Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +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
+# Set the working directory inside the container
 WORKDIR /app
 
-# Copy all files from the current directory on the host to the container's /app directory
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install Python dependencies listed in requirements.txt
-RUN pip3 install -r requirements.txt
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-# 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"]
-
-# NOTE: Disable XSRF protection for easier external access in order to make batch predictions
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:sales_forecast_api"]

app.py

@@ -1,54 +1,80 @@
-import requests
-import streamlit as st
+import joblib
 import pandas as pd
+from flask import Flask, request, jsonify
 
-st.title("Sales Prediction for SuperKart")
-
-# Batch Prediction
-st.subheader("Online Prediction")
-
-# Input fields for product data
-Product_Weight=st.number_input("Product_Weight")
-Product_Sugar_Content=st.selectbox("Sugar content",["Low Sugar","Regular","No Sugar","reg"])
-Product_Allocated_Area=st.number_input("Product_Allocated_Area")
-Product_Type=st.selectbox("Product Type",["Frozen Foods","Dairy","Canned","Baking Goods","Health and Hygiene","Snack Foods","Meat","Household","Hard Drinks","Fruits and Vegetables","Breads","Soft Drinks","Breakfast","Others","Starchy Foods","Seafood"])
-Product_MRP=st.number_input("Product_MRP")
-Store_Establishment_Year=st.number_input("Store_Establishment_Year",min_value=1900, max_value=9999)
-Store_Size=st.selectbox("Store size", ["Medium","High","Small"])
-Store_Location_City_Type=st.selectbox("Store_Location_City_Type",["Tier 1","Tier 2","Tier 3"])
-Store_Type=st.selectbox("Store_Type",["Food Mart","Supermarket Type1","Supermarket Type2","Departmental Store"])
-
-sales_data={
-      'Product_Weight': Product_Weight,
-      'Product_Sugar_Content': Product_Sugar_Content,
-      'Product_Allocated_Area': Product_Allocated_Area,
-      'Product_Type': Product_Type,
-      'Product_MRP': Product_MRP,
-      'Store_Establishment_Year': Store_Establishment_Year,
-      'Store_Size': Store_Size,
-      'Store_Location_City_Type': Store_Location_City_Type,
-      'Store_Type': Store_Type
-}
-
-if st.button("Predict", type='primary'):
-  response = requests.post("https://Shalyn-backend.hf.space/v1/sales", json=sales_data)
-    if response.status_code == 200:
-        result = response.json()
-        sales_prediction = result["Prediction"]  # Extract only the value
-        st.write(f"Based on the information provided, the sales forecast is likely to be {sales_prediction}.")
-    else:
-        st.error("Error in API request")
-
-# Batch Prediction
-st.subheader("Batch Prediction")
-
-file = st.file_uploader("Upload CSV file", type=["csv"])
-if file is not None:
-    if st.button("Predict for Batch", type='primary'):
-        response = requests.post("https://Shalyn-backend.hf.space/v1/salesbatch", files={"file": file})    
-        if response.status_code == 200:
-            result = response.json()
-            st.header("Batch Prediction Results")
-            st.write(result)
-        else:
-            st.error("Error in API request")
+#initialise flask app
+sales_forecast_api = Flask('Sales forecasting')
+
+# load the model
+
+model = joblib.load('deployment_files/sales_forecast_v1_0.joblib')
+
+#define home page
+@sales_forecast_api.get('/')
+def home():
+  return 'Welcome to the sales forecase api'
+
+#define an endpoint for prediction
+@sales_forecast_api.post('/v1/sales')
+def sales_predict():
+  #get data from json request
+  sales_data = request.get_json()
+
+  #get relevant details
+  sample = {
+      'Product_Weight': sales_data['Product_Weight'],
+      'Product_Sugar_Content': sales_data['Product_Sugar_Content'],
+      'Product_Allocated_Area': sales_data['Product_Allocated_Area'],
+      'Product_Type': sales_data['Product_Type'],
+      'Product_MRP': sales_data['Product_MRP'],
+      'Store_Establishment_Year': sales_data['Store_Establishment_Year'],
+      'Store_Size': sales_data['Store_Size'],
+      'Store_Location_City_Type': sales_data['Store_Location_City_Type'],
+      'Store_Type': sales_data['Store_Type']
+      }
+
+  input_data = pd.DataFrame([sample])
+
+#convert the categorical to dummies
+  categorical_columns_for_dummies = ['Product_Sugar_Content','Product_Type','Store_Size','Store_Location_City_Type','Store_Type']
+  input_df_dummies = pd.get_dummies(input_data, columns=categorical_columns_for_dummies, drop_first=True)
+
+  #make model to predict
+  prediction = model.predict(input_df_dummies.reindex(columns=X_train.columns, fill_value=0))
+
+  return jsonify({'Prediction':prediction[0]})
+
+
+#defining endpoint for batch
+@sales_forecast_api.post('/v1/salesbatch')
+
+def sales_batch_predict():
+  #get the file from the request
+  file = request.files['file']
+  #read the file to df
+  input_data = pd.read_csv(file)
+
+#convert the categorical to dummies
+  categorical_columns_for_dummies = ['Product_Sugar_Content','Product_Type','Store_Size','Store_Location_City_Type','Store_Type']
+  input_df_dummies = pd.get_dummies(input_data, columns=categorical_columns_for_dummies, drop_first=False)
+  input_df_aligned =input_df_dummies.reindex(columns=X_train.columns, fill_value=0)
+
+#predict
+  predictions = model.predict(input_df_aligned).tolist() # Predict and convert to list
+  product_id_list = input_data.Product_Id.tolist() # Convert to list
+  store_id_list = input_data.Store_Id.tolist() # Convert to list
+
+  # Create a list of dictionaries for the output
+  output_list = []
+  for i in range(len(product_id_list)):
+    output_list.append({
+        'Product_Id': product_id_list[i],
+        'Store_Id': store_id_list[i],
+        'Prediction': predictions[i]
+    })
+
+  return jsonify(output_list)
+
+#run the flask app in debug mode
+if __name__ == '__main__':
+  sales_forecast_api.run(debug=True)

requirements.txt

@@ -1,11 +1,13 @@
-pandas==2.2.2
-numpy==2.0.2
-scikit-learn==1.6.1
-xgboost==2.1.4
-joblib==1.4.2
-Werkzeug==2.2.2
-flask==2.2.2
-gunicorn==20.1.0
+scikit-learn==1.4.2
+pandas==2.0.3
+numpy==1.25.2
+matplotlib==3.7.1
+seaborn==0.13.1
+joblib==1.3.2
+huggingface_hub==0.20.3
+Flask==3.0.2
+gunicorn==21.2.0
 requests==2.28.1
 uvicorn[standard]
 streamlit==1.43.2
+Werkzeug>=3.0.0