Download app.py from manasranjanpani/ExtraaLearnCustomerPredictionFrontendDemo: direct link, hf CLI and curl.
- Browser
- Download file 5.79 kB
-
https://huggingface.co/spaces/manasranjanpani/ExtraaLearnCustomerPredictionFrontendDemo/resolve/main/app.py
- Command line
-
hf download hf://spaces/manasranjanpani/ExtraaLearnCustomerPredictionFrontendDemo/app.py
-
curl -L -o app.py https://huggingface.co/spaces/manasranjanpani/ExtraaLearnCustomerPredictionFrontendDemo/resolve/main/app.py
5.79 kB
| import streamlit as st | |
| import pandas as pd | |
| import requests | |
| # Set the title of the Streamlit app | |
| st.title("ExtraaLearn Customer Prediction") | |
| # Section for online prediction | |
| st.subheader("Single Customer Prediction") | |
| # Collect user input for customer features | |
| age = st.number_input("Age", min_value=15, max_value=80, step=1, value=25) | |
| current_occupation = st.selectbox("Current Occupation", [ | |
| "Student", "Unemployed", "Employed", "Self-Employed", "Professional" | |
| ]) | |
| first_interaction = st.selectbox("First Interaction", [ | |
| "Website", "Mobile App", "Referral", "Advertisement", "Social Media" | |
| ]) | |
| # Updated: profileCompleted as dropdown with High/Medium/Low | |
| profile_completed = st.selectbox("Profile Completed", ["High", "Medium", "Low"]) | |
| website_visits = st.number_input("Website Visits", min_value=0, max_value=100, step=1, value=15) | |
| time_spent_on_website = st.number_input("Time Spent on Website (seconds)", min_value=0, max_value=3600, step=10, value=1200) | |
| page_views_per_visit = st.number_input("Page Views Per Visit", min_value=1, max_value=20, step=1, value=8) | |
| last_activity = st.selectbox("Last Activity", [ | |
| "Login", "Course View", "Payment Page", "Profile Update", "Website 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"]) | |
| # Convert user input into a dictionary matching the API requirements | |
| input_data = { | |
| 'age': age, | |
| 'currentOccupation': current_occupation, | |
| 'firstInteraction': first_interaction, | |
| 'profileCompleted': profile_completed, # This will now be "High", "Medium", or "Low" | |
| 'websiteVisits': website_visits, | |
| 'timeSpentOnWebsite': time_spent_on_website, | |
| 'pageViewsPerVisit': page_views_per_visit, | |
| 'lastActivity': last_activity, | |
| 'printMediaType1': print_media_type1, | |
| 'printMediaType2': print_media_type2, | |
| 'digitalMedia': digital_media, | |
| 'educationalChannels': educational_channels, | |
| 'referral': referral | |
| } | |
| # Make prediction when the "Predict" button is clicked | |
| if st.button("Predict Customer Conversion"): | |
| try: | |
| response = requests.post( | |
| "https://manasranjanpani-extraalearncustomerpredictionbackend.hf.space/v1/customers", | |
| json=input_data | |
| ) | |
| if response.status_code == 200: | |
| result = response.json() | |
| prediction = result['predicted_customer_status'] | |
| st.success(f"Predicted Customer Conversion Score: {prediction:.2f}") | |
| # Display additional info if available | |
| if 'input_received' in result: | |
| st.info(f"Processed {len(result['input_received']['fields_processed'])} features successfully") | |
| else: | |
| error_data = response.json() | |
| st.error(f"Error making prediction: {error_data.get('error', 'Unknown error')}") | |
| except requests.exceptions.RequestException as e: | |
| st.error(f"Connection error: {e}") | |
| except Exception as e: | |
| st.error(f"Unexpected error: {e}") | |
| # Section for batch prediction | |
| st.subheader("Batch Prediction") | |
| # Allow users to upload a CSV file for batch prediction | |
| uploaded_file = st.file_uploader("Upload CSV file for batch prediction", type=["csv"]) | |
| if uploaded_file is not None: | |
| # Display preview of uploaded data | |
| st.write("Preview of uploaded data:") | |
| batch_data = pd.read_csv(uploaded_file) | |
| st.dataframe(batch_data.head()) | |
| # Check if required columns are present | |
| required_columns = list(input_data.keys()) | |
| missing_columns = [col for col in required_columns if col not in batch_data.columns] | |
| if missing_columns: | |
| st.warning(f"Missing required columns in CSV: {missing_columns}") | |
| st.info(f"Required columns: {required_columns}") | |
| else: | |
| st.success("All required columns present!") | |
| # Make batch prediction when the "Predict Batch" button is clicked | |
| if uploaded_file is not None and st.button("Predict Batch"): | |
| try: | |
| # Reset file pointer to beginning | |
| uploaded_file.seek(0) | |
| response = requests.post( | |
| "https://manasranjanpani-extraalearncustomerpredictionbackend.hf.space/v1/customersbatch", | |
| files={"file": uploaded_file} | |
| ) | |
| if response.status_code == 200: | |
| predictions = response.json() | |
| st.success("Batch predictions completed!") | |
| # Display predictions in a nice format | |
| if 'predictions' in predictions: | |
| st.write("Predictions:") | |
| for i, pred in enumerate(predictions['predictions']): | |
| st.write(f"Customer {i+1}: {pred:.2f}") | |
| else: | |
| # If predictions are keyed by ID | |
| predictions_df = pd.DataFrame(list(predictions.items()), columns=['Customer ID', 'Prediction']) | |
| st.dataframe(predictions_df) | |
| else: | |
| error_data = response.json() | |
| st.error(f"Error making batch prediction: {error_data.get('error', 'Unknown error')}") | |
| except requests.exceptions.RequestException as e: | |
| st.error(f"Connection error: {e}") | |
| except Exception as e: | |
| st.error(f"Unexpected error: {e}") | |
| # Add information section | |
| st.subheader("Check API Status") | |
| if st.button("Check API Status"): | |
| try: | |
| response = requests.get("https://manasranjanpani-extraalearncustomerpredictionbackend.hf.space/ping") | |
| if response.status_code == 200: | |
| st.success("API is running and responsive") | |
| else: | |
| st.error("API is not responding properly") | |
| except: | |
| st.error("Cannot connect to API") | |