Guardar mis cambios locales

app.py

@@ -1,51 +1,48 @@
-import streamlit as st
 import pandas as pd
 import matplotlib.pyplot as plt
 from statsmodels.tsa.arima.model import ARIMA
 import pickle
+import gradio as gr
 
-def main():
-    st.title("MLCast v1.1 - Intelligent Sales Forecasting System")
-    uploaded_file = st.file_uploader("Upload your store data here (must contain Date and Sales)", type="csv")
+def load_model():
+    with open('Forecast_TimeSeries_Sales/arima_sales_model.pkl', 'rb') as f:
+        arima_model = pickle.load(f)
+    return arima_model
+
+def forecast_sales(uploaded_file, forecast_period=30):
+    df = pd.read_csv(uploaded_file)
+    if 'Date' in df.columns and 'Sale' in df.columns:
+        df['Date'] = pd.to_datetime(df['Date'])
+        df = df.rename(columns={'Date': 'ds', 'Sale': 'y'})
+
+        arima_model = load_model()
+        forecast = arima_model.get_forecast(steps=forecast_period)
+        forecast_index = pd.date_range(df['ds'].max(), periods=forecast_period + 1, freq='D')[1:]
+        forecast_df = pd.DataFrame({'Date': forecast_index, 'Sales Forecast': forecast.predicted_mean})
+        
+        # Create the plot
+        fig, ax = plt.subplots(figsize=(10, 6))
+        ax.plot(df['ds'], df['y'], label='Historical Sales', color='blue')
+        ax.plot(forecast_df['Date'], forecast_df['Sales Forecast'], label='Sales Forecast', color='red', linestyle='--')
+        ax.set_xlabel('Date')
+        ax.set_ylabel('Sales')
+        ax.set_title('Sales Forecasting with ARIMA')
+        ax.legend()
+        return fig
+    else:
+        return "The uploaded file must contain at least 'Date' and 'Sales' columns."
+
+def setup_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("## MLCast v1.1 - Intelligent Sales Forecasting System")
+        with gr.Row():
+            file_input = gr.File(label="Upload your store data here (must contain Date and Sales)")
+            forecast_button = gr.Button("Forecast Sales")
+        output_plot = gr.Plot()
+        forecast_button.click(forecast_sales, inputs=[file_input], outputs=[output_plot])
     
-    if uploaded_file is not None:
-        df = pd.read_csv(uploaded_file)
-        if 'Date' in df.columns and 'Sale' in df.columns:
-            st.success("File uploaded successfully!")
-            st.write(df.head())
-            df['Date'] = pd.to_datetime(df['Date'])
-            df_arima = df.rename(columns={'Date': 'ds', 'Sale': 'y'})
-            
-            with open('Forecast_TimeSeries_Sales\arima_sales_model.pkl', 'rb') as f:
-                arima_model = pickle.load(f)
-            
-            forecast_period = 30
-            forecast = arima_model.get_forecast(steps=forecast_period)
-            forecast_index = pd.date_range(df['Date'].max(), periods=forecast_period + 1, freq='D')[1:]
-            forecast_df = pd.DataFrame({'Date': forecast_index, 'Sales Forecast': forecast.predicted_mean})
-            
-            fig, ax = plt.subplots(figsize=(10, 6))
-            ax.plot(df['Date'], df['Sale'], label='Historical Sales', color='blue')
-            ax.plot(forecast_df['Date'], forecast_df['Sales Forecast'], label='Sales Forecast', color='red', linestyle='--')
-            ax.set_xlabel('Date')
-            ax.set_ylabel('Sales')
-            ax.set_title('Sales Forecasting with ARIMA')
-            ax.legend()
-            st.pyplot(fig)
-            
-            st.sidebar.title("Adjust Forecast Range")
-            start_date = st.sidebar.date_input('Start Date', df['Date'].min())
-            end_date = st.sidebar.date_input('End Date', df['Date'].max())
-            filtered_df = df[(df['Date'] >= pd.to_datetime(start_date)) & (df['Date'] <= pd.to_datetime(end_date))]
-            fig_filtered, ax_filtered = plt.subplots(figsize=(10, 6))
-            ax_filtered.plot(filtered_df['Date'], filtered_df['Sale'], label=f'Sales from {start_date} to {end_date}')
-            ax_filtered.set_xlabel('Date')
-            ax_filtered.set_ylabel('Sale')
-            ax_filtered.set_title(f'Sales Forecasting from {start_date} to {end_date}')
-            ax_filtered.legend()
-            st.pyplot(fig_filtered)
-        else:
-            st.error("The uploaded file must contain at least 'Date' and 'Sales' columns.")
+    return demo
 
 if __name__ == "__main__":
-    main()
+    interface = setup_interface()
+    interface.launch()