Create train.py

train.py

@@ -0,0 +1,63 @@
+# train.py
+import pandas as pd, numpy as np, pickle
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.multioutput import MultiOutputRegressor
+from sklearn.metrics import mean_absolute_error
+
+CSV_PATH = "student_allinone_300_padded.csv"  # change path if needed
+FEATURES = ["Attendance","StudyHours","ParentalSupport","SleepHours",
+            "ReadingHours","BehaviorScore","PretestScore",
+            "HomeworkCompletion","Participation"]
+TARGETS = ["AssignmentAvg","TestScore"]
+
+def main():
+    df = pd.read_csv(CSV_PATH).copy()
+
+    # === Highly recommended: make targets depend on inputs (if your CSV targets were random) ===
+    rng = np.random.default_rng(42)
+    if ("AssignmentAvg" in df.columns) and ("TestScore" in df.columns):
+        # Always recompute to ensure consistency
+        df["AssignmentAvg"] = (
+            df["PretestScore"] * 0.5
+            + df["StudyHours"] * 3
+            + df["HomeworkCompletion"] * 0.20
+            + df["Participation"] * 2
+            + rng.integers(-5, 6, size=len(df))
+        ).clip(0, 100).round(2)
+
+        df["TestScore"] = (
+            df["PretestScore"] * 0.6
+            + df["Attendance"] * 0.20
+            + df["ParentalSupport"] * 3
+            + df["SleepHours"] * 2
+            + df["ReadingHours"] * 2
+            + df["BehaviorScore"] * 2
+            + rng.integers(-5, 6, size=len(df))
+        ).clip(0, 100).round(2)
+
+    X = df[FEATURES]
+    y = df[TARGETS]
+
+    Xtr, Xte, ytr, yte = train_test_split(X, y, test_size=0.2, random_state=42)
+    model = MultiOutputRegressor(RandomForestRegressor(n_estimators=200, random_state=42)).fit(Xtr, ytr)
+    mae = mean_absolute_error(yte, model.predict(Xte))
+    print("MAE:", round(mae, 3))
+
+    # Save feature bounds so app can clip
+    feature_mins = X.min().to_dict()
+    feature_maxs = X.max().to_dict()
+
+    with open("student_model.pkl", "wb") as f:
+        pickle.dump({
+            "model": model,
+            "features": FEATURES,
+            "targets": TARGETS,
+            "feature_mins": feature_mins,
+            "feature_maxs": feature_maxs
+        }, f)
+
+    print("Saved student_model.pkl with bounds.")
+
+if __name__ == "__main__":
+    main()