Create app.py

app.py

@@ -0,0 +1,91 @@
+import gradio as gr
+import pandas as pd
+from fuzzywuzzy import process, fuzz
+import tempfile
+
+def auto_correct_names(series, threshold=90):
+    """Auto-correct typos in chatter names using fuzzy matching."""
+    unique_names = series.dropna().unique()
+    name_mapping = {}
+    
+    for name in unique_names:
+        matches = process.extractBests(
+            name, unique_names, 
+            scorer=fuzz.token_sort_ratio, 
+            score_cutoff=threshold
+        )
+        if matches:
+            best_match = max(matches, key=lambda x: (x[1], list(series).count(x[0])))
+            name_mapping[name] = best_match[0]
+    
+    return series.replace(name_mapping)
+
+def process_file(input_file):
+    """Process uploaded Excel file and return output"""
+    try:
+        # Read input file
+        input_df = pd.read_excel(input_file.name, header=1)
+        
+        # Store original date order
+        date_columns = input_df.columns[1:].tolist()
+        
+        # Melt to long format
+        df_long = input_df.melt(
+            id_vars=[input_df.columns[0]], 
+            var_name='DATE', 
+            value_name='CHATTER'
+        )
+        
+        # Force date order
+        df_long['DATE'] = pd.Categorical(
+            df_long['DATE'], 
+            categories=date_columns,
+            ordered=True
+        )
+        
+        # Clean names
+        df_long['CHATTER'] = auto_correct_names(df_long['CHATTER'])
+        
+        # Group and pivot
+        grouped = df_long.groupby(['CHATTER', 'DATE'], observed=True)[input_df.columns[0]] \
+            .apply(lambda x: ', '.join(sorted(x))).reset_index()
+        
+        pivoted = grouped.pivot(index='CHATTER', columns='DATE', values=input_df.columns[0])
+        chatter_order = grouped['CHATTER'].value_counts().index.tolist()
+        final_df = pivoted.reindex(chatter_order)[date_columns].fillna("OFF")
+        
+        # Create temp file for output
+        with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as tmp:
+            final_df.to_excel(tmp.name, sheet_name='Schedule')
+            return final_df, tmp.name
+
+    except Exception as e:
+        return f"Error processing file: {str(e)}", None
+
+# Gradio interface
+with gr.Blocks(title="Schedule Processor") as demo:
+    gr.Markdown("# 📅 Schedule Processor")
+    gr.Markdown("Upload your schedule Excel file and download the formatted version")
+    
+    with gr.Row():
+        input_file = gr.File(label="Upload Schedule File", type="file")
+        output_file = gr.File(label="Download Processed File", visible=False)
+    
+    output_table = gr.Dataframe(label="Preview", headers=[])
+    
+    btn = gr.Button("Process File")
+    
+    def process_and_show(file):
+        df, out_path = process_file(file)
+        if out_path:
+            return df, gr.File.update(value=out_path, visible=True), gr.Dataframe.update(value=df)
+        return df, gr.File.update(visible=False), gr.Dataframe.update(visible=False)
+    
+    btn.click(
+        process_and_show,
+        inputs=input_file,
+        outputs=[output_table, output_file, output_table]
+    )
+
+if __name__ == "__main__":
+    demo.launch()