Update app.py

app.py

@@ -6,71 +6,65 @@ def process_file(file):
     # 1. Validate extension
     name = file.name.lower()
     if not name.endswith(('.xls', '.xlsx', '.xlsm')):
-        return "Error: Please upload .xls/.xlsx/.xlsm file.", None
+        return "Error: Please upload a .xls, .xlsx or .xlsm file.", None
 
-    # 2. Read without header, drop blank columns, and skip header rows if needed
-    df = pd.read_excel(file.name, header=None)  # read raw data :contentReference[oaicite:7]{index=7}
-    df = df.dropna(axis=1, how="all")           # drop fully empty cols :contentReference[oaicite:8]{index=8}
-    # If your file has descriptive top rows, you can also do:
-    # df = pd.read_excel(file.name, header=None, skiprows=2)  # adjust as needed :contentReference[oaicite:9]{index=9}
+    # 2. Read sheet 0 without header rows (so data starts at row 0)
+    df = pd.read_excel(file.name, header=None)
+    df = df.dropna(axis=1, how="all")  # drop any fully empty columns
 
-    # 3. Define output schema
-    headers = [
+    # 3. Prepare output schema
+    output_headers = [
         "Usage", "District", "Address", "Longitude", "Latitude",
         "Floor", "Unit", "Area", "PriceInMillion",
-        "InstrumentDate", "Year", "WeekNumber",
-        "DeliveryDate", "MemoNo."
+        "PricePerSquareFeet", "InstrumentDate", "Year",
+        "WeekNumber", "DeliveryDate", "MemoNo."
     ]
-    output_df = pd.DataFrame("", index=range(len(df)), columns=headers)
+    output_df = pd.DataFrame("", index=range(len(df)), columns=output_headers)
 
-    # 4. Map positional columns via iloc
-    output_df["Usage"] = df.iloc[:, 0]             # Column1 → Usage :contentReference[oaicite:10]{index=10}
-    output_df["Floor"] = df.iloc[:, 1]             # Column2 → Floor :contentReference[oaicite:11]{index=11}
-    output_df["Unit"] = df.iloc[:, 2]              # Column3 → Unit :contentReference[oaicite:12]{index=12}
+    # 4. Map exactly as requested:
+    output_df["Address"]             = df.iloc[:, 0]  # col 1 → Address
+    output_df["Floor"]               = df.iloc[:, 1]  # col 2 → Floor
+    output_df["Unit"]                = df.iloc[:, 2]  # col 3 → Unit
+    output_df["Area"]                = df.iloc[:, 3]  # col 4 → Area
+    output_df["PriceInMillion"]      = pd.to_numeric(
+                                          df.iloc[:, 4]
+                                            .replace(r"[^0-9\.]", "", regex=True),
+                                          errors="coerce"
+                                      )               # col 5 → PriceInMillion
+    output_df["PricePerSquareFeet"]  = pd.to_numeric(
+                                          df.iloc[:, 5]
+                                            .replace(r"[^0-9\.]", "", regex=True),
+                                          errors="coerce"
+                                      )               # col 6 → PricePerSquareFeet
+    output_df["InstrumentDate"]      = pd.to_datetime(
+                                          df.iloc[:, 6],
+                                          errors="coerce"
+                                      )               # col 7 → InstrumentDate
 
-    # 5. Clean and map Area (extract number from "507 ft2")
-    output_df["Area"] = (
-        df.iloc[:, 3]
-          .astype(str)
-          .str.extract(r"(\d+\.?\d*)", expand=False)  # extract numeric :contentReference[oaicite:13]{index=13}
-          .astype(float)
-    )
-
-    # 6. Map and clean PriceInMillion (remove non‐digits then convert)
-    output_df["PriceInMillion"] = pd.to_numeric(
-        df.iloc[:, 4].replace(r"[^0-9\.]", "", regex=True),
-        errors="coerce"
-    )  # robust numeric conversion :contentReference[oaicite:14]{index=14}
-
-    # 7. Map PricePerSquareFeet into "District" if that’s your intended slot
-    output_df["District"] = df.iloc[:, 5]         # Column6 → District :contentReference[oaicite:15]{index=15}
-
-    # 8. Parse InstrumentDate and derive Year & WeekNumber
-    output_df["InstrumentDate"] = pd.to_datetime(
-        df.iloc[:, 6], errors="coerce"
-    )  # robust parsing :contentReference[oaicite:16]{index=16}
-    output_df["Year"] = output_df["InstrumentDate"].dt.year
+    # 5. Derive Year & WeekNumber
+    output_df["Year"]       = output_df["InstrumentDate"].dt.year
     output_df["WeekNumber"] = output_df["InstrumentDate"].dt.isocalendar().week
 
-    # 9. (Optional) Leave DeliveryDate & MemoNo. blank or map if available
+    # 6. (Leave DeliveryDate & MemoNo. blank unless you have source columns)
     # output_df["DeliveryDate"] = ...
     # output_df["MemoNo."]      = ...
 
-    # 10. Save output with data‑clean‑YYMMDD filename
-    suffix = datetime.now().strftime("%y%m%d")
+    # 7. Generate output filename
+    suffix   = datetime.now().strftime("%y%m%d")
     out_name = f"data-clean-{suffix}.xlsx"
-    output_df.to_excel(out_name, index=False)
 
+    # 8. Save and return
+    output_df.to_excel(out_name, index=False)
     return output_df, out_name
 
-with gr.Blocks() as demo:
-    gr.Markdown("## Excel → data‑clean Mapping Tool")
+with gr.Blocks(title="Excel → data‑clean Mapper") as demo:
+    gr.Markdown("## Upload your .xls/.xlsx/.xlsm file for data‑clean mapping")
     with gr.Row():
-        inp = gr.File(label="Upload .xls/.xlsx/.xlsm")
-        btn = gr.Button("Process")
+        file_in = gr.File(label="Input File")
+        btn     = gr.Button("Process")
     with gr.Row():
-        df_view     = gr.Dataframe(label="Mapped Data")
-        df_download = gr.File(label="Download Output")
-    btn.click(process_file, inputs=[inp], outputs=[df_view, df_download])
+        df_out    = gr.Dataframe(label="Mapped Data")
+        download  = gr.File(label="Download Output")
+    btn.click(process_file, inputs=[file_in], outputs=[df_out, download])
 
 demo.launch()