Fix pandas chained assignment warnings

Author: mtandrita

Diabetes Prediction [END 2 END]/diabetes_pipeline/data_preprocessing.py

@@ -2,39 +2,46 @@
 
 import pandas as pd
 import numpy as np
+from pathlib import Path
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
 
-def load_and_preprocess(csv_path='dataset/kaggle_diabetes.csv', test_size=0.2, random_state=0):
+BASE_DIR = Path(__file__).resolve().parent
+
+def load_and_preprocess(
+    csv_path=BASE_DIR / "dataset" / "kaggle_diabetes.csv",
+    test_size=0.2,
+    random_state=0
+):
     # Load dataset
     df = pd.read_csv(csv_path)
-    
-    # Rename column
+
+    # Rename column (IMPORTANT: this defines feature names forever)
     df = df.rename(columns={'DiabetesPedigreeFunction': 'DPF'})
-    
-    # Replace 0s with NaN
+
+    # Replace invalid zeros
     cols_with_zero = ['Glucose','BloodPressure','SkinThickness','Insulin','BMI']
     df[cols_with_zero] = df[cols_with_zero].replace(0, np.nan)
-    
+
     # Fill NaNs
     df['Glucose'] = df['Glucose'].fillna(df['Glucose'].mean())
     df['BloodPressure'] = df['BloodPressure'].fillna(df['BloodPressure'].mean())
     df['SkinThickness'] = df['SkinThickness'].fillna(df['SkinThickness'].median())
     df['Insulin'] = df['Insulin'].fillna(df['Insulin'].median())
     df['BMI'] = df['BMI'].fillna(df['BMI'].median())
-    
-    # Features & Target
+
+    # Features & target
     X = df.drop(columns='Outcome')
     y = df['Outcome']
-    
-    # Train/Test Split
+
+    # Split
     X_train, X_test, y_train, y_test = train_test_split(
         X, y, test_size=test_size, random_state=random_state
     )
-    
-    # Feature Scaling
+
+    # Scaling
     scaler = StandardScaler()
     X_train_scaled = scaler.fit_transform(X_train)
     X_test_scaled = scaler.transform(X_test)
-    
+
     return X_train_scaled, X_test_scaled, y_train, y_test, scaler