Machine studying in Action is exclusive booklet that blends the foundational theories of laptop studying with the sensible realities of establishing instruments for daily facts research. you are going to use the versatile Python programming language to construct courses that enforce algorithms for information class, forecasting, innovations, and higher-level good points like summarization and simplification.
About the Book
A computer is related to benefit while its functionality improves with event. studying calls for algorithms and courses that catch facts and ferret out the fascinating or valuable styles. as soon as the really expert area of analysts and mathematicians, computing device studying is changing into a ability wanted by means of many.
Machine studying in Action is a in actual fact written instructional for builders. It avoids educational language and takes you directly to the strategies you will use on your day by day paintings. Many (Python) examples current the center algorithms of statistical information processing, information research, and information visualization in code you could reuse. you are going to comprehend the recommendations and the way they slot in with tactical projects like category, forecasting, options, and higher-level positive factors like summarization and simplification.
Readers want no past adventure with computer studying or statistical processing. Familiarity with Python is helpful.
buy of the print booklet comes with a proposal of a loose PDF, ePub, and Kindle publication from Manning. additionally on hand is all code from the e-book.
- A no-nonsense introduction
- Examples exhibiting universal ML tasks
- Everyday facts analysis
- Implementing vintage algorithms like Apriori and Adaboos
Table of Contents
PART 1 CLASSIFICATION
- Machine studying basics
- Classifying with k-Nearest Neighbors
- Splitting datasets one function at a time: selection trees
- Classifying with chance idea: naïve Bayes
- Logistic regression
- Support vector machines
- Improving category with the AdaBoost meta algorithm
PART 2 FORECASTING NUMERIC VALUES WITH REGRESSION
- Predicting numeric values: regression
- Tree-based regression
PART three UNSUPERVISED LEARNING
- Grouping unlabeled goods utilizing k-means clustering
- Association research with the Apriori algorithm
- Efficiently discovering widespread itemsets with FP-growth
PART four extra TOOLS
- Using crucial part research to simplify data
- Simplifying facts with the singular worth decomposition
- Big info and MapReduce