LassoAttributeSelector (magpie API)

java.lang.Object
- magpie.attributes.selectors.BaseAttributeSelector
- - magpie.attributes.selectors.PythonBasedAttributeSelector
  - - magpie.attributes.selectors.LassoAttributeSelector

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Citable, Commandable, Options, Printable
```
public class LassoAttributeSelector
extends PythonBasedAttributeSelector
implements Citable
```
Uses a combination of LASSO and screening attribute sets with linear regression to select attributes. Based on work by Ghiringhelli et al. and Pilania et al..
This method works by first using compressed sensing (i.e., LASSO) to select a subset of attributes that best describe a property, and then selecting a smaller set of attributes from the LASSO set by finding a set with maximum fitness with a linear regression model.
There are a few options for how to do this and all are implemented by this class
1. How many attributes to select with LASSO
2. Whether to remove attributes that are strongly correlated with others in the LASSO subset
3. Whether to evaluate the linear regression model on the training set or in cross-validation
4. The maximum size of the final attribute set
5. Whether to determine the attribute set size by selecting the attribute set with the highest accuracy in cross-validation
Usage: -n_lasso <# lasso> -max_dim <dim> [-corr_downselect <# corr>] [-cv_method <cv frac> <cv iters>] [-pick_best] [-debug]
# lasso: Number of attributes to select with LASSO
max dim: Maximum dimension of final set
# corr: Set size after removing strongly-correlated attributes (by default, this step is not run)
cv frac: Fraction of entries to withhold during cross validation (by default, cross-validation is not performed)
cv iter: Number of cross-validation tests to run
-pick_best: Whether to pick dimension based on cross-validation results
-debug: Print status messages from the underlying Python script to screen
See Also:

Serialized Form

Field Summary

Fields
Modifier and Type	Field and Description
`protected double`	`CVFraction` Fraction of entries to withhold of cv test set.
`protected int`	`CVIterations` Number of times to repeat CV test.
`protected int`	`MaxCount` Maximum number of attributes to select.
`protected int`	`NDownselect` Number of entries to downselect to based on correlations.
`protected int`	`NLASSO` Number of attributes to pick via LASSO.
`protected boolean`	`SelectSizeAutomatically` Whether to pick dataset size via cross-validation.

Fields inherited from class magpie.attributes.selectors.PythonBasedAttributeSelector
Debug

Fields inherited from class magpie.attributes.selectors.BaseAttributeSelector
trained

Constructor Summary

Constructors
Constructor and Description

LassoAttributeSelector()

Constructors
Constructor and Description
`LassoAttributeSelector()`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`protected java.util.List<java.lang.String>`	`assembleSystemCall(java.io.File codePath, Dataset data)` Prepare the system call with all command-line arguments
`java.util.List<org.apache.commons.lang3.tuple.Pair<java.lang.String,Citation>>`	`getCitations()` Return a list of citations for this object and any underlying objects.
`protected java.lang.String`	`getScriptPath()` Get the path to the Python script to be run.
`java.lang.String`	`printDescription(boolean htmlFormat)` Print full name of object, and a simple description of the options.
`java.lang.String`	`printUsage()` Print out required format for options.
`void`	`setCVFraction(double cvFraction)` Set the fraction of entries to without during cross-validation.
`void`	`setCVIterations(int nIter)` Set the number of iterations to perform during cross-validation.
`void`	`setMaximumDimension(int count)` Set the maximum number of attributes to select
`void`	`setNDownselect(int num)` Set number of attributes to downselect to by removing strongly-correlated entries.
`void`	`setNLASSO(int NLASSO)` Set the number of parameters to determine via LASSO
`void`	`setOptions(java.util.List<java.lang.Object> Options)` Set any options for this object.
`void`	`setSelectSizeAutomatically(boolean x)` Set whether to determine number of attributes through cross-validation.

Methods inherited from class magpie.attributes.selectors.PythonBasedAttributeSelector
spawnStderrReader, train_protected

Methods inherited from class magpie.attributes.selectors.BaseAttributeSelector
about, applyAttributeSelection, clone, getSelectionNames, getSelections, isTrained, printCommand, printSelections, run, runCommand, train

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - NLASSO
```
protected int NLASSO
```
    Number of attributes to pick via LASSO. Default = 20
  - NDownselect
```
protected int NDownselect
```
    Number of entries to downselect to based on correlations. A negative number indicates that this step should be skipped. Default: Skip
  - MaxCount
```
protected int MaxCount
```
    Maximum number of attributes to select. Default = 5
  - CVFraction
```
protected double CVFraction
```
    Fraction of entries to withhold of cv test set. A negative number indicates that CV will not be used. Default: No CV
  - CVIterations
```
protected int CVIterations
```
    Number of times to repeat CV test. Default: 100
  - SelectSizeAutomatically
```
protected boolean SelectSizeAutomatically
```
    Whether to pick dataset size via cross-validation.
- Constructor Detail
  - LassoAttributeSelector
```
public LassoAttributeSelector()
```
- Method Detail
  - setOptions
```
public void setOptions(java.util.List<java.lang.Object> Options)
                throws java.lang.Exception
```
    Description copied from interface: Options
    
    Set any options for this object. If parsing the options fails, return an Exception with the usage as its message.
    
    Specified by:
    
    setOptions in interface Options
    
    Parameters:
    
    Options - Array of options as Objects - can be null
    
    Throws:
    
    java.lang.Exception - if problem with inputs
  - printUsage
```
public java.lang.String printUsage()
```
    Description copied from interface: Options
    
    Print out required format for options. For consistency, should start with "Usage: ".
    
    Specified by:
    
    printUsage in interface Options
    
    Returns:
    
    Usage for this function
  - getScriptPath
```
protected java.lang.String getScriptPath()
```
    Description copied from class: PythonBasedAttributeSelector
    
    Get the path to the Python script to be run.
    
    Specified by:
    
    getScriptPath in class PythonBasedAttributeSelector
    
    Returns:
    
    Path
  - setCVFraction
```
public void setCVFraction(double cvFraction)
```
    Set the fraction of entries to without during cross-validation. Set to a negative number to use training set fitness rather than CV score
    
    Parameters:
    
    cvFraction - Fraction of entries to use as test set
  - setCVIterations
```
public void setCVIterations(int nIter)
```
    Set the number of iterations to perform during cross-validation.
    
    Parameters:
    
    nIter - Number of iterations
  - setMaximumDimension
```
public void setMaximumDimension(int count)
```
    Set the maximum number of attributes to select
    
    Parameters:
    
    count - Maximum number of attributes
  - setNDownselect
```
public void setNDownselect(int num)
```
    Set number of attributes to downselect to by removing strongly-correlated entries. Set to negative to skip this step
    
    Parameters:
    
    num - Size of dataset after downselection
  - setSelectSizeAutomatically
```
public void setSelectSizeAutomatically(boolean x)
```
    Set whether to determine number of attributes through cross-validation.
    
    Parameters:
    
    x - Desired setting
  - setNLASSO
```
public void setNLASSO(int NLASSO)
```
    Set the number of parameters to determine via LASSO
    
    Parameters:
    
    NLASSO - Number of attributes
  - assembleSystemCall
```
protected java.util.List<java.lang.String> assembleSystemCall(java.io.File codePath,
                                                              Dataset data)
```
    Prepare the system call with all command-line arguments
    
    Specified by:
    
    assembleSystemCall in class PythonBasedAttributeSelector
    
    Parameters:
    
    codePath - Path to executable or script to be run
    
    data - Dataset being used to train attribute selector
    
    Returns:
    
    Command to be executed
  - printDescription
```
public java.lang.String printDescription(boolean htmlFormat)
```
    Description copied from interface: Printable
    
    Print full name of object, and a simple description of the options. This description should print enough information to reproduce how this object was created, but not necessarily enough to run it (e.g., coefficients for the model).
    Example: For a model training a separate WekaRegression for intermetallics
    magpie.models.regression.SplitRegression
    Splitter: AllMetalsSplitter
    All Metals: magpie.models.regression.WekaRegression trees.REPTree
    Contains Nonmetal: magpie.regression.LASSORegreession -maxterms 2
    
    Specified by:
    
    printDescription in interface Printable
    
    Overrides:
    
    printDescription in class BaseAttributeSelector
    
    Parameters:
    
    htmlFormat - Whether format for output to an HTML page (e.g., <div> to create indentation) or for printing to screen.
    
    Returns:
    
    String describing the model
    
    See Also:
    
    #printModel()
  - getCitations
```
public java.util.List<org.apache.commons.lang3.tuple.Pair<java.lang.String,Citation>> getCitations()
```
    Description copied from interface: Citable
    
    Return a list of citations for this object and any underlying objects.
    
    Specified by:
    
    getCitations in interface Citable
    
    Returns:
    
    List of pairs: [Reason for Citation], [Citation]

Class LassoAttributeSelector

Field Summary

Fields inherited from class magpie.attributes.selectors.PythonBasedAttributeSelector

Fields inherited from class magpie.attributes.selectors.BaseAttributeSelector

Constructor Summary

Method Summary

Methods inherited from class magpie.attributes.selectors.PythonBasedAttributeSelector

Methods inherited from class magpie.attributes.selectors.BaseAttributeSelector

Methods inherited from class java.lang.Object

Field Detail

NLASSO

NDownselect

MaxCount

CVFraction

CVIterations

SelectSizeAutomatically

Constructor Detail

LassoAttributeSelector

Method Detail

setOptions

printUsage

getScriptPath

setCVFraction

setCVIterations

setMaximumDimension

setNDownselect

setSelectSizeAutomatically

setNLASSO

assembleSystemCall

printDescription

getCitations