Chapter 1, Jupyter Fundamentals, covers the fundamentals of data analysis in Jupyter. We will start with usage instructions and features of Jupyter such as magic functions and tab completion. We will then transition to data science specific material. We will run an exploratory analysis in a live Jupyter Notebook. We will use visual assists such as scatter plots, histograms, and violin plots to deepen our understanding of the data. We will also perform simple predictive modeling.,
Chapter 2, Data Cleaning and Advanced Machine Learning, shows how predictive models can be trained in Jupyter Notebooks. We will talk about how to plan a machine learning strategy. This chapter also explains the machine learning terminology such as supervised learning, unsupervised learning, classification, and regression. We will discuss methods for preprocessing data using scikit-learn and pandas.,
Chapter 3, Web Scraping and Interactive Visualizations, explains how to scrap web page tables and then use interactive visualizations to study the data. We will start by looking at how HTTP requests work, focusing on GET requests and their response status codes. Then, we will go into the Jupyter Notebook and make HTTP requests with Python using the Requests library. We will see how Jupyter can be used to render HTML in the notebook, along with actual web pages that can be interacted with. After making requests, we will see how Beautiful Soup can be used to parse text from the HTML, and used this library to scrape tabular data.
Chapter 4, Introduction to Neural Networks and Deep Learning, helps you set up and configure deep learning environment and start looking at individual models and case studies. It also discusses neural networks and its idea along with their origins and explores their power.
Chapter 5, Model Architecture, shows how to predict Bitcoin prices using deep learning model.
Chapter 6, Model Evaluation and Optimization, shows how to evaluate a neural network model. We will modify the network's hyper parameters to improve its performance.
Chapter 7, Productization, explains how to create a working application from a deep learning model. We will deploy our Bitcoin prediction model as an application that is capable of handling new data by creating a new models.
