Initial commit: Sentiment analysis app (models on HuggingFace)

.gitignore

@@ -0,0 +1,26 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Virtual environments
+venv/
+env/
+ENV/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Testing
+.pytest_cache/
+.coverage
+
+# Logs
+*.log

DEPLOY.md

@@ -0,0 +1,110 @@
+# 🚀 Deployment Guide - Using HuggingFace Models
+
+## ✅ Perfect Setup!
+
+You've uploaded your models to HuggingFace at: **`anis80/anisproject`**
+
+The app is now configured to download models from there automatically!
+
+---
+
+## 📤 Deploy to Render (Recommended - Free)
+
+### Step 1: Push to GitHub
+
+```powershell
+cd e:\anis
+
+# Add GitHub remote (replace YOUR_USERNAME)
+git remote add origin https://github.com/YOUR_USERNAME/sentiment-analysis-backend.git
+git branch -M main
+
+# Push to GitHub
+git push -u origin main
+```
+
+### Step 2: Deploy to Render
+
+1. Go to: **https://render.com**
+2. Sign up with GitHub
+3. Create **"New Web Service"**
+4. Connect your `sentiment-analysis-backend` repository
+5. Configure:
+   - **Name**: `sentiment-analysis-api`
+   - **Runtime**: `Python 3`
+   - **Build Command**: `pip install -r requirements.txt`
+   - **Start Command**: `uvicorn app:app --host 0.0.0.0 --port $PORT`
+   - **Instance Type**: **Free**
+6. Click **"Create Web Service"**
+
+### Step 3: Wait for Deployment (3-5 minutes)
+
+Your API will be live at: `https://sentiment-analysis-api-XXXX.onrender.com`
+
+---
+
+## 🌐 Alternative: Deploy to HuggingFace Spaces
+
+Since your models are already on HuggingFace, you can also deploy there:
+
+### Create Space
+
+1. Go to: https://huggingface.co/new-space
+2. Name: `sentiment-analysis-api`
+3. SDK: **Docker**
+4. Hardware: **CPU basic (Free)**
+
+### Push Code
+
+```powershell
+cd e:\anis
+
+# Add HuggingFace remote
+git remote add hf https://huggingface.co/spaces/anis80/sentiment-analysis-api
+git push hf main
+```
+
+---
+
+## ✅ Benefits of This Approach
+
+- ✅ **No large files in repository** (only ~10KB of code)
+- ✅ **Models downloaded on startup** from HuggingFace
+- ✅ **Works on any platform** (Render, HuggingFace, Railway, etc.)
+- ✅ **Easy model updates** - just update on HuggingFace
+- ✅ **Free deployment** on both platforms
+
+---
+
+## 🧪 Test Locally First
+
+```powershell
+cd e:\anis
+pip install -r requirements.txt
+python app.py
+```
+
+Visit: http://localhost:7860/docs
+
+---
+
+## 📝 Update Frontend
+
+Once deployed, update `index.html` lines 72-73:
+
+```javascript
+const predictApi = 'https://YOUR_DEPLOYMENT_URL/predict';
+const statusApi = 'https://YOUR_DEPLOYMENT_URL/status';
+```
+
+Then deploy frontend to Vercel!
+
+---
+
+## 💰 Cost: $0/month 🎉
+
+Both Render and HuggingFace offer free tiers perfect for this project!
+
+---
+
+**Ready to deploy?** Choose Render or HuggingFace and follow the steps above! 🚀

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy models and application
+COPY models-20260120T133709Z-3-002 models-20260120T133709Z-3-002
+COPY app.py .
+
+# Expose port 7860 (HuggingFace Spaces default)
+EXPOSE 7860
+
+# Run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

Procfile

@@ -0,0 +1 @@
+web: uvicorn app:app --host 0.0.0.0 --port $PORT

README.md

@@ -0,0 +1,56 @@
+# Sentiment Analysis API
+
+A FastAPI-based sentiment analysis service using ensemble machine learning models (KNN, Random Forest, Extra Trees).
+
+## Features
+
+- **Fast predictions** using pre-trained ML models
+- **RESTful API** with automatic documentation
+- **CORS enabled** for web frontend integration
+- **Ensemble learning** for improved accuracy
+
+## API Endpoints
+
+### `GET /`
+Health check and API information
+
+### `GET /status`
+Returns model status and readiness
+
+### `POST /predict`
+Analyzes sentiment of input text
+
+**Request body:**
+```json
+{
+  "text": "Your text here"
+}
+```
+
+**Response:**
+```json
+{
+  "predicted_sentiment": "positive",
+  "input_text": "Your text here"
+}
+```
+
+## Models
+
+This API uses three pre-trained models:
+- **Label Encoder**: Encodes sentiment labels
+- **TF-IDF Vectorizer**: Converts text to numerical features
+- **Voting Classifier**: Ensemble of KNN, Random Forest, and Extra Trees
+
+## Local Development
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+The API will be available at `http://localhost:7860`
+
+## Documentation
+
+Interactive API documentation available at `/docs` (Swagger UI) and `/redoc` (ReDoc)

START_HERE.md

@@ -0,0 +1,49 @@
+# 🎯 Quick Deploy - 3 Simple Steps
+
+## ✅ Your Setup
+- Models: `anis80/anisproject` on HuggingFace ✅
+- Backend: Ready to deploy (downloads models automatically)
+- Frontend: Ready for Vercel
+
+---
+
+## 🚀 Deploy in 3 Steps
+
+### Step 1: Push to GitHub (2 min)
+```powershell
+cd e:\anis
+git remote add origin https://github.com/YOUR_USERNAME/sentiment-backend.git
+git branch -M main
+git push -u origin main
+```
+
+### Step 2: Deploy Backend (3 min)
+
+**Option A - Render (Recommended):**
+1. https://render.com → Sign up with GitHub
+2. New Web Service → Select your repo
+3. Start: `uvicorn app:app --host 0.0.0.0 --port $PORT`
+4. Plan: Free → Deploy
+
+**Option B - HuggingFace:**
+```powershell
+git remote add hf https://huggingface.co/spaces/anis80/sentiment-api
+git push hf main
+```
+
+### Step 3: Deploy Frontend (2 min)
+1. Update `index.html` lines 72-73 with your backend URL
+2. Push to GitHub
+3. https://vercel.com → Import repo → Deploy
+
+---
+
+## ✅ Test
+- Backend: `https://YOUR_URL/docs`
+- Frontend: Enter text → Click Analyze → See result!
+
+---
+
+**Total Time: ~7 minutes | Cost: $0/month** 🎉
+
+See `final_deployment.md` for detailed instructions.

app.py

@@ -0,0 +1,161 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+import joblib
+import os
+from pathlib import Path
+from huggingface_hub import hf_hub_download
+
+# Initialize FastAPI app
+app = FastAPI(
+    title="Sentiment Analysis API",
+    description="API for sentiment analysis using ensemble ML models",
+    version="1.0.0"
+)
+
+# Configure CORS - allow all origins for Vercel frontend
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # In production, replace with your Vercel domain
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Define request/response models
+class TextInput(BaseModel):
+    text: str
+
+class PredictionResponse(BaseModel):
+    predicted_sentiment: str
+    input_text: str
+
+class StatusResponse(BaseModel):
+    status: str
+    model_name: str
+    message: str
+
+# Global variables for models
+label_encoder = None
+tfidf_vectorizer = None
+voting_classifier = None
+MODEL_NAME = "Voting Classifier (KNN + RF + ET)"
+
+# HuggingFace Model Hub configuration
+REPO_ID = "anis80/anisproject"  # Your HuggingFace model repository
+MODEL_FILES = {
+    "label_encoder": "label_encoder.joblib",
+    "tfidf_vectorizer": "tfidf_vectorizer.joblib",
+    "voting_classifier": "voting_classifier_knn_rf_et-001.joblib"
+}
+
+def download_model_from_hub(filename: str) -> str:
+    """Download a model file from HuggingFace Model Hub"""
+    try:
+        print(f"📥 Downloading {filename} from HuggingFace Model Hub...")
+        file_path = hf_hub_download(
+            repo_id=REPO_ID,
+            filename=filename,
+            cache_dir="./model_cache"
+        )
+        print(f"✅ Downloaded {filename}")
+        return file_path
+    except Exception as e:
+        print(f"❌ Error downloading {filename}: {str(e)}")
+        raise e
+
+# Load models on startup
+@app.on_event("startup")
+async def load_models():
+    global label_encoder, tfidf_vectorizer, voting_classifier
+    
+    try:
+        print(f"🚀 Starting model loading from HuggingFace: {REPO_ID}")
+        
+        # Download and load each model
+        label_encoder_path = download_model_from_hub(MODEL_FILES["label_encoder"])
+        label_encoder = joblib.load(label_encoder_path)
+        
+        tfidf_path = download_model_from_hub(MODEL_FILES["tfidf_vectorizer"])
+        tfidf_vectorizer = joblib.load(tfidf_path)
+        
+        classifier_path = download_model_from_hub(MODEL_FILES["voting_classifier"])
+        voting_classifier = joblib.load(classifier_path)
+        
+        print("✅ All models loaded successfully from HuggingFace Model Hub!")
+        
+    except Exception as e:
+        print(f"❌ Error loading models: {str(e)}")
+        print(f"⚠️  Make sure models are uploaded to: https://huggingface.co/{REPO_ID}")
+        raise e
+
+# Health check endpoint
+@app.get("/")
+async def root():
+    return {
+        "message": "Sentiment Analysis API is running",
+        "model_source": f"HuggingFace: {REPO_ID}",
+        "endpoints": {
+            "predict": "/predict",
+            "status": "/status",
+            "docs": "/docs"
+        }
+    }
+
+# Status endpoint
+@app.get("/status", response_model=StatusResponse)
+async def get_status():
+    if voting_classifier is None:
+        raise HTTPException(status_code=503, detail="Models not loaded")
+    
+    return StatusResponse(
+        status="ready",
+        model_name=MODEL_NAME,
+        message=f"All models loaded from {REPO_ID}"
+    )
+
+# Prediction endpoint
+@app.post("/predict", response_model=PredictionResponse)
+async def predict_sentiment(input_data: TextInput):
+    try:
+        # Validate models are loaded
+        if None in [label_encoder, tfidf_vectorizer, voting_classifier]:
+            raise HTTPException(
+                status_code=503, 
+                detail="Models not loaded. Please try again later."
+            )
+        
+        # Validate input
+        if not input_data.text or not input_data.text.strip():
+            raise HTTPException(
+                status_code=400, 
+                detail="Text input cannot be empty"
+            )
+        
+        # Preprocess and transform the text
+        text_tfidf = tfidf_vectorizer.transform([input_data.text])
+        
+        # Make prediction
+        prediction = voting_classifier.predict(text_tfidf)
+        
+        # Decode the prediction
+        sentiment = label_encoder.inverse_transform(prediction)[0]
+        
+        return PredictionResponse(
+            predicted_sentiment=sentiment,
+            input_text=input_data.text
+        )
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        print(f"Prediction error: {str(e)}")
+        raise HTTPException(
+            status_code=500, 
+            detail=f"Prediction failed: {str(e)}"
+        )
+
+# For local testing
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)

index.html

@@ -0,0 +1,185 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Sentiment Analysis</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+</head>
+<body class="bg-gray-900 text-white min-h-screen flex items-center justify-center font-sans p-4">
+
+    <div class="container mx-auto max-w-2xl w-full p-8 bg-gray-800 rounded-2xl shadow-2xl border border-gray-700">
+
+        <h1 class="text-4xl font-bold text-center mb-2 text-cyan-400">
+            Sentiment Analysis Engine
+        </h1>
+        <p id="modelName" class="text-center text-gray-400 mb-8 h-6">
+            (Loading model...)
+        </p>
+
+        <div id="errorDiv" class="hidden p-3 mb-4 bg-red-800 border border-red-600 text-red-100 rounded-lg">
+            <span id="errorMessage"></span>
+        </div>
+
+        <div class="mb-6 relative">
+            <label for="textInput" class="block text-lg font-medium text-gray-300 mb-2">
+                Enter your text:
+            </label>
+            <textarea id="textInput" rows="5"
+                class="w-full p-4 bg-gray-700 border border-gray-600 rounded-lg text-white text-base focus:ring-2 focus:ring-cyan-500 focus:outline-none transition duration-200"
+                placeholder="Type something... (e.g., 'I love this product!')"></textarea>
+        </div>
+
+        <div class="flex flex-col sm:flex-row gap-4">
+            <button id="analyzeButton"
+                class="w-full bg-cyan-600 hover:bg-cyan-500 text-white text-lg font-bold py-3 px-6 rounded-lg shadow-lg transition duration-300 ease-in-out transform hover:scale-105 flex items-center justify-center">
+                <svg id="spinner" class="animate-spin -ml-1 mr-3 h-5 w-5 text-white hidden" xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 24 24">
+                    <circle class="opacity-25" cx="12" cy="12" r="10" stroke="currentColor" stroke-width="4"></circle>
+                    <path class="opacity-75" fill="currentColor" d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4zm2 5.291A7.962 7.962 0 014 12H0c0 3.042 1.135 5.824 3 7.938l3-2.647z"></path>
+                </svg>
+                <span id="buttonText">Analyze Sentiment</span>
+            </button>
+            <button id="clearButton"
+                class="w-full sm:w-auto bg-gray-600 hover:bg-gray-500 text-white font-bold py-3 px-6 rounded-lg transition duration-300">
+                Clear
+            </button>
+        </div>
+
+        <div id="result" class="mt-8 p-6 bg-gray-700 rounded-lg hidden border border-gray-600">
+            <h2 class="text-2xl font-semibold mb-4 text-gray-200">Analysis Result:</h2>
+            <div id="sentiment" class="text-4xl font-extrabold text-center flex items-center justify-center gap-4">
+                <span id="sentimentIcon"></span>
+                <span id="sentimentText"></span>
+            </div>
+        </div>
+    </div>
+
+    <script>
+        // Select all DOM elements
+        const textInput = document.getElementById('textInput');
+        const analyzeButton = document.getElementById('analyzeButton');
+        const clearButton = document.getElementById('clearButton');
+        const resultDiv = document.getElementById('result');
+        const sentimentText = document.getElementById('sentimentText');
+        const sentimentIcon = document.getElementById('sentimentIcon');
+        const modelNameEl = document.getElementById('modelName');
+        const errorDiv = document.getElementById('errorDiv');
+        const errorMessage = document.getElementById('errorMessage');
+        const spinner = document.getElementById('spinner');
+        const buttonText = document.getElementById('buttonText');
+
+        // API endpoints
+        const predictApi = '/predict';
+        const statusApi = '/status';
+
+        // Icon SVGs
+        const icons = {
+            positive: `<svg xmlns="http://www.w3.org/2000/svg" class="h-10 w-10 text-green-400" viewBox="0 0 20 20" fill="currentColor"><path fill-rule="evenodd" d="M10 18a8 8 0 100-16 8 8 0 000 16zm3.707-9.293a1 1 0 00-1.414-1.414L9 10.586 7.707 9.293a1 1 0 00-1.414 1.414l2 2a1 1 0 001.414 0l4-4z" clip-rule="evenodd" /></svg>`,
+            negative: `<svg xmlns="http://www.w3.org/2000/svg" class="h-10 w-10 text-red-400" viewBox="0 0 20 20" fill="currentColor"><path fill-rule="evenodd" d="M10 18a8 8 0 100-16 8 8 0 000 16zM8.707 7.293a1 1 0 00-1.414 1.414L8.586 10l-1.293 1.293a1 1 0 101.414 1.414L10 11.414l1.293 1.293a1 1 0 001.414-1.414L11.414 10l1.293-1.293a1 1 0 00-1.414-1.414L10 8.586 8.707 7.293z" clip-rule="evenodd" /></svg>`,
+            neutral: `<svg xmlns="http://www.w3.org/2000/svg" class="h-10 w-10 text-yellow-400" viewBox="0 0 20 20" fill="currentColor"><path fill-rule="evenodd" d="M10 18a8 8 0 100-16 8 8 0 000 16zM7 10a1 1 0 11-2 0 1 1 0 012 0zm7 0a1 1 0 11-2 0 1 1 0 012 0z" clip-rule="evenodd" /></svg>`,
+            other: `<svg xmlns="http://www.w3.org/2000/svg" class="h-10 w-10 text-blue-400" viewBox="0 0 20 20" fill="currentColor"><path fill-rule="evenodd" d="M18 10a8 8 0 11-16 0 8 8 0 0116 0zm-7-4a1 1 0 11-2 0 1 1 0 012 0zM9 9a1 1 0 000 2v3a1 1 0 001 1h1a1 1 0 100-2v-3a1 1 0 00-1-1H9z" clip-rule="evenodd" /></svg>`
+        };
+
+        // Fetch model status on page load
+        window.addEventListener('load', async () => {
+            try {
+                const response = await fetch(statusApi);
+                if (!response.ok) throw new Error('Status check failed');
+                const data = await response.json();
+                modelNameEl.textContent = `(Active Model: ${data.model_name || 'N/A'})`;
+            } catch (error) {
+                modelNameEl.textContent = '(Could not load model status)';
+                console.error('Error fetching status:', error);
+            }
+        });
+
+        // Analyze button click event
+        analyzeButton.addEventListener('click', async () => {
+            const text = textInput.value;
+            if (!text) {
+                showError('Please enter some text to analyze.');
+                return;
+            }
+
+            setLoading(true);
+
+            try {
+                const response = await fetch(predictApi, {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify({ text: text })
+                });
+
+                if (!response.ok) {
+                    throw new Error('Network response was not ok');
+                }
+
+                const data = await response.json();
+
+                if (data.predicted_sentiment) {
+                    displayResult(data.predicted_sentiment);
+                } else if (data.error) {
+                    showError('Error from server: ' + data.error);
+                }
+
+            } catch (error) {
+                console.error('Error:', error);
+                showError('Could not connect to the analysis server. Is it running?');
+            } finally {
+                setLoading(false);
+            }
+        });
+
+        // Clear button click event
+        clearButton.addEventListener('click', () => {
+            textInput.value = '';
+            resultDiv.classList.add('hidden');
+            errorDiv.classList.add('hidden');
+        });
+
+        // Function to manage loading state
+        function setLoading(isLoading) {
+            analyzeButton.disabled = isLoading;
+            if (isLoading) {
+                spinner.classList.remove('hidden');
+                buttonText.textContent = 'Analyzing...';
+            } else {
+                spinner.classList.add('hidden');
+                buttonText.textContent = 'Analyze Sentiment';
+            }
+        }
+
+        // Function to show error messages
+        function showError(message) {
+            errorMessage.textContent = message;
+            errorDiv.classList.remove('hidden');
+            resultDiv.classList.add('hidden');
+        }
+
+        // Function to display results
+        function displayResult(sentiment) {
+            sentimentText.textContent = sentiment;
+            const sentimentKey = sentiment.toLowerCase();
+            let iconSvg = icons.other; // Default
+            let colorClass = 'text-blue-400';
+
+            if (sentimentKey.includes('positive')) {
+                iconSvg = icons.positive;
+                colorClass = 'text-green-400';
+            } else if (sentimentKey.includes('negative')) {
+                iconSvg = icons.negative;
+                colorClass = 'text-red-400';
+            } else if (sentimentKey.includes('neutral')) {
+                iconSvg = icons.neutral;
+                colorClass = 'text-yellow-400';
+            }
+            
+            sentimentIcon.innerHTML = iconSvg;
+            sentimentText.className = colorClass; // Only set color class
+            
+            resultDiv.classList.remove('hidden');
+            errorDiv.classList.add('hidden');
+        }
+    </script>
+</body>
+</html>

requirements.txt

@@ -0,0 +1,8 @@
+fastapi==0.109.0
+uvicorn[standard]==0.27.0
+pydantic==2.5.3
+joblib==1.3.2
+scikit-learn==1.4.0
+numpy==1.26.3
+scipy==1.11.4
+huggingface-hub==0.20.3

vercel.json

@@ -0,0 +1,15 @@
+{
+    "version": 2,
+    "builds": [
+        {
+            "src": "index.html",
+            "use": "@vercel/static"
+        }
+    ],
+    "routes": [
+        {
+            "src": "/(.*)",
+            "dest": "/index.html"
+        }
+    ]
+}