Update app.py

app.py

@@ -3,7 +3,7 @@ import pandas as pd
 from neuralprophet import NeuralProphet
 import io
 import warnings
-import torch
+import torch.optim.lr_scheduler as lr_scheduler
 
 warnings.filterwarnings("ignore", category=UserWarning)
 
@@ -15,10 +15,12 @@ df.fillna(method='ffill', inplace=True)
 df.dropna(inplace=True)
 
 class CustomNeuralProphet(NeuralProphet):
-    def lr_scheduler_step(self, epoch: int = None) -> None:
-        # Override the lr_scheduler_step method to avoid the MisconfigurationException
-        if self.lr_scheduler is not None and isinstance(self.lr_scheduler, torch.optim.lr_scheduler.OneCycleLR):
-            self.lr_scheduler.step()
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.lr_scheduler = lr_scheduler.ReduceLROnPlateau(self.trainer.optimizers[0], mode='min', factor=0.5, patience=10, verbose=True)
+
+    def lr_scheduler_step(self, metrics):
+        self.lr_scheduler.step(metrics)
 
 m = CustomNeuralProphet(
     n_forecasts=30,
@@ -27,7 +29,7 @@ m = CustomNeuralProphet(
     num_hidden_layers=3,
     yearly_seasonality=True,
     n_changepoints=150,
-    trend_reg_threshold=False,  # Disable trend regularization threshold
+    trend_reg_threshold=False,
     d_hidden=3,
     global_normalization=True,
     seasonality_reg=1,
@@ -44,28 +46,19 @@ forecast = m.predict(future)
 
 
 def predict_vn_index(option=None):
-    fig1 = m.plot(forecast)
-    fig1_path = "forecast_plot1.png"
-    fig1.savefig(fig1_path)
-
-    # Add code to generate the second image (fig2)
-    fig2 = m.plot_latest_forecast(forecast)  # Replace this line with code to generate the second image
-    fig2_path = "forecast_plot2.png"
-    fig2.savefig(fig2_path)
+    fig = m.plot(forecast)
+    path = "forecast_plot.png"
+    fig.savefig(path)
     disclaimer = "Quý khách chỉ xem đây là tham khảo, công ty không chịu bất cứ trách nhiệm nào về tình trạng đầu tư của quý khách."
-
-    return fig1_path, fig2_path, disclaimer
+    return path, disclaimer
 
 
 if __name__ == "__main__":
     dropdown = gr.inputs.Dropdown(["VNIndex"], label="Choose an option", default="VNIndex")
-    outputs = [
-        gr.outputs.Image(type="filepath", label="First Image"),
-        gr.outputs.Image(type="filepath", label="Second Image"),
-        gr.outputs.Textbox(label="Disclaimer")
-    ]
-    interface = gr.Interface(fn=predict_vn_index, inputs=dropdown, outputs=outputs, title="Dự báo VN Index 30 ngày tới")
-    interface.launch()
+    image_output = gr.outputs.Image(type="file", label="Forecast Plot")
+    disclaimer_output = gr.outputs.Textbox(label="Disclaimer")
+    interface = gr.Interface(fn=predict_vn_index, inputs=dropdown, outputs=[image_output, disclaimer_output], title="Dự báo VN Index 30 ngày tới")
+    interface.launch(share=True)