Initial commit

.gitignore

@@ -0,0 +1,139 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# Environments
+.env
+.env.local
+.env.development
+.env.test
+.env.production
+
+# Flask
+instance/
+.webassets-cache
+
+# Scrapy
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Logs
+*.log
+logs/
+
+# Model files (if you want to exclude them)
+# *.pkl
+# *.joblib
+# *.h5
+# *.model
+
+# Data files (if you want to exclude them)
+# *.csv
+# *.json
+# *.xlsx
+
+# Temporary files
+*.tmp
+*.temp
+*.bak
+*.swp
+*~.nib
+
+# Docker
+.dockerignore
+
+# Git
+.git/
+.gitattributes
+
+# Backup files
+*.backup
+*.old

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /flask_model_api
+
+COPY requirements.txt requirements.txt
+RUN pip install --upgrade pip && pip install -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["python", "app.py"]

README copy.md

@@ -0,0 +1,119 @@
+---
+title: Iris Flower Classification
+emoji: 🌸
+colorFrom: blue
+colorTo: purple
+sdk: docker
+sdk_version: "4.36.2"
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# 🌸 Iris Flower Classification API
+
+Aplikasi Machine Learning untuk klasifikasi bunga Iris menggunakan Decision Tree Algorithm. API ini dapat memprediksi spesies bunga Iris (Setosa, Versicolor, atau Virginica) berdasarkan fitur morfologi bunga.
+
+## 📊 Dataset & Model
+
+- **Dataset**: Iris Dataset dari scikit-learn
+- **Algorithm**: Decision Tree Classifier
+- **Features**: 
+  - Sepal Length (cm)
+  - Sepal Width (cm) 
+  - Petal Length (cm)
+  - Petal Width (cm)
+- **Target Classes**: Setosa, Versicolor, Virginica
+
+## 🚀 API Endpoints
+
+### 1. Home Page
+```
+GET /
+```
+Web interface interaktif untuk testing model
+
+### 2. Predict Species
+```
+POST /predict
+Content-Type: application/json
+
+{
+  "sepal_length": 5.1,
+  "sepal_width": 3.5,
+  "petal_length": 1.4,
+  "petal_width": 0.2
+}
+```
+
+### 3. Model Information
+```
+GET /model-info
+```
+Informasi detail tentang model dan feature importance
+
+### 4. Health Check
+```
+GET /health
+```
+Status kesehatan API
+
+## 🧪 Example Usage
+
+### Prediksi Setosa:
+```json
+{
+  "sepal_length": 5.1,
+  "sepal_width": 3.5,
+  "petal_length": 1.4,
+  "petal_width": 0.2
+}
+```
+
+### Prediksi Versicolor:
+```json
+{
+  "sepal_length": 7.0,
+  "sepal_width": 3.2,
+  "petal_length": 4.7,
+  "petal_width": 1.4
+}
+```
+
+### Prediksi Virginica:
+```json
+{
+  "sepal_length": 6.3,
+  "sepal_width": 3.3,
+  "petal_length": 6.0,
+  "petal_width": 2.5
+}
+```
+
+## 📈 Model Performance
+
+- **Accuracy**: 100% (pada test set)
+- **Algorithm**: Decision Tree dengan random_state=42
+- **Training Data**: 120 samples
+- **Test Data**: 30 samples
+
+## 🔗 Key Decision Rules
+
+Berdasarkan Decision Tree yang dihasilkan:
+
+1. **Setosa**: Petal Length ≤ 2.45 cm
+2. **Versicolor**: Petal Length > 2.45 cm AND Petal Width ≤ 1.75 cm
+3. **Virginica**: Petal Length > 2.45 cm AND Petal Width > 1.75 cm
+
+## 🛠️ Technology Stack
+
+- **Backend**: Flask + Python 3.11
+- **ML**: scikit-learn, pandas, numpy
+- **Model Persistence**: joblib
+- **Container**: Docker
+- **Deployment**: Hugging Face Spaces
+
+## 👨‍💻 Author
+
+Tugas 27 - Machine Learning Model Deployment
+**Universitas/Institusi**: Infinite Learning

app.py

@@ -0,0 +1,275 @@
+import os
+
+import joblib
+import numpy as np
+import pandas as pd
+from flask import Flask, jsonify, render_template_string, request
+from flask_cors import CORS
+from sklearn.datasets import load_iris
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeClassifier
+
+app = Flask(__name__)
+CORS(app)
+
+# Global variables for model and iris data
+model = None
+iris = None
+feature_names = None
+target_names = None
+
+def load_or_train_model():
+    """Load existing model or train new one if not exists"""
+    global model, iris, feature_names, target_names
+    
+    # Load iris dataset
+    iris = load_iris()
+    feature_names = iris.feature_names
+    target_names = iris.target_names
+    
+    model_path = 'iris_decision_tree_model.pkl'
+    
+    if os.path.exists(model_path):
+        # Load existing model
+        model = joblib.load(model_path)
+        print("Model loaded from file")
+    else:
+        # Train new model
+        print("Training new model...")
+        X = iris.data
+        y = iris.target
+        
+        X_train, X_test, y_train, y_test = train_test_split(
+            X, y, test_size=0.2, random_state=42
+        )
+        
+        model = DecisionTreeClassifier(random_state=42)
+        model.fit(X_train, y_train)
+        
+        # Save model
+        joblib.dump(model, model_path)
+        
+        # Print accuracy
+        y_pred = model.predict(X_test)
+        accuracy = accuracy_score(y_test, y_pred)
+        print(f"Model trained with accuracy: {accuracy:.4f}")
+
+# Initialize model on startup
+load_or_train_model()
+
+@app.route('/')
+def home():
+    html = """
+    <!DOCTYPE html>
+    <html>
+    <head>
+        <title>Iris Flower Classification API</title>
+        <style>
+            body { font-family: Arial, sans-serif; margin: 40px; background-color: #f5f5f5; }
+            .container { max-width: 800px; margin: 0 auto; background: white; padding: 30px; border-radius: 10px; box-shadow: 0 0 20px rgba(0,0,0,0.1); }
+            h1 { color: #2c3e50; text-align: center; }
+            .feature { margin: 10px 0; }
+            .feature label { display: inline-block; width: 200px; font-weight: bold; }
+            .feature input { padding: 8px; width: 200px; border: 1px solid #ddd; border-radius: 4px; }
+            button { background: #3498db; color: white; padding: 10px 20px; border: none; border-radius: 4px; cursor: pointer; margin: 10px 5px; }
+            button:hover { background: #2980b9; }
+            .result { margin: 20px 0; padding: 15px; background: #ecf0f1; border-radius: 5px; }
+            .examples { background: #f8f9fa; padding: 15px; border-radius: 5px; margin: 20px 0; }
+        </style>
+    </head>
+    <body>
+        <div class="container">
+            <h1>🌸 Iris Flower Classification API</h1>
+            <p>Masukkan nilai fitur bunga Iris untuk memprediksi spesiesnya:</p>
+            
+            <form id="irisForm">
+                <div class="feature">
+                    <label>Sepal Length (cm):</label>
+                    <input type="number" step="0.1" id="sepal_length" placeholder="e.g., 5.1" required>
+                </div>
+                <div class="feature">
+                    <label>Sepal Width (cm):</label>
+                    <input type="number" step="0.1" id="sepal_width" placeholder="e.g., 3.5" required>
+                </div>
+                <div class="feature">
+                    <label>Petal Length (cm):</label>
+                    <input type="number" step="0.1" id="petal_length" placeholder="e.g., 1.4" required>
+                </div>
+                <div class="feature">
+                    <label>Petal Width (cm):</label>
+                    <input type="number" step="0.1" id="petal_width" placeholder="e.g., 0.2" required>
+                </div>
+                
+                <button type="submit">Prediksi Spesies</button>
+                <button type="button" onclick="loadExample(1)">Contoh Setosa</button>
+                <button type="button" onclick="loadExample(2)">Contoh Versicolor</button>
+                <button type="button" onclick="loadExample(3)">Contoh Virginica</button>
+            </form>
+            
+            <div id="result" class="result" style="display:none;">
+                <h3>Hasil Prediksi:</h3>
+                <p id="prediction"></p>
+                <p id="confidence"></p>
+            </div>
+            
+            <div class="examples">
+                <h3>Contoh Data:</h3>
+                <p><strong>Setosa:</strong> Sepal Length: 5.1, Sepal Width: 3.5, Petal Length: 1.4, Petal Width: 0.2</p>
+                <p><strong>Versicolor:</strong> Sepal Length: 7.0, Sepal Width: 3.2, Petal Length: 4.7, Petal Width: 1.4</p>
+                <p><strong>Virginica:</strong> Sepal Length: 6.3, Sepal Width: 3.3, Petal Length: 6.0, Petal Width: 2.5</p>
+            </div>
+        </div>
+
+        <script>
+            function loadExample(type) {
+                if (type === 1) {
+                    document.getElementById('sepal_length').value = 5.1;
+                    document.getElementById('sepal_width').value = 3.5;
+                    document.getElementById('petal_length').value = 1.4;
+                    document.getElementById('petal_width').value = 0.2;
+                } else if (type === 2) {
+                    document.getElementById('sepal_length').value = 7.0;
+                    document.getElementById('sepal_width').value = 3.2;
+                    document.getElementById('petal_length').value = 4.7;
+                    document.getElementById('petal_width').value = 1.4;
+                } else if (type === 3) {
+                    document.getElementById('sepal_length').value = 6.3;
+                    document.getElementById('sepal_width').value = 3.3;
+                    document.getElementById('petal_length').value = 6.0;
+                    document.getElementById('petal_width').value = 2.5;
+                }
+            }
+            
+            document.getElementById('irisForm').addEventListener('submit', function(e) {
+                e.preventDefault();
+                
+                const data = {
+                    sepal_length: parseFloat(document.getElementById('sepal_length').value),
+                    sepal_width: parseFloat(document.getElementById('sepal_width').value),
+                    petal_length: parseFloat(document.getElementById('petal_length').value),
+                    petal_width: parseFloat(document.getElementById('petal_width').value)
+                };
+                
+                fetch('/predict', {
+                    method: 'POST',
+                    headers: {
+                        'Content-Type': 'application/json',
+                    },
+                    body: JSON.stringify(data)
+                })
+                .then(response => response.json())
+                .then(data => {
+                    if (data.error) {
+                        alert('Error: ' + data.error);
+                    } else {
+                        document.getElementById('prediction').innerHTML = 
+                            `<strong>Spesies: ${data.species}</strong>`;
+                        document.getElementById('confidence').innerHTML = 
+                            `Confidence: ${data.confidence}`;
+                        document.getElementById('result').style.display = 'block';
+                    }
+                })
+                .catch(error => {
+                    alert('Error: ' + error);
+                });
+            });
+        </script>
+    </body>
+    </html>
+    """
+    return html
+
+@app.route('/predict', methods=['POST'])
+def predict_iris():
+    try:
+        # Ambil data dari request
+        data = request.json
+        
+        if not data:
+            return jsonify({'error': 'No data provided'}), 400
+        
+        # Validasi input
+        required_fields = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']
+        for field in required_fields:
+            if field not in data:
+                return jsonify({'error': f'Missing field: {field}'}), 400
+            if not isinstance(data[field], (int, float)):
+                return jsonify({'error': f'Invalid value for {field}. Must be a number'}), 400
+        
+        # Konversi ke array numpy
+        features = np.array([[
+            data['sepal_length'],
+            data['sepal_width'], 
+            data['petal_length'],
+            data['petal_width']
+        ]])
+        
+        # Validasi range nilai (opsional)
+        if any(val < 0 for val in features[0]):
+            return jsonify({'error': 'All feature values must be positive'}), 400
+        
+        # Prediksi
+        prediction = model.predict(features)[0]
+        prediction_proba = model.predict_proba(features)[0]
+        
+        # Konversi ke nama spesies
+        species = target_names[prediction]
+        confidence = f"{prediction_proba[prediction]:.2%}"
+        
+        # Tambahan info untuk debugging
+        probabilities = {
+            target_names[i]: f"{prob:.2%}" 
+            for i, prob in enumerate(prediction_proba)
+        }
+        
+        return jsonify({
+            'species': species,
+            'species_code': int(prediction),
+            'confidence': confidence,
+            'all_probabilities': probabilities,
+            'input_features': {
+                'sepal_length': data['sepal_length'],
+                'sepal_width': data['sepal_width'],
+                'petal_length': data['petal_length'],
+                'petal_width': data['petal_width']
+            }
+        })
+        
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/model-info', methods=['GET'])
+def model_info():
+    """Endpoint untuk mendapatkan informasi model"""
+    try:
+        # Dapatkan feature importance
+        feature_importance = model.feature_importances_
+        feature_info = {
+            feature_names[i]: float(importance) 
+            for i, importance in enumerate(feature_importance)
+        }
+        
+        return jsonify({
+            'model_type': 'Decision Tree Classifier',
+            'features': list(feature_names),
+            'target_classes': list(target_names),
+            'feature_importance': feature_info,
+            'tree_depth': model.get_depth(),
+            'number_of_leaves': model.get_n_leaves(),
+            'training_samples': len(iris.data)
+        })
+        
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/health', methods=['GET'])
+def health():
+    return jsonify({
+        'status': 'OK', 
+        'message': 'Iris Classification API is running',
+        'model_loaded': model is not None
+    }), 200
+
+if __name__ == '__main__':
+    app.run(debug=True, host='0.0.0.0', port=7860)

iris_dataset_info.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cdf80af780e5869c3dcb58a9cd0727be89385b7e95f2bf5e0dca0a22b199a2
+size 432

iris_decision_tree_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf10bdbf4836130c150782b8526ebe4cfdb0d0317fa3780cfa87ef555a0af13e
+size 3297

requirements.txt

@@ -0,0 +1,19 @@
+# Core data science libraries
+pandas>=1.3.0
+numpy>=1.21.0
+matplotlib>=3.4.0
+seaborn>=0.11.0
+scikit-learn>=1.0.0
+
+# Web framework and API
+Flask>=2.0.0
+flask-cors>=3.0.0
+
+# Machine learning model persistence
+joblib>=1.0.0
+
+# Development and notebook
+jupyter>=1.0.0
+
+# Optional: for better performance
+gunicorn>=20.0.0