Book Overview & Buying
Table Of Contents

Python Machine Learning Blueprints - Second Edition

By : Alexander Combs, Saurabh Chhajed, Michael Roman

Buy this Book

Python Machine Learning Blueprints

By: Alexander Combs, Saurabh Chhajed, Michael Roman

Buy this Book

Overview of this book

Machine learning is transforming the way we understand and interact with the world around us. This book is the perfect guide for you to put your knowledge and skills into practice and use the Python ecosystem to cover key domains in machine learning. This second edition covers a range of libraries from the Python ecosystem, including TensorFlow and Keras, to help you implement real-world machine learning projects. The book begins by giving you an overview of machine learning with Python. With the help of complex datasets and optimized techniques, you’ll go on to understand how to apply advanced concepts and popular machine learning algorithms to real-world projects. Next, you’ll cover projects from domains such as predictive analytics to analyze the stock market and recommendation systems for GitHub repositories. In addition to this, you’ll also work on projects from the NLP domain to create a custom news feed using frameworks such as scikit-learn, TensorFlow, and Keras. Following this, you’ll learn how to build an advanced chatbot, and scale things up using PySpark. In the concluding chapters, you can look forward to exciting insights into deep learning and you'll even create an application using computer vision and neural networks. By the end of this book, you’ll be able to analyze data seamlessly and make a powerful impact through your projects.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

The Python Machine Learning Ecosystem

Data science/machine learning workflow

Python libraries and functions for each stage of the data science workflow

Setting up your machine learning environment

Summary

Build an App to Find Underpriced Apartments

Sourcing apartment listing data

Inspecting and preparing the data

Visualizing our data

Visualizing the data

Modeling the data

Extending the model

Summary

Build an App to Find Cheap Airfares

Sourcing airfare pricing data

Retrieving fare data with advanced web scraping

Parsing the DOM to extract pricing data

Identifying outlier fares with anomaly detection techniques

Sending real-time alerts using IFTTT

Putting it all together

Summary

Forecast the IPO Market Using Logistic Regression

The IPO market

Data cleansing and feature engineering

Binary classification with logistic regression

Generating the importance of a feature from our model

Summary

Create a Custom Newsfeed

Creating a supervised training set with Pocket

Using the Embedly API to download story bodies

Basics of Natural Language Processing

Support Vector Machines

IFTTT integration with feeds, Google Sheets, and email

Setting up your daily personal newsletter

Summary

Predict whether Your Content Will Go Viral

What does research tell us about virality?

Sourcing shared counts and content

Exploring the features of shareability

Building a predictive content scoring model

Summary

Use Machine Learning to Forecast the Stock Market

Types of market analysis

What does research tell us about the stock market?

How to develop a trading strategy

Building the regression model

Summary

Classifying Images with Convolutional Neural Networks

Image-feature extraction

Convolutional neural networks

Building a convolutional neural network to classify images in the Zalando Research dataset, using Keras

Summary

Building a Chatbot

The Turing Test

The history of chatbots

The design of chatbots

Building a chatbot

Sequence-to-sequence modeling for chatbots

Summary

Build a Recommendation Engine

Collaborative filtering

Content-based filtering

Hybrid systems

Building a recommendation engine

Summary

What's Next?

Summary of the projects

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Hybrid systems

We've now looked at the two primary forms of recommender systems, but you should know that, in any large-scale production environment, you're likely to see recommendations that leverage both of these. This is known as a hybrid system, and the reason hybrid systems are preferred is that they help eliminate the drawbacks that can be present when using either system alone. The two systems together create a more robust solution.

Let's examine the pros and cons of each type.