Getting Started with Machine Learning in Python

Getting Started with Machine Learning in Python

by Rudy Lai
Released September 2018
Publisher(s): Packt Publishing
ISBN: 9781788477437

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

A+ guide to using Machine Learning to classify objects, predict future prices, and automatically learn fixes to problems

About This Video

  • Learn about supervised learning: how to classify data points and predict future numbers
  • Practical exercises on unsupervised learning: how to segment clients and cluster documents
  • Intuition-driven practical tour through Machine Learning, packed with step-by-step instructions, working examples, and helpful advice

In Detail

Machine Learning is a hot topic. And you want to get involved! From developers to analysts, this course aims to bring Machine Learning to those with coding experience and numerical skills.

In this course, we introduce, via intuition rather than theory, the core of what makes Machine Learning work. Learn how to use labeled datasets to classify objects or predict future values, so that you can provide more accurate and valuable analysis. Use unlabelled datasets to do segmentation and clustering, so that you can separate a large dataset into sensible groups.

You will learn to understand and estimate the value of your dataset. We guide you through creating the best performance metric for your task at hand, and how that takes you to the correct model to solve your problem. Understand how to clean data for your application, and how to recognize which Machine Learning task you are dealing with.

If you want to move past Excel and if-then-else into automatically learned ML solutions, this course is for you!

This course uses Python 3.6, while not the latest version available, it provides relevant and informative content for legacy users of Python.

Audience

This course is for anyone, with a little coding experience and basic numerical skills, who wants to go beyond hardcoded, rule-based programming and use their datasets to automatically learn new algorithms that solve problems. From developers to analysts, this course aims to bring Machine Learning to everyone. It uses intuition as a base from which to explain the theory behind Machine Learning and its algorithms. Basic Python skills are assumed.

Publisher resources

Download Example Code

Table of contents

  1. Chapter 1 : Launching a Python Environment to Create Machine Learning Models
    1. The Course Overview
    2. Machine Learning versus Rule-Based Programming
    3. Understanding What Machine Learning Can Do Using the Tasks Framework
    4. Creating Machine-Learned Models with Python and scikit-learn
    5. Supervised Versus Unsupervised Learning
  2. Chapter 2 : Prepare Your Datasets for Machine Learning with Data Cleaning
    1. In this video, we will fix your machine learning models by understanding your data source
    2. Dealing with Missing Values – An Example
    3. Standardization and Normalization to Deal with Variables with Different Scales
    4. Eliminating Duplicate Entries
  3. Chapter 3 : Put Data into Their Right Categories with Classification
    1. How Do We Learn Rules to Classify Objects?
    2. Understanding Logistic Regression – Your First Classifier
    3. Applying Logistic Regression to the Iris Classification Task
    4. Closing Our First Machine Learning Pipeline with a Simple Model Evaluator
  4. Chapter 4 : Predict Numbers in the Future with Regression
    1. Creating Formulas That Predict the Future – A House Price Example
    2. Understanding Linear Regression – Your First Regressor
    3. Applying Linear Regression to the Boston House Price Task
    4. Evaluating Numerical Predictions with Least Squares
  5. Chapter 5 : Unsupervised Learning: Segmenting Groups and Detecting Outliers
    1. Exploring Unsupervised Learning and Its Usefulness
    2. Finding Groups Automatically with K-means Clustering
    3. Reducing the Number of Variables in Your Data with PCA
    4. Smooth out Your Histograms with Kernel Density Estimation
  6. Chapter 6 : Modeling Complex Relationships with Nonlinear Models
    1. Create Explainable Models with Decision Trees
    2. Automatic Feature Engineering with Support Vector Machines
    3. Deal with Nonlinear Relationships with Polynomial Regression
    4. Reduce the Number of Learned Rules with Regularization

Product information

  • Title: Getting Started with Machine Learning in Python
  • Author(s): Rudy Lai
  • Release date: September 2018
  • Publisher(s): Packt Publishing
  • ISBN: 9781788477437