Mercurial > repos > bgruening > nn_classifier

comparison nn_classifier.xml @ 5:25a68adb2ade 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 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
author bgruening
date Fri, 16 Feb 2018 09:13:21 -0500
parents 4354c286f7a7
children c64f57fe1b97
comparison
equal deleted inserted replaced
4:c85acc0197c6 5:25a68adb2ade
31 31
32 data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False ) 32 data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
33 prediction = classifier_object.predict(data) 33 prediction = classifier_object.predict(data)
34 prediction_df = pandas.DataFrame(prediction) 34 prediction_df = pandas.DataFrame(prediction)
35 res = pandas.concat([data, prediction_df], axis=1) 35 res = pandas.concat([data, prediction_df], axis=1)
36 res.to_csv(path_or_buf = "$outfile", sep="\t", index=False) 36 res.to_csv(path_or_buf = "$outfile_predict", sep="\t", index=False)
37 37
38 #else: 38 #else:
39 39
40 data_train = pandas.read_csv("$selected_tasks.infile_train", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False ) 40 data_train = pandas.read_csv("$selected_tasks.infile_train", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
41 41
55 55
56 my_class = getattr(sklearn.neighbors, classifier) 56 my_class = getattr(sklearn.neighbors, classifier)
57 classifier_object = my_class(**options) 57 classifier_object = my_class(**options)
58 classifier_object.fit(data,labels) 58 classifier_object.fit(data,labels)
59 59
60 pickle.dump(classifier_object,open("$outfile", 'w+')) 60 pickle.dump(classifier_object,open("$outfile_fit", 'w+'))
61 61
62 #end if 62 #end if
63 63
64 ]]> 64 ]]>
65 </configfile> 65 </configfile>
66 </configfiles> 66 </configfiles>
67 <inputs> 67 <inputs>
68 <expand macro="train_loadConditional"><!--Todo: add sparse to targets--> 68 <expand macro="train_loadConditional" model="zip"><!--Todo: add sparse to targets-->
69 <param name="selected_algorithm" type="select" label="Classifier type"> 69 <param name="selected_algorithm" type="select" label="Classifier type">
70 <option value="nneighbors">Nearest Neighbors</option> 70 <option value="nneighbors">Nearest Neighbors</option>
71 <option value="ncentroid">Nearest Centroid</option> 71 <option value="ncentroid">Nearest Centroid</option>
72 </param> 72 </param>
73 <when value="nneighbors"> 73 <when value="nneighbors">
81 <param argument="n_neighbors" type="integer" optional="true" value="5" label="Number of neighbors" help=" "/> 81 <param argument="n_neighbors" type="integer" optional="true" value="5" label="Number of neighbors" help=" "/>
82 </expand> 82 </expand>
83 </when> 83 </when>
84 <when value="RadiusNeighborsClassifier"> 84 <when value="RadiusNeighborsClassifier">
85 <expand macro="nn_advanced_options"> 85 <expand macro="nn_advanced_options">
86 <param argument="radius" type="float" optional="true" value="1.0" label="Radius" help="Range of parameter space to use by default for :meth ''radius_neighbors'' queries."/> 86 <param argument="radius" type="float" optional="true" value="1.0" label="Radius"
87 help="Range of parameter space to use by default for :meth ''radius_neighbors'' queries."/>
87 </expand> 88 </expand>
88 </when> 89 </when>
89 </conditional> 90 </conditional>
90 </when> 91 </when>
91 <when value="ncentroid"> 92 <when value="ncentroid">
92 <section name="options" title="Advanced Options" expanded="False"> 93 <section name="options" title="Advanced Options" expanded="False">
93 <param argument="metric" type="text" optional="true" value="euclidean" label="Metric" help="The metric to use when calculating distance between instances in a feature array."/> 94 <param argument="metric" type="text" optional="true" value="euclidean" label="Metric"
94 <param argument="shrink_threshold" type="float" optional="true" value="" label="Shrink threshold" help="Floating point number for shrinking centroids to remove features."/> 95 help="The metric to use when calculating distance between instances in a feature array."/>
96 <param argument="shrink_threshold" type="float" optional="true" value="" label="Shrink threshold"
97 help="Floating point number for shrinking centroids to remove features."/>
95 </section> 98 </section>
96 </when> 99 </when>
97 </expand> 100 </expand>
98 </inputs> 101 </inputs>
99 <outputs> 102
100 <data format="txt" name="outfile"/> 103 <expand macro="output"/>
101 </outputs> 104
102 <tests> 105 <tests>
103 <test> 106 <test>
104 <param name="infile_train" value="train_set.tabular" ftype="tabular"/> 107 <param name="infile_train" value="train_set.tabular" ftype="tabular"/>
105 <param name="selected_task" value="train"/> 108 <param name="selected_task" value="train"/>
106 <param name="selected_algorithm" value="nneighbors"/> 109 <param name="selected_algorithm" value="nneighbors"/>
107 <param name="sampling_method" value="KNeighborsClassifier" /> 110 <param name="sampling_method" value="KNeighborsClassifier" />
108 <param name="algorithm" value="brute" /> 111 <param name="algorithm" value="brute" />
109 <output name="outfile" file="nn_model01.txt"/> 112 <output name="outfile_fit" file="nn_model01.txt"/>
110 </test> 113 </test>
111 <test> 114 <test>
112 <param name="infile_train" value="train_set.tabular" ftype="tabular"/> 115 <param name="infile_train" value="train_set.tabular" ftype="tabular"/>
113 <param name="selected_task" value="train"/> 116 <param name="selected_task" value="train"/>
114 <param name="selected_algorithm" value=""/> 117 <param name="selected_algorithm" value=""/>
115 <param name="selected_algorithm" value="nneighbors"/> 118 <param name="selected_algorithm" value="nneighbors"/>
116 <param name="sampling_method" value="RadiusNeighborsClassifier" /> 119 <param name="sampling_method" value="RadiusNeighborsClassifier" />
117 <output name="outfile" file="nn_model02.txt"/> 120 <output name="outfile_fit" file="nn_model02.txt"/>
118 </test> 121 </test>
119 <test> 122 <test>
120 <param name="infile_train" value="train_set.tabular" ftype="tabular"/> 123 <param name="infile_train" value="train_set.tabular" ftype="tabular"/>
121 <param name="selected_task" value="train"/> 124 <param name="selected_task" value="train"/>
122 <param name="selected_algorithm" value="ncentroid"/> 125 <param name="selected_algorithm" value="ncentroid"/>
123 <output name="outfile" file="nn_model03.txt"/> 126 <output name="outfile_fit" file="nn_model03.txt"/>
124 </test> 127 </test>
125 <test> 128 <test>
126 <param name="infile_model" value="nn_model01.txt" ftype="txt"/> 129 <param name="infile_model" value="nn_model01.txt" ftype="txt"/>
127 <param name="infile_data" value="test_set.tabular" ftype="tabular"/> 130 <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
128 <param name="selected_task" value="load"/> 131 <param name="selected_task" value="load"/>
129 <output name="outfile" file="nn_prediction_result01.tabular"/> 132 <output name="outfile_predict" file="nn_prediction_result01.tabular"/>
130 </test> 133 </test>
131 <test> 134 <test>
132 <param name="infile_model" value="nn_model02.txt" ftype="txt"/> 135 <param name="infile_model" value="nn_model02.txt" ftype="txt"/>
133 <param name="infile_data" value="test_set.tabular" ftype="tabular"/> 136 <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
134 <param name="selected_task" value="load"/> 137 <param name="selected_task" value="load"/>
135 <output name="outfile" file="nn_prediction_result02.tabular"/> 138 <output name="outfile_predict" file="nn_prediction_result02.tabular"/>
136 </test> 139 </test>
137 <test> 140 <test>
138 <param name="infile_model" value="nn_model03.txt" ftype="txt"/> 141 <param name="infile_model" value="nn_model03.txt" ftype="txt"/>
139 <param name="infile_data" value="test_set.tabular" ftype="tabular"/> 142 <param name="infile_data" value="test_set.tabular" ftype="tabular"/>
140 <param name="selected_task" value="load"/> 143 <param name="selected_task" value="load"/>
141 <output name="outfile" file="nn_prediction_result03.tabular"/> 144 <output name="outfile_predict" file="nn_prediction_result03.tabular"/>
142 </test> 145 </test>
143 </tests> 146 </tests>
144 <help><![CDATA[ 147 <help><![CDATA[
145 **What it does** 148 **What it does**
146 This module implements the k-nearest neighbors classification algorithms. 149 This module implements the k-nearest neighbors classification algorithms.