fix: Update clean method to work with both csv input types

app.py

@@ -60,20 +60,27 @@ def plot_anomalies(df_test_value, data, anomalies):
     return fig
 
 def clean_data(df):
-    # Convert "Date" and "Hour" columns into datetime format
-    df["timestamp"] = pd.to_datetime(df["Date"] + ' ' + df["Hour"].astype(str) + ":00:00")
-
-    # Keep only necessary columns
-    df = df[["timestamp", "Hourly_Labor_Hours_Total"]]
-
-    # Rename column
-    df.rename(columns={"Hourly_Labor_Hours_Total": "value"}, inplace=True)
-
+    # Check if 'Date' and 'Hour' columns exist in the dataframe
+    if "Date" in df.columns and "Hour" in df.columns:
+        # Convert "Date" and "Hour" columns into datetime format
+        df["timestamp"] = pd.to_datetime(df["Date"] + ' ' + df["Hour"].astype(str) + ":00:00")
+        # Keep only necessary columns
+        df = df[["timestamp", "Hourly_Labor_Hours_Total"]]
+        # Rename column
+        df.rename(columns={"Hourly_Labor_Hours_Total": "value"}, inplace=True)
+    elif "timestamp" in df.columns:
+        # If 'timestamp' column exists, rename the value column if necessary
+        if "Hourly_Labor_Hours_Total" in df.columns:
+            df.rename(columns={"Hourly_Labor_Hours_Total": "value"}, inplace=True)
+        df = df[["timestamp", "value"]]
+    else:
+        raise ValueError("Input data must have either 'Date' and 'Hour' columns, or a 'timestamp' column.")
     return df
 
 def master(file):
     # read file
     data = pd.read_csv(file.name)
+    data['timestamp'] = pd.to_datetime(data['timestamp'])
 
     # clean data
     data = clean_data(data)