build_prediction_model.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import numpy as np

# Load the dataset
df = pd.read_csv('/kaggle/input/students-performance-in-exams/StudentsPerformance.csv')

# Rename columns for consistency
df.rename(columns={
    'parental level of education': 'parental_level_of_education',
    'test preparation course': 'test_preparation_course',
    'math score': 'math_score',
    'reading score': 'reading_score',
    'writing score': 'writing_score',
    'race/ethnicity': 'race_ethnicity'
}, inplace=True)

# Create the target variable: average score
df['average_score'] = df[['math_score', 'reading_score', 'writing_score']].mean(axis=1)

print("--- Building Predictive Model ---")

# Define features (X) and target (y)
X = df.drop(['math_score', 'reading_score', 'writing_score', 'average_score'], axis=1)
y = df['average_score']

# One-hot encode categorical features
X = pd.get_dummies(X, columns=['gender', 'race_ethnicity', 'parental_level_of_education', 'lunch', 'test_preparation_course'], drop_first=True)

# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

print(f"Training features shape: {X_train.shape}")
print(f"Test features shape: {X_test.shape}")

# Initialize and train the RandomForestRegressor model
model = RandomForestRegressor(n_estimators=100, random_state=42, n_jobs=-1) # n_jobs=-1 uses all available cores
print("\nTraining RandomForestRegressor...")
model.fit(X_train, y_train)
print("Model training complete.")

# Make predictions on the test set
y_pred = model.predict(X_test)

# Evaluate the model
mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y_test, y_pred)

print("\n--- Model Evaluation ---")
print(f"Mean Absolute Error (MAE): {mae:.3f}")
print(f"Mean Squared Error (MSE): {mse:.3f}")
print(f"Root Mean Squared Error (RMSE): {rmse:.3f}")
print(f"R-squared (R2): {r2:.3f}")

# Feature Importances
print("\n--- Feature Importances ---")
feature_importances = pd.Series(model.feature_importances_, index=X.columns)
print(feature_importances.sort_values(ascending=False).head(10))

print("\nPredictive model building complete.")