Page 13 - Data Science Algorithms in a Week

Preface

Data science is a discipline at the intersection of machine learning, statistics and data
mining with the objective to gain new knowledge from the existing data by the means of
algorithmic and statistical analysis. In this book you will learn the 7 most important ways in
Data Science to analyze the data. Each chapter first explains its algorithm or analysis as a
simple concept supported by a trivial example. Further examples and exercises are used to
build and expand the knowledge of a particular analysis.

What this book covers

Chapter 1, Classification Using K Nearest Neighbors, Classify a data item based on the k most
similar items.
Chapter 2, Naive Bayes, Learn Bayes Theorem to compute the probability a data item
belonging to a certain class.

Chapter 3, Decision Trees, Organize your decision criteria into the branches of a tree and use
a decision tree to classify a data item into one of the classes at the leaf node.

Chapter 4, Random Forest, Classify a data item with an ensemble of decision trees to
improve the accuracy of the algorithm by reducing the negative impact of the bias.
Chapter 5, Clustering into K Clusters, Divide your data into k clusters to discover the
patterns and similarities between the data items. Exploit these patterns to classify new data.

Chapter 6, Regression, Model a phenomena in your data by a function that can predict the
values for the unknown data in a simple way.

Chapter 7, Time Series Analysis, Unveil the trend and repeating patters in time dependent
data to predict the future of the stock market, Bitcoin prices and other time events.
Appendix A, Statistics, Provides a summary of the statistical methods and tools useful to a
data scientist.

Appendix B, R Reference, Reference to the basic Python language constructs.
Appendix C, Python Reference, Reference to the basic R language constructs, commands and
functions used throughout the book.