What this book covers

Chapter 1, The Groundwork – Julia’s Environment, explains how to set up the Julia’s environment (Command Line(REPL) and Jupyter Notebook) and explains Julia’s ecosystem, why Julia is special, and package management. It also gives an introduction to parallel processing and multiple dispatch and explains how Julia is suited for data science.

Chapter 2, Data Munging, explains the need for and process of data preparation, also called data munging. Data munging refers to changing data from one state to other, in well-defined reversible steps. It is preparing data to be used for analytics and visualizations.

Chapter 3, Data Exploration, explains that statistics is the core of data science, shows that Julia provides various statistical functions. This chapter will give a high-level overview of statistics and will explain the techniques required to apply those statistical concepts to general problems using Julia’s statistical packages, such as Stats.jl and Distributions.jl.

Chapter 4, Deep Dive into Inferential Statistics, continues statistics is the core of the data science and is Julia provides various statistical functions. This chapter will give high level overview of advance statistics and then will explain the techniques to apply those statistical concepts on general problems using Julia’s statistical packages such as Stats.jl and Distributions.jl.

Chapter 5, Making Sense of Data Using Visualization, explains why data visualization is essential part of data science and how it makes communicating the results more effective and reaches out to larger audience. This chapter will go through the Vega, Asciiplot, and Gadfly packages of Julia, which are used for data visualization.

Chapter 6, Supervised Machine Learning, says "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E" – Tom M. Mitchell. Machine learning is a field of study that gives computers the ability to learn and enhance without being explicitly programmed. This chapter will explain that Julia is a high-level language with a great performance, and is nicely suited for machine learning. This chapter will focus on supervised machine learning algorithms such as Naive Bayes, regression, and decision trees.

Chapter 7, Unsupervised Machine Learning, explains that unsupervised learning is a little bit different and harder than supervised learning. The aim is to get the system to learn something but we don’t know what it will learn. This chapter will focus on unsupervised learning algorithms such as clustering.

Chapter 8, Creating Ensemble Models, explains that a group of people has the ability to take better decisions than a single individual, especially when each group member comes in with their own biases. This is also true for machine learning. This chapter will focus on a machine learning technique called ensemble learning, an example being random forest.

Chapter 9, Time Series, shows the capacity to demonstrate and perform decision modeling, and explains that examination is a crucial component of some real-world applications running from emergency medical treatment in intensive care units to military command and control frameworks. This chapter focuses on time series data and forecasting using Julia.

Chapter 10, Collaborative Filtering and Recommendation System, explains that every day we are confronted with decisions and choices. These can range from our clothes to the movies we watch or what to eat when we order online. We take decisions in business too. For instance, which stock should we invest in? What if decision making could be automated, and suitable recommendations could be given to us. This chapter focuses on recommendation systems and techniques such as collaborative filtering and association rule mining.

Chapter 11, Introduction to Deep Learning, explains that deep learning refers to a class of machine learning techniques that do unsupervised or supervised feature extraction and pattern analysis or classification by exploiting multiple layers of non-linear information processing. This chapter will introduce us to deep learning in Julia. Deep learning is a new branch of machine learning with one goal – Artificial Intelligence. We will also learn about Julia's framework, Julia's, Mocha.jl, with which we can implement deep learning.