Update app.py

app.py

@@ -15,10 +15,15 @@ class TimeSeriesForecaster:
         self.original_series = None
         self.context = None
 
-    def preprocess_data(self, df, date_column, value_column, context_length=100, prediction_length=365):
+    def preprocess_data(self, df, date_column, value_column, context_length=100, prediction_length=30):
         """
         Prepare time series data from DataFrame
         """
+        # Validasi panjang prediksi
+        if prediction_length > 30:
+            st.warning("Prediction length dibatasi maksimal 30 langkah. Akan disesuaikan.")
+            prediction_length = min(prediction_length, 30)
+        
         # Ensure data is sorted by date
         df = df.sort_values(by=date_column)
         
@@ -34,12 +39,15 @@ class TimeSeriesForecaster:
         # Convert to tensor
         self.context = torch.tensor(self.original_series[-context_length:], dtype=torch.float32)
         
-        return self.context, context_length
+        return self.context, prediction_length
 
-    def forecast(self, context, prediction_length=365, num_samples=100):
+    def forecast(self, context, prediction_length=30, num_samples=100):
         """
         Perform time series forecasting
         """
+        # Pastikan prediksi tidak melebihi 30 langkah
+        prediction_length = min(prediction_length, 30)
+        
         forecasts = self.pipeline.predict(context, prediction_length, num_samples=num_samples)
         return forecasts
 
@@ -85,7 +93,7 @@ class TimeSeriesForecaster:
             label='90% Prediction Interval'
         )
         
-        plt.title('Advanced Time Series Forecast', fontsize=18, fontweight='bold', color='#2C3E50')
+        plt.title('Advanced Time Series Forecast (Max 30 Steps)', fontsize=18, fontweight='bold', color='#2C3E50')
         plt.xlabel('Time Steps', fontsize=12, color='#34495E')
         plt.ylabel('Value', fontsize=12, color='#34495E')
         plt.legend(frameon=False)
@@ -188,10 +196,10 @@ def main():
         with col4:
             prediction_length = st.slider(
                 'Forecast Horizon', 
-                min_value=30, 
-                max_value=1000, 
-                value=365,
-                help="Number of future time steps to predict"
+                min_value=1, 
+                max_value=30,  # Dibatasi maksimal 30
+                value=30,       # Default 30
+                help="Number of future time steps to predict (max 30)"
             )
         
         # Forecast generation
@@ -201,7 +209,7 @@ def main():
                 forecaster = TimeSeriesForecaster()
                 
                 # Preprocess data
-                context, _ = forecaster.preprocess_data(
+                context, prediction_length = forecaster.preprocess_data(
                     df, 
                     date_column, 
                     value_column,