This will help us in productionized of the Machine Learning model. Also

• ML Model Design
• Pickle of ML model (Serialized)
• Flask Rest Endpoint
• Containerized the ML Model with Docker
• Deploy on AWS Beanstalk

• Python 3
• Scikit-Learn
• Numpy
• Pandas
• Flask
• AWS
• Docker

• Data Preparation & Cleaning
• Creating model
• Analysis of data
• Correlation
• missing values
• Drive Features

• Correction
• Correlation
• Converting
• Fixing
• Classifying

• Use the Scikit-learn model for training Model and fit and train the model.

• Pipeline make the chains of several step together.
• Scikit learn have a good class Pipeline this usesfor Creating the Pipeline for data pre-processing and joining all the pipe in serial form.
• from sklearn.pipeline import make_pipeline .

• Requirements files" are files containing a list of items to be installed using pip install like so
• pip install -r requirements.txt
• pip freeze > requirements.txt

• docker build .
• docker run image
• docker build -t ml-as-a-service:latest .
• docker run -d -p 5000:5000 ml-as-a-service
• docekr ps : check running images