Muaxacker/ECMW-P

An imbalance-aware monthly early warning system for classifying crop market conditions in Ethiopia as Favorable or Unfavorable using historical market and climate data. The project applies CRISP-DM, handles class imbalance with SMOTE, and compares C4.5-inspired Decision Tree, PART-inspired Tree, and Naïve Bayes models. An interactive prototype prov # 🚀 How to Deploy This App To share this app as a "real-life" link with farmers and colleagues, follow these steps: ### Option 1: Vercel (Recommended - Free & Instant) 1. **Create a GitHub Repository**: Upload all these files (maintaining the folder structure) to a new GitHub repo. 2. **Link to Vercel**: Go to Vercel.com, sign up, and click "New Project". Select your GitHub repo. 3. **Configure Environment Variable**: - In the Vercel dashboard, go to **Settings > Environment Variables**. - Add a key named `API_KEY`. - Paste your **Google Gemini API Key** as the value. 4. **Deploy**: Click "Deploy". You will get a link like `crop-warning.vercel.app`. ### Option 2: Netlify (Free) 1. Drag and drop the folder containing these files into Netlify Drop. 2. Go to **Site Settings > Build & Deploy > Environment**. 3. Add the `API_KEY` variable. ### Mobile Installation Once the app is live at your link, users can: - **Android**: Open the link in Chrome, click the three dots, and select "Install App". - **iOS**: Open the link in Safari, click the Share icon, and select "Add to Home Screen". The app will then appear as a native app on their phone, complete with its own icon!