Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Automated Machine Learning Hands on AutoML for beginners
Rating: 4.4 out of 5(33 ratings)
335 students

Automated Machine Learning Hands on AutoML for beginners

How to use AutoML in python AutoML in practise What is Automated Machine Learning
Created byDan We
Last updated 7/2024
English
English [Auto],

What you'll learn

  • A hands on overview of free python automl packages and how to use them
  • What is automl
  • How to use automl in python
  • Automated machine learning in practise

Course content

2 sections • 18 lectures • 2h 27m total length

  • Resources0:01
  • 2 AutoML hands on for beginners intro7:16

    Discover automated machine learning (AutoML) that empowers non-experts and data scientists to automate data preprocessing, feature engineering, model selection, and neural network design, accelerating the data science workflow.

  • Important note0:30
  • 3 Auto EDA18:41

    Explore exploratory data analysis with two auto EDA tools in Python, using Google Colab or Jupyter, showcasing pandas profiling and auto EDA to generate quick, visual data reports.

  • 4 The 1st AutoML Library Regression example14:06

    Explore AutoML, built on TensorFlow, through the first AutoML library regression example, using a train/test split, max trials, and mean squared error evaluation.

  • 5 The 1st AutoML Library Classification example6:57

    Learn how to perform a wine data classification with an AutoML library, split data into training and testing, train a classifier, and evaluate accuracy on unseen data.

  • 6 The 2nd AutoML Library Regression example13:19

    Learn to apply AutoML with AutoGluon for tabular regression on insurance and wine data, using a tabular predictor, label charges, train/test split, and mean squared error evaluation.

  • 7 The 2nd AutoML Library Classification example6:30

    Split the wine data into training and testing sets, build gluon tabular data sets and a tabular predictor, and evaluate wine quality with an accuracy score.

  • Important note0:24
  • 8 The 3rd AutoML Library Regression example13:39

    Learn to use hyperopt as a regression AutoML framework, including data preparation, one-hot encoding with pandas, train-test splits, and evaluation with mean squared error on insurance and wine datasets.

  • 9 The 3rd AutoML Library Classification example6:51

    Explore classification with AutoML using hyperopt and any classifier on the wine dataset. Train with train-test splits and evaluate accuracy, discovering the gradient boosting classifier as the best model.

  • 10 The 4th AutoML Library Regression example10:51

    Install and import the imager auto-ml library in Colab, train a regression model with AutoML, and explore explain, perform, up tuner, and compete modes using root mean squared error.

  • 11 The 4th AutoML Library Classification example4:58

    Learn to use an AutoML library for classification on the wine dataset: split data, train multiple models, evaluate with accuracy, and visualize leaderboard results with plots.

  • 12 The 5th AutoML Library Regression example9:58

    Learn to use Light AutoML for tabular regression: install, configure a regression task, train a model, and evaluate predictions with mean squared error on a split dataset.

  • 13 The 5th AutoML Library Classification example9:55

    Apply Light AutoML to a wine dataset binary classification task, label-encode the target, split train and test, train and predict, and evaluate accuracy.

  • 14 The 6th AutoMLLibrary Regression example13:25

    Learn to use H2O AutoML for regression, from installation and data conversion to training, evaluation, and prediction with mean squared error as a metric.

  • 15 The 6th AutoML Library Classification example10:25

    Explore how to perform classification with H2O AutoML: split data, convert the target to a vector, train models, and inspect predictions, accuracy, and the leaderboard for best performers.

Requirements

  • We only use free AutoML libraries
  • Python knowledge is helpful - this is not a "learning python" class
  • AutoML requires us to write some python code but not a lot

Description

What is Automated Machine Learning (AutoML)

Will Automated Machine Learning replace Datascientists?

How to use AutoML in python

What AutoML options are available and free to use?


If you are a beginner and want answers to those questions and try AutoML yourself then this course is for you.

Here we go through various AutomatedMachine Learning (and Deep Learning) frameworks which are currently available (not an extensive list of course there are many more).

The main goal is to get an overview of what AutoML is and how to use it in python. We focus on free AutoML libraries instead of commercial ones so that you can follow along and try them yourself. The course has demo datasets for regression as well as a classification task so we see both supervised learning tasks for each AutoML libary we are going to cover.

Feel free to try out Automated Machine Learning with your own data as well

For this course you should have used Python before (Even AutoML requires us to write a tiny little bit of code)


Please also understand what this course is not

This course does not offer:

A basic introduction to what is ML/DL or an introduction to python

An in-depth  theoretic dive into each hyperparameter which can be adjusted / tuned

An all-in-one solution for every project you want to take in the future


This course does offer:

hands on code examples on how to apply those libraries on demo datasets

Specific relevant information for each library you need to be aware of when you use it

Helpful tools for any data scientist of business person who wants to reduce redundant and repetitive tasks and free some time to focus on the main steps in the data science life cyclle

Who this course is for:

  • You want to get an overview over automl
  • You want to use automl for free
  • hands on code example on how to apply those libraries on demo datasets
  • This course is NOT A basic introduction to what is ML/DL or an introduction to python
  • This course is NOT a data science theory course
  • This course is NOT an in-depth dive into each hyperparameter which can be adjusted / tuned

Report abuse