Update app.py

app.py

@@ -13,34 +13,74 @@ import requests
 from dotenv import load_dotenv
 from werkzeug.utils import secure_filename
 
-# Load environment variables
+# =========================================================
+# ENV & APP CONFIG
+# =========================================================
 load_dotenv()
 OPENWEATHER_API_KEY = os.getenv("OPENWEATHER_API_KEY")
 
-# Inisialisasi Flask
 app = Flask(__name__)
-UPLOAD_FOLDER = '/tmp/uploads'
+UPLOAD_FOLDER = "/tmp/uploads"
 os.makedirs(UPLOAD_FOLDER, exist_ok=True)
 
-# Label klasifikasi tanah
-class_labels = ['Alluvial Soil', 'Black Soil', 'Clay Soil', 'Non Soil', 'Red Soil']
+# =========================================================
+# GLOBAL PLACEHOLDERS (LAZY LOADING)
+# =========================================================
+soil_model = None
+crop_model = None
+crop_model_label = None
+soil_df = None
+agri_df = None
+
+class_labels = [
+    "Alluvial Soil",
+    "Black Soil",
+    "Clay Soil",
+    "Non Soil",
+    "Red Soil"
+]
 num_classes = len(class_labels)
 
-# Load model ViT (PyTorch)
-soil_model = timm.create_model("vit_base_patch16_224", pretrained=False, num_classes=num_classes)
-soil_model.head = nn.Linear(soil_model.head.in_features, num_classes)
-soil_model.load_state_dict(torch.load("models/best_vit_model.pth", map_location=torch.device("cpu")))
-soil_model.eval()
-
-# Load model crop recommendation
-crop_model = joblib.load("models/model_random_forest.joblib")
-crop_model_label = joblib.load("models/label_encoder.joblib")
-
-# Load data referensi
-soil_df = pd.read_csv("data/soil_data.csv")
-agri_df = pd.read_csv("data/tips_menanam_dan_manfaat_tanaman.csv")
-
-# Fungsi preprocessing gambar (PyTorch style)
+# =========================================================
+# MODEL & DATA LOADERS (LAZY)
+# =========================================================
+def load_soil_model():
+    global soil_model
+    if soil_model is None:
+        model = timm.create_model(
+            "vit_base_patch16_224",
+            pretrained=False,
+            num_classes=num_classes
+        )
+        model.head = nn.Linear(model.head.in_features, num_classes)
+        state = torch.load(
+            "models/best_vit_model.pth",
+            map_location=torch.device("cpu")
+        )
+        model.load_state_dict(state)
+        model.eval()
+        soil_model = model
+    return soil_model
+
+
+def load_crop_model():
+    global crop_model, crop_model_label
+    if crop_model is None:
+        crop_model = joblib.load("models/model_random_forest.joblib")
+        crop_model_label = joblib.load("models/label_encoder.joblib")
+    return crop_model, crop_model_label
+
+
+def load_dataframes():
+    global soil_df, agri_df
+    if soil_df is None:
+        soil_df = pd.read_csv("data/soil_data.csv")
+    if agri_df is None:
+        agri_df = pd.read_csv("data/tips_menanam_dan_manfaat_tanaman.csv")
+
+# =========================================================
+# IMAGE PREPROCESS
+# =========================================================
 def preprocess_image(img_path):
     transform = transforms.Compose([
         transforms.Resize((224, 224)),
@@ -50,197 +90,164 @@ def preprocess_image(img_path):
     img = Image.open(img_path).convert("RGB")
     return transform(img).unsqueeze(0)
 
-# Fungsi prediksi jenis tanah
+# =========================================================
+# SOIL PREDICTION
+# =========================================================
 def predict_soil_type(img_path):
+    model = load_soil_model()
     img_tensor = preprocess_image(img_path)
     with torch.no_grad():
-        outputs = soil_model(img_tensor)
+        outputs = model(img_tensor)
         probabilities = torch.softmax(outputs, dim=1).numpy()[0]
-    predicted_index = np.argmax(probabilities)
-    predicted_class = class_labels[predicted_index]
-    accuracy = float(probabilities[predicted_index])
-    return predicted_class, accuracy
-
-# Hitung jarak dengan haversine
-def find_nearest_soil_data_weighted(soil_type, lat, lon, n_points=1):
-    filtered = soil_df[soil_df['Soil_Type'] == soil_type].copy()
+    idx = int(np.argmax(probabilities))
+    return class_labels[idx], float(probabilities[idx])
+
+# =========================================================
+# HAVERSINE & SOIL DATA
+# =========================================================
+def find_nearest_soil_data_weighted(soil_type, lat, lon):
+    load_dataframes()
+    filtered = soil_df[soil_df["Soil_Type"] == soil_type].copy()
     if filtered.empty:
         return None
 
     user_lat, user_lon = radians(lat), radians(lon)
 
     def haversine(row):
-        lat2, lon2 = radians(row['Location_Latitude']), radians(row['Location_Longitude'])
-        dlat = lat2 - user_lat
-        dlon = lon2 - user_lon
-        a = sin(dlat / 2)**2 + cos(user_lat) * cos(lat2) * sin(dlon / 2)**2
-        c = 2 * atan2(sqrt(a), sqrt(1 - a))
+        lat2, lon2 = radians(row["Location_Latitude"]), radians(row["Location_Longitude"])
+        dlat, dlon = lat2 - user_lat, lon2 - user_lon
+        a = sin(dlat/2)**2 + cos(user_lat)*cos(lat2)*sin(dlon/2)**2
+        c = 2 * atan2(sqrt(a), sqrt(1-a))
         return 6371 * c
 
-    filtered['Distance_km'] = filtered.apply(haversine, axis=1)
-    nearest = filtered.nsmallest(n_points, 'Distance_km').copy()
+    filtered["Distance_km"] = filtered.apply(haversine, axis=1)
+    row = filtered.nsmallest(1, "Distance_km").iloc[0]
 
-    row = nearest.iloc[0]
     return {
-        "latitude": float(row['Location_Latitude']),
-        "longitude": float(row['Location_Longitude']),
-        "pH": float(row['pH']),
-        "N": float(row['Nitrogen_N_ppm']),
-        "P": float(row['Phosphorus_P_ppm']),
-        "K": float(row['Potassium_K_ppm']),
-        "distance_km": float(row['Distance_km'])
+        "latitude": float(row["Location_Latitude"]),
+        "longitude": float(row["Location_Longitude"]),
+        "pH": float(row["pH"]),
+        "N": float(row["Nitrogen_N_ppm"]),
+        "P": float(row["Phosphorus_P_ppm"]),
+        "K": float(row["Potassium_K_ppm"]),
+        "distance_km": float(row["Distance_km"])
     }
 
-# Ambil data cuaca dari OpenWeather
+# =========================================================
+# WEATHER & GEO
+# =========================================================
 def get_weather_data(lat, lon):
-    url = f"https://api.openweathermap.org/data/2.5/weather?lat={lat}&lon={lon}&appid={OPENWEATHER_API_KEY}&units=metric"
-    res = requests.get(url)
+    url = (
+        f"https://api.openweathermap.org/data/2.5/weather"
+        f"?lat={lat}&lon={lon}&appid={OPENWEATHER_API_KEY}&units=metric"
+    )
+    res = requests.get(url, timeout=10)
     if res.status_code != 200:
         return None
     data = res.json()
     return {
-        "temperature": float(data['main']['temp']),
-        "humidity": float(data['main']['humidity']),
+        "temperature": float(data["main"]["temp"]),
+        "humidity": float(data["main"]["humidity"])
     }
 
-# Ambil tips bertani dan manfaat tanaman
-def get_farming_tips(df, crop_name):
-    crop_name_str = str(crop_name)
-    match = df[df['Nama Tanaman'].str.lower() == crop_name_str.lower()]
-    if not match.empty:
-        row = match.iloc[0]
-        return {
-            "id": int(row['ID']) if 'ID' in row else None,
-            "Nama Tanaman": row['Nama Tanaman'],
-            "Tips Menanam": row.get('Tips Menanam', 'Tidak tersedia'),
-            "Manfaat": row.get('Manfaat', 'Tidak tersedia')
-        }
-    return None
 
-# Reverse geocoding
 def get_location_name(lat, lon):
     try:
         url = f"https://nominatim.openstreetmap.org/reverse?lat={lat}&lon={lon}&format=json"
         headers = {"User-Agent": "soil-api/1.0"}
-        response = requests.get(url, headers=headers, timeout=10)
-        if response.status_code == 200:
-            data = response.json()
-            return data.get("display_name", "Tidak ditemukan")
-        else:
-            return "Tidak ditemukan"
+        res = requests.get(url, headers=headers, timeout=10)
+        if res.status_code == 200:
+            return res.json().get("display_name", "Tidak ditemukan")
     except Exception:
-        return "Tidak ditemukan"
+        pass
+    return "Tidak ditemukan"
 
-# Halaman landing
-@app.route('/')
+# =========================================================
+# FARMING TIPS
+# =========================================================
+def get_farming_tips(df, crop_name):
+    match = df[df["Nama Tanaman"].str.lower() == str(crop_name).lower()]
+    if not match.empty:
+        row = match.iloc[0]
+        return {
+            "Nama Tanaman": row["Nama Tanaman"],
+            "Tips Menanam": row.get("Tips Menanam", "Tidak tersedia"),
+            "Manfaat": row.get("Manfaat", "Tidak tersedia")
+        }
+    return {"Tanaman": crop_name, "Pesan": "Data tidak tersedia"}
+
+# =========================================================
+# ROUTES
+# =========================================================
+@app.route("/")
 def index():
-    html_content = """
-    <!DOCTYPE html>
-    <html>
-    <head>
-        <title>Soil & Crop Recommender</title>
-    </head>
-    <body style="font-family: Arial; text-align: center; padding: 50px;">
-        <h1>Welcome to the Soil & Crop Recommendation API 🌱</h1>
-        <p>Use the <code>/analyze</code> endpoint with an image and coordinates to get soil predictions and crop suggestions.</p>
-        <p><strong>POST /analyze</strong> with form-data:</p>
-        <ul style="list-style: none;">
-            <li><code>image</code>: soil image file</li>
-            <li><code>lat</code>: latitude</li>
-            <li><code>lon</code>: longitude</li>
-        </ul>
-        <p>Happy Farming! 🌾</p>
-    </body>
-    </html>
-    """
-    return render_template_string(html_content)
-
-# Endpoint analisis
-@app.route('/analyze', methods=['POST'])
+    return render_template_string("""
+    <h1>🌱 Soil & Crop Recommendation API</h1>
+    <p>POST <code>/analyze</code> with image, lat, lon</p>
+    """)
+
+
+@app.route("/analyze", methods=["POST"])
 def analyze():
-    if 'image' not in request.files:
+    if "image" not in request.files:
         return jsonify({"error": "Gambar tidak ditemukan"}), 400
 
-    image_file = request.files['image']
-    if image_file.filename == '':
-        return jsonify({"error": "Nama file gambar kosong"}), 400
-
     try:
-        lat = float(request.form.get('lat'))
-        lon = float(request.form.get('lon'))
-        if not (-90 <= lat <= 90 and -180 <= lon <= 180):
-            raise ValueError("Out of bounds")
+        lat = float(request.form.get("lat"))
+        lon = float(request.form.get("lon"))
     except:
         return jsonify({"error": "Koordinat tidak valid"}), 400
 
+    image_file = request.files["image"]
     filename = secure_filename(image_file.filename)
     image_path = os.path.join(UPLOAD_FOLDER, filename)
     image_file.save(image_path)
 
-    predicted_soil, soil_accuracy = predict_soil_type(image_path)
-    nearest_data = find_nearest_soil_data_weighted(predicted_soil, lat, lon)
-    if nearest_data is None:
-        return jsonify({"error": "Data jenis tanah tidak ditemukan"}), 404
+    soil_type, soil_acc = predict_soil_type(image_path)
+    nearest = find_nearest_soil_data_weighted(soil_type, lat, lon)
+    if not nearest:
+        return jsonify({"error": "Data tanah tidak ditemukan"}), 404
 
-    location_name = get_location_name(nearest_data['latitude'], nearest_data['longitude'])
     weather = get_weather_data(lat, lon)
     if not weather:
-        return jsonify({"error": "Gagal mengambil data cuaca"}), 500
-
-    input_data = pd.DataFrame([{
-        'temperature': weather['temperature'],
-        'humidity': weather['humidity'],
-        'ph': nearest_data['pH'],
-        'N': nearest_data['N'],
-        'P': nearest_data['P'],
-        'K': nearest_data['K'],
+        return jsonify({"error": "Gagal mengambil cuaca"}), 500
+
+    crop_model, crop_label = load_crop_model()
+    input_df = pd.DataFrame([{
+        "temperature": weather["temperature"],
+        "humidity": weather["humidity"],
+        "ph": nearest["pH"],
+        "N": nearest["N"],
+        "P": nearest["P"],
+        "K": nearest["K"]
     }])
 
-    if hasattr(crop_model, "predict_proba"):
-        proba = crop_model.predict_proba(input_data)[0]
-        top_idx = np.argsort(proba)[::-1][:5]
-        recommended_crops = [
-            str(crop_model_label.inverse_transform([crop_model.classes_[i]])[0])
-            if hasattr(crop_model_label, "inverse_transform") else str(crop_model.classes_[i])
-            for i in top_idx
-        ]
-        crop_percentages = [round(float(proba[i]) * 100, 2) for i in top_idx]
-    else:
-        pred = crop_model.predict(input_data)[0]
-        recommended_crops = [str(crop_model_label.inverse_transform([pred])[0])] if hasattr(crop_model_label, "inverse_transform") else [str(pred)]
-        crop_percentages = [100.0]
-
-    tips_list = []
-    for crop in recommended_crops:
-        tips = get_farming_tips(agri_df, crop)
-        tips_list.append(tips if tips else {"Tanaman": crop, "Pesan": "Data tidak tersedia"})
-
-    result = {
-        "Class_Name": predicted_soil,
-        "soil_prediction_accuracy": round(soil_accuracy * 100, 2),
-        "nearest_soil_data": {
-            "latitude": nearest_data['latitude'],
-            "longitude": nearest_data['longitude'],
-            "location_name": location_name,
-            "pH": nearest_data['pH'],
-            "N": nearest_data['N'],
-            "P": nearest_data['P'],
-            "K": nearest_data['K'],
-            "distance_km": round(nearest_data['distance_km'], 2)
-        },
+    proba = crop_model.predict_proba(input_df)[0]
+    top_idx = np.argsort(proba)[::-1][:5]
+
+    load_dataframes()
+    crops = [
+        crop_label.inverse_transform([crop_model.classes_[i]])[0]
+        for i in top_idx
+    ]
+    percentages = [round(float(proba[i]) * 100, 2) for i in top_idx]
+
+    tips = [get_farming_tips(agri_df, c) for c in crops]
+
+    return jsonify({
+        "soil_type": soil_type,
+        "soil_accuracy": round(soil_acc * 100, 2),
+        "location": get_location_name(nearest["latitude"], nearest["longitude"]),
         "weather": weather,
         "recommended_crops": [
-            {
-                "crop": crop,
-                "recommendation_percentage": percent
-            }
-            for crop, percent in zip(recommended_crops, crop_percentages)
+            {"crop": c, "percentage": p}
+            for c, p in zip(crops, percentages)
         ],
-        "farming_tips": tips_list
-    }
-
-    return jsonify(result)
-
-# Jalankan server
-if __name__ == '__main__':
-    app.run(debug=True)
+        "farming_tips": tips
+    })
+
+# =========================================================
+# RUN SERVER (HF SPACES)
+# =========================================================
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)