Update app.py

app.py

@@ -1,48 +1,22 @@
 import pandas as pd
 import pickle
 import gradio as gr
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import LabelEncoder
-from sklearn.tree import DecisionTreeClassifier
 
 # =========================
-# 1️⃣ Load & Train Model
+# Load Model & Encoders
 # =========================
 
-df = pd.read_csv("bank-full.csv", sep=";", engine="python", quotechar='"')
+with open("bank_dt_model.pkl", "rb") as f:
+    model = pickle.load(f)
+
+with open("le_dict.pkl", "rb") as f:
+    le_dict = pickle.load(f)
 
 categorical_cols = [
     'job', 'marital', 'education', 'default',
     'housing', 'loan', 'contact', 'month', 'poutcome'
 ]
 
-le_dict = {}
-for col in categorical_cols:
-    le = LabelEncoder()
-    df[col] = le.fit_transform(df[col])
-    le_dict[col] = le
-
-le_y = LabelEncoder()
-df['y'] = le_y.fit_transform(df['y'])
-
-X = df.drop('y', axis=1)
-y = df['y']
-
-X_train, X_test, y_train, y_test = train_test_split(
-    X, y, test_size=0.2, random_state=42, stratify=y
-)
-
-model = DecisionTreeClassifier(
-    criterion='gini',
-    random_state=42,
-    min_samples_leaf=5
-)
-model.fit(X_train, y_train)
-
-# =========================
-# Feature Order
-# =========================
-
 feature_order = [
     'age', 'job', 'marital', 'education', 'default',
     'balance', 'housing', 'loan', 'contact', 'day',
@@ -51,7 +25,7 @@ feature_order = [
 ]
 
 # =========================
-# 2️⃣ Prediction Function
+# Prediction Function
 # =========================
 
 def predict(
@@ -61,7 +35,7 @@ def predict(
     previous, poutcome
 ):
     try:
-        input_dict = {
+        input_data = {
             'age': int(age),
             'job': le_dict['job'].transform([job])[0],
             'marital': le_dict['marital'].transform([marital])[0],
@@ -80,25 +54,25 @@ def predict(
             'poutcome': le_dict['poutcome'].transform([poutcome])[0],
         }
 
-        df_input = pd.DataFrame([input_dict], columns=feature_order)
+        df_input = pd.DataFrame([input_data], columns=feature_order)
 
         pred = model.predict(df_input)[0]
-        prob = model.predict_proba(df_input)[0][pred]
+        confidence = model.predict_proba(df_input)[0][pred]
 
         message = (
-            "✅ Likely to subscribe. Recommend follow-up call."
+            "✅ Likely to subscribe. Recommend follow-up."
             if pred == 1 else
             "❌ Unlikely to subscribe."
         )
 
-        return message, round(prob, 3)
+        return message, round(float(confidence), 3)
 
     except Exception as e:
         return f"Error: {str(e)}", None
 
 
 # =========================
-# 3️⃣ Gradio UI
+# Gradio UI
 # =========================
 
 inputs = [
@@ -122,15 +96,15 @@ inputs = [
 
 outputs = [
     gr.Textbox(label="Prediction"),
-    gr.Number(label="Confidence Score")
+    gr.Number(label="Confidence")
 ]
 
 app = gr.Interface(
     fn=predict,
     inputs=inputs,
     outputs=outputs,
-    title="💳 Bank Subscription Prediction (Decision Tree)",
-    description="AI-powered customer subscription prediction using classical ML"
+    title="🏦 Bank Term Deposit Predictor",
+    description="Decision Tree model deployed using Hugging Face Spaces"
 )
 
 app.launch()