Practical Machine Learning for Beginners in 2022

Name: Practical Machine Learning for Beginners in 2022
Rating: 4.1 (135 reviews)

Model Building to Deployment

Created byOlanrewaju Oyinbooke

Last updated 2/2022

English

English [Auto],

What you'll learn

Understand how to take a model from notebook to deployment
Ability to use Flask framework for machine learning model deployment
Ability to Use Postman application to test your model API endpoints
Understand How to leverage on Datasist ibrary for faster model building and deployment

Course content

3 sections • 8 lectures • 1h 48m total length

Introduction14:35
Explore the end-to-end lifecycle of practical machine learning, from a car pricing use case and data exploration to deploying a model via a Flask API and monitoring business impact.

Import Data to MS SQL Database and Connect Using Python24:06
Load Excel data into a Microsoft SQL server, install pyodbc, and connect to the database with Python to read and analyze data.
Exploratory Data Analysis using Datasist Library11:18
Explore data with the Datasist library to perform quick exploratory data analysis, descriptive statistics, and visualizations that reveal missing values, feature types, and distributions.
Feature Engineering11:31
Master feature engineering to improve machine learning performance by creating meaningful features including age, handling missing values, encoding categorical data, and assessing feature importance to boost predictive models.
Model Building by Training an Algorithm14:01
Train a simple model using inputs and a target, split data into train and test, and evaluate metrics to gauge performance; save and compare feature impacts for production readiness.
Model Deployment Using Streamlit12:04
Deploy a machine learning model with streamlit by loading a pickle file and exposing input variables for real-time predictions in a simple web interface.
Model Deployment Using FastAPI13:40
deploy a practical machine learning model using fastapi, loading a pickled model, defining a prediction route, and exploring openapi docs and swagger for testing.

Requirements

Introductory knowledge to Python suffices

Description

This course is for every beginner in the data science space. We have been there before and we understood what your learning challenges are. This short course will focus on showing you end to end what it takes to build and deploy a simple machine learning solution.

We will be building a car pricing prediction engine. This will be purely hands-on.

You will be able to deploy this solution using the flask framework as an API and also as a Platform.

We will also introduce you to libraries that make it easy to quickly explore, build, and deploy a machine learning solution.

This course assumes you do not have any prior knowledge of Machine Learning or that you have taken a couple of courses but still missing the full picture.

Machine learning models are not useful in silos and this free course will show you the full picture and cover the knowledge gaps.

You will also be able to put to use your knowledge of HTML as we build a simple web interface to interact with the solution.

This course will also introduce you to Postman Application. It is a popular use for testing API and solutions. Postman will help us to interact with the API deployment of our model while our browser is sufficient for interacting with the platform deployment.

We will be making use of the following major applications:

1. Jupyter Notebook

2. Visual Studio Code

3. Postman

Who this course is for:

Data Science Enthusiast
Beginner Python Developers curious about Data Science
Data Analyst willing to move to the predictive space
Business People curious about model building and deployment

Practical Machine Learning for Beginners in 2022

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 15min

Installing the Required Applications1 lecture • 7min

Build and Deploy a Machine Learning Model6 lectures • 1hr 27min

Requirements

Description

Who this course is for: