Create data_preprocessing/preprocessing.py

data_preprocessing/preprocessing.py

@@ -0,0 +1,48 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+def load_data(file_path):
+    """
+    Load dataset from a CSV file.
+    
+    Args:
+        file_path (str): Path to the CSV file.
+        
+    Returns:
+        pd.DataFrame: Loaded dataset.
+    """
+    return pd.read_csv(file_path)
+
+def preprocess_data(df):
+    """
+    Preprocess the dataset by handling missing values and encoding categorical variables.
+    
+    Args:
+        df (pd.DataFrame): Raw dataset.
+        
+    Returns:
+        pd.DataFrame: Preprocessed dataset.
+    """
+    # Handle missing values
+    df = df.dropna()
+    
+    # Encode categorical variables
+    df = pd.get_dummies(df)
+    
+    return df
+
+def split_data(df, target_column, test_size=0.2):
+    """
+    Split the dataset into training and testing sets.
+    
+    Args:
+        df (pd.DataFrame): Preprocessed dataset.
+        target_column (str): Name of the target column.
+        test_size (float): Proportion of the dataset to include in the test split.
+        
+    Returns:
+        X_train, X_test, y_train, y_test: Split datasets.
+    """
+    X = df.drop(columns=[target_column])
+    y = df[target_column]
+    return train_test_split(X, y, test_size=test_size, random_state=42)