Upload folder using huggingface_hub

Dockerfile

@@ -1,21 +1,16 @@
+# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
 
+# Install Python dependencies listed in requirements.txt
 RUN pip3 install -r requirements.txt
 
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+# 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"]
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

app.py

@@ -0,0 +1,59 @@
+import streamlit as st
+import requests
+import json
+import pandas as pd
+
+# Streamlit UI
+st.title('Boston Housing Price Predictor 🏠')
+st.write('Enter the details of the area to predict the median home value.')
+
+# Create input fields for each feature
+crim = st.number_input('Per capita crime rate (CRIM)', value=0.0)
+zn = st.number_input('Proportion of residential land zoned for lots over 25,000 sq.ft. (ZN)', value=0.0)
+indus = st.number_input('Proportion of non-retail business acres per town (INDUS)', value=0.0)
+chas = st.selectbox('Tract bounds Charles River? (CHAS)', options=[0, 1], format_func=lambda x: 'Yes' if x == 1 else 'No')
+nox = st.number_input('Nitric oxides concentration (NOX)', value=0.0)
+rm = st.number_input('Average number of rooms per dwelling (RM)', value=0.0)
+age = st.number_input('Proportion of owner-occupied units built prior to 1940 (AGE)', value=0.0)
+dis = st.number_input('Weighted distances to five Boston employment centers (DIS)', value=0.0)
+rad = st.number_input('Index of accessibility to radial highways (RAD)', value=0.0)
+tax = st.number_input('Full-value property-tax rate per $10,000 (TAX)', value=0.0)
+ptratio = st.number_input('Pupil-teacher ratio by town (PTRATIO)', value=0.0)
+lstat = st.number_input('% lower status of the population (LSTAT)', value=0.0)
+
+# Create a dictionary of the input features
+input_data = {
+    'CRIM': crim,
+    'ZN': zn,
+    'INDUS': indus,
+    'CHAS': chas,
+    'NOX': nox,
+    'RM': rm,
+    'AGE': age,
+    'DIS': dis,
+    'RAD': rad,
+    'TAX': tax,
+    'PTRATIO': ptratio,
+    'LSTAT': lstat
+}
+
+# Button to make a prediction
+if st.button('Predict Median Home Value'):
+    # Define the backend API URL (replace with your deployed URL)
+    API_URL = "http://localhost:5000/predict" # For local testing
+    # API_URL = "https://<your-space-name>.hf.space/predict" # For Hugging Face
+
+    try:
+        response = requests.post(API_URL, json=input_data)
+        if response.status_code == 200:
+            prediction = response.json()['prediction']
+            st.success(f'The predicted median home value is: ${prediction:.2f} (in thousands)')
+            st.markdown(f'**Predicted Value**: ${prediction * 1000:,.2f}')
+        else:
+            st.error(f"Error from API: {response.text}")
+    except requests.exceptions.ConnectionError:
+        st.error("Connection error. Please ensure the backend is running.")
+
+st.markdown("---")
+st.write("This application uses a machine learning model to predict the median value of homes in Boston suburbs.")
+st.markdown("")

requirements.txt

@@ -1,3 +1,3 @@
-altair
-pandas
-streamlit
+streamlit==1.36.0
+requests==2.32.3
+pandas==2.2.2