Book Image

Large Scale Machine Learning with Python

By : Luca Massaron, Bastiaan Sjardin, Alberto Boschetti
Book Image

Large Scale Machine Learning with Python

By: Luca Massaron, Bastiaan Sjardin, Alberto Boschetti

Overview of this book

Large Python machine learning projects involve new problems associated with specialized machine learning architectures and designs that many data scientists have yet to tackle. But finding algorithms and designing and building platforms that deal with large sets of data is a growing need. Data scientists have to manage and maintain increasingly complex data projects, and with the rise of big data comes an increasing demand for computational and algorithmic efficiency. Large Scale Machine Learning with Python uncovers a new wave of machine learning algorithms that meet scalability demands together with a high predictive accuracy. Dive into scalable machine learning and the three forms of scalability. Speed up algorithms that can be used on a desktop computer with tips on parallelization and memory allocation. Get to grips with new algorithms that are specifically designed for large projects and can handle bigger files, and learn about machine learning in big data environments. We will also cover the most effective machine learning techniques on a map reduce framework in Hadoop and Spark in Python.
Table of Contents (17 chapters)
Large Scale Machine Learning with Python
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Preface
Index

Bootstrap aggregation


Bagging is an abbreviation of bootstrap aggregation. The bootstrapping technique originated in a context where analysts had to deal with a scarcity of data. With this statistical approach, subsamples were used to estimate population parameters when a statistical distribution couldn't be figured out a priori. The goal of bootstrapping is to provide a more robust estimate for population parameters where more variability is introduced to a smaller dataset by random subsampling with replacement. Generally, bootstrapping follows the following basic steps:

  1. Randomly sample a batch of size x with replacement from a given dataset.

  2. Calculate a metric or parameter from each sample to estimate the population parameters.

  3. Aggregate the results.

In recent years, bootstrap methods have been used for parameters of machine learning models as well. An ensemble is most effective when its classifiers provide highly diverse decision boundaries. This diversity in ensembles can be achieved in...