Upload folder using huggingface_hub

Dockerfile

@@ -1,17 +1,16 @@
-# Use an official Python runtime as a parent image
+# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory in the container
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-# Copy the current directory contents into the container at /app
-COPY . /app
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
 
-# Install any needed packages specified in requirements.txt
-RUN pip install --no-cache-dir -r requirements.txt
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install -r requirements.txt
 
-# Make port 5000 available to the world outside this container
-EXPOSE 5000
+# Define the command to run the Streamlit app on port 8501 and make it accessible externally
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
 
-# Run app.py when the container launches
-CMD ["python", "app.py"]
+# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

app.py

@@ -1,33 +1,71 @@
 
-import flask
-import joblib
-import pandas as pd
+import streamlit as st
+import requests
+import json
 
-# Load the trained model
-model = joblib.load('tuned_random_forest_model.pkl') # Replace with the actual model filename
+st.title("Lead Conversion Prediction")
 
-app = flask.Flask(__name__)
+st.write("Enter the lead details to predict conversion likelihood.")
 
-@app.route('/')
-def home():
-    return "Lead Conversion Prediction Backend"
+# Input fields for lead features (replace with your actual features)
+age = st.number_input("Age", min_value=0)
+current_occupation = st.selectbox("Current Occupation", ['Professional', 'Unemployed', 'Student'])
+first_interaction = st.selectbox("First Interaction", ['Website', 'Mobile App'])
+profile_completed = st.selectbox("Profile Completed", ['Low', 'Medium', 'High'])
+website_visits = st.number_input("Website Visits", min_value=0)
+time_spent_on_website = st.number_input("Time Spent on Website (seconds)", min_value=0)
+page_views_per_visit = st.number_input("Page Views per Visit", min_value=0.0)
+last_activity = st.selectbox("Last Activity", ['Email Activity', 'Website Activity', 'Phone Activity'])
+print_media_type1 = st.selectbox("Print Media Type 1", ['Yes', 'No'])
+print_media_type2 = st.selectbox("Print Media Type 2", ['Yes', 'No'])
+digital_media = st.selectbox("Digital Media", ['Yes', 'No'])
+educational_channels = st.selectbox("Educational Channels", ['Yes', 'No'])
+referral = st.selectbox("Referral", ['Yes', 'No'])
+
+
+# Create a dictionary with the input data
+input_data = {
+    'age': [age],
+    'current_occupation': [current_occupation],
+    'first_interaction': [first_interaction],
+    'profile_completed': [profile_completed],
+    'website_visits': [website_visits],
+    'time_spent_on_website': [time_spent_on_website],
+    'page_views_per_visit': [page_views_per_visit],
+    'last_activity': [last_activity],
+    'print_media_type1': [print_media_type1],
+    'print_media_type2': [print_media_type2],
+    'digital_media': [digital_media],
+    'educational_channels': [educational_channels],
+    'referral': [referral]
+}
+
+# Convert input data to a list of dictionaries (required by the backend)
+input_data_list = [dict(zip(input_data, t)) for t in zip(*input_data.values())]
+
+
+# Button to trigger prediction
+if st.button("Predict Conversion"):
+    # Replace with the URL of your deployed backend API
+    backend_url = "YOUR_BACKEND_API_URL/predict" # e.g., "https://your-username-your-backend-space.hf.space/predict"
 
-@app.route('/predict', methods=['POST'])
-def predict():
     try:
-        # Get the data from the request
-        data = flask.request.get_json(force=True)
-        df_predict = pd.DataFrame(data)
+        # Send a POST request to the backend API
+        response = requests.post(backend_url, json=input_data_list)
+
+        if response.status_code == 200:
+            predictions = response.json()
+            prediction = predictions[0] # Assuming the backend returns a list with a single prediction
 
-        # Make predictions
-        predictions = model.predict(df_predict)
+            if prediction == 1:
+                st.success("This lead is likely to convert!")
+            else:
+                st.warning("This lead is less likely to convert.")
 
-        # Return the predictions as JSON
-        return flask.jsonify(predictions.tolist())
+        else:
+            st.error(f"Error from backend: {response.status_code}")
+            st.error(response.text)
 
     except Exception as e:
-        return flask.jsonify({'error': str(e)})
+        st.error(f"An error occurred: {e}")
 
-if __name__ == '__main__':
-    # Run the Flask app
-    app.run(host='0.0.0.0', port=5000)

requirements.txt

@@ -1,4 +1,4 @@
-flask==3.0.3
-joblib==1.4.2
+streamlit==1.36.0
+requests==2.32.3
 pandas==2.2.2
 scikit-learn==1.6.1