Upload folder using huggingface_hub

app.py

@@ -4,22 +4,22 @@
 import streamlit as st
 import pandas as pd
 import pickle
+from huggingface_hub import hf_hub_download
+import joblib
 
-# 1️⃣ App title
+# App title
 st.title("Customer Status Prediction")
 
 st.write("""
 This web app predicts the **status** of a customer based on their activity and profile information.
 """)
-# Load the trained model
-@st.cache_resource
-def load_model():
-    return joblib.load("my_model_v1_0.joblib")
 
-model = load_model()
+# Download and load the model
+model_path = hf_hub_download(repo_id="NaikGayatri/ModelDeploymentAssignmentBackEnd", filename="my_model_v1_0.joblib")
+model = joblib.load(model_path)
 
 
-# 3️⃣ Create UI for user input
+# Create UI for user input
 st.sidebar.header("Provide Input Features")
 
 # Numeric Inputs
@@ -39,7 +39,7 @@ digital_media = st.sidebar.selectbox("Digital Media", ["Email", "Social Media",
 educational_channels = st.sidebar.selectbox("Educational Channels", ["Online Course", "Webinar", "None"])
 referral = st.sidebar.selectbox("Referral", ["Friend", "Advertisement", "Other"])
 
-# 4️⃣ Convert user input to DataFrame
+# Convert user input to DataFrame
 input_dict = {
     'age': age,
     'website_visits': website_visits,
@@ -58,11 +58,11 @@ input_dict = {
 
 input_df = pd.DataFrame([input_dict])
 
-# 5️⃣ Make prediction
+# Make prediction
 if st.button("Predict Status"):
     prediction = model.predict(input_df)
     prediction_proba = model.predict_proba(input_df)[:, 1]
 
     st.write(f"**Predicted Status:** {prediction[0]}")
-    st.write(f"**Probability of Positive Status:** {prediction_proba[0]:.2f}")
+###    st.write(f"**Probability of Positive Status:** {prediction_proba[0]:.2f}")
 

requirements.txt

@@ -4,3 +4,4 @@ scikit-learn==1.6.1
 xgboost==2.1.4
 joblib==1.4.2
 streamlit==1.43.2
+huggingface_hub==0.32.6