Mercurial > repos > xuebing > sharplabtool

comparison tools/human_genome_variation/lps.xml @ 0:9071e359b9a3

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author xuebing
date Fri, 09 Mar 2012 19:37:19 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:9071e359b9a3
1 <tool id="hgv_lps" name="LPS" version="1.0.0">
2 <description>LASSO-Patternsearch algorithm</description>
3
4 <command interpreter="bash">
5 lps_tool_wrapper.sh $lambda_fac $input_file $label_column $output_file $log_file
6 Initialization 0
7 #if $advanced.options == "true":
8 Sample $advanced.sample
9 Verbosity $advanced.verbosity
10 Standardize $advanced.standardize
11 initialLambda $advanced.initialLambda
12 #if $advanced.continuation.continuation == "1":
13 Continuation $advanced.continuation.continuation
14 continuationSteps $advanced.continuation.continuationSteps
15 accurateIntermediates $advanced.continuation.accurateIntermediates
16 #end if
17 printFreq $advanced.printFreq
18 #if $advanced.newton.newton == "1":
19 Newton $advanced.newton.newton
20 NewtonThreshold $advanced.newton.newtonThreshold
21 #end if
22 HessianSampleFraction $advanced.hessianSampleFraction
23 BB 0
24 Monotone 0
25 FullGradient $advanced.fullGradient
26 GradientFraction $advanced.gradientFraction
27 InitialAlpha $advanced.initialAlpha
28 AlphaIncrease $advanced.alphaIncrease
29 AlphaDecrease $advanced.alphaDecrease
30 AlphaMax $advanced.alphaMax
31 c1 $advanced.c1
32 MaxIter $advanced.maxIter
33 StopTol $advanced.stopTol
34 IntermediateTol $advanced.intermediateTol
35 FinalOnly $advanced.finalOnly
36 #end if
37 </command>
38
39 <inputs>
40 <param name="input_file" type="data" format="tabular" label="Dataset"/>
41 <param name="label_column" type="data_column" data_ref="input_file" numerical="true" label="Label column" help="Column containing outcome labels: +1 or -1."/>
42 <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.">
43 <validator type="in_range" message="0.00 &lt; lambda_fac &lt;= 1.00" min="0.00" max="1.00"/>
44 </param>
45 <conditional name="advanced">
46 <param name="options" type="select" label="Advanced Options">
47 <option value="false" selected="true">Hide advanced options</option>
48 <option value="true">Show advanced options</option>
49 </param>
50 <when value="false">
51 <!-- no options -->
52 </when>
53 <when value="true">
54 <!-- HARDCODED: 'Sample' we don't support passing an array -->
55 <param name="sample" type="float" value="1.0" label="Sample fraction" help="Sample this fraction of the data set.">
56 <validator type="in_range" message="0.0 &lt;= sample &lt;= 1.0" min="0.0" max="1.0"/>
57 </param>
58 <!-- HARDCODED: 'Initialization' = 0 :: Initialize at beta=0 -->
59 <param name="verbosity" type="select" format="integer" label="Verbosity">
60 <option value="0" selected="true">Little output</option>
61 <option value="1">More output</option>
62 <option value="2">Still more output</option>
63 </param>
64 <param name="standardize" type="select" format="integer" label="Standardize" help="Scales and shifts each column so that it has mean zero and variance 1.">
65 <option value="0" selected="true">Don't standardize</option>
66 <option value="1">Standardize</option>
67 </param>
68 <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.">
69 <validator type="in_range" message="0.0 &lt; initialLambda &lt; 1.0" min="0.0" max="1.0"/>
70 </param>
71 <conditional name="continuation">
72 <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.">
73 <option value="0" selected="true">Don't use continuation</option>
74 <option value="1">Use continuation</option>
75 </param>
76 <when value="0">
77 <!-- no options -->
78 </when>
79 <when value="1">
80 <param name="continuationSteps" type="integer" value="5" label="Continuation steps" help="Number of lambda values to use in continuation &lt;em&gt;prior&lt;/em&gt; to target value lambda_fac."/>
81
82 <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.">
83 <option value="0" selected="true">Don't need accurate intemediates</option>
84 <option value="1">Calculate accurate intermediates</option>
85 </param>
86 </when>
87 </conditional> <!-- name="continuation" -->
88 <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.">
89 <validator type="in_range" message="printFreq &gt;= 1" min="1"/>
90 </param>
91 <conditional name="newton">
92 <param name="newton" type="select" format="integer" label="Projected Newton steps">
93 <option value="0" selected="true">No Newton steps</option>
94 <option value="1">Try projected Newton steps</option>
95 </param>
96 <when value="0">
97 <!-- no options -->
98 </when>
99 <when value="1">
100 <param name="newtonThreshold" type="integer" value="500" label="Newton threshold" help="Maximum size of free variable subvector for Newton."/>
101 </when>
102 </conditional>
103 <param name="hessianSampleFraction" type="float" value="1.0" label="Hessian sample fraction" help="Fraction of terms to use in approximate Hessian calculation.">
104 <validator type="in_range" message="0.01 &lt; hessianSampleFraction &lt;= 1.00" min="0.01" max="1.00"/>
105 </param>
106 <!-- HARDCODED: 'BB' = 0 :: don't use Barzilai-Borwein steps -->
107 <!-- HARDCODED: 'Monotone' = 0 :: don't force monotonicity -->
108 <param name="fullGradient" type="select" format="integer" label="Partial gradient vector selection">
109 <option value="0">Use randomly selected partial gradient, including current active components ("biased")</option>
110 <option value="1">Use full gradient vector at every step</option>
111 <option value="2">Randomly selected partial gradient, without regard to current active set ("unbiased")</option>
112 </param>
113 <param name="gradientFraction" type="float" value="0.1" label="Gradient fraction" help="Fraction of inactive gradient vector to evaluate.">
114 <validator type="in_range" message="0.0 &lt; gradientFraction &lt;= 1" min="0.0" max="1.0"/>
115 </param>
116 <param name="initialAlpha" type="float" value="1.0" label="Initial value of alpha"/>
117 <param name="alphaIncrease" type="float" value="2.0" label="Alpha increase" help="Factor by which to increase alpha after descent not obtained."/>
118 <param name="alphaDecrease" type="float" value="0.8" label="Alpha decrease" help="Factor by which to decrease alpha after successful first-order step."/>
119 <param name="alphaMax" type="float" value="1e12" label="Alpha max" help="Maximum value of alpha; terminate with error if we exceed this."/>
120 <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.">
121 <validator type="in_range" message="0.0 &lt; c1 &lt; 1.0" min="0.0" max="1.0"/>
122 </param>
123 <param name="maxIter" type="integer" value="10000" label="Maximum number of iterations" help="Terminate with error if we exceed this."/>
124 <param name="stopTol" type="float" value="1e-6" label="Stop tolerance" help="Convergence tolerance for target value of lambda."/>
125 <param name="intermediateTol" type="float" value="1e-4" label="Intermediate tolerance" help="Convergence tolerance for intermediate values of lambda."/>
126 <param name="finalOnly" type="select" format="integer" label="Final only">
127 <option value="0" selected="true">Return information for all intermediate values</option>
128 <option value="1">Just return information at the last lambda</option>
129 </param>
130 </when> <!-- value="advanced" -->
131 </conditional> <!-- name="advanced" -->
132 </inputs>
133
134 <outputs>
135 <data name="output_file" format="tabular" label="${tool.name} on ${on_string}: results"/>
136 <data name="log_file" format="txt" label="${tool.name} on ${on_string}: log"/>
137 </outputs>
138
139 <requirements>
140 <requirement type="package">lps_tool</requirement>
141 </requirements>
142
143 <tests>
144 <test>
145 <param name="input_file" value="lps_arrhythmia.tabular"/>
146 <param name="label_column" value="280"/>
147 <param name="lambda_fac" value="0.03"/>
148 <param name="options" value="true"/>
149 <param name="sample" value="1.0"/>
150 <param name="verbosity" value="1"/>
151 <param name="standardize" value="0"/>
152 <param name="initialLambda" value="0.9"/>
153 <param name="continuation" value="1"/>
154 <param name="continuationSteps" value="10"/>
155 <param name="accurateIntermediates" value="0"/>
156 <param name="printFreq" value="1"/>
157 <param name="newton" value="1"/>
158 <param name="newtonThreshold" value="500"/>
159 <param name="hessianSampleFraction" value="1.0"/>
160 <param name="fullGradient" value="1"/>
161 <param name="gradientFraction" value="0.5"/>
162 <param name="initialAlpha" value="1.0"/>
163 <param name="alphaIncrease" value="2.0"/>
164 <param name="alphaDecrease" value="0.8"/>
165 <param name="alphaMax" value="1e12"/>
166 <param name="c1" value="1e-3"/>
167 <param name="maxIter" value="2500"/>
168 <param name="stopTol" value="1e-6"/>
169 <param name="intermediateTol" value="1e-6"/>
170 <param name="finalOnly" value="0"/>
171 <output name="ouput_file" file="lps_arrhythmia_beta.tabular"/>
172 <output name="log_file" file="lps_arrhythmia_log.txt"/>
173 </test>
174 </tests>
175
176 <help>
177 **Dataset formats**
178
179 The input and output datasets are tabular_. The columns are described below.
180 There is a second output dataset (a log) that is in text_ format.
181 (`Dataset missing?`_)
182
183 .. _tabular: ./static/formatHelp.html#tab
184 .. _text: ./static/formatHelp.html#text
185 .. _Dataset missing?: ./static/formatHelp.html
186
187 -----
188
189 **What it does**
190
191 The LASSO-Patternsearch algorithm fits your dataset to an L1-regularized
192 logistic regression model. A benefit of using L1-regularization is
193 that it typically yields a weight vector with relatively few non-zero
194 coefficients.
195
196 For example, say you have a dataset containing M rows (subjects)
197 and N columns (attributes) where one of these N attributes is binary,
198 indicating whether or not the subject has some property of interest P.
199 In simple terms, LPS calculates a weight for each of the other attributes
200 in your dataset. This weight indicates how "relevant" that attribute
201 is for predicting whether or not a given subject has property P.
202 The L1-regularization causes most of these weights to be equal to zero,
203 which means LPS will find a "small" subset of the remaining N-1 attributes
204 in your dataset that can be used to predict P.
205
206 In other words, LPS can be used for feature selection.
207
208 The input dataset is tabular, and must contain a label column which
209 indicates whether or not a given row has property P. In the current
210 version of this tool, P must be encoded using +1 and -1. The Lambda_fac
211 parameter ranges from 0 to 1, and controls how sparse the weight
212 vector will be. At the low end, when Lambda_fac = 0, there will be
213 no regularization. At the high end, when Lambda_fac = 1, there will be
214 "too much" regularization, and all of the weights will equal zero.
215
216 The LPS tool creates two output datasets. The first, called the results
217 file, is a tabular dataset containing one column of weights for each
218 value of the regularization parameter lambda that was tried. The weight
219 columns are in order from left to right by decreasing values of lambda.
220 The first N-1 rows in each column are the weights for the N-1 attributes
221 in your input dataset. The final row is a constant, the intercept.
222
223 Let **x** be a row from your input dataset and let **b** be a column
224 from the results file. To compute the probability that row **x** has
225 a label value of +1:
226
227 Probability(row **x** has label value = +1) = 1 / [1 + exp{**x** \* **b**\[1..N-1\] + **b**\[N\]}]
228
229 where **x** \* **b**\[1..N-1\] represents matrix multiplication.
230
231 The second output dataset, called the log file, is a text file which
232 contains additional data about the fitted L1-regularized logistic
233 regression model. These data include the number of features, the
234 computed value of lambda_max, the actual values of lambda used, the
235 optimal values of the log-likelihood and regularized log-likelihood
236 functions, the number of non-zeros, and the number of iterations.
237
238 Website: http://pages.cs.wisc.edu/~swright/LPS/
239
240 -----
241
242 **Example**
243
244 - input file::
245
246 +1 1 0 0 0 0 1 0 1 1 ...
247 +1 1 1 1 0 0 1 0 1 1 ...
248 +1 1 0 1 0 1 0 1 0 1 ...
249 etc.
250
251 - output results file::
252
253 0
254 0
255 0
256 0
257 0.025541
258 etc.
259
260 - output log file::
261
262 Data set has 100 vectors with 50 features.
263 calculateLambdaMax: n=50, m=100, m+=50, m-=50
264 computed value of lambda_max: 5.0000e-01
265
266 lambda=2.96e-02 solution:
267 optimal log-likelihood function value: 6.46e-01
268 optimal *regularized* log-likelihood function value: 6.79e-01
269 number of nonzeros at the optimum: 5
270 number of iterations required: 43
271 etc.
272
273 -----
274
275 **References**
276
277 Koh K, Kim S-J, Boyd S. (2007)
278 An interior-point method for large-scale l1-regularized logistic regression.
279 Journal of Machine Learning Research. 8:1519-1555.
280
281 Shi W, Wahba G, Wright S, Lee K, Klein R, Klein B. (2008)
282 LASSO-Patternsearch algorithm with application to ophthalmology and genomic data.
283 Stat Interface. 1(1):137-153.
284
285 <!--
286 Wright S, Novak R, Figueiredo M. (2009)
287 Sparse reconstruction via separable approximation.
288 IEEE Transactions on Signal Processing. 57:2479-2403.
289
290 Shi J, Yin W, Osher S, Sajda P. (2010)
291 A fast hybrid algorithm for large scale l1-regularized logistic regression.
292 Journal of Machine Learning Research. 11:713-741.
293
294 Byrd R, Chin G, Neveitt W, Nocedal J. (2010)
295 On the use of stochastic Hessian information in unconstrained optimization.
296 Technical Report. Northwestern University. June 16, 2010.
297
298 Wright S. (2010)
299 Accelerated block-coordinate relaxation for regularized optimization.
300 Technical Report. University of Wisconsin. August 10, 2010.
301 -->
302
303 </help>
304 </tool>