Upload folder using huggingface_hub

app.py

@@ -106,7 +106,8 @@ with tab2:
                     )
 
                 st.dataframe(df)
+                error_summary_table(df)
                 plot_actual_vs_predicted_scatter(df)
-
+                
         except Exception as e:
             st.error(f"⚠️ Error while processing the file: {e}")

predictor/error_summary_table.py

@@ -0,0 +1,33 @@
+
+import altair as alt
+import pandas as pd
+import streamlit as st
+
+def error_summary_table(df: pd.DataFrame):
+    if "Product_Store_Sales_Total" not in df.columns or "Predicted_Sales" not in df.columns:
+        st.warning("Required columns missing for error summary.")
+        return
+
+    plot_df = df[["Product_Store_Sales_Total", "Predicted_Sales"]].dropna().copy()
+    plot_df["Error"] = abs(plot_df["Product_Store_Sales_Total"] - plot_df["Predicted_Sales"])
+
+    # Define thresholds
+    conditions = [
+        (plot_df["Error"] <= 500),
+        (plot_df["Error"] > 500) & (plot_df["Error"] <= 1500),
+        (plot_df["Error"] > 1500)
+    ]
+    labels = ["Accurate (<=500)", "Moderate (501-1500)", "High Error (>1500)"]
+    plot_df["Error_Category"] = pd.cut(
+        plot_df["Error"],
+        bins=[-float('inf'), 500, 1500, float('inf')],
+        labels=labels
+    )
+
+    summary = plot_df["Error_Category"].value_counts().reset_index()
+    summary.columns = ["Error Category", "Number of Records"]
+
+    st.subheader("🔍 Error Summary")
+    st.table(summary)
+
+    return summary