Deploying AI & Machine Learning Models for Business | Python

Name: Deploying AI & Machine Learning Models for Business | Python
Rating: 4.4 (2320 reviews)

Learn to build Machine Learning, Deep Learning & NLP Models & Deploy them with Docker Containers (DevOps) (in Python)

Created byUNP United Network of Professionals

Last updated 4/2022

English

What you'll learn

How to synchronize the versatility of DevOps & Machine Learning
Master Docker , Docker Files, Docker Applications & Docker Containers (DevOps)
Flask Basics & Application Program Interface (API)
Build & Deploy a Random Forest Model
Build a Text based (Natural Language Processing : NLP ) CLUSTERING (KMeans) Model and expose it as an API
Build an API which will run a Deep Learning Model (Convolutional Neural Network : CNN) Model for Image Recognition & Classification

Course content

8 sections • 54 lectures • 4h 12m total length

Introduction1:06
I have a model. Now what?1:04
Skills Checklist1:32
Use this skills checklist to determine if this Python-based course fits you. Gain basic programming, machine learning, and the ability to build end-to-end data science projects like a software engineer.
Learning Goals0:38

Introduction0:38
Explore the basics of Flask as a tool through hands-on exercises, guiding you to code along with Spyder IDE to familiarize yourself with the package.
Setting up a Flask Project1:39
Simple Flask API to add two numbers4:25
Taking user input with GET requests4:13
Learn how to take user input in Flask using the request object and get request query parameters A and B, cast to integers, add them, and return the result.
POST request with Flask5:49
Learn how to implement post requests in flask to keep inputs out of the url, using request.form and postman to test body parameters securely.
Using Flask in the context of Machine Learning3:26

Introduction0:38
API & Dataset Overview1:05
Training the Random Forest model5:29
Pickling the Random Forest model2:39
Exposing the Random Forest model as a Flask API5:48
Testing the API model4:24
Providing file input to Flask API7:25
Flasgger for autogenerating UI8:33
Learn to use Flasgger to auto generate a user interface for Flask APIs, exposing machine learning models as APIs with a clean interface for business users.
Summary1:38

Introduction0:46
Base Image & FROM command3:26
COPY and EXPOSE commands3:30
Learn to transfer files from the host file system into a Docker image using the copy command and expose ports, such as 5000, for Flask apps.
WORKDIR, RUN and CMD commands4:08
Set the working directory, run installation commands, and configure a persistent CMD in a Dockerfile to build a reproducible, isolated environment for deploying Python apps such as a Flask server.
Preparing the flask scripts for dockerizing2:03
Prepare the flask scripts for dockerizing by building a dockerfile. Containerize the app, use relative paths for loading the pickle, and test the swagger input predict function.
Writing the Dockerfile8:35
Building the docker image8:33
Build a docker image for a Flask demo using essential docker commands. Resolve common issues such as docker file naming, login errors, and creating a requirements.txt to install Flask.
Running the Random Forest model on Docker8:52

Introduction2:07
Stemming & Lemmatization for cleaner text10:34
Converting unstructured to structured data9:44
KMeans Clustering8:34
Preparing the excel output10:01
Prepare an Excel output by writing to a BytesIO binary object using an XLSX writer, encode as utf-8, name the sheet clusters, and optionally zip multiple outputs for API delivery.
Making the output Downloadable6:18
Configure a zip download for deploying ai and machine learning outputs by sending a memory file as an attachment named cluster_output.zip, setting content-disposition and cross-origin headers, and validating with Postman.
Finding top keywords for kmeans clusters7:09
Extract top keywords for kmeans clusters by mapping cluster centers to feature names, ranking words by weights, and compiling per-cluster top ten keywords for insights and reporting.
Final output with charts7:05
Summary1:27
Containerize an end-to-end unstructured text clustering app with a Flask API using Docker, aiming for a production-grade deployment and GitHub sharing.
Dockerizing the text clustering app

Introduction0:48
Visualizing the input images7:14
Preparing the input images9:20
Building the deep learning model10:31
Training and saving the trained deep learning model3:01
train a convolutional neural network with Keras, normalize inputs, apply one hot encoding to outputs, save the trained model, and load it later to make predictions with a TensorFlow backend.
Generating test images4:08
Flask API wrapper for making predictions8:09
Load the deep learning model and build a Flask API to accept image uploads for predictions. Document the endpoint with Swagger, process 28x28 grayscale images, and return the predicted digit.
Summary2:10
Expose a trained deep learning model as a Flask-powered API, enabling mobile and desktop apps to obtain predictions. Deploy the API with Docker to standardize the environment.
Dockerizing the deep learning app

Requirements

Basic programming in any language
Basic Mathematics
Some exposure to Python (but not mandatory)

Description

Machine Learning, as we know it is the new buzz word in the industry today. This is practiced in every sector of business imaginable to provide data-driven solutions to complex business problems. This poses the challenge of deploying the solution, built by the Machine Learning technique so that it can be used across the intended Business Unit and not operated in silos.

This is an extensive and well-thought course created & designed by UNP's elite team of Data Scientists from around the world to focus on the challenges that are being faced by Data Scientists and Computational Solution Architects across the industry which is summarized the below sentence :

"I HAVE THE MACHINE LEARNING MODEL, IT IS WORKING AS EXPECTED !! NOW, WHAT ?????"

This course will help you create a solid foundation of the essential topics of data science along with a solid foundation of deploying those created solutions through Docker containers which eventually will expose your model as a service (API) which can be used by all who wish for it.

At the end of this course, you will be able to:

Learn about Docker, Docker Files, Docker Containers
Learn Flask Basics & Application Program Interface (API)
Build a Random Forest Model and deploy it.
Build a Natural Language Processing based Test Clustering Model (K-Means) and visualize it.
Build an API for Image Processing and Recognition with a Deep Learning Model under the hood (Convolutional Neural Network: CNN)

This course is a perfect blend of foundations of data science, industry standards, broader understanding of machine learning and practical applications and most importantly deploying them.

Who this course is for:

Anyone willing to venture into the realm of data science
Anyone who would be interested in deploying a Data Science Solution, can be Regression, NLP or even Deep Learning Models

Deploying AI & Machine Learning Models for Business | Python

What you'll learn

Explore related topics

Course content

Course Overview4 lectures • 4min

Docker basics5 lectures • 8min

Flask basics6 lectures • 20min

Exposing a Random Forest Machine Learning service as an API9 lectures • 38min

Writing and building the Dockerfile8 lectures • 40min

Building a production grade Docker application5 lectures • 34min

Building NLP based Text Clustering application9 lectures • 1hr 3min

API for image recognition with deep learning8 lectures • 45min

Requirements

Description

Who this course is for: