Google Cloud Platform for Data Science: A Crash Course on Big Data, Machine Learning, and Data Analytics Services
- Добавил: literator
- Дата: 18-11-2023, 06:38
- Комментариев: 0
![](/uploads/posts/2023-11/thumbs/1700278731_google-cloud-platform-for-data-science.png)
Автор: Shitalkumar R. Sukhdeve, Sandika S. Sukhdeve
Издательство: Apress
Год: 2024
Страниц: 231
Язык: английский
Формат: pdf
Размер: 10.2 MB
This book is your practical and comprehensive guide to learning Google Cloud Platform (GCP) for Data Science, using only the free tier services offered by the platform.
Data Science and Machine Learning are increasingly becoming critical to businesses of all sizes, and the cloud provides a powerful platform for these applications. GCP offers a range of Data Science services that can be used to store, process, and analyze large datasets, and train and deploy Machine Learning models.
The book is organized into seven chapters covering various topics such as GCP account setup, Google Colaboratory, Big Data and Machine Learning, Data Visualization and Business Intelligence, Data Processing and Transformation, Data Analytics and Storage, and Advanced Topics. Each chapter provides step-by-step instructions and examples illustrating how to use GCP services for Data Science and Big Data projects.
Readers will learn how to set up a Google Colaboratory account and run Jupyter notebooks, access GCP services and data from Colaboratory, use BigQuery for data analytics, and deploy Machine Learning models using Vertex AI. The book also covers how to visualize data using Looker Data Studio, run data processing pipelines using Google Cloud Dataflow and Dataprep, and store data using Google Cloud Storage and SQL.
Google Colaboratory, or Colab, is a robust cloud-based platform for Data Science. In the Chapter 2, we delve into the features and capabilities of Colab. You will learn how to create and run Jupyter notebooks, including Machine Learning models, leveraging Colab's seamless integration with GCP services. We also discuss the benefits of using Colab for collaborative data analysis and experimentation.
The Chapter 3 explores the world of big data and Machine Learning on GCP. We delve into BigQuery, a scalable data warehouse, and its practical use cases. Next, we focus on BigQuery ML, which enables you to build Machine Learning models directly within BigQuery. We then focus on Google Cloud AI Platform, where you will learn to train and deploy machine learning models. Additionally, we introduce TensorFlow, a popular framework for deep learning on GCP. Lastly, we explore Google Cloud Dataproc, which facilitates the efficient processing of large-scale datasets.
What You Will Learn:
Set up a GCP account and project
Explore BigQuery and its use cases, including machine learning
Understand Google Cloud AI Platform and its capabilities
Use Vertex AI for training and deploying machine learning models
Explore Google Cloud Dataproc and its use cases for big data processing
Create and share data visualizations and reports with Looker Data Studio
Explore Google Cloud Dataflow and its use cases for batch and stream data processing
Run data processing pipelines on Cloud Dataflow
Explore Google Cloud Storage and its use cases for data storage
Get an introduction to Google Cloud SQL and its use cases for relational databases
Get an introduction to Google Cloud Pub/Sub and its use cases for real-time data streaming
Who This Book Is For:
Data scientists, machine learning engineers, and analysts who want to learn how to use Google Cloud Platform (GCP) for their Data Science and Big Data projects.
Скачать Google Cloud Platform for Data Science: A Crash Course on Big Data, Machine Learning, and Data Analytics Services
![](/templates/LitmyL/images/LitMyru.png)
[related-news] [/related-news]
Внимание
Уважаемый посетитель, Вы зашли на сайт как незарегистрированный пользователь.
Мы рекомендуем Вам зарегистрироваться либо войти на сайт под своим именем.
Уважаемый посетитель, Вы зашли на сайт как незарегистрированный пользователь.
Мы рекомендуем Вам зарегистрироваться либо войти на сайт под своим именем.