Everand Logo

Welcome to Everand!

  • Discover millions of audiobooks, ebooks, and so much more with a free trial

    From $11.99/month after trial. Cancel anytime.

    Deep Learning for Data Architects: Unleash the power of Python's deep learning algorithms (English Edition)
    Deep Learning for Data Architects: Unleash the power of Python's deep learning algorithms (English Edition)
    Deep Learning for Data Architects: Unleash the power of Python's deep learning algorithms (English Edition)
    Ebook432 pages2 hours

    Deep Learning for Data Architects: Unleash the power of Python's deep learning algorithms (English Edition)

    By Shekhar Khandelwal

    ()

    Read preview

    About this ebook

    “Deep Learning for Data Architects” is a comprehensive guide that bridges the gap between data architecture and deep learning. It provides a solid foundation in Python for data science and serves as a launchpad into the world of AI and deep learning.

    The book begins by addressing the challenges of transforming raw data into actionable insights. It provides a practical understanding of data handling and covers the construction of neural network-based predictive models. The book then explores specialized networks such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). The book delves into the theory and practical aspects of these networks and offers Python code implementations for each. The final chapter of the book introduces Transformers, a revolutionary model that has had a significant impact on natural language processing (NLP). This chapter provides you with a thorough understanding of how Transformers work and includes Python code implementations.

    By the end of the book, you will be able to use deep learning to solve real-world problems.
    LanguageEnglish
    PublisherBPB Online LLP
    Release dateAug 16, 2023
    ISBN9789355515292
    Deep Learning for Data Architects: Unleash the power of Python's deep learning algorithms (English Edition)

    Related to Deep Learning for Data Architects

    Related ebooks

    Intelligence (AI) & Semantics For You

    View More
    View More

    Related podcast episodes

    Related categories

    Reviews for Deep Learning for Data Architects

    0 ratings

    0 ratings0 reviews

    What did you think?

    Tap to rate

    Review must be at least 10 words

      Book preview

      Deep Learning for Data Architects - Shekhar Khandelwal

      CHAPTER 1

      Python for Data Science

      You can’t build a great building on a weak foundation. You must have a solid foundation if you are going to have a super-strong structure.

      — Gordon B. Hinkley

      Data is the most important component of data science. Python libraries for data science are built specifically to solve various peripheral issues that Data Scientists may face, like data sourcing, cleaning, pre-processing, and working with big data. It is important to know what these libraries have to offer and the sneaky tricks that can be implemented in our day-to-day data wrangling. The high-level methods within these libraries save you a lot of time performing humongous tasks, using just a few lines of code.

      Additionally, data has to be sourced from all over the place. Hence, as someone who is building predictive models, maybe in academia or at work, should be familiar with different kinds of data that one can deal with and how to source them using Python.

      Plus, when you work on your personal system, you have to be really cautious about how you utilize the available resources in terms of computing hardware and so on. Hence, it is of utmost importance to know various tricks that can help you with memory management. The tricks that usually go unnoticed and unexplored within Python packages, if explored, can significantly improve your efficiency while dealing with data.

      Structure

      In this chapter, we will cover the following topics:

      Setting up the development environment

      Advance Python libraries for data science

      Reading and writing data to and from various file formats

      Improving efficiency with the pandas read_csv method

      Objectives

      After studying this chapter, you should be able to set up your laptop with the required tools and technologies to embark on your journey of implementing various deep learning models that will be discussed in this book. Also, you should be able to install various Python packages that are prerequisites for building any predictive model. Once the development environment is set up, you will learn about various Python libraries that are available for scientific computing, machine learning and deep learning. Additionally, you will learn how to maximize your productivity in a limited hardware environment, since machine learning and deep learning are computationally expensive.

      Setting up the development environment

      As part of the environment setup, we will look at how to install the Anaconda tool, which gives access to almost all the required underlying tools and technologies for development. Further, we will understand how to get started with Jupyter Notebook, which is the IDE for Data Scientists. Finally, we will look at how to enhance the notebook by installing important plugins for better usability of the tool.

      Installing Anaconda

      The first and foremost tool that has to be installed on your machine is Anaconda. Anaconda is a distribution of packages for the Python and R programming languages. It includes a package manager called conda that can be used to install, update, and manage packages within the Anaconda environment.

      Tools that come along with Anaconda are as follows:

      Jupyter Notebook

      Orange

      Spyder

      PyCharm

      VS Code

      RStudio

      IBM Watson Studio

      Each of these software can be installed separately as well. However, with anaconda, all of them can be installed in one shot.

      Follow the steps to install Anaconda on your machine:

      Go to the home page of Anaconda at https://www.anaconda.com/products/individual.

      It will look like as shown in Figure 1.1:

      Figure 1.1: Anaconda home page

      Click on Download and download the installer of the choice of your operating system, as shown in the following screenshot:

      Figure 1.2: Anaconda installers

      Double-click on the downloaded installer and follow the installation wizard, as shown in the following screenshot:

      Figure 1.3: Anaconda installation wizard

      Click the Close button after you complete the installation of Anaconda on your machine.

      Now, let’s get started with Jupyter Notebook.

      Getting Started with Jupyter Notebook

      Once Anaconda is installed, you can proceed to launch the Jupyter Notebook on the web browser:

      Open the Anaconda Navigator app on your machine. The screen will look as shown in Figure 1.4:

      Figure 1.4: Anaconda Navigator

      Click on the Launch button under the Jupyter Notebook icon. This will launch the Jupyter homepage on your default browser, as shown in the following screenshot:

      Figure 1.5: Jupyter Notebook

      Further, you can navigate to the desired folder in your filesystem and go to the folder where you want to create a notebook to start building your projects.

      Click on the New dropdown and click on the Python 3 option, as shown in the following screenshot:

      Figure 1.6: Notebook IDE

      This will create a new notebook with the name Untitled, which can be renamed as shown in the following screenshot:

      Figure 1.7: Notebook cell

      You can start writing Python code in the cells, as shown in Figure 1.6, and run them right there using the respective buttons provided at the top of the IDE:

      Figure 1.8: Notebook Hello World

      Enhancing Jupyter Notebook usability

      Many seasoned data scientists usually work on the vanilla setup of Jupyter notebook. However, it is important to know that there are many more amazing features of the Jupyter Notebook that are usually not explored by most users. Once you explore them and start using them, you will realize how important they are to further enhance your usability and productivity with building models and applications using Jupyter Notebook.

      These features are the ability to incorporate latex in the markdown cells of the notebook, code prettify for making the code look neater to promote best practices and preserve its integrity, the ability to automatically create a table of contents of your exploratory data analysis steps, code auto-completion with notebook, the ability to save code snippets for reusability, and many more.

      Installing the required Python packages

      Python, as we know, is a multi-utility programming language. It is also the most preferred programming language for data science due to the amazing scientific computing, visualization and algorithm implementation libraries.

      In this section, we will install the most important Python packages that are required to build any machine learning and deep learning model in

      Enjoying the preview?
      Page 1 of 1