app.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score

# ----------------------------
# Load dataset
CSV_PATH = "test_score_prediction_dataset.csv"
df = pd.read_csv(CSV_PATH)

# Features and target
X = df[["AP", "Honors", "GPA_Points", "Credits_Earned"]]
y = df["Predicted_Test_Score"]

# Train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# ----------------------------
# Train model (Random Forest)
model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Predict and evaluate
y_pred = model.predict(X_test)
print("R² Score:", r2_score(y_test, y_pred))