6. Decision Trees and Other Supervised Learning Methods | Predictive Analytics using Rattle and Qlik Sense

Sign In Start Free Trial

Book Overview & Buying
Table Of Contents
Feedback & Rating

Predictive Analytics using Rattle and Qlik Sense

By : Ferran Garcia Pagans, Fernando G Pagans

4 (5)

Predictive Analytics using Rattle and Qlik Sense

4 (5)

By: Ferran Garcia Pagans, Fernando G Pagans

Overview of this book

If you are a business analyst who wants to understand how to improve your data analysis and how to apply predictive analytics, then this book is ideal for you. This book assumes you have some basic knowledge of statistics and a spreadsheet editor such as Excel, but knowledge of QlikView is not required.

Preface

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Free Chapter

1. Getting Ready with Predictive Analytics

1. Getting Ready with Predictive Analytics

Analytics, predictive analytics, and data visualization

Purpose of the book

Introducing R, Rattle, and Qlik Sense Desktop

Installing the environment

Downloading and installing Rattle

Installing Qlik Sense Desktop

Exploring Qlik Sense Desktop

Further learning

Summary

2. Preparing Your Data

2. Preparing Your Data

Datasets, observations, and variables

Loading data

Transforming data

Cleaning up

Exporting data

Further learning

Summary

3. Exploring and Understanding Your Data

3. Exploring and Understanding Your Data

Text summaries

Visualizing distributions

Correlations among input variables

Further learning

Summary

4. Creating Your First Qlik Sense Application

4. Creating Your First Qlik Sense Application

Customer segmentation and customer buying behavior

Loading data and creating a data model

Creating a simple data app

Associative logic

Creating charts

Analyzing your data

Further learning

Summary

5. Clustering and Other Unsupervised Learning Methods

5. Clustering and Other Unsupervised Learning Methods

Machine learning – unsupervised and supervised learning

Further learning

Summary

6. Decision Trees and Other Supervised Learning Methods

6. Decision Trees and Other Supervised Learning Methods

Partitioning datasets and model optimization

Decision Tree Learning

Entropy and information gain

Underfitting and overfitting

Using a Decision Tree to classify credit risks

Ensemble classifiers

Other models

Further learning

Summary

7. Model Evaluation

7. Model Evaluation

Cross-validation

Regression performance

Measuring the performance of classifiers

Further learning

Summary

8. Visualizations, Data Applications, Dashboards, and Data Storytelling

8. Visualizations, Data Applications, Dashboards, and Data Storytelling

Data visualization in Qlik Sense

Data analysis, data applications, and dashboards

Data storytelling with Qlik Sense

Further learning

Summary

9. Developing a Complete Application

9. Developing a Complete Application

Understanding the bike rental problem

Exploring the data with Qlik Sense

Creating a Qlik Sense App to control the activity

Using Rattle to forecast the demand

Model evaluation

Further learning

Summary

Index

Index

Customer Reviews

4 (5)

5 star

40%

4 star

40%

3 star

0

2 star

20%

1 star

0

Ensemble classifiers

Thomas G Dietterich defines Ensemble methods as follows:

"Ensemble methods are learning algorithms that construct a set of classifiers and then classify new data points by taking a (weighted) vote of their prediction."

You can get more information from http://web.engr.oregonstate.edu/~tgd/publications/mcs-ensembles.pdf.

Ensemble methods create a set of weak classifiers and combine them into a strong classifier. A weak classifier is a classifier that performs slightly better than a classifier that randomly guesses the prediction. Rattle offers two types of ensemble models: Random Forest and Boosting.

Boosting

Boosting is an ensemble method, so it creates a set of different classifiers. Imagine that you have m classifiers, we can define a classifier x as:

When we need to evaluate a new observation, we can calculate the average of all m tree's predictions using the following formula:

We can improve this evaluation by adding a weight to each tree, as shown here in this formula...

Search

Your notes and bookmarks