Mercurial > repos > bgruening > sklearn_numeric_clustering

changeset 3:a8951d76b7d2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit a349cb4673231f12344e418513a08691925565d9
author bgruening
date Fri, 03 Jun 2016 13:57:01 -0400
parents fe2d62fbf47b
children 4fcf8b052fed
files main_macros.xml test-data/prp_model01 test-data/prp_model02 test-data/prp_model03 test-data/prp_model04 test-data/prp_model05 test-data/prp_model06 test-data/prp_model07 test-data/prp_model08 test-data/prp_model09 test-data/prp_result01 test-data/prp_result02 test-data/prp_result03 test-data/prp_result04 test-data/prp_result05 test-data/prp_result06 test-data/prp_result07 test-data/prp_result08 test-data/prp_result09
diffstat 19 files changed, 159 insertions(+), 40 deletions(-) [+]
line wrap: on
line diff
--- a/main_macros.xml	Tue May 31 16:52:04 2016 -0400
+++ b/main_macros.xml	Fri Jun 03 13:57:01 2016 -0400
@@ -10,7 +10,7 @@
 
   <xml name="macro_stdio">
     <stdio>
-        <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
+        <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
     </stdio>
   </xml>
 
@@ -23,7 +23,7 @@
             <option value="load">Load a model and predict</option>
         </param>
         <when value="load">
-            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
+            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
             <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
             <conditional name="prediction_options">
                 <param name="prediction_option" type="select" label="Select the type of prediction">
@@ -37,7 +37,7 @@
             </conditional>
         </when>
         <when value="train">
-            <param name="infile_train" type="data" format="@TRAIN@" label="Training samples (tabular)" />
+            <param name="infile_train" type="data" format="@TRAIN@" label="Training samples (tabular)"/>
             <conditional name="selected_algorithms">
                 <yield />
             </conditional>
@@ -52,7 +52,7 @@
             <option value="load">Load a model and predict</option>
         </param>
         <when value="load">
-            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
+            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
             <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
             <conditional name="prediction_options">
                 <param name="prediction_option" type="select" label="Select the type of prediction">
@@ -275,6 +275,10 @@
     </conditional>
   </xml>
 
+  <xml name="multitype_input" token_format="tabular" token_help="All datasets with tabular format are supporetd.">
+    <param name="infile_transform" type="data" format="@FORMAT@" label="Select a dataset to transform:" help="@HELP@"/>
+  </xml>
+
 
   <!--Advanced options-->
   <xml name="nn_advanced_options">
@@ -525,58 +529,64 @@
 
   <xml name="sparse_preprocessors">
     <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
-      <option value="StandardScaler" selected="true">Standardize features by removing the mean and scaling to unit variance</option>
-      <option value="Binarizer">Binarize data</option>
-      <option value="Imputer">Complete missing values</option>
-      <option value="MaxAbsScaler">Scale features by their maximum absolute value</option>
-      <option value="Normalizer">Normalize samples individually to unit norm</option>
+      <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
+      <option value="Binarizer">Binarizer (Binarizes data)</option>
+      <option value="Imputer">Imputer (Completes missing values)</option>
+      <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
+      <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
       <yield/>
     </param>
   </xml>
 
   <xml name="sparse_preprocessor_options">
     <when value="Binarizer">
+        <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
         <section name="options" title="Advanced Options" expanded="False">
-            <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing binarization" help=" "/>
-            <param argument="threshold" type="float" optional="true" value="0.0" label="Threshold" help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/>
+          <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing binarization" help=" "/>
+          <param argument="threshold" type="float" optional="true" value="0.0" label="Threshold" help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/>
         </section>
     </when>
     <when value="Imputer">
-        <section name="options" title="Advanced Options" expanded="False">
-            <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing imputation" help=" "/>
-            <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
-                <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
-                <option value="median">Replace missing values using the median along the axis</option>
-                <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
-            </param>
-            <param argument="missing_values" type="text" optional="true" value="NaN" label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
-            <param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
-                <option value="0" selected="true">Impute along columns</option>
-                <option value="1">Impute along rows</option>
-            </param>
-        </section>
+      <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
+      <section name="options" title="Advanced Options" expanded="False">
+          <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing imputation" help=" "/>
+          <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
+              <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
+              <option value="median">Replace missing values using the median along the axis</option>
+              <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
+          </param>
+          <param argument="missing_values" type="text" optional="true" value="NaN" label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
+          <param argument="axis" type="boolean" optional="true" truevalue="1" falsevalue="0" label="Impute along axis = 1" help="If fasle, axis = 0 is selected for imputation. "/>
+          <!--param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
+              <option value="0" selected="true">Impute along columns</option>
+              <option value="1">Impute along rows</option>
+          </param-->
+      </section>
     </when>
     <when value="StandardScaler">
-        <section name="options" title="Advanced Options" expanded="False">
-            <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for performing inplace scaling" help=" "/>
-            <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" "/>
-            <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
-        </section>
+      <expand macro="multitype_input"/>
+      <section name="options" title="Advanced Options" expanded="False">
+        <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for performing inplace scaling" help=" "/>
+        <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" "/>
+        <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
+      </section>
     </when>
     <when value="MaxAbsScaler">
-        <section name="options" title="Advanced Options" expanded="False">
-            <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing scaling" help=" "/>
-        </section>
+      <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
+      <section name="options" title="Advanced Options" expanded="False">
+        <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing scaling" help=" "/>
+      </section>
     </when>
     <when value="Normalizer">
-        <section name="options" title="Advanced Options" expanded="False">
-            <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
-                <option value="l1" selected="true">l1</option>
-                <option value="l2">l2</option>
-                <option value="max">max</option>
-                <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing row normalization" help=" "/>
-            </param>
-        </section>
+      <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
+      <section name="options" title="Advanced Options" expanded="False">
+        <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
+          <option value="l1" selected="true">l1</option>
+          <option value="l2">l2</option>
+          <option value="max">max</option>
+          <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing row normalization" help=" "/>
+        </param>
+      </section>
     </when>
     <yield/>
   </xml>
Binary file test-data/prp_model01 has changed
Binary file test-data/prp_model02 has changed
Binary file test-data/prp_model03 has changed
Binary file test-data/prp_model04 has changed
Binary file test-data/prp_model05 has changed
Binary file test-data/prp_model06 has changed
Binary file test-data/prp_model07 has changed
Binary file test-data/prp_model08 has changed
Binary file test-data/prp_model09 has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result01	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,15 @@
+0.340792241503	-0.392122793309	0.249050728091	-0.769815625858	-0.170138220973
+-0.862075755531	-0.190485884192	0.24710543975	0.742293134619	-0.679070605191
+-0.448575437572	0.199203123002	-0.812112096739	0.278559309077	0.0406914316875
+1.33428163284	1.66416082626	-3.00011335793	-0.670112383949	-0.0704503877547
+0.761526726038	0.917627410889	-1.95449332713	-0.567530116888	0.100635636548
+0.351707781935	0.635120251133	-1.51891502937	-0.309716974447	0.0995703002013
+-1.15469955812	-0.528932346979	0.727954822594	0.826185585523	-0.612742173567
+-0.176836714677	-1.58302563298	1.83524452493	-1.05539551285	0.237779665023
+-0.0458904476457	0.408969436205	-1.15586321892	-0.0244669672622	0.0750175270781
+-2.32259976346	-1.54646621316	2.23314889088	1.4052188635	-0.511535448293
+0.33596216675	-0.162180718453	-0.0355684060349	-0.595834626266	-0.284612086542
+0.0981742501127	-0.298032722308	0.182304008722	-0.42567750847	-0.299001698602
+0.693972528706	-0.0466258179106	-0.253067281294	-0.917227391557	-0.219285708489
+-1.85600914205	-0.890335299747	0.832008450126	1.07651729919	0.0955850219353
+0.723568479543	-0.413574630084	0.19661484069	-1.219698096	-0.0291442646963
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result02	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,15 @@
+0.550784381577	0.350971359358	0.502498373312	0.211812771111	0.0
+0.386180696401	0.506954745611	0.610959953576	0.829092800063	0.0
+0.550737573876	0.654016374015	0.444310040377	0.773048255119	1.0
+1.0	1.0	0.0	0.51724422759	1.0
+0.823558618145	0.798565194368	0.187092218148	0.496321347636	1.0
+0.726600991352	0.736783396223	0.280504967611	0.575389760123	1.0
+0.301036110273	0.418099007976	0.699639917598	0.834457321393	0.0
+0.331241792594	0.0	0.754571193936	0.0	0.0
+0.638113449084	0.692528816807	0.3634266159	0.670011816531	1.0
+0.0	0.172514309297	1.0	0.980398332569	0.0
+0.5767922297	0.426577166098	0.466098581577	0.299914603172	0.0
+0.523801457189	0.399913876039	0.515787235724	0.356280111142	0.0
+0.646217780792	0.437603275863	0.405592753791	0.18180023196	0.0
+0.203868992411	0.402791922863	0.784299102259	1.0	1.0
+0.608135890641	0.315311438334	0.461117228336	0.0313433043898	0.0
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result03	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,15 @@
+1.0	-0.409899987374	-0.649450145317	0.510268556953	-0.229110484125	0.0	0.168017999649	0.266209606365	-0.209159075052	0.0939123845501	-0.0	0.421785491252	-0.331393988464	0.148795837209	-0.0	0.260374000215	-0.116907876117	0.0	0.052491613936	-0.0	0.0
+1.0	-1.10383560019	0.0611191480175	1.01725565283	1.79193066057	0.0	1.21845303225	-0.067465491435	-1.12288300409	-1.97799685621	-0.0	0.00373555025439	0.062173798817	0.10952127528	0.0	1.03480906321	1.82285159394	0.0	3.21101549229	0.0	0.0
+1.0	-0.41009731911	0.731046118333	0.238276079462	1.60843479815	1.0	0.168179811141	-0.299800053274	-0.0977163813954	-0.659614798685	-0.41009731911	0.53442842713	0.174190802982	1.17584001578	0.731046118333	0.0567754900438	0.383251537773	0.238276079462	2.5870624999	1.60843479815	1.0
+1.0	1.48390157074	2.30714564103	-1.83858336229	0.770904924566	1.0	2.20196387164	3.42357704065	-2.72827673924	1.14394702845	1.48390157074	5.32292100892	-4.24187958998	1.77858993636	2.30714564103	3.38038878009	-1.41737296821	-1.83858336229	0.59429440272	0.770904924566	1.0
+1.0	0.74006063964	1.38952620136	-0.96404935579	0.702401167325	1.0	0.547689750344	1.02833364938	-0.71345498289	0.519819457174	0.74006063964	1.93078306427	-1.33957183927	0.976004825864	1.38952620136	0.929391160399	-0.677149392866	-0.96404935579	0.49336739986	0.702401167325	1.0
+1.0	0.331307031883	1.10808437795	-0.527405721679	0.961279646112	1.0	0.109764349375	0.367116146335	-0.174733224248	0.318478706363	0.331307031883	1.22785098866	-0.584410041034	1.0651789587	1.10808437795	0.27815679526	-0.506984385493	-0.527405721679	0.924058558029	0.961279646112	1.0
+1.0	-1.4627878344	-0.343655746393	1.43177660405	1.80949467985	0.0	2.13974824847	0.502695445045	-2.09438539798	-2.6469068041	-0.0	0.118099272029	-0.492038257533	-0.621843244798	-0.0	2.0499842439	2.59079214776	0.0	3.27427099641	0.0	0.0
+1.0	-1.33544682955	-2.24827087098	1.6885444678	-0.922608257112	0.0	1.78341823456	3.00244620662	-2.25496135608	1.23209427188	-0.0	5.0547219093	-3.79630534131	2.07427326979	-0.0	2.85118241974	-1.55786506849	0.0	0.851205996091	-0.0	0.0
+1.0	-0.0417384245742	0.906486336146	-0.13980113811	1.27108242642	1.0	0.00174209608594	-0.0378353115688	0.00583507925839	-0.0530529779827	-0.0417384245742	0.821717477619	-0.126727821474	1.15221885167	0.906486336146	0.0195443582169	-0.177698769845	-0.13980113811	1.61565053475	1.27108242642	1.0
+1.0	-2.73189476502	-1.46239633785	2.83576394706	2.28732123255	0.0	7.46324900714	3.99511289976	-7.74700868181	-6.24872090112	-0.0	2.13860304896	-4.14701081119	-3.34497019397	-0.0	8.04155716345	6.48630308661	0.0	5.23183842087	0.0	0.0
+1.0	-0.300256196558	-0.305034204892	0.340123288396	0.0593443810367	0.0	0.0901537835715	0.091588410181	-0.102124124935	-0.0178185181372	-0.0	0.0930458661541	-0.103749236841	-0.0181020660843	-0.0	0.115683851309	0.020184406026	0.0	0.00352175556063	0.0	0.0
+1.0	-0.523654501136	-0.426496596688	0.572385315213	0.243891110892	0.0	0.27421403656	0.223336862575	-0.299732146695	-0.127714678006	-0.0	0.181899346986	-0.244120388933	-0.104018728758	-0.0	0.327624949071	0.139599690386	0.0	0.0594828739721	0.0	0.0
+1.0	-0.00757221265553	-0.254805682403	0.0572980350837	-0.327374762308	0.0	5.73384045006e-05	0.00192944281299	-0.000433872906398	0.00247895131825	-0.0	0.0649259357849	-0.0145998649299	0.0834169497114	-0.0	0.00328306482445	-0.0187579306162	0.0	0.107174234996	-0.0	0.0
+1.0	-1.87242461384	-0.413385894664	1.82750303608	2.35149919802	1.0	3.50597393451	0.774033924183	-3.42186166662	-4.4030049778	-1.87242461384	0.170887897907	-0.755463977571	-0.972076599775	-0.413385894664	3.33976734688	4.29737192372	1.82750303608	5.52954847829	2.35149919802	1.0
+1.0	-0.168117705611	-0.811895938369	0.316838713275	-0.819986910541	0.0	0.0282635629399	0.136494082353	-0.0532661975245	0.137854318031	-0.0	0.65917501474	-0.257240064426	0.665744042184	-0.0	0.10038677023	-0.259803597638	0.0	0.672378533459	-0.0	0.0
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result04	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,15 @@
+0.0	-0.253855596808	0.134420613871	-0.560212076994	0.0
+-0.580706111253	0.269877398274	0.534957856136	0.571982134735	0.0
+-0.000165133108783	0.763654517468	-0.0804627978317	0.469187120466	1.0
+1.5847898825	1.9253361878	-1.72125318508	0.0	1.0
+0.962321505733	1.24899458116	-1.03034124258	-0.0383760408013	1.0
+0.620264240423	1.04155475721	-0.685377754397	0.106648574849	1.0
+-0.881088095119	-0.028466436412	0.862443663986	0.581821558844	0.0
+-0.774525327099	-1.43228418232	1.06529910722	-0.948711918516	0.0
+0.308088625944	0.89296467989	-0.379156802711	0.280201159646	1.0
+-1.94311479736	-0.853046623285	1.97164195151	0.849501639775	0.0
+0.0917532091045	0.0	0.0	-0.398618667806	0.0
+-0.0951931852238	-0.0895252058342	0.183494989243	-0.295234953979	0.0
+0.336679935704	0.0370214907519	-0.223441677167	-0.615260064152	0.0
+-1.22388442495	-0.079861817192	1.17508115529	0.885454357124	1.0
+0.202330657224	-0.373588074037	-0.0183956151589	-0.891223086637	0.0
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result05	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,7 @@
+%%MatrixMarket matrix coordinate real general
+%
+3 3 4
+1 1 1
+2 3 1
+3 1 1
+3 3 1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result06	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,9 @@
+%%MatrixMarket matrix coordinate real general
+%
+3 3 6
+1 1 1
+1 3 -0.2
+2 3 11
+3 1 0.04
+3 2 -5
+3 3 2.6
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result07	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,15 @@
+0.108665139011	-0.5565683482	0.0169733875077	-0.958962367167	-0.816496580928
+-0.571099536518	0.0792679658547	0.465423608048	0.979765457216	-0.816496580928
+0.108471837009	0.678736447658	-0.223614760609	0.803743046655	1.22474487139
+1.96379316226	2.0890722453	-2.06067941621	0.000324237526991	1.22474487139
+1.23514229057	1.26796195008	-1.28711935665	-0.065389486603	1.22474487139
+0.834735886268	1.01612031648	-0.900890721629	0.182945343826	1.22474487139
+-0.922721566735	-0.282935381937	0.832083851483	0.99661412602	-0.816496580928
+-0.797981006883	-1.98723568294	1.05920522412	-1.6242152405	-0.816496580928
+0.469308433082	0.835725023547	-0.558039074324	0.480130421839	1.22474487139
+-2.16591192182	-1.28401423621	2.07396641364	1.45497967458	-0.816496580928
+0.216069881629	-0.248375798767	-0.133526859597	-0.682255742645	-0.816496580928
+-0.00276638101632	-0.357063579425	0.0719181270631	-0.505225264563	-0.816496580928
+0.50277693294	-0.203429980112	-0.383697028135	-1.05322452049	-0.816496580928
+-1.32399310738	-0.345331774338	1.1821195963	1.51654378855	1.22474487139
+0.345509957574	-0.701929166993	-0.154122991003	-1.52577347424	-0.816496580928
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result08	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,9 @@
+%%MatrixMarket matrix coordinate real general
+%
+3 3 6
+1 1 1
+1 3 -0.01818181818181818
+2 3 1
+3 1 0.04
+3 2 -1
+3 3 0.2363636363636364
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/prp_result09	Fri Jun 03 13:57:01 2016 -0400
@@ -0,0 +1,9 @@
+%%MatrixMarket matrix coordinate real general
+%
+3 3 6
+1 1 0.8333333333333334
+1 3 -0.1666666666666667
+2 3 1
+3 1 0.005235602094240837
+3 2 -0.6544502617801047
+3 3 0.3403141361256544