Beskrivning
Beskrivning
Discover a variety of data-mining algorithms that are useful for selecting small sets of important features from among unwieldy masses of candidates, or extracting useful features from measured variables.
As a serious data miner you will often be faced with thousands of candidate features for your prediction or classification application, with most of the features being of little or no value. You’ll know that many of these features may be useful only in combination with certain other features while being practically worthless alone or in combination with most others. Some features may have enormous predictive power, but only within a small, specialized area of the feature space. The problems that plague modern data miners are endless. This book helps you solve this problem by presenting modern feature selection techniques and the code to implement them. Some of these techniques are:
- Forward selection componentanalysis
- Local feature selection
- Linking features and a targetwith a hidden Markov model
- Improvements on traditionalstepwise selection
- Nominal-to-ordinalconversion
All algorithms are intuitively justified and supported by the relevant equations and explanatory material. The author also presents and explains complete, highly commented source code.
The example code is in C++ and CUDA C but Python or other code can be substituted; the algorithm is important, not the code that’s used to write it.
What You Will Learn
- Combine principal componentanalysis with forward and backward stepwise selection to identify acompact subset of a large collection of variables that captures themaximum possible variation within the entire set.
- Identify features that mayhave predictive power over only a small subset of the feature domain. Suchfeatures can be profitably used by modern predictive models but may bemissed by other feature selection methods.
- Find an underlying hiddenMarkov model that controls the distributions of feature variables and thetarget simultaneously. The memory inherent in this method is especiallyvaluable in high-noise applications such as prediction of financialmarkets.
- Improve traditional stepwiseselection in three ways: examine a collection of ’best-so-far’ featuresets; test candidate features for inclusion with cross validation toautomatically and effectively limit model complexity; and at each step estimatethe probability that our results so far could be just the product ofrandom good luck. We also estimate the probability that the improvementobtained by adding a new variable could have been just good luck.Take a potentially valuablenominal variable (a category or class membership) that is unsuitable forinput to a prediction model, and assign to each category a sensiblenumeric value that can be used as a model input.
Who This Book Is For
Intermediate to advanced data science programmers and analysts.
