Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,168 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import os
+import plotly.express as px
+from io import StringIO
+from datetime import datetime, timedelta
+
+# Debug: Verify file paths
+st.write("Debug: Checking file paths...")
+files_to_check = ["inference.py", "new_best_improved_model.pth", "scaler.pkl", "feature_names.json"]
+for file in files_to_check:
+    if os.path.exists(file):
+        st.write(f"{file} found")
+    else:
+        st.error(f"{file} not found")
+
+try:
+    from inference import load_model_and_artifacts, forecast
+except Exception as e:
+    st.error(f"Error importing inference: {str(e)}")
+    st.stop()
+
+st.title("Store Sales Forecasting")
+
+try:
+    model, scaler, feature_names = load_model_and_artifacts()
+    st.success("Model and artifacts loaded successfully")
+except Exception as e:
+    st.error(f"Error loading model or artifacts: {str(e)}")
+    st.stop()
+
+# Display model metrics
+st.header("Model Performance Metrics")
+metrics = {
+    "MAE": 710.75,
+    "RMSE": 1108.51,
+    "MAPE": 7.14,
+    "R2": 0.8633
+}
+st.write(f"- **MAE**: ${metrics['MAE']:.2f}")
+st.write(f"- **RMSE**: ${metrics['RMSE']:.2f}")
+st.write(f"- **MAPE**: {metrics['MAPE']:.2f}%")
+st.write(f"- **R² Score**: {metrics['R2']:.4f}")
+
+# Synthetic data generation
+st.header("Test with Synthetic Data")
+if st.button("Generate Synthetic Sample Data"):
+    np.random.seed(42)
+    sequence_length = 21
+    n_features = len(feature_names)
+    synthetic_data = np.zeros((sequence_length, n_features))
+
+    # Generate realistic data based on training sales range (~$3,000–19,000)
+    for i, feature in enumerate(feature_names):
+        if feature == "sales":
+            synthetic_data[:, i] = np.random.normal(8955, 3307, sequence_length)  # Mean=8954.97, std=3307.49
+        elif feature == "onpromotion":
+            synthetic_data[:, i] = np.random.choice([0, 1], sequence_length, p=[0.8, 0.2])
+        elif feature in ["dayofweek_sin", "dayofweek_cos", "month_sin", "month_cos"]:
+            synthetic_data[:, i] = np.sin(np.linspace(0, 2 * np.pi, sequence_length))
+        elif feature == "trend":
+            synthetic_data[:, i] = np.linspace(0, sequence_length, sequence_length)
+        elif feature == "is_weekend":
+            synthetic_data[:, i] = np.random.choice([0, 1], sequence_length, p=[0.7, 0.3])
+        elif feature == "quarter":
+            synthetic_data[:, i] = np.random.choice([1, 2, 3, 4], sequence_length)
+        elif "lag" in feature:
+            synthetic_data[:, i] = np.roll(synthetic_data[:, 0], int(feature.split('_')[-1])) if i > 0 else np.zeros(sequence_length)
+        elif "ma" in feature or "std" in feature:
+            synthetic_data[:, i] = np.random.normal(8955, 1000, sequence_length)
+        elif "ratio" in feature:
+            synthetic_data[:, i] = np.random.normal(1, 0.2, sequence_length)
+        elif "promo" in feature:
+            synthetic_data[:, i] = np.random.choice([0, 1], sequence_length, p=[0.8, 0.2])
+        elif feature == "dcoilwtico":
+            synthetic_data[:, i] = np.random.normal(80, 10, sequence_length)
+        elif feature == "is_holiday":
+            synthetic_data[:, i] = np.random.choice([0, 1], sequence_length, p=[0.9, 0.1])
+
+    synthetic_df = pd.DataFrame(synthetic_data, columns=feature_names)
+    end_date = datetime.now().date()
+    dates = [end_date - timedelta(days=x) for x in range(sequence_length-1, -1, -1)]
+    synthetic_df.index = dates
+    st.session_state["synthetic_df"] = synthetic_df
+
+    st.subheader("Synthetic Sample Data Preview")
+    st.write(synthetic_df.head())
+
+    csv_buffer = StringIO()
+    synthetic_df.to_csv(csv_buffer)
+    st.download_button(
+        label="Download Synthetic Sample CSV",
+        data=csv_buffer.getvalue(),
+        file_name="synthetic_sample.csv",
+        mime="text/csv"
+    )
+
+    try:
+        sequences = synthetic_df[feature_names].values
+        sequences = scaler.transform(sequences)
+        sequences = sequences.reshape(-1, sequence_length, n_features)
+        predictions, uncertainties = forecast(model, scaler, sequences)
+        
+        forecast_dates = [end_date + timedelta(days=x*7) for x in range(1, 14)]
+        df_predictions = pd.DataFrame({
+            'Date': forecast_dates,
+            'Predicted Sales ($)': predictions[0],
+            'Uncertainty ($)': uncertainties[0]
+        })
+        
+        st.subheader("Forecast Results")
+        st.table(df_predictions)
+        
+        fig = px.line(df_predictions, x='Date', y='Predicted Sales ($)', title='13-Week Sales Forecast')
+        fig.add_scatter(
+            x=df_predictions['Date'],
+            y=df_predictions['Predicted Sales ($)'] + df_predictions['Uncertainty ($)'],
+            mode='lines', name='Upper Bound', line=dict(dash='dash', color='red')
+        )
+        fig.add_scatter(
+            x=df_predictions['Date'],
+            y=df_predictions['Predicted Sales ($)'] - df_predictions['Uncertainty ($)'],
+            mode='lines', name='Lower Bound', line=dict(dash='dash', color='red'),
+            fill='tonexty', fillcolor='rgba(255, 0, 0, 0.1)'
+        )
+        st.plotly_chart(fig)
+    except Exception as e:
+        st.error(f"Error generating forecast: {str(e)}")
+
+# Manual CSV upload
+st.header("Upload Your Own Data")
+st.write("Upload a CSV with 21 timesteps and 20 features.")
+uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+
+if uploaded_file is not None:
+    try:
+        data = pd.read_csv(uploaded_file)
+        if set(feature_names).issubset(data.columns) and len(data) == 21:
+            sequences = data[feature_names].values
+            sequences = scaler.transform(sequences)
+            sequences = sequences.reshape(-1, 21, len(feature_names))
+            predictions, uncertainties = forecast(model, scaler, sequences)
+            df_predictions = pd.DataFrame({
+                'Week': range(1, 14),
+                'Predicted Sales ($)': predictions[0],
+                'Uncertainty ($)': uncertainties[0]
+            })
+            st.subheader("Forecast Results")
+            st.table(df_predictions)
+            
+            fig = px.line(df_predictions, x='Week', y='Predicted Sales ($)', title='13-Week Sales Forecast')
+            fig.add_scatter(
+                x=df_predictions['Week'],
+                y=df_predictions['Predicted Sales ($)'] + df_predictions['Uncertainty ($)'],
+                mode='lines', name='Upper Bound', line=dict(dash='dash', color='red')
+            )
+            fig.add_scatter(
+                x=df_predictions['Week'],
+                y=df_predictions['Predicted Sales ($)'] - df_predictions['Uncertainty ($)'],
+                mode='lines', name='Lower Bound', line=dict(dash='dash', color='red'),
+                fill='tonexty', fillcolor='rgba(255, 0, 0, 0.1)'
+            )
+            st.plotly_chart(fig)
+        else:
+            st.error(f"Invalid CSV. Ensure 21 rows and columns: {', '.join(feature_names)}")
+    except Exception as e:
+        st.error(f"Error processing CSV or making prediction: {str(e)}")