Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working directory
+COPY . .
+
+# 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 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:churn_predictor_api"]

app.py

@@ -0,0 +1,75 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+#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})
+
+
+#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=True))
+   input_df_aligned =input_df_dummies.reindex(columns=X_train.columns, fill_value=0)
+
+#predict 
+   predictions = [
+       model.predict(input_df_aligned.drop(['Product_Id','Store_Id'],axis=1)).ToList()
+   ]
+   product_id_list = input_data.Product_Id.values.ToList()
+   store_id_list = input_data.Store_Id.values.ToList()
+   output_dict = dict(zip(product_id_list,store_id_list, predictions))
+   
+
+  retrun output_dict
+
+#run the flask app in debug mode
+if __name__ == '__main__':
+  app.run(debug=True)

requirements.txt

@@ -0,0 +1,8 @@
+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