Update app.py

app.py

@@ -6,110 +6,66 @@ import numpy as np
 import requests
 import pandas as pd
 from fastapi.middleware.wsgi import WSGIMiddleware
+from tensorflow.keras.models import load_model
 
 flask_app = Flask(__name__)
 
-# Load model dan scaler yang sudah disimpan
-with open('model.pkl', 'rb') as model_file:
-    model = pickle.load(model_file)
-
+# Load model dan scaler
+model = load_model('model.keras')  # Pastikan model.keras ada di direktori yang sama dengan app.py
 with open('scaler.pkl', 'rb') as scaler_file:
     scaler = pickle.load(scaler_file)
 
-# Halaman utama
+with open('scaler1.pkl', 'rb') as scaler_file:
+    scaler_pred = pickle.load(scaler_file)
+
+# Konfigurasi
+stockname = "ADARO"
+FEATURES = ['High', 'Low', 'Open', 'Close', 'Volume']
+sequence_length = 50
+
+# Endpoint untuk halaman utama (HTML)
 @flask_app.route('/')
 def home():
     return render_template('index.html')
 
-# Endpoint untuk prediksi berdasarkan input pengguna
-@flask_app.route('/predict', methods=['POST'])
+# Endpoint untuk prediksi harga saham
+@flask_app.route('/predict', methods=['GET'])
 def predict():
-    try:
-        # Mendapatkan data dari form input
-        input_data = request.get_json()
-
-        # Ambil nilai input (pastikan semuanya adalah angka)
-        sell_1 = float(input_data['features'][2])
-        sell_2 = float(input_data['features'][1])
-        sell_3 = float(input_data['features'][0])
-
-        # Normalisasi data menggunakan scaler
-        last_row = np.array([
-            scaler.transform([[sell_1]]).flatten()[0],
-            scaler.transform([[sell_2]]).flatten()[0],
-            scaler.transform([[sell_3]]).flatten()[0]
-        ]).reshape(1, -1)
-
-        # Buat DataFrame dari nilai yang telah dinormalisasi
-        last_row_df = pd.DataFrame(last_row, columns=['sell-1', 'sell-2', 'sell-3'])
-
-        # Prediksi harga berdasarkan model
-        predicted_value_normalized = model.predict(last_row_df)
-        predicted_value = scaler.inverse_transform(predicted_value_normalized.reshape(-1, 1))
-
-        # Ambil harga emas terakhir untuk perhitungan persentase
-        last_price_inversed = sell_1  # Menggunakan harga hari ketiga (sell_3) sebagai harga terakhir
-
-        # Hitung perubahan persentase
-        percentage_change = ((predicted_value[0][0] - last_price_inversed) / last_price_inversed) * 100
-
-        # Tentukan tanda perubahan (positif atau negatif)
-        change_sign = '+' if percentage_change > 0 else ''
-
-        # Kembalikan hasil prediksi dalam bentuk JSON
-        return jsonify({
-            'last_price': last_price_inversed,
-            'predicted_value': predicted_value[0][0],
-            'percentage_change': f"{change_sign}{percentage_change:.2f}%",
-            'raw_data': input_data
-        })
-
-
-    except Exception as e:
-        return jsonify({'error': str(e)}), 400
-
-# Endpoint untuk prediksi otomatis berdasarkan data API
-@flask_app.route('/auto-predict', methods=['POST'])
-def auto_predict():
-    try:
-        # Mendapatkan data yang dikirimkan dari frontend
-        input_data = request.get_json()
-        print(input_data)
-        # Ambil nilai input (pastikan semuanya adalah angka)
-        price_day_1 = float(input_data['features'][0])
-        price_day_2 = float(input_data['features'][1])
-        price_day_3 = float(input_data['features'][2])
-        last_row = np.array([
-            scaler.transform([[price_day_1]]).flatten()[0],
-            scaler.transform([[price_day_2]]).flatten()[0],
-            scaler.transform([[price_day_3]]).flatten()[0]
-        ]).reshape(1, -1)
-        last_row_df = pd.DataFrame(last_row, columns=['sell-1', 'sell-2', 'sell-3'])
-        # Prediksi harga
-        predicted_value_normalized = model.predict(last_row_df)
-        predicted_value = scaler.inverse_transform(predicted_value_normalized.reshape(-1, 1))
-
-        # Ambil harga emas terakhir untuk perhitungan persentase
-        last_price_inversed = price_day_3
-
-        # Hitung perubahan persentase
-        percentage_change = ((predicted_value[0][0] - last_price_inversed) / last_price_inversed) * 100
-
-        # Tentukan tanda perubahan (positif atau negatif)
-        if percentage_change > 0:
-            change_sign = '+'
-        else:
-            change_sign = ''
-
-        return jsonify({
-            'last_price': last_price_inversed,
-            'predicted_value': predicted_value[0][0],
-            'percentage_change': f"{change_sign}{percentage_change:.2f}%",
-            'raw_data': input_data
-        })
-
-    except Exception as e:
-        return jsonify({'error': str(e)}), 400
+    # Load data
+    url = 'https://raw.githubusercontent.com/atsugaa/psd/refs/heads/main/ADRO.csv'
+    df = pd.read_csv(url)
+    df['Date'] = pd.to_datetime(df['Date'], dayfirst=True).dt.date
+    df.set_index('Date', inplace=True)
+    df.index = pd.to_datetime(df.index)
+    df = df.sort_values(by=['Date'])
+
+    # Ambil fitur yang diperlukan
+    input_df = df[FEATURES]
+    target_df = df['Close']
+    last_N_days = input_df[-sequence_length:].values
+
+    # Pastikan data mencukupi
+    if len(last_N_days) < sequence_length:
+        return jsonify({"error": "Data tidak mencukupi untuk prediksi"}), 400
+
+    # Skala data
+    last_N_days_scaled = scaler.transform(last_N_days)
+
+    # Siapkan data untuk prediksi
+    X_test_new = [last_N_days_scaled]
+
+    # Prediksi harga
+    pred_price_scaled = model.predict(np.array(X_test_new))
+    pred_price_unscaled = scaler_pred.inverse_transform(pred_price_scaled.reshape(-1, 1))
+
+    # Hitung perubahan dan hasil akhir
+    price_today = np.round(df['Close'][-1], 2)
+    predicted_price = np.round(pred_price_unscaled.ravel()[0], 2)
+    change_percent = np.round(100 - (price_today * 100) / predicted_price, 2)
+
+    # Kirim respons ke halaman HTML
+    return render_template('index.html', stock=stockname, price_today=price_today, 
+                           predicted_price=predicted_price, change_percent=change_percent)
 
 app = FastAPI()
 app.mount("/", WSGIMiddleware(flask_app))