Update app.py

app.py

@@ -1,25 +1,61 @@
 import gradio as gr
 import joblib
-import numpy as np
-from sentence_transformers import SentenceTransformer
+import json
 import lightgbm as lgb
+from sentence_transformers import SentenceTransformer
+import numpy as np
+
+# Load models from Hugging Face Hub
+ridge = joblib.load("Essay/ridge_model.pkl")
+lgb_model = lgb.Booster(model_file="Essay/lightgbm_model.txt")
+encoder = joblib.load("Essay/scaler_encoder.pkl")
 
-# Load models
-ridge = joblib.load("model/ridge_model.pkl")
-lgbm = lgb.Booster(model_file="model/lgb_model.txt")
-sbert = SentenceTransformer('paraphrase-mpnet-base-v2')
+# Load metadata column order
+with open("Essay/metadata_columns.json", "r") as f:
+    metadata_columns = json.load(f)
 
-def predict_score(essay_text):
-    embedding = sbert.encode([essay_text])
-    ridge_score = ridge.predict(embedding)[0]
-    lgbm_score = lgbm.predict(embedding)[0]
-    final_score = 0.5 * ridge_score + 0.5 * lgbm_score
-    return round(final_score, 2)
+# Load SBERT model (will download at runtime)
+sbert = SentenceTransformer("sentence-transformers/paraphrase-mpnet-base-v2")
 
-gr.Interface(
+def predict_score(essay_text, gender, race_ethnicity, disability, disadvantaged, ell_status):
+    # Encode essay
+    essay_embedding = sbert.encode([essay_text])
+    
+    # Prepare metadata as dict
+    metadata_input = {
+        "gender": gender,
+        "race_ethnicity": race_ethnicity,
+        "student_disability_status": disability,
+        "economically_disadvantaged": disadvantaged,
+        "ell_status": ell_status
+    }
+
+    # Convert to array in correct order
+    metadata_values = [metadata_input[col] for col in metadata_columns]
+    metadata_array = encoder.transform([metadata_values])  # shape: (1, n)
+
+    # Combine essay embedding + metadata
+    full_input = np.hstack([essay_embedding, metadata_array])
+
+    # Predict from both models
+    ridge_score = ridge.predict(full_input)[0]
+    lgb_score = lgb_model.predict(full_input)[0]
+    final_score = round((0.5 * ridge_score + 0.5 * lgb_score), 2)
+    return final_score
+
+# Gradio UI
+iface = gr.Interface(
     fn=predict_score,
-    inputs="text",
-    outputs="number",
-    title="Automated Essay Scorer",
-    description="Paste your essay below and get a predicted score."
-).launch()
+    inputs=[
+        gr.Textbox(label="Essay Text", lines=10, placeholder="Paste your essay here..."),
+        gr.Dropdown(["Male", "Female", "Other"], label="Gender"),
+        gr.Dropdown(["Asian", "Black", "Hispanic", "White", "Other"], label="Race/Ethnicity"),
+        gr.Dropdown(["Yes", "No"], label="Student has Disability"),
+        gr.Dropdown(["Yes", "No"], label="Economically Disadvantaged"),
+        gr.Dropdown(["Yes", "No"], label="ELL Status")
+    ],
+    outputs=gr.Number(label="Predicted Essay Score"),
+    title="Automated Essay Scoring App"
+)
+
+iface.launch()