Spaces:

pacman2223
/

exo-ml

Sleeping

App Files Files Community

pacman2223 commited on Oct 5, 2025

Commit

0b2787c

verified ·

1 Parent(s): 28616e4

Upload 6 files

Browse files

Files changed (6) hide show

Dockerfile +15 -0
index.html +714 -0
main.py +304 -0
models/xgb_rf.pkl +3 -0
models/xgboost.pkl +3 -0
requirements.txt +26 -0

Dockerfile ADDED Viewed

	@@ -0,0 +1,15 @@

+FROM ubuntu:22.04
+WORKDIR /code
+# install app dependencies
+RUN apt-get update && apt-get install -y python3 python3-pip
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+# install app
+COPY . .
+# final configuration
+EXPOSE 8000
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

index.html ADDED Viewed

	@@ -0,0 +1,714 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Exoplanet Prediction System</title>
+    <style>
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+        }
+        body {
+            font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+            background: linear-gradient(135deg, #0f0c29 0%, #302b63 50%, #24243e 100%);
+            min-height: 100vh;
+            color: #fff;
+            overflow-x: hidden;
+        }
+        .stars {
+            position: fixed;
+            width: 100%;
+            height: 100%;
+            pointer-events: none;
+        }
+        .star {
+            position: absolute;
+            width: 2px;
+            height: 2px;
+            background: white;
+            border-radius: 50%;
+            animation: twinkle 3s infinite;
+        }
+        @keyframes twinkle {
+            0%, 100% { opacity: 0.3; }
+            50% { opacity: 1; }
+        }
+        .container {
+            max-width: 1200px;
+            margin: 0 auto;
+            padding: 40px 20px;
+            position: relative;
+            z-index: 1;
+        }
+        .header {
+            text-align: center;
+            margin-bottom: 50px;
+        }
+        .header h1 {
+            font-size: 3rem;
+            background: linear-gradient(45deg, #667eea 0%, #764ba2 100%);
+            -webkit-background-clip: text;
+            -webkit-text-fill-color: transparent;
+            background-clip: text;
+            margin-bottom: 10px;
+            text-shadow: 0 0 30px rgba(102, 126, 234, 0.5);
+        }
+        .header p {
+            color: #a0aec0;
+            font-size: 1.1rem;
+        }
+        .tabs {
+            display: flex;
+            gap: 10px;
+            margin-bottom: 30px;
+            justify-content: center;
+        }
+        .tab {
+            padding: 15px 30px;
+            background: rgba(255, 255, 255, 0.05);
+            border: 2px solid rgba(255, 255, 255, 0.1);
+            border-radius: 15px;
+            cursor: pointer;
+            transition: all 0.3s ease;
+            font-size: 1rem;
+            color: #fff;
+            backdrop-filter: blur(10px);
+        }
+        .tab:hover {
+            background: rgba(255, 255, 255, 0.1);
+            transform: translateY(-2px);
+        }
+        .tab.active {
+            background: linear-gradient(45deg, #667eea 0%, #764ba2 100%);
+            border-color: #667eea;
+            box-shadow: 0 10px 30px rgba(102, 126, 234, 0.3);
+        }
+        .tab-content {
+            display: none;
+            animation: fadeIn 0.5s ease;
+        }
+        .tab-content.active {
+            display: block;
+        }
+        @keyframes fadeIn {
+            from { opacity: 0; transform: translateY(20px); }
+            to { opacity: 1; transform: translateY(0); }
+        }
+        .card {
+            background: rgba(255, 255, 255, 0.05);
+            backdrop-filter: blur(10px);
+            border: 1px solid rgba(255, 255, 255, 0.1);
+            border-radius: 20px;
+            padding: 40px;
+            box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
+        }
+        .form-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
+            gap: 25px;
+            margin-bottom: 30px;
+        }
+        .form-group {
+            display: flex;
+            flex-direction: column;
+        }
+        label {
+            margin-bottom: 8px;
+            color: #a0aec0;
+            font-size: 0.9rem;
+            font-weight: 500;
+        }
+        input[type="number"], input[type="file"] {
+            padding: 12px 15px;
+            background: rgba(255, 255, 255, 0.05);
+            border: 1px solid rgba(255, 255, 255, 0.2);
+            border-radius: 10px;
+            color: #fff;
+            font-size: 1rem;
+            transition: all 0.3s ease;
+        }
+        input[type="number"]:focus, input[type="file"]:focus, select:focus {
+            outline: none;
+            border-color: #667eea;
+            box-shadow: 0 0 20px rgba(102, 126, 234, 0.3);
+        }
+        select {
+            background: rgba(255, 255, 255, 0.05);
+            border: 1px solid rgba(255, 255, 255, 0.2);
+            border-radius: 10px;
+            color: #fff;
+            padding: 12px 15px;
+            font-size: 1rem;
+            cursor: pointer;
+            transition: all 0.3s ease;
+        }
+        select option {
+            background: #302b63;
+            color: #fff;
+        }
+        select:hover {
+            border-color: rgba(255, 255, 255, 0.4);
+        }
+        input::placeholder {
+            color: rgba(255, 255, 255, 0.3);
+        }
+        .btn {
+            padding: 15px 40px;
+            background: linear-gradient(45deg, #667eea 0%, #764ba2 100%);
+            border: none;
+            border-radius: 12px;
+            color: #fff;
+            font-size: 1.1rem;
+            font-weight: 600;
+            cursor: pointer;
+            transition: all 0.3s ease;
+            box-shadow: 0 10px 30px rgba(102, 126, 234, 0.3);
+            width: 100%;
+        }
+        .btn:hover {
+            transform: translateY(-3px);
+            box-shadow: 0 15px 40px rgba(102, 126, 234, 0.5);
+        }
+        .btn:disabled {
+            opacity: 0.6;
+            cursor: not-allowed;
+            transform: none;
+        }
+        .result {
+            margin-top: 30px;
+            padding: 25px;
+            background: rgba(255, 255, 255, 0.05);
+            border-radius: 15px;
+            border: 1px solid rgba(255, 255, 255, 0.1);
+            animation: slideUp 0.5s ease;
+        }
+        @keyframes slideUp {
+            from { opacity: 0; transform: translateY(30px); }
+            to { opacity: 1; transform: translateY(0); }
+        }
+        .result h3 {
+            margin-bottom: 15px;
+            color: #667eea;
+            font-size: 1.5rem;
+        }
+        .result-item {
+            display: flex;
+            justify-content: space-between;
+            padding: 10px 0;
+            border-bottom: 1px solid rgba(255, 255, 255, 0.1);
+        }
+        .result-item:last-child {
+            border-bottom: none;
+        }
+        .result-label {
+            color: #a0aec0;
+        }
+        .result-value {
+            font-weight: 600;
+            color: #fff;
+        }
+        .badge {
+            display: inline-block;
+            padding: 8px 20px;
+            border-radius: 20px;
+            font-size: 0.9rem;
+            font-weight: 600;
+        }
+        .badge.positive {
+            background: linear-gradient(45deg, #11998e 0%, #38ef7d 100%);
+        }
+        .badge.negative {
+            background: linear-gradient(45deg, #ee0979 0%, #ff6a00 100%);
+        }
+        .upload-area {
+            border: 2px dashed rgba(255, 255, 255, 0.3);
+            border-radius: 15px;
+            padding: 40px;
+            text-align: center;
+            margin-bottom: 30px;
+            transition: all 0.3s ease;
+            cursor: pointer;
+        }
+        .upload-area:hover {
+            border-color: #667eea;
+            background: rgba(102, 126, 234, 0.1);
+        }
+        .upload-icon {
+            font-size: 3rem;
+            margin-bottom: 15px;
+            opacity: 0.5;
+        }
+        .file-info {
+            margin-top: 15px;
+            color: #667eea;
+            font-weight: 500;
+        }
+        .loading {
+            display: inline-block;
+            width: 20px;
+            height: 20px;
+            border: 3px solid rgba(255, 255, 255, 0.3);
+            border-radius: 50%;
+            border-top-color: #fff;
+            animation: spin 1s linear infinite;
+            margin-right: 10px;
+            vertical-align: middle;
+        }
+        @keyframes spin {
+            to { transform: rotate(360deg); }
+        }
+        .error {
+            background: rgba(238, 9, 121, 0.1);
+            border: 1px solid rgba(238, 9, 121, 0.3);
+            color: #ff6b9d;
+            padding: 15px;
+            border-radius: 10px;
+            margin-top: 15px;
+        }
+        .info-tooltip {
+            display: inline-block;
+            margin-left: 5px;
+            width: 16px;
+            height: 16px;
+            background: rgba(255, 255, 255, 0.2);
+            border-radius: 50%;
+            text-align: center;
+            line-height: 16px;
+            font-size: 0.7rem;
+            cursor: help;
+        }
+        .fireworks-container {
+            position: fixed;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            pointer-events: none;
+            z-index: 9999;
+        }
+        .firework {
+            position: absolute;
+            width: 4px;
+            height: 4px;
+            border-radius: 50%;
+            animation: firework-launch 1s ease-out forwards;
+        }
+        @keyframes firework-launch {
+            0% {
+                transform: translateY(0);
+                opacity: 1;
+            }
+            100% {
+                transform: translateY(-400px);
+                opacity: 0;
+            }
+        }
+        .particle {
+            position: absolute;
+            width: 6px;
+            height: 6px;
+            border-radius: 50%;
+            animation: particle-explode 1s ease-out forwards;
+        }
+        @keyframes particle-explode {
+            0% {
+                transform: translate(0, 0) scale(1);
+                opacity: 1;
+            }
+            100% {
+                opacity: 0;
+                transform: scale(0);
+            }
+        }
+    </style>
+</head>
+<body>
+    <div class="stars" id="stars"></div>
+    <div class="fireworks-container" id="fireworks"></div>
+    <div class="container">
+        <div class="header">
+            <h1>🪐 Exoplanet Detection System</h1>
+            <p>AI-Powered Classification of Kepler Objects of Interest</p>
+        </div>
+        <div class="tabs">
+            <div class="tab active" onclick="switchTab('manual')">Manual Prediction</div>
+            <div class="tab" onclick="switchTab('batch')">Batch Upload</div>
+        </div>
+        <div id="manual-tab" class="tab-content active">
+            <div class="card">
+                <form id="prediction-form">
+                    <div class="form-group" style="margin-bottom: 30px;">
+                        <label>Select Model <span class="info-tooltip" title="Choose which ML model to use for prediction">?</span></label>
+                        <select id="model-select" name="model" style="padding: 12px 15px; background: rgba(255, 255, 255, 0.05); border: 1px solid rgba(255, 255, 255, 0.2); border-radius: 10px; color: #fff; font-size: 1rem; width: 100%; cursor: pointer; transition: all 0.3s ease;">
+                            <!-- <option value="random_forest">Random Forest</option> -->
+                            <option value="xgboost">XGBoost</option>
+                            <option value="ensemble">XGB + RF</option>
+                            <!-- <option value="logistic_regression">Logistic Regression</option>
+                            <option value="svm">Support Vector Machine</option>
+                            <option value="neural_network">Neural Network</option>
+                            <option value="gradient_boosting">Gradient Boosting</option> -->
+                        </select>
+                    </div>
+                    <div class="form-grid">
+                        <div class="form-group">
+                            <label>Signal-to-Noise Ratio <span class="info-tooltip" title="Transit signal-to-noise ratio">?</span></label>
+                            <input type="number" step="0.01" name="koi_model_snr" placeholder="e.g., 15.5" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Planetary Radius (Earth radii) <span class="info-tooltip" title="Planet size relative to Earth">?</span></label>
+                            <input type="number" step="0.01" name="koi_prad" placeholder="e.g., 2.3" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Stellar Eclipse Flag <span class="info-tooltip" title="0 or 1">?</span></label>
+                            <input type="number" min="0" max="1" name="koi_fpflag_ss" placeholder="0 or 1" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Centroid Offset Flag <span class="info-tooltip" title="0 or 1">?</span></label>
+                            <input type="number" min="0" max="1" name="koi_fpflag_co" placeholder="0 or 1" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Orbital Period (days) <span class="info-tooltip" title="Time for one complete orbit">?</span></label>
+                            <input type="number" step="0.01" name="koi_period" placeholder="e.g., 10.5" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Transit Depth (ppm) <span class="info-tooltip" title="Parts per million">?</span></label>
+                            <input type="number" step="0.01" name="koi_depth" placeholder="e.g., 500.0" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Not Transit-Like Flag <span class="info-tooltip" title="0 or 1">?</span></label>
+                            <input type="number" min="0" max="1" name="koi_fpflag_nt" placeholder="0 or 1" required>
+                        </div>
+                        <div class="form-group">
+                            <label>Insolation Flux (Earth units) <span class="info-tooltip" title="Amount of stellar radiation">?</span></label>
+                            <input type="number" step="0.01" name="koi_insol" placeholder="e.g., 1.2" required>
+                        </div>
+                    </div>
+                    <button type="submit" class="btn" id="predict-btn">
+                        Predict Exoplanet
+                    </button>
+                </form>
+                <div id="result-container"></div>
+            </div>
+        </div>
+        <div id="batch-tab" class="tab-content">
+            <div class="card">
+                <div class="form-group" style="margin-bottom: 30px;">
+                    <label>Select Model <span class="info-tooltip" title="Choose which ML model to use for batch predictions">?</span></label>
+                    <select id="batch-model-select" name="model" style="padding: 12px 15px; background: rgba(255, 255, 255, 0.05); border: 1px solid rgba(255, 255, 255, 0.2); border-radius: 10px; color: #fff; font-size: 1rem; width: 100%; cursor: pointer; transition: all 0.3s ease;">
+                        <!-- <option value="random_forest">Random Forest</option> -->
+                        <option value="xgboost">XGBoost</option>
+                        <option value="ensemble">XGB + RF</option>
+                        <!-- <option value="logistic_regression">Logistic Regression</option>
+                        <option value="svm">Support Vector Machine</option>
+                        <option value="neural_network">Neural Network</option>
+                        <option value="gradient_boosting">Gradient Boosting</option> -->
+                    </select>
+                </div>
+                <div class="upload-area" onclick="document.getElementById('csv-file').click()">
+                    <div class="upload-icon">📁</div>
+                    <h3>Upload CSV File</h3>
+                    <p style="color: #a0aec0; margin-top: 10px;">Click to browse or drag and drop your CSV file</p>
+                    <input type="file" id="csv-file" accept=".csv" style="display: none;" onchange="handleFileSelect(event)">
+                    <div id="file-info" class="file-info"></div>
+                </div>
+                <button class="btn" id="batch-btn" onclick="uploadBatch()" disabled>
+                    Process Batch Predictions
+                </button>
+                <div id="batch-result-container"></div>
+            </div>
+        </div>
+    </div>
+    <script>
+        // Create stars
+        const starsContainer = document.getElementById('stars');
+        for (let i = 0; i < 100; i++) {
+            const star = document.createElement('div');
+            star.className = 'star';
+            star.style.left = Math.random() * 100 + '%';
+            star.style.top = Math.random() * 100 + '%';
+            star.style.animationDelay = Math.random() * 3 + 's';
+            starsContainer.appendChild(star);
+        }
+        // API endpoint - update this to your actual API URL
+        const API_URL = 'http://localhost:8000';
+        function switchTab(tab) {
+            document.querySelectorAll('.tab').forEach(t => t.classList.remove('active'));
+            document.querySelectorAll('.tab-content').forEach(c => c.classList.remove('active'));
+            event.target.classList.add('active');
+            document.getElementById(tab + '-tab').classList.add('active');
+        }
+        document.getElementById('prediction-form').addEventListener('submit', async (e) => {
+            e.preventDefault();
+            const btn = document.getElementById('predict-btn');
+            btn.disabled = true;
+            btn.innerHTML = '<span class="loading"></span>Predicting...';
+            const formData = new FormData(e.target);
+            const data = Object.fromEntries(formData);
+            // Extract model selection
+            const selectedModel = data.model;
+            delete data.model;
+            // Convert to numbers
+            Object.keys(data).forEach(key => {
+                data[key] = parseFloat(data[key]);
+            });
+            try {
+                const response = await fetch(`${API_URL}/predict?model=${selectedModel}`, {
+                    method: 'POST',
+                    headers: {
+                        'Content-Type': 'application/json',
+                    },
+                    body: JSON.stringify(data)
+                });
+                const result = await response.json();
+                displayResult(result, selectedModel);
+            } catch (error) {
+                document.getElementById('result-container').innerHTML = `
+                    <div class="error">
+                        <strong>Error:</strong> ${error.message}<br>
+                        <small>Make sure the API server is running at ${API_URL}</small>
+                    </div>
+                `;
+            } finally {
+                btn.disabled = false;
+                btn.innerHTML = 'Predict Exoplanet';
+            }
+        });
+        function displayResult(result, modelName) {
+            let badgeClass, statusText;
+            if (result.prediction === 1) {
+                badgeClass = 'positive';
+                statusText = 'Confirmed Exoplanet';
+            } else if (result.prediction === 2) {
+                badgeClass = 'positive';
+                statusText = 'Exoplanet Candidate';
+            } else {
+                badgeClass = 'negative';
+                statusText = 'False Positive';
+            }
+            const modelDisplay = modelName ? modelName.replace(/_/g, ' ').replace(/\b\w/g, l => l.toUpperCase()) : 'N/A';
+            const html = `
+                <div class="result">
+                    <h3>Prediction Results</h3>
+                    <div class="result-item">
+                        <span class="result-label">Model Used:</span>
+                        <span class="result-value">${modelDisplay}</span>
+                    </div>
+                    <div class="result-item">
+                        <span class="result-label">Classification:</span>
+                        <span class="badge ${badgeClass}">${result.classification}</span>
+                    </div>
+                    <div class="result-item">
+                        <span class="result-label">Confidence:</span>
+                        <span class="result-value">${(result.probability * 100).toFixed(2)}%</span>
+                    </div>
+                    <div class="result-item">
+                        <span class="result-label">Status:</span>
+                        <span class="result-value">${statusText}</span>
+                    </div>
+                </div>
+            `;
+            document.getElementById('result-container').innerHTML = html;
+            // Launch fireworks if exoplanet is confirmed!
+            if (result.prediction === 1) {
+                launchFireworks();
+            }
+        }
+        function launchFireworks() {
+            const container = document.getElementById('fireworks');
+            const colors = ['#ff0844', '#ffb199', '#ffd23f', '#00d9ff', '#7b5cff', '#ff006e', '#8338ec', '#3a86ff'];
+            // Launch 15 fireworks over 3 seconds
+            for (let i = 0; i < 15; i++) {
+                setTimeout(() => {
+                    createFirework(container, colors);
+                }, i * 200);
+            }
+        }
+        function createFirework(container, colors) {
+            const startX = Math.random() * window.innerWidth;
+            const startY = window.innerHeight;
+            const endX = startX;
+            const endY = Math.random() * (window.innerHeight * 0.5) + 100;
+            const color = colors[Math.floor(Math.random() * colors.length)];
+            // Create launch trail
+            const firework = document.createElement('div');
+            firework.className = 'firework';
+            firework.style.left = startX + 'px';
+            firework.style.top = startY + 'px';
+            firework.style.backgroundColor = color;
+            container.appendChild(firework);
+            // Explode after launch
+            setTimeout(() => {
+                explode(container, endX, endY, color);
+                firework.remove();
+            }, 1000);
+        }
+        function explode(container, x, y, color) {
+            const particleCount = 50;
+            for (let i = 0; i < particleCount; i++) {
+                const particle = document.createElement('div');
+                particle.className = 'particle';
+                particle.style.left = x + 'px';
+                particle.style.top = y + 'px';
+                particle.style.backgroundColor = color;
+                const angle = (Math.PI * 2 * i) / particleCount;
+                const velocity = 100 + Math.random() * 100;
+                const tx = Math.cos(angle) * velocity;
+                const ty = Math.sin(angle) * velocity;
+                particle.style.setProperty('--tx', tx + 'px');
+                particle.style.setProperty('--ty', ty + 'px');
+                particle.style.animation = `particle-explode ${0.8 + Math.random() * 0.4}s ease-out forwards`;
+                particle.style.transform = `translate(${tx}px, ${ty}px)`;
+                container.appendChild(particle);
+                setTimeout(() => particle.remove(), 1500);
+            }
+        }
+        let selectedFile = null;
+        function handleFileSelect(event) {
+            selectedFile = event.target.files[0];
+            if (selectedFile) {
+                document.getElementById('file-info').innerHTML = `Selected: ${selectedFile.name} (${(selectedFile.size / 1024).toFixed(2)} KB)`;
+                document.getElementById('batch-btn').disabled = false;
+            }
+        }
+        async function uploadBatch() {
+            if (!selectedFile) return;
+            const btn = document.getElementById('batch-btn');
+            btn.disabled = true;
+            btn.innerHTML = '<span class="loading"></span>Processing...';
+            const selectedModel = document.getElementById('batch-model-select').value;
+            const formData = new FormData();
+            formData.append('file', selectedFile);
+            try {
+                const response = await fetch(`${API_URL}/predict/batch?model=${selectedModel}`, {
+                    method: 'POST',
+                    body: formData
+                });
+                if (response.ok) {
+                    const blob = await response.blob();
+                    const url = window.URL.createObjectURL(blob);
+                    const a = document.createElement('a');
+                    a.href = url;
+                    a.download = `predictions_${selectedModel}_${selectedFile.name}`;
+                    document.body.appendChild(a);
+                    a.click();
+                    window.URL.revokeObjectURL(url);
+                    document.body.removeChild(a);
+                    const modelDisplay = selectedModel.replace(/_/g, ' ').replace(/\b\w/g, l => l.toUpperCase());
+                    document.getElementById('batch-result-container').innerHTML = `
+                        <div class="result">
+                            <h3>✅ Success!</h3>
+                            <p>Your predictions using <strong>${modelDisplay}</strong> have been downloaded.</p>
+                        </div>
+                    `;
+                } else {
+                    throw new Error('Upload failed');
+                }
+            } catch (error) {
+                document.getElementById('batch-result-container').innerHTML = `
+                    <div class="error">
+                        <strong>Error:</strong> ${error.message}<br>
+                        <small>Make sure the API server is running and the CSV has all required columns.</small>
+                    </div>
+                `;
+            } finally {
+                btn.disabled = false;
+                btn.innerHTML = 'Process Batch Predictions';
+            }
+        }
+    </script>
+</body>
+</html>

main.py ADDED Viewed

	@@ -0,0 +1,304 @@

+from fastapi import FastAPI, File, UploadFile, HTTPException, Query
+from fastapi.responses import StreamingResponse
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel, Field
+from typing import List, Optional
+import pandas as pd
+import io
+import pickle
+import joblib
+import numpy as np
+from enum import Enum
+app = FastAPI(
+    title="Exoplanet Prediction API",
+    description="API for predicting exoplanet candidates using KOI features",
+    version="1.0.0"
+)
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # In production, replace with specific origins
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+# Define available models
+class ModelType(str, Enum):
+    random_forest = "random_forest"
+    xgboost = "xgboost"
+    ensemble = "ensemble"
+    # logistic_regression = "logistic_regression"
+    # svm = "svm"
+    # neural_network = "neural_network"
+    # gradient_boosting = "gradient_boosting"
+# Dictionary to store loaded models
+models = {}
+def load_models():
+    """Load all available models on startup"""
+    # models['random_forest'] = pickle.load(open('models/xgb_rf.pkl', 'rb'))
+    models['xgboost'] = joblib.load('models/xgboost.pkl')
+    models['ensemble'] = joblib.load('models/xgb_rf.pkl')
+    # models['logistic_regression'] = pickle.load(open('models/logistic_regression.pkl', 'rb'))
+    # models['svm'] = pickle.load(open('models/svm.pkl', 'rb'))
+    # models['neural_network'] = pickle.load(open('models/neural_network.pkl', 'rb'))
+    # models['gradient_boosting'] = pickle.load(open('models/gradient_boosting.pkl', 'rb'))
+# Load models when app starts
+@app.on_event("startup")
+async def startup_event():
+    load_models()
+    print("Models loaded successfully")
+class PredictionInput(BaseModel):
+    koi_model_snr: float = Field(..., description="Transit signal-to-noise ratio")
+    koi_prad: float = Field(..., description="Planetary radius in Earth radii")
+    koi_fpflag_ss: int = Field(..., ge=0, le=1, description="Stellar eclipse flag")
+    koi_fpflag_co: int = Field(..., ge=0, le=1, description="Centroid offset flag")
+    koi_period: float = Field(..., description="Orbital period in days")
+    koi_depth: float = Field(..., description="Transit depth in parts per million")
+    koi_fpflag_nt: int = Field(..., ge=0, le=1, description="Not transit-like flag")
+    koi_insol: float = Field(..., description="Insolation flux in Earth units")
+    class Config:
+        json_schema_extra = {
+            "example": {
+                "koi_model_snr": 15.5,
+                "koi_prad": 2.3,
+                "koi_fpflag_ss": 0,
+                "koi_fpflag_co": 0,
+                "koi_period": 10.5,
+                "koi_depth": 500.0,
+                "koi_fpflag_nt": 0,
+                "koi_insol": 1.2
+            }
+        }
+class PredictionOutput(BaseModel):
+    prediction: int
+    probability: float
+    classification: str
+class BatchPredictionOutput(BaseModel):
+    predictions: List[dict]
+    total_processed: int
+def prepare_features(data: dict) -> np.ndarray:
+    """Convert input dictionary to feature array in correct order"""
+    feature_order = [
+        'koi_model_snr', 'koi_prad', 'koi_fpflag_ss', 'koi_fpflag_co',
+        'koi_period', 'koi_depth', 'koi_fpflag_nt', 'koi_insol'
+    ]
+    return np.array([[data[f] for f in feature_order]])
+def preprocess(data):
+    for col in data.columns:
+        if data[col].isnull().sum() > 0 and data[col].dtype != 'O':
+            data.fillna({col: data[col].fillna(0)}, inplace=True)
+    return data
+def make_prediction(features: np.ndarray, model_name: str):
+    """Make prediction using the selected model"""
+    if model_name in models:
+        model = models[model_name]
+        prediction = model.predict(features)[0]
+        probability = model.predict_proba(features)[0][1] if hasattr(model, 'predict_proba') else 0.5
+    else:
+        raise HTTPException(status_code=400, detail=f"Model {model_name} not found")
+    # Placeholder for demonstration - replace with actual model prediction
+    prediction = np.random.choice([0, 1, 2])  # 0=false positive, 1=confirmed, 2=candidate
+    probability = np.random.random()
+    return prediction, probability
+@app.get("/")
+def read_root():
+    return {
+        "message": "Exoplanet Prediction API",
+        "available_models": [model.value for model in ModelType],
+        "endpoints": {
+            "/predict": "Single prediction (POST)",
+            "/predict/batch": "Batch prediction from CSV (POST)",
+            "/models": "List available models (GET)",
+            "/health": "Health check (GET)",
+            "/docs": "API documentation"
+        }
+    }
+@app.get("/models")
+def list_models():
+    """List all available models"""
+    return {
+        "available_models": [model.value for model in ModelType],
+        "loaded_models": list(models.keys()) if models else []
+    }
+@app.get("/health")
+def health_check():
+    return {
+        "status": "healthy",
+        "models_loaded": len(models),
+        "available_models": [model.value for model in ModelType]
+    }
+@app.post("/predict", response_model=PredictionOutput)
+def predict_single(
+    input_data: PredictionInput,
+    model: ModelType = Query(ModelType.ensemble, description="Model to use for prediction")
+):
+    """
+    Make a single prediction for exoplanet classification using the specified model
+    """
+    try:
+        features = prepare_features(input_data.dict())
+        prediction, probability = make_prediction(features, model.value)
+        if prediction == 1:
+            classification = "Confirmed Exoplanet"
+        elif prediction == 2:
+            classification = "Exoplanet Candidate"
+        else:
+            classification = "False Positive"
+        return PredictionOutput(
+            prediction=int(prediction),
+            probability=float(probability),
+            classification=classification
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Prediction error: {str(e)}")
+@app.post("/predict/batch")
+async def predict_batch(
+    file: UploadFile = File(...),
+    model: ModelType = Query(ModelType.ensemble, description="Model to use for predictions")
+):
+    """
+    Make batch predictions from CSV file using the specified model
+    Returns a CSV file with predictions
+    """
+    if not file.filename.endswith('.csv'):
+        raise HTTPException(status_code=400, detail="File must be a CSV")
+    try:
+        # Read CSV file
+        contents = await file.read()
+        df = pd.read_csv(io.BytesIO(contents))
+        # Validate required columns
+        required_cols = [
+            'koi_model_snr', 'koi_prad', 'koi_fpflag_ss', 'koi_fpflag_co',
+            'koi_period', 'koi_depth', 'koi_fpflag_nt', 'koi_insol'
+        ]
+        missing_cols = set(required_cols) - set(df.columns)
+        if missing_cols:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Missing required columns: {missing_cols}"
+            )
+        cleaned_df = preprocess(df)
+        # Make predictions
+        predictions = []
+        probabilities = []
+        for _, row in cleaned_df.iterrows():
+            features = prepare_features(row[required_cols].to_dict())
+            pred, prob = make_prediction(features, model.value)
+            predictions.append(pred)
+            probabilities.append(prob)
+        # Add predictions to dataframe
+        cleaned_df['prediction'] = predictions
+        cleaned_df['probability'] = probabilities
+        cleaned_df['classification'] = cleaned_df['prediction'].map({
+            1: 'Confirmed Exoplanet',
+            2: 'Exoplanet Candidate',
+            0: 'False Positive'
+        })
+        # Convert to CSV for download
+        output = io.StringIO()
+        df.to_csv(output, index=False)
+        output.seek(0)
+        return StreamingResponse(
+            iter([output.getvalue()]),
+            media_type="text/csv",
+            headers={"Content-Disposition": f"attachment; filename=predictions_{model.value}_{file.filename}"}
+        )
+    except pd.errors.EmptyDataError:
+        raise HTTPException(status_code=400, detail="CSV file is empty")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Processing error: {str(e)}")
+@app.post("/predict/batch/json", response_model=BatchPredictionOutput)
+async def predict_batch_json(
+    file: UploadFile = File(...),
+    model: ModelType = Query(ModelType.ensemble, description="Model to use for predictions")
+):
+    """
+    Make batch predictions from CSV file using the specified model
+    Returns JSON response with predictions
+    """
+    if not file.filename.endswith('.csv'):
+        raise HTTPException(status_code=400, detail="File must be a CSV")
+    try:
+        contents = await file.read()
+        df = pd.read_csv(io.BytesIO(contents))
+        print("file received and read")
+        required_cols = [
+            'koi_model_snr', 'koi_prad', 'koi_fpflag_ss', 'koi_fpflag_co',
+            'koi_period', 'koi_depth', 'koi_fpflag_nt', 'koi_insol'
+        ]
+        missing_cols = set(required_cols) - set(df.columns)
+        if missing_cols:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Missing required columns: {missing_cols}"
+            )
+        cleaned_df = preprocess(df)
+        print("data cleaned")
+        results = []
+        for idx, row in cleaned_df.iterrows():
+            features = prepare_features(row[required_cols].to_dict())
+            pred, prob = make_prediction(features, model.value)
+            if pred == 1:
+                classification = "Confirmed Exoplanet"
+            elif pred == 2:
+                classification = "Exoplanet Candidate"
+            else:
+                classification = "False Positive"
+            results.append({
+                "row_index": int(idx),
+                "prediction": int(pred),
+                "probability": float(prob),
+                "classification": classification
+            })
+        return BatchPredictionOutput(
+            predictions=results,
+            total_processed=len(results)
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Processing error: {str(e)}")
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

models/xgb_rf.pkl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:694f36481655114b66faf14964ee947499e290880e7f7ef17e4488a278286171
+size 24705012

models/xgboost.pkl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91de04887b8b3a6303446497ac82f52dc2e5248d8c378df6f8818f2020a7fa86
+size 666119

requirements.txt ADDED Viewed

	@@ -0,0 +1,26 @@

+annotated-types==0.7.0
+anyio==4.11.0
+click==8.3.0
+fastapi==0.118.0
+h11==0.16.0
+idna==3.10
+joblib==1.5.2
+numpy==2.3.3
+nvidia-nccl-cu12==2.28.3
+pandas==2.3.3
+pydantic==2.11.10
+pydantic_core==2.33.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.2
+scikit-learn==1.7.2
+scipy==1.16.2
+six==1.17.0
+sniffio==1.3.1
+starlette==0.48.0
+threadpoolctl==3.6.0
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2025.2
+uvicorn==0.37.0
+xgboost==3.0.5