Create app.py

app.py

@@ -0,0 +1,56 @@
+import pandas as pd
+import gradio as gr
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+import joblib
+import os
+
+# --- Load Dataset ---
+# Make sure you upload your CSV into the Space with the same name
+df = pd.read_csv("course_history_with_difficulty.csv")
+
+# Convert True/False into integers for modeling
+df["AP"] = df["AP"].astype(int)
+df["Honors"] = df["Honors"].astype(int)
+
+# --- Features & Target ---
+X = df[["AP", "Honors", "Credits_Attempted", "Credits_Earned"]]
+y = df["Weighted_GPA_Points"]
+
+# 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 as best baseline) ---
+model = RandomForestRegressor(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+
+# Save model for persistence
+joblib.dump(model, "gpa_model.pkl")
+
+# Reload model (useful when restarting Space)
+model = joblib.load("gpa_model.pkl")
+
+# --- Prediction Function ---
+def predict(ap, honors, credits_attempted, credits_earned):
+    features = [[int(ap), int(honors), float(credits_attempted), float(credits_earned)]]
+    prediction = model.predict(features)[0]
+    return round(prediction, 2)
+
+# --- Gradio UI ---
+demo = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Checkbox(label="AP"),
+        gr.Checkbox(label="Honors"),
+        gr.Number(label="Credits Attempted"),
+        gr.Number(label="Credits Earned")
+    ],
+    outputs=gr.Number(label="Predicted GPA Points"),
+    title="GPA Prediction Model",
+    description="Enter course details to predict GPA points (weighted)."
+)
+
+if __name__ == "__main__":
+    demo.launch()