Mercurial > repos > bgruening > svm_classifier
annotate svm.xml @ 10:f37546afddba draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 97c4f22cdcfa6cddeeffc7b102c418a7ff12a888
author | bgruening |
---|---|
date | Tue, 05 Jun 2018 06:44:41 -0400 |
parents | 9a9396e5d153 |
children | 78c664cc1841 |
rev | line source |
---|---|
0
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
1 <tool id="svm_classifier" name="Support vector machines (SVMs)" version="@VERSION@"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
2 <description>for classification</description> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
3 <macros> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
4 <import>main_macros.xml</import> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
5 <!-- macro name="class_weight" argument="class_weight"--> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
6 </macros> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
7 <expand macro="python_requirements"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
8 <expand macro="macro_stdio"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
9 <version_command>echo "@VERSION@"</version_command> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
10 <command><![CDATA[ |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
11 python "$svc_script" '$inputs' |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
12 ]]> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
13 </command> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
14 <configfiles> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
15 <inputs name="inputs"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
16 <configfile name="svc_script"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
17 <![CDATA[ |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
18 import sys |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
19 import json |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
20 import numpy as np |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
21 import sklearn.svm |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
22 import pandas |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
23 import pickle |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
24 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
25 input_json_path = sys.argv[1] |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
26 params = json.load(open(input_json_path, "r")) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
27 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
28 #if $selected_tasks.selected_task == "load": |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
29 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
30 classifier_object = pickle.load(open("$infile_model", 'rb')) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
31 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
32 data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False ) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
33 prediction = classifier_object.predict(data) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
34 prediction_df = pandas.DataFrame(prediction) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
35 res = pandas.concat([data, prediction_df], axis=1) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
36 res.to_csv(path_or_buf = "$outfile_predict", sep="\t", index=False) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
37 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
38 #else: |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
39 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
40 data_train = pandas.read_csv("$selected_tasks.infile_train", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False ) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
41 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
42 data = data_train.ix[:,0:len(data_train.columns)-1] |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
43 labels = np.array(data_train[data_train.columns[len(data_train.columns)-1]]) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
44 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
45 options = params["selected_tasks"]["selected_algorithms"]["options"] |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
46 selected_algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"] |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
47 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
48 if not(selected_algorithm=="LinearSVC"): |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
49 if options["kernel"]: |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
50 options["kernel"] = str(options["kernel"]) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
51 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
52 my_class = getattr(sklearn.svm, selected_algorithm) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
53 classifier_object = my_class(**options) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
54 classifier_object.fit(data,labels) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
55 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
56 pickle.dump(classifier_object,open("$outfile_fit", 'w+')) |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
57 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
58 #end if |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
59 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
60 ]]> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
61 </configfile> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
62 </configfiles> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
63 <inputs> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
64 <expand macro="train_loadConditional" model="zip"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
65 <param name="selected_algorithm" type="select" label="Classifier type"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
66 <option value="SVC">C-Support Vector Classification</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
67 <option value="NuSVC">Nu-Support Vector Classification</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
68 <option value="LinearSVC">Linear Support Vector Classification</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
69 </param> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
70 <when value="SVC"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
71 <expand macro="svc_advanced_options"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
72 <expand macro="C"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
73 </expand> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
74 </when> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
75 <when value="NuSVC"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
76 <expand macro="svc_advanced_options"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
77 <param argument="nu" type="float" optional="true" value="0.5" label="Nu control parameter" help="Controls the number of support vectors. Should be in the interval (0, 1]. "/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
78 </expand> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
79 </when> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
80 <when value="LinearSVC"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
81 <section name="options" title="Advanced Options" expanded="False"> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
82 <expand macro="C"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
83 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
84 <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results."/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
85 <!--expand macro="class_weight"/--> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
86 <param argument="max_iter" type="integer" optional="true" value="1000" label="Maximum number of iterations" help="The maximum number of iterations to be run."/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
87 <param argument="loss" type="select" label="Loss function" help="Specifies the loss function. ''squared_hinge'' is the square of the hinge loss."> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
88 <option value="squared_hinge" selected="true">Squared hinge</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
89 <option value="hinge">Hinge</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
90 </param> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
91 <param argument="penalty" type="select" label="Penalization norm" help=" "> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
92 <option value="l1" >l1</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
93 <option value="l2" selected="true">l2</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
94 </param> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
95 <param argument="dual" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use the shrinking heuristic" help="Select the algorithm to either solve the dual or primal optimization problem. Prefer dual=False when n_samples > n_features."/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
96 <param argument="multi_class" type="select" label="Multi-class strategy" help="Determines the multi-class strategy if y contains more than two classes."> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
97 <option value="ovr" selected="true">ovr</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
98 <option value="crammer_singer" >crammer_singer</option> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
99 </param> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
100 <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Calculate the intercept for this model" help="If set to false, data is expected to be already centered."/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
101 <param argument="intercept_scaling" type="float" optional="true" value="1" label="Add synthetic feature to the instance vector" help=" "/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
102 </section> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
103 </when> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
104 </expand> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
105 </inputs> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
106 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
107 <expand macro="output"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
108 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
109 <tests> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
110 <test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
111 <param name="infile_train" value="train_set.tabular" ftype="tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
112 <param name="selected_task" value="train"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
113 <param name="selected_algorithm" value="SVC"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
114 <param name="random_state" value="5"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
115 <output name="outfile_fit" file="svc_model01.txt"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
116 </test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
117 <test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
118 <param name="infile_train" value="train_set.tabular" ftype="tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
119 <param name="selected_task" value="train"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
120 <param name="selected_algorithm" value="NuSVC"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
121 <param name="random_state" value="5"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
122 <output name="outfile_fit" file="svc_model02.txt"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
123 </test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
124 <test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
125 <param name="infile_train" value="train_set.tabular" ftype="tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
126 <param name="selected_task" value="train"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
127 <param name="selected_algorithm" value="LinearSVC"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
128 <param name="random_state" value="5"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
129 <output name="outfile_fit" file="svc_model03.txt"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
130 </test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
131 <test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
132 <param name="infile_model" value="svc_model01.txt" ftype="txt"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
133 <param name="infile_data" value="test_set.tabular" ftype="tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
134 <param name="selected_task" value="load"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
135 <output name="outfile_predict" file="svc_prediction_result01.tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
136 </test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
137 <test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
138 <param name="infile_model" value="svc_model02.txt" ftype="txt"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
139 <param name="infile_data" value="test_set.tabular" ftype="tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
140 <param name="selected_task" value="load"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
141 <output name="outfile_predict" file="svc_prediction_result02.tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
142 </test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
143 <test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
144 <param name="infile_model" value="svc_model03.txt" ftype="txt"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
145 <param name="infile_data" value="test_set.tabular" ftype="tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
146 <param name="selected_task" value="load"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
147 <output name="outfile_predict" file="svc_prediction_result03.tabular"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
148 </test> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
149 </tests> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
150 <help><![CDATA[ |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
151 **What it does** |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
152 This module implements the Support Vector Machine (SVM) classification algorithms. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
153 Support vector machines (SVMs) are a set of supervised learning methods used for classification, regression and outliers detection. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
154 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
155 **The advantages of support vector machines are:** |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
156 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
157 1- Effective in high dimensional spaces. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
158 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
159 2- Still effective in cases where number of dimensions is greater than the number of samples. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
160 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
161 3- Uses a subset of training points in the decision function (called support vectors), so it is also memory efficient. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
162 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
163 4- Versatile: different Kernel functions can be specified for the decision function. Common kernels are provided, but it is also possible to specify custom kernels. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
164 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
165 **The disadvantages of support vector machines include:** |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
166 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
167 1- If the number of features is much greater than the number of samples, the method is likely to give poor performances. |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
168 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
169 2- SVMs do not directly provide probability estimates, these are calculated using an expensive five-fold cross-validation |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
170 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
171 For more information check http://scikit-learn.org/stable/modules/neighbors.html |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
172 |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
173 ]]> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
174 </help> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
175 <expand macro="sklearn_citation"/> |
9a9396e5d153
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
bgruening
parents:
diff
changeset
|
176 </tool> |