mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-10-25 00:12:08 +08:00
305 lines
14 KiB
XML
305 lines
14 KiB
XML
<tool id="hgv_lps" name="LPS" version="1.0.0">
|
|
<description>LASSO-Patternsearch algorithm</description>
|
|
|
|
<command interpreter="bash">
|
|
lps_tool_wrapper.sh $lambda_fac $input_file $label_column $output_file $log_file
|
|
Initialization 0
|
|
#if $advanced.options == "true":
|
|
Sample $advanced.sample
|
|
Verbosity $advanced.verbosity
|
|
Standardize $advanced.standardize
|
|
initialLambda $advanced.initialLambda
|
|
#if $advanced.continuation.continuation == "1":
|
|
Continuation $advanced.continuation.continuation
|
|
continuationSteps $advanced.continuation.continuationSteps
|
|
accurateIntermediates $advanced.continuation.accurateIntermediates
|
|
#end if
|
|
printFreq $advanced.printFreq
|
|
#if $advanced.newton.newton == "1":
|
|
Newton $advanced.newton.newton
|
|
NewtonThreshold $advanced.newton.newtonThreshold
|
|
#end if
|
|
HessianSampleFraction $advanced.hessianSampleFraction
|
|
BB 0
|
|
Monotone 0
|
|
FullGradient $advanced.fullGradient
|
|
GradientFraction $advanced.gradientFraction
|
|
InitialAlpha $advanced.initialAlpha
|
|
AlphaIncrease $advanced.alphaIncrease
|
|
AlphaDecrease $advanced.alphaDecrease
|
|
AlphaMax $advanced.alphaMax
|
|
c1 $advanced.c1
|
|
MaxIter $advanced.maxIter
|
|
StopTol $advanced.stopTol
|
|
IntermediateTol $advanced.intermediateTol
|
|
FinalOnly $advanced.finalOnly
|
|
#end if
|
|
</command>
|
|
|
|
<inputs>
|
|
<param name="input_file" type="data" format="tabular" label="Dataset"/>
|
|
<param name="label_column" type="data_column" data_ref="input_file" numerical="true" label="Label column" help="Column containing outcome labels: +1 or -1."/>
|
|
<param name="lambda_fac" label="Lambda_fac" type="float" value="0.03" help="Target value of the regularization parameter, expressed as a fraction of the calculated lambda_max.">
|
|
<validator type="in_range" message="0.00 < lambda_fac <= 1.00" min="0.00" max="1.00"/>
|
|
</param>
|
|
<conditional name="advanced">
|
|
<param name="options" type="select" label="Advanced Options">
|
|
<option value="false" selected="true">Hide advanced options</option>
|
|
<option value="true">Show advanced options</option>
|
|
</param>
|
|
<when value="false">
|
|
<!-- no options -->
|
|
</when>
|
|
<when value="true">
|
|
<!-- HARDCODED: 'Sample' we don't support passing an array -->
|
|
<param name="sample" type="float" value="1.0" label="Sample fraction" help="Sample this fraction of the data set.">
|
|
<validator type="in_range" message="0.0 <= sample <= 1.0" min="0.0" max="1.0"/>
|
|
</param>
|
|
<!-- HARDCODED: 'Initialization' = 0 :: Initialize at beta=0 -->
|
|
<param name="verbosity" type="select" format="integer" label="Verbosity">
|
|
<option value="0" selected="true">Little output</option>
|
|
<option value="1">More output</option>
|
|
<option value="2">Still more output</option>
|
|
</param>
|
|
<param name="standardize" type="select" format="integer" label="Standardize" help="Scales and shifts each column so that it has mean zero and variance 1.">
|
|
<option value="0" selected="true">Don't standardize</option>
|
|
<option value="1">Standardize</option>
|
|
</param>
|
|
<param name="initialLambda" type="float" value="0.8" label="Initial lambda" help="First value of lambda to be used in the continuation scheme, expressed as a fraction of lambda_max.">
|
|
<validator type="in_range" message="0.0 < initialLambda < 1.0" min="0.0" max="1.0"/>
|
|
</param>
|
|
<conditional name="continuation">
|
|
<param name="continuation" type="select" format="integer" label="Continuation" help="Use continuation strategy to start with a larger value of lambda, decreasing it successively to lambda_fac.">
|
|
<option value="0" selected="true">Don't use continuation</option>
|
|
<option value="1">Use continuation</option>
|
|
</param>
|
|
<when value="0">
|
|
<!-- no options -->
|
|
</when>
|
|
<when value="1">
|
|
<param name="continuationSteps" type="integer" value="5" label="Continuation steps" help="Number of lambda values to use in continuation <em>prior</em> to target value lambda_fac."/>
|
|
|
|
<param name="accurateIntermediates" type="select" format="integer" label="Accurate intermediates" help="Indicates whether accurate solutions are required for lambda values other than the target value lambda_fac.">
|
|
<option value="0" selected="true">Don't need accurate intemediates</option>
|
|
<option value="1">Calculate accurate intermediates</option>
|
|
</param>
|
|
</when>
|
|
</conditional> <!-- name="continuation" -->
|
|
<param name="printFreq" type="integer" value="1" label="Print frequency" help="Print a progress report every NI iterations, where NI is the supplied value of this parameter.">
|
|
<validator type="in_range" message="printFreq >= 1" min="1"/>
|
|
</param>
|
|
<conditional name="newton">
|
|
<param name="newton" type="select" format="integer" label="Projected Newton steps">
|
|
<option value="0" selected="true">No Newton steps</option>
|
|
<option value="1">Try projected Newton steps</option>
|
|
</param>
|
|
<when value="0">
|
|
<!-- no options -->
|
|
</when>
|
|
<when value="1">
|
|
<param name="newtonThreshold" type="integer" value="500" label="Newton threshold" help="Maximum size of free variable subvector for Newton."/>
|
|
</when>
|
|
</conditional>
|
|
<param name="hessianSampleFraction" type="float" value="1.0" label="Hessian sample fraction" help="Fraction of terms to use in approximate Hessian calculation.">
|
|
<validator type="in_range" message="0.01 < hessianSampleFraction <= 1.00" min="0.01" max="1.00"/>
|
|
</param>
|
|
<!-- HARDCODED: 'BB' = 0 :: don't use Barzilai-Borwein steps -->
|
|
<!-- HARDCODED: 'Monotone' = 0 :: don't force monotonicity -->
|
|
<param name="fullGradient" type="select" format="integer" label="Partial gradient vector selection">
|
|
<option value="0">Use randomly selected partial gradient, including current active components ("biased")</option>
|
|
<option value="1">Use full gradient vector at every step</option>
|
|
<option value="2">Randomly selected partial gradient, without regard to current active set ("unbiased")</option>
|
|
</param>
|
|
<param name="gradientFraction" type="float" value="0.1" label="Gradient fraction" help="Fraction of inactive gradient vector to evaluate.">
|
|
<validator type="in_range" message="0.0 < gradientFraction <= 1" min="0.0" max="1.0"/>
|
|
</param>
|
|
<param name="initialAlpha" type="float" value="1.0" label="Initial value of alpha"/>
|
|
<param name="alphaIncrease" type="float" value="2.0" label="Alpha increase" help="Factor by which to increase alpha after descent not obtained."/>
|
|
<param name="alphaDecrease" type="float" value="0.8" label="Alpha decrease" help="Factor by which to decrease alpha after successful first-order step."/>
|
|
<param name="alphaMax" type="float" value="1e12" label="Alpha max" help="Maximum value of alpha; terminate with error if we exceed this."/>
|
|
<param name="c1" type="float" value="1e-3" help="Parameter defining the margin by which the first-order step is required to decrease before being taken.">
|
|
<validator type="in_range" message="0.0 < c1 < 1.0" min="0.0" max="1.0"/>
|
|
</param>
|
|
<param name="maxIter" type="integer" value="10000" label="Maximum number of iterations" help="Terminate with error if we exceed this."/>
|
|
<param name="stopTol" type="float" value="1e-6" label="Stop tolerance" help="Convergence tolerance for target value of lambda."/>
|
|
<param name="intermediateTol" type="float" value="1e-4" label="Intermediate tolerance" help="Convergence tolerance for intermediate values of lambda."/>
|
|
<param name="finalOnly" type="select" format="integer" label="Final only">
|
|
<option value="0" selected="true">Return information for all intermediate values</option>
|
|
<option value="1">Just return information at the last lambda</option>
|
|
</param>
|
|
</when> <!-- value="advanced" -->
|
|
</conditional> <!-- name="advanced" -->
|
|
</inputs>
|
|
|
|
<outputs>
|
|
<data name="output_file" format="tabular" label="${tool.name} on ${on_string}: results"/>
|
|
<data name="log_file" format="txt" label="${tool.name} on ${on_string}: log"/>
|
|
</outputs>
|
|
|
|
<requirements>
|
|
<requirement type="package">lps_tool</requirement>
|
|
</requirements>
|
|
|
|
<tests>
|
|
<test>
|
|
<param name="input_file" value="lps_arrhythmia.tabular"/>
|
|
<param name="label_column" value="280"/>
|
|
<param name="lambda_fac" value="0.03"/>
|
|
<param name="options" value="true"/>
|
|
<param name="sample" value="1.0"/>
|
|
<param name="verbosity" value="1"/>
|
|
<param name="standardize" value="0"/>
|
|
<param name="initialLambda" value="0.9"/>
|
|
<param name="continuation" value="1"/>
|
|
<param name="continuationSteps" value="10"/>
|
|
<param name="accurateIntermediates" value="0"/>
|
|
<param name="printFreq" value="1"/>
|
|
<param name="newton" value="1"/>
|
|
<param name="newtonThreshold" value="500"/>
|
|
<param name="hessianSampleFraction" value="1.0"/>
|
|
<param name="fullGradient" value="1"/>
|
|
<param name="gradientFraction" value="0.5"/>
|
|
<param name="initialAlpha" value="1.0"/>
|
|
<param name="alphaIncrease" value="2.0"/>
|
|
<param name="alphaDecrease" value="0.8"/>
|
|
<param name="alphaMax" value="1e12"/>
|
|
<param name="c1" value="1e-3"/>
|
|
<param name="maxIter" value="2500"/>
|
|
<param name="stopTol" value="1e-6"/>
|
|
<param name="intermediateTol" value="1e-6"/>
|
|
<param name="finalOnly" value="0"/>
|
|
<output name="ouput_file" file="lps_arrhythmia_beta.tabular"/>
|
|
<output name="log_file" file="lps_arrhythmia_log.txt"/>
|
|
</test>
|
|
</tests>
|
|
|
|
<help>
|
|
**Dataset formats**
|
|
|
|
The input and output datasets are tabular_. The columns are described below.
|
|
There is a second output dataset (a log) that is in text_ format.
|
|
(`Dataset missing?`_)
|
|
|
|
.. _tabular: ./static/formatHelp.html#tab
|
|
.. _text: ./static/formatHelp.html#text
|
|
.. _Dataset missing?: ./static/formatHelp.html
|
|
|
|
-----
|
|
|
|
**What it does**
|
|
|
|
The LASSO-Patternsearch algorithm fits your dataset to an L1-regularized
|
|
logistic regression model. A benefit of using L1-regularization is
|
|
that it typically yields a weight vector with relatively few non-zero
|
|
coefficients.
|
|
|
|
For example, say you have a dataset containing M rows (subjects)
|
|
and N columns (attributes) where one of these N attributes is binary,
|
|
indicating whether or not the subject has some property of interest P.
|
|
In simple terms, LPS calculates a weight for each of the other attributes
|
|
in your dataset. This weight indicates how "relevant" that attribute
|
|
is for predicting whether or not a given subject has property P.
|
|
The L1-regularization causes most of these weights to be equal to zero,
|
|
which means LPS will find a "small" subset of the remaining N-1 attributes
|
|
in your dataset that can be used to predict P.
|
|
|
|
In other words, LPS can be used for feature selection.
|
|
|
|
The input dataset is tabular, and must contain a label column which
|
|
indicates whether or not a given row has property P. In the current
|
|
version of this tool, P must be encoded using +1 and -1. The Lambda_fac
|
|
parameter ranges from 0 to 1, and controls how sparse the weight
|
|
vector will be. At the low end, when Lambda_fac = 0, there will be
|
|
no regularization. At the high end, when Lambda_fac = 1, there will be
|
|
"too much" regularization, and all of the weights will equal zero.
|
|
|
|
The LPS tool creates two output datasets. The first, called the results
|
|
file, is a tabular dataset containing one column of weights for each
|
|
value of the regularization parameter lambda that was tried. The weight
|
|
columns are in order from left to right by decreasing values of lambda.
|
|
The first N-1 rows in each column are the weights for the N-1 attributes
|
|
in your input dataset. The final row is a constant, the intercept.
|
|
|
|
Let **x** be a row from your input dataset and let **b** be a column
|
|
from the results file. To compute the probability that row **x** has
|
|
a label value of +1:
|
|
|
|
Probability(row **x** has label value = +1) = 1 / [1 + exp{**x** \* **b**\[1..N-1\] + **b**\[N\]}]
|
|
|
|
where **x** \* **b**\[1..N-1\] represents matrix multiplication.
|
|
|
|
The second output dataset, called the log file, is a text file which
|
|
contains additional data about the fitted L1-regularized logistic
|
|
regression model. These data include the number of features, the
|
|
computed value of lambda_max, the actual values of lambda used, the
|
|
optimal values of the log-likelihood and regularized log-likelihood
|
|
functions, the number of non-zeros, and the number of iterations.
|
|
|
|
Website: http://pages.cs.wisc.edu/~swright/LPS/
|
|
|
|
-----
|
|
|
|
**Example**
|
|
|
|
- input file::
|
|
|
|
+1 1 0 0 0 0 1 0 1 1 ...
|
|
+1 1 1 1 0 0 1 0 1 1 ...
|
|
+1 1 0 1 0 1 0 1 0 1 ...
|
|
etc.
|
|
|
|
- output results file::
|
|
|
|
0
|
|
0
|
|
0
|
|
0
|
|
0.025541
|
|
etc.
|
|
|
|
- output log file::
|
|
|
|
Data set has 100 vectors with 50 features.
|
|
calculateLambdaMax: n=50, m=100, m+=50, m-=50
|
|
computed value of lambda_max: 5.0000e-01
|
|
|
|
lambda=2.96e-02 solution:
|
|
optimal log-likelihood function value: 6.46e-01
|
|
optimal *regularized* log-likelihood function value: 6.79e-01
|
|
number of nonzeros at the optimum: 5
|
|
number of iterations required: 43
|
|
etc.
|
|
|
|
-----
|
|
|
|
**References**
|
|
|
|
Koh K, Kim S-J, Boyd S. (2007)
|
|
An interior-point method for large-scale l1-regularized logistic regression.
|
|
Journal of Machine Learning Research. 8:1519-1555.
|
|
|
|
Shi W, Wahba G, Wright S, Lee K, Klein R, Klein B. (2008)
|
|
LASSO-Patternsearch algorithm with application to ophthalmology and genomic data.
|
|
Stat Interface. 1(1):137-153.
|
|
|
|
<!--
|
|
Wright S, Novak R, Figueiredo M. (2009)
|
|
Sparse reconstruction via separable approximation.
|
|
IEEE Transactions on Signal Processing. 57:2479-2403.
|
|
|
|
Shi J, Yin W, Osher S, Sajda P. (2010)
|
|
A fast hybrid algorithm for large scale l1-regularized logistic regression.
|
|
Journal of Machine Learning Research. 11:713-741.
|
|
|
|
Byrd R, Chin G, Neveitt W, Nocedal J. (2010)
|
|
On the use of stochastic Hessian information in unconstrained optimization.
|
|
Technical Report. Northwestern University. June 16, 2010.
|
|
|
|
Wright S. (2010)
|
|
Accelerated block-coordinate relaxation for regularized optimization.
|
|
Technical Report. University of Wisconsin. August 10, 2010.
|
|
-->
|
|
|
|
</help>
|
|
</tool>
|