Step 1: Import libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error
import os
Step 2: Check dataset folder (optional but useful)
print("Files in dataset folder:")
print(os.listdir("/kaggle/input/student-exam-performance-dataset"))
Step 3: Load dataset (IMPORTANT: include file name)
data = pd.read_csv("/kaggle/input/student-exam-performance-dataset/student_exam_performance_dataset.csv")
Step 4: Preview data
print("\nFirst 5 rows:")
print(data.head())
Step 5: Select important columns
X = data[["study_hours_per_day", "sleep_hours", "attendance_rate"]]
y = data["final_exam_score"]
Step 6: Split dataset
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42
)
Step 7: Create model
model = LinearRegression()
Step 8: Train model
model.fit(X_train, y_train)
Step 9: Predict
y_pred = model.predict(X_test)
Step 10: Evaluate
error = mean_absolute_error(y_test, y_pred)
print("\nMean Absolute Error:", error)
Step 11: Custom prediction
sample = pd.DataFrame([[5, 7, 80]], columns=X.columns)
prediction = model.predict(sample)
print("\nPredicted Exam Score:", prediction)
