"""
Iris Flower Classifier — Web App
================================
A Flask web app that takes flower measurements and predicts the species.
Run with: python app.py
"""

import joblib
import numpy as np
from flask import Flask, render_template, request, jsonify

app = Flask(__name__)

# Load trained model artifacts
model = joblib.load('models/iris_model.pkl')
scaler = joblib.load('models/scaler.pkl')
label_encoder = joblib.load('models/label_encoder.pkl')
metadata = joblib.load('models/metadata.pkl')

SPECIES_INFO = {
    'Iris-setosa': {
        'emoji': '🌸',
        'color': '#FF6B6B',
        'description': 'Small flowers with short, narrow petals. Found in Arctic and temperate regions.',
    },
    'Iris-versicolor': {
        'emoji': '🌺',
        'color': '#4ECDC4',
        'description': 'Medium-sized flowers with wider petals. Native to North America.',
    },
    'Iris-virginica': {
        'emoji': '🌷',
        'color': '#A06CD5',
        'description': 'Large flowers with long, wide petals. Found in eastern North America.',
    },
}


@app.route('/')
def index():
    return render_template('index.html', model_name=metadata['model_name'],
                         accuracy=metadata['accuracy'])


@app.route('/predict', methods=['POST'])
def predict():
    try:
        data = request.get_json()
        features = np.array([[
            float(data['sepal_length']),
            float(data['sepal_width']),
            float(data['petal_length']),
            float(data['petal_width']),
        ]])

        scaled = scaler.transform(features)
        prediction = model.predict(scaled)[0]
        species = label_encoder.inverse_transform([prediction])[0]

        # Get confidence (decision function or probability)
        try:
            proba = model.predict_proba(scaled)[0]
            confidence = float(max(proba)) * 100
            all_proba = {label_encoder.inverse_transform([i])[0]: round(float(p) * 100, 1)
                        for i, p in enumerate(proba)}
        except AttributeError:
            confidence = 95.0
            all_proba = {species: 95.0}

        info = SPECIES_INFO.get(species, {})

        return jsonify({
            'species': species,
            'confidence': round(confidence, 1),
            'probabilities': all_proba,
            'emoji': info.get('emoji', '🌿'),
            'color': info.get('color', '#666'),
            'description': info.get('description', ''),
        })

    except Exception as e:
        return jsonify({'error': str(e)}), 400


if __name__ == '__main__':
    print(f"\nIris Classifier Web App")
    print(f"Model: {metadata['model_name']} (accuracy: {metadata['accuracy']:.1%})")
    print(f"Open: http://localhost:5000\n")
    app.run(debug=True, port=5000)