Production Grade Machine Learning Service

Overview

Production Grade Machine Learning Service

Stack

Flask as the web framework.
Redis for a fast loading of the trained model and other data between the workers.
NGINX as a web server and reverse proxy.
Gunicorn automatically creates parallel workers/threads according to the capacity of the machine it is running on.
Celery to support asynchronous time-consuming requests as training and initializing the ML model.

Important Info

● Made to help you scale from a basic Machine Learning project for research purposes to a production grade Machine Learning web service.
● General purpose project, so it assumes that your service needs initialization, training, saving models to the databases for further usage in estimation.
● Based on Docker, so it could be scalable and OS-agnostic.

For the detailed API, use the file ml-service.yml on any swagger editor, and you will see the API definition.

You can find a postman collection of this service in the file MLServiceStructure.postman_collection.json, use it to validate your deployment.

Don't forget to create the file ./src/config.properties , use the following template to add the auth-related configuration:
NOTE: expiry_time_unit MUST BE ONE OF THE FOLLOWING:
(days | seconds | microseconds | milliseconds | minutes | hours | weeks)

[auth_info]
expiry=XXXX
expiry_time_unit=XXXX  

expiry is basically the amount of time in expiry_time_unit for the generated bearer tokens to expire. example:

[auth_info]
expiry=120
expiry_time_unit=seconds  

Also Don't forget to create the file ./redis/config.properties , use the following template to add the redis information:

MASTER_USER=XXXXX
REDIS_MASTER_PW=XXXXX
REDIS_CELERY_PW=XXXXX
HOST=redis
END_FILE=true

There are no restrictions about the values of XXXX in this file, you can use your own or use the following example:

MASTER_USER=master_user
REDIS_MASTER_PW=1234pw!@$
REDIS_CELERY_PW=4321wp!@$
HOST=redis
END_FILE=true
Owner
Abdullah Zaiter
Abdullah Zaiter
dirty_cat is a Python module for machine-learning on dirty categorical variables.

dirty_cat dirty_cat is a Python module for machine-learning on dirty categorical variables.

637 Dec 29, 2022
Napari sklearn decomposition

napari-sklearn-decomposition A simple plugin to use with napari This napari plug

1 Sep 01, 2022
PROTEIN EXPRESSION ANALYSIS FOR DOWN SYNDROME

PROTEIN-EXPRESSION-ANALYSIS-FOR-DOWN-SYNDROME Down syndrome (DS) is a chromosomal disorder where organisms have an extra chromosome 21, sometimes know

1 Jan 20, 2022
Python library for multilinear algebra and tensor factorizations

scikit-tensor is a Python module for multilinear algebra and tensor factorizations

Maximilian Nickel 394 Dec 09, 2022
GAM timeseries modeling with auto-changepoint detection. Inspired by Facebook Prophet and implemented in PyMC3

pm-prophet Pymc3-based universal time series prediction and decomposition library (inspired by Facebook Prophet). However, while Faceook prophet is a

Luca Giacomel 314 Dec 25, 2022
LinearRegression2 Tvads and CarSales

LinearRegression2_Tvads_and_CarSales This project infers the insight that how the TV ads for cars and car Sales are being linked with each other. It i

Ashish Kumar Yadav 1 Dec 29, 2021
Markov bot - A Writing bot based on Markov Chain for Data Structure Lab

基于马尔可夫链的写作机器人 前端 用html/css完成 Demo展示(已给出文本的相应展示) 用户提供相关的语料库后训练的成果 后端 要完成的几个接口 解析文

DysprosiumDy 9 May 05, 2022
Simulation of early COVID-19 using SIR model and variants (SEIR ...).

COVID-19-simulation Simulation of early COVID-19 using SIR model and variants (SEIR ...). Made by the Laboratory of Sustainable Life Assessment (GYRO)

José Paulo Pereira das Dores Savioli 1 Nov 17, 2021
Kaggle Competition using 15 numerical predictors to predict a continuous outcome.

Kaggle-Comp.-Data-Mining Kaggle Competition using 15 numerical predictors to predict a continuous outcome as part of a final project for a stats data

moisey alaev 1 Dec 28, 2021
Self Organising Map (SOM) for clustering of atomistic samples through unsupervised learning.

Self Organising Map for Clustering of Atomistic Samples - V2 Description Self Organising Map (also known as Kohonen Network) implemented in Python for

Franco Aquistapace 0 Nov 16, 2021
monolish: MONOlithic Liner equation Solvers for Highly-parallel architecture

monolish is a linear equation solver library that monolithically fuses variable data type, matrix structures, matrix data format, vendor specific data transfer APIs, and vendor specific numerical alg

RICOS Co. Ltd. 179 Dec 21, 2022
Predicting job salaries from ads - a Kaggle competition

Predicting job salaries from ads - a Kaggle competition

Zygmunt Zając 57 Oct 23, 2020
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learn

Vowpal Wabbit 8.1k Dec 30, 2022
A machine learning web application for binary classification using streamlit

Machine Learning web App This is a machine learning web application for binary classification using streamlit options this application contains 3 clas

abdelhak mokri 1 Dec 20, 2021
flexible time-series processing & feature extraction

A corona statistics and information telegram bot.

PreDiCT.IDLab 206 Dec 28, 2022
Interactive Web App with Streamlit and Scikit-learn that applies different Classification algorithms to popular datasets

Interactive Web App with Streamlit and Scikit-learn that applies different Classification algorithms to popular datasets Datasets Used: Iris dataset,

Samrat Mitra 2 Nov 18, 2021
Machine Learning approach for quantifying detector distortion fields

DistortionML Machine Learning approach for quantifying detector distortion fields. This project is a feasibility study for training a surrogate model

Joel Bernier 1 Nov 05, 2021
To design and implement the Identification of Iris Flower species using machine learning using Python and the tool Scikit-Learn.

To design and implement the Identification of Iris Flower species using machine learning using Python and the tool Scikit-Learn.

Astitva Veer Garg 1 Jan 11, 2022
A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.

pmdarima Pmdarima (originally pyramid-arima, for the anagram of 'py' + 'arima') is a statistical library designed to fill the void in Python's time se

alkaline-ml 1.3k Dec 22, 2022
A machine learning project that predicts the price of used cars in the UK

Car Price Prediction Image Credit: AA Cars Project Overview Scraped 3000 used cars data from AA Cars website using Python and BeautifulSoup. Cleaned t

Victor Umunna 7 Oct 13, 2022