Building Machine Learning Web Apps with Python
4.2 (49 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
648 students enrolled

Building Machine Learning Web Apps with Python

Going Beyond Machine Learning Models
4.2 (49 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
648 students enrolled
Created by Jesse E. Agbe
Last updated 6/2020
English
English [Auto]
Current price: $48.99 Original price: $69.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 24 hours on-demand video
  • 1 article
  • 15 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Building Machine Learning Models with Python
  • Build Machine Learning Web Apps
  • How to Convert ML Models into Simple and Useful Products
  • How to Use ML Models as Packages
  • Embedding ML Models into Web Apps [Flask,Streamlit,etc]
  • How to use Streamlit to build ML apps
  • How to use Flask to build web applications
  • Productionize ML Models
Requirements
  • Understand the basics of python and machine learning
  • Basic Knowledge of HTML,CSS
  • Ability to work around a computer and a terminal
  • Determination
Description

Course Description

Artificial Intelligence and Machine Learning is affecting every area of our lives and society. Google, Amazon, Netflix, Uber, Facebook and many more industries are using AI and ML models in their products.

The opportunities and advantages of Machine Learning is quite numerous.

What if you could also build your own machine learning models?

What if you can build something useful from the ML model you have spend time creating and make some profit whiles helping people and changing the world?


In this wonderful course, we will be exploring the various ways of converting your machine learning models into useful web applications and products.

We will move beyond just building machine learning models into build products from our ML Models.

Products that you can give to your customers and other users to benefit from. We will be adding simple UI to our AI and ML models.


With every section of the course you will develop new skills and improve your understanding of this challenging yet important sub-field of Data Science and Machine Learning.

This course is unscripted,fun and exciting but at the same time we dive deep into building Machine Learning web applications.

What You will Gain in this Course

In this course you will develop new skills as you  learn:

  1.     how to setup your Data Science and ML work-space locally.

  2.     how to build machine learning models.

  3.     how to interpret ML models with Eli5.

  4.     how to serialize and save ML models.

  5.     how to build ML web apps using the models we have created.

  6.     how to build packages from your ML Models.

  7.     how to deploy your products.

    etc

Join us as we explore the world of building Machine Learning apps and tools.



Who this course is for:
  • Programmers and Developers
  • Any one interested in building web apps
  • ML Engineers and Data Scientist
  • Beginner Python Developers interested in Machine Learning and Data Science
  • People curious about how to build and productionize their machine learning models
Course content
Expand all 84 lectures 23:56:24
+ Introduction To Building ML Apps
17 lectures 02:07:46

Course Introduction and Outline

Preview 04:44

Ways To Productionize Your Machine Learning Models

  • Using Web Apps (Flask,Pyramid,Django,Express,etc)

  • Using Your ML Models as API

  • Using Streamlit

  • Using Your ML Models as a Package

  • Using Docker

Preview 05:27
How to Setup Your Workspace
06:51

Using Pipenv

How to Install Pipenv on Your System

pip install pipenv

How to Setup Your Workspace - Using Pipenv
21:41
How to Setup Your Workspace - Using Pipes
02:56
How to Setup Your Workspace - Using Poetry
09:06
Where to Find Datasets
04:48
Building Machine Learning Models - Salary Prediction - Introduction
08:17
Building Machine Learning Models - Salary Prediction
07:08
Building Machine Learning Models - Interpreting ML Models
05:07
Building Machine Learning Models - Bible Passage Prediction
14:25
Building Machine Learning Models - Saving ML Models
04:01

In this lecture we will be going on a fast pace to get an idea of how to build models for gender classification of names. We will be using these saved models in the next sections to build packages and other products.

Building Machine Learning Models - Gender Classification - Quick Overview
05:25
Building Machine Learning Models - Evaluating Car Quality with ML
18:06
+ Crash Courses On Web Frameworks
13 lectures 03:48:56
Flask Crash Course - Introduction
04:42
Flask Crash Course - Rendering HTML
03:55
Flask Crash Course - Working with Jinja
04:21
Flask Crash Course - Receiving Data From Front-End
09:16
Flask Crash Course - Processing Data at Back-End
01:23
Flask Crash Course - Working with Databases
10:43
Flask Crash Course - Retrieving Data From Database
05:59
Flask Crash Course - Searching Databases
04:33

Streamlit  Crash Course

Streamlit - A Machine Learning Framework for building ML Tools

Installation

pip install streamlit

Streamlit Crash Course
47:32
Streamlit Crash Course - Plots and Work Around
15:47
Introduction to Hug Framework For API Development
09:55
Streamlit- Building A simple CRUD Blog App
01:10:51
Streamlit - Adding a Login Section To the Blog
39:59
+ Building ML Apps
28 lectures 08:18:12
Introduction To Building ML Apps
00:27
Building ML Flask Apps
02:02
Building ML Flask Apps - Installation and Basic App
04:21
Building ML Flask Apps - Embedding ML Into Flask
21:24
Building ML Flask Apps - Beautifying the Front-End
00:53
Salary Predictor ML App - Demo
10:40
Building ML Web Apps - Setting Up and Exploratory Data Analysis of App
11:19
Salary Predictor ML App - EDA Aspect
16:10
Salary Predictor ML App - EDA Aspect 2
05:19
Building ML Apps - Salary Predictor - Prediction Aspect
22:51
Building ML Apps - Salary Predictor - Prediction Aspect 2
14:25
Building ML Apps - Salary Predictor - Metrics and Monitoring App
15:03
Building ML Apps - Salary Predictor - Countries Aspect
17:35
Building ML Apps - CMC - Predictor - Setting Up
09:07
Building ML Apps - CMC - Predictor - EDA
26:57
Building ML Apps - CMC - Predictor - Prediction
29:31
Building NLP Apps - Sentiment Analysis and Emoji App
33:43
Building NLP Apps - Summary and Entity Checker App
35:57

This utilizes the new feature which is found only version 0.52.1 and upwards.

To install you will need to use this

pip install streamlit==0.52.1


Building A Drag a Drop ML App
43:50
Course Materials and Codes
00:12
Building ML Apps - Password Strength Classifier (Password Masking Feature)
30:03
Building ML Apps - Car Evaluation ML App
32:26
Building Computer Vision ML App - Face Detection App - Demo
05:08
Building Computer Vision ML App - Face Detection App - Building the App
40:23
Emoji Lookup App with Streamlit - Demo
04:23
Trend Analysis App For Programming Languages Search Term -Demo
08:05
Trend Analysis App with Streamlit (For Programming Languages)
50:55
+ Using ML Models as Packages
11 lectures 01:39:35
Building the Model For Gender Classification of Names
05:25
Using ML Models as Packages - Gender Classifier ML Package Demo
02:35
Gender Classifier ML Package - Creating the Class
07:29
Gender Classifier ML Package - Adding the Prediction to Package
09:17
Gender Classifier ML Package - Loading Different Models
05:24
Gender Classifier ML Package - Classifying Names
05:59
Gender Classifier ML Package - Unit Testing Our Package
04:42
Gender Classifier ML Package - Building Our Package with Setuptools
08:25
Gender Classifier ML Package - Building Our Package with Poetry
08:19
Gender Classifier ML Package - Publishing Our Package
03:51
Spam Detector ML Package - In Depth
38:09
+ Using ML Models as API
5 lectures 01:30:44
Introduction to FastAPI
08:22
  1. In this lecture we will learn how to serve or use our ML models as API using FastAPI, a high performance framework.

Serving Machine Learning Models As API
21:19
Adding Validations To Parameters
06:47

So far we have seen how to productionize our ML models in several ways. Another great tool you can use to simplify the building of these ML products is to use Hug.

Hug is a framework that exposes your code in several ways specifically in 3 Main Ways

  1. Local Package

  2. API

  3. CLI

In this section we will learn how to do so.

Building 3 Machine Learning Products at Once with Hug Framework
27:51
Building A Simple API,CLI and Package with Hug Framework
26:25
+ Deploying Our ML Apps
7 lectures 01:53:59
How to Deploy Streamlit Apps to Heroku
24:38
Updating an Already Deployed App
06:04
How to Deploy Streamlit Apps to AWS EC2
23:15
How to Deploy Streamlit Apps with Docker
17:31
How to Deploy Streamlit Apps on Google Cloud Platform (App Engine)
15:12
Updating and Deleting A Streamlit App on GCP
05:26
How to Deploy Streamlit OpenCV app - Face Detection App on Heroku
21:53
+ Bonus Section - Data Science Project From Scratch
3 lectures 04:37:12
Data Science Project 1 - Hepatitis Mortality Prediction
02:43:20
Data Science Project 1 - Hepatitis Predictor ML App with Streamlit
01:10:41
Data Science Project 1 - Hepatitis Predictor ML App with Flask
43:11