Automated Machine Learning with AutoGluon Library in Python

Name: Automated Machine Learning with AutoGluon Library in Python
Rating: 4.8 (157 reviews)

Discover how to easily automate entire machine learning pipelines with the extremely powerful Autogluon library from AWS

Created byJose Portilla, Pierian Training

Last updated 7/2023

English

What you'll learn

Understand the basics of the Autogluon Python library and its capabilities for automating machine learning tasks.
Learn how to install and set up the Autogluon Python library in your local environment.
Develop skills in data preparation and cleaning processes that are critical for successful machine learning outcomes using Autogluon.
Discover best practices for selecting and configuring machine learning models to achieve optimal results with minimal effort.
Explore how to use Autogluon to create high-accuracy models for image classification tasks, including object detection, segmentation, and classification.
Understand how to use Autogluon to perform natural language processing (NLP) tasks such as sentiment analysis.
Learn how to train and deploy time series models using Autogluon to make accurate predictions for future events or trends.
Gain hands-on experience in using Autogluon to analyze tabular data and build predictive models for business applications and financial forecasting.

Course content

5 sections • 37 lectures • 5h 33m total length

Course Downloads and Files0:43
Course Welcome1:50
Access the course resources, including slides and a data zip, from the first lecture. Review the AutoGluon documentation and use the provided notebooks to troubleshoot typos before posting questions.
Course Curriculum Overview7:31
AutoGluon Overview7:26
Explore Autogluon, an open source library from Amazon that automates machine learning for tabular, image, and text data, offering ensemble models, cross-validation, and simple feature engineering.

Introduction to Tabular Data Section2:45
OPTIONAL: Supervised Learning Overview17:00
AutoGluon Classification Part One: Data and Split15:12
AutoGluon Classification Part Two: Training the Model18:17
OPTIONAL: Train Test Splits and Cross-Validation6:29
AutoGluon Classification Part Three: Validation12:24
Validate models with a holdout test dataset to measure performance on unseen data. Use AutoGluon’s tabular predictor to predict new data, then evaluate accuracy, precision, and recall.
OPTIONAL: Understanding Classification Metrics17:00
AutoGluon Classification Part Four: Interpretability12:46
Explore model-agnostic feature interpretability in AutoGluon by using permutation shuffling to rank features like lead time and special requests and assess their impact on predictions.
AutoGluon Regression: Data, Split, Training, and Validation13:07
OPTIONAL: Regression Metrics8:20
Explore regression metrics in Autogluon, comparing mean absolute error, mean squared error, and root mean squared error, and understand how to interpret these in context of continuous predictions.
AutoGluon Fit Parameters: Inference Constraints and Manual Hyperparameters17:15
Advanced AutoGluon: Presets and Deployment10:19
Advanced AutoGluon: Custom Feature Engineering Pipeline6:26
Discover AutoGluon’s automated feature engineering for tabular data, using the auto ml pipeline feature generator and built-in generators, with options to customize a feature pipeline.

Introduction to Multi-Modal Data Problems5:58
Optional: Download Trained Book Rating Prediction Model Here0:13
Natural Language - MultiClass Problem - Part One12:01
Natural Language - MultiClass Problem - Part Two5:44
Optional: Download Trained Sentiment Analysis Model0:22
MultiModalPredictor on Binary Class with Natural Language Text19:01
Discover how the multimodal predictor combines text, images, and tabular data with transformer models from a model zoo to excel in binary classification on natural language data.
Optional: Download Trained MultiModal Image, Natural Language, and Tabular Model0:04
MultiModalPredictor with Image, Natural Text, and Tabular Data13:25
Build a multimodal predictor using image, text, and tabular data with AutoGluon, integrating pet adoption data from Petfinder Kaggle, setting full image paths and train-test splits for prediction.

Introduction to Time Series1:43
Explore time series forecasting with Autogluon, building probabilistic forecasts using ETS, ARIMA, and neural networks. See single variate and multivariate time series with known and past covariance.
Overview of Time Series in AutoGluon12:15
Learn how to forecast a single variate time series with AutoGluon, focusing on data formatting, train/validation splits, and using known and past covariates for multivariate forecasting.
Single Variate Time Series Forecasting in AutoGluon - Part One11:34
Single Variate Time Series Forecasting in AutoGluon - Part Two10:31
Single Variate Time Series Forecasting in AutoGluon - Part Three9:00
Visualize single variate forecasts in AutoGluon by plotting the mean forecast and the 10%–90% confidence interval with matplotlib, using a reusable plot_predictions function for training and prediction data.
Known Covariate Time Series Forecasting in AutoGluon - Part One17:51
Known Covariate Time Series Forecasting in AutoGluon - Part Two4:08
learn to use AutoGluon time series predictor with known covariates to forecast future dates, feeding future events like holidays and day of week, and visualize predictions.
Past Covariate Time Series Forecasting6:55
Leverage past covariates to improve multivariate time series forecasts with Autogluon. Forecast pollution seven days ahead using a time series data frame and visualize results with confidence intervals.

Introduction to Images2:34
Explore image classification and object detection with AutoGluon, using the multimodal predictor and Openai's clip, and run experiments in Google Colab to handle image data.
Google Colab Notebook Online Set-Up7:06
Set up Google Colab notebooks, configure runtime for GPU or TPU, and install Autogluon plus MKV Fool and MMDet for detection to enable multimodal prediction.
Image Classification8:41
OpenAI CLIP with AutoGluon9:29

Requirements

Some Python experience required.
Previous machine learning experience helpful, but no required.

Description

Welcome to our online course on Autogluon!

Are you tired of spending countless hours performing repetitive and time-consuming tasks when it comes to machine learning? Do you want to automate your machine learning tasks and achieve strong predictive performance in your applications with minimal effort? Look no further than Autogluon.

Our comprehensive online course is designed to provide you with the skills and knowledge necessary to use the Autogluon Python library for automating machine learning tasks. With just a few lines of code, you can train and deploy high-accuracy machine learning and deep learning models on image, text, time series, and tabular data.

Throughout the course, you will learn how to install and set up the Autogluon Python library in your local or cloud-based environment. You will also develop skills in data preparation and cleaning processes that are critical for successful machine learning outcomes using Autogluon. Additionally, we will cover best practices for selecting and configuring machine learning models to achieve optimal results with minimal effort.

Our course will also take a deep dive into using Autogluon to create high-accuracy models for image classification tasks, including object detection, segmentation, and classification. You will also learn how to use Autogluon to perform natural language processing (NLP) tasks such as sentiment analysis, language translation, and named entity recognition.

But that's not all! We will also cover how to train and deploy time series models using Autogluon to make accurate predictions for future events or trends. You'll gain hands-on experience in using Autogluon to analyze tabular data and build predictive models for business applications and financial forecasting.

By the end of this course, you will have developed skills in model interpretation and evaluation techniques to assess the accuracy and reliability of machine learning models created using Autogluon. You'll be able to apply the knowledge gained from this course to real-world scenarios, such as developing predictive models for customer churn, fraud detection, or personalized recommendations.

Our course is designed for data scientists, machine learning engineers, and software developers who are looking to automate their machine learning tasks and achieve strong predictive performance in their applications. Prior experience with Python programming and machine learning concepts is recommended but not required.

Enroll today in our comprehensive online course and learn how to use Autogluon to automate your machine learning tasks and achieve strong predictive performance in your applications with minimal effort.

Who this course is for:

Data scientists, machine learning engineers, and software developers who are looking to automate their machine learning tasks

Automated Machine Learning with AutoGluon Library in Python

What you'll learn

Explore related topics

Course content

Course Overview and Introduction4 lectures • 18min

Tabular Data - Classification and Regression13 lectures • 2hr 37min

Multi-Modal Datasets8 lectures • 57min

Time Series Forecasting8 lectures • 1hr 14min

Image Classification and Object Detection4 lectures • 28min

Requirements

Description

Who this course is for: