Render --- ## 🧠 Machine Learning Details | Property | Details | |---|---| | Data collection | SurveyCTO (manual, from volunteers) | | Dataset size | Small / experimental scale | | Preprocessing | Pandas | | Model framework | Scikit-learn | | Model serialization | Joblib (`.pkl`) | Because of the limited dataset size, this model is a **proof-of-concept** — not a fully optimized predictive system. See Future Improvements for the roadmap. --- ## 🛠 Tech Stack **Backend** — Flask · Pandas · Scikit-learn · Joblib **Frontend** — Bootstrap 5 · Flatpickr · Font Awesome (all via CDN) **Deployment** — Render **Data Collection** — SurveyCTO --- ## 🚀 Running Locally ### 1. Clone the repository ```bash git clone github.com cd time_estimate ``` ### 2. Create and activate a vir …