feat: Clean and add sales_hourly_short.csv

app.py

@@ -80,6 +80,20 @@ def clean_data(df):
         # Rename column
         df.rename(columns={"Hourly_Labor_Hours_Total": "value"}, inplace=True)
 
+    elif "Date_CY" in df.columns and "Hour" in df.columns and "Net_Sales_CY" in df.columns:
+        # Convert "Date" and "Hour" columns into datetime format
+        df["timestamp"] = pd.to_datetime(df["Date_CY"]) + pd.to_timedelta(df["Hour"].astype(int), unit='h')
+
+        # Handle the case where hour is 24
+        df.loc[df["timestamp"].dt.hour == 24, "timestamp"] = df["timestamp"] + pd.DateOffset(days=1)
+        df["timestamp"] = df["timestamp"].dt.floor('h')
+
+        # Keep only necessary columns
+        df = df[["timestamp", "Net_Sales_CY"]]
+
+        # Rename column
+        df.rename(columns={"Net_Sales_CY": "value"}, inplace=True)
+
         return df
 
     else:
@@ -116,7 +130,7 @@ iface = gr.Interface(
     fn=master,
     inputs=gr.inputs.File(label="CSV File"),
     outputs=outputs,
-    examples=["art_daily_jumpsup.csv","labor_hourly_short.csv"],
+    examples=["art_daily_jumpsup.csv","labor_hourly_short.csv, sales_hourly_short.csv"],
     title="Timeseries Anomaly Detection Using an Autoencoder",
     description="Anomaly detection of timeseries data."
 )