Create src/data_processing.py

src/data_processing.py

@@ -0,0 +1,22 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+def load_data(file_path):
+    """Load data from a CSV file."""
+    return pd.read_csv(file_path)
+
+def clean_data(df):
+    """Clean the dataset by handling missing values and duplicates."""
+    df = df.dropna()
+    df = df.drop_duplicates()
+    return df
+
+def preprocess_data(df, target_column):
+    """Preprocess the data by splitting into features and target."""
+    X = df.drop(columns=[target_column])
+    y = df[target_column]
+    return X, y
+
+def split_data(X, y, test_size=0.2, random_state=42):
+    """Split the data into training and testing sets."""
+    return train_test_split(X, y, test_size=test_size, random_state=random_state)