Update DSIP/preprocess.py

DSIP/preprocess.py

@@ -11,6 +11,9 @@ def parse(csv_path):
     # Step 1: Load the dataset
     # file_path = "dataset.csv"  # Path to the original dataset
     data = pd.read_csv(csv_path)
+
+    # Drop dupes
+    data = data.drop_duplicates()
     
     # Step 2: Define the feature columns (X) and target column (y)
     X = data[["name", "attendance percentage", "average sleep time", "average screen time"]]  # Feature columns