|
20
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_sample-classifier_split-table" name="qiime sample-classifier split-table"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Split a feature table into training and testing sets.</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime sample-classifier split-table
|
|
|
10
|
|
|
11 --i-table=$itable
|
|
|
12 # if $input_files_mmetadatafile:
|
|
|
13 # def list_dict_to_string(list_dict):
|
|
|
14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
15 # for d in list_dict[1:]:
|
|
|
16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
17 # end for
|
|
|
18 # return $file_list
|
|
|
19 # end def
|
|
|
20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
|
|
|
21 # end if
|
|
|
22
|
|
|
23 #if '__ob__' in str($mmetadatacolumn):
|
|
|
24 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[')
|
|
|
25 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
26 #end if
|
|
|
27 #if '__cb__' in str($mmetadatacolumn):
|
|
|
28 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']')
|
|
|
29 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
30 #end if
|
|
|
31 #if 'X' in str($mmetadatacolumn):
|
|
|
32 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\')
|
|
|
33 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
34 #end if
|
|
|
35 #if '__sq__' in str($mmetadatacolumn):
|
|
|
36 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'")
|
|
|
37 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
38 #end if
|
|
|
39 #if '__db__' in str($mmetadatacolumn):
|
|
|
40 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"')
|
|
|
41 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
42 #end if
|
|
|
43
|
|
|
44 --m-metadata-column=$mmetadatacolumn
|
|
|
45
|
|
|
46
|
|
|
47 --p-test-size=$ptestsize
|
|
|
48
|
|
|
49 #if str($prandomstate):
|
|
|
50 --p-random-state=$prandomstate
|
|
|
51 #end if
|
|
|
52 #if $pnostratify:
|
|
|
53 --p-no-stratify
|
|
|
54 #end if
|
|
|
55
|
|
|
56 #if str($pmissingsamples) != 'None':
|
|
|
57 --p-missing-samples=$pmissingsamples
|
|
|
58 #end if
|
|
|
59
|
|
|
60 --o-training-table=otrainingtable
|
|
|
61
|
|
|
62 --o-test-table=otesttable
|
|
|
63
|
|
|
64 #if str($examples) != 'None':
|
|
|
65 --examples=$examples
|
|
|
66 #end if
|
|
|
67
|
|
|
68 ;
|
|
|
69 cp otesttable.qza $otesttable
|
|
|
70
|
|
|
71 ]]></command>
|
|
|
72 <inputs>
|
|
|
73 <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency¹ | RelativeFrequency² | PresenceAbsence³ | Balance⁴ | PercentileNormalized⁵ | Design⁶] Feature table containing all features that should be used for target prediction. [required]" name="itable" optional="False" type="data" />
|
|
|
74 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
|
|
|
75 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
|
|
|
76 </repeat>
|
|
|
77 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric | Categorical] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" />
|
|
|
78 <param exclude_min="True" label="--p-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) Fraction of input samples to exclude from training set and use for classifier testing. [default: 0.2]" max="1.0" min="0.0" name="ptestsize" optional="True" type="float" value="0.2" />
|
|
|
79 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
|
|
|
80 <param label="--p-no-stratify: Do not evenly stratify training and test data among metadata categories. If True, all values in column must match at least two samples. [default: True]" name="pnostratify" selected="False" type="boolean" />
|
|
|
81 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
|
|
|
82 <option selected="True" value="None">Selection is Optional</option>
|
|
|
83 <option value="error">error</option>
|
|
|
84 <option value="ignore">ignore</option>
|
|
|
85 </param>
|
|
|
86 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
87
|
|
|
88 </inputs>
|
|
|
89
|
|
|
90 <outputs>
|
|
|
91 <data format="qza" label="${tool.name} on ${on_string}: trainingtable.qza" name="otrainingtable" />
|
|
|
92 <data format="qza" label="${tool.name} on ${on_string}: testtable.qza" name="otesttable" />
|
|
|
93
|
|
|
94 </outputs>
|
|
|
95
|
|
|
96 <help><![CDATA[
|
|
|
97 Split a feature table into training and testing sets.
|
|
|
98 ###############################################################
|
|
|
99
|
|
|
100 Split a feature table into training and testing sets. By default stratifies
|
|
|
101 training and test sets on a metadata column, such that values in that
|
|
|
102 column are evenly represented across training and test sets.
|
|
|
103
|
|
|
104 Parameters
|
|
|
105 ----------
|
|
|
106 table : FeatureTable[Frequency¹ | RelativeFrequency² | PresenceAbsence³ | Balance⁴ | PercentileNormalized⁵ | Design⁶]
|
|
|
107 Feature table containing all features that should be used for target
|
|
|
108 prediction.
|
|
|
109 metadata : MetadataColumn[Numeric | Categorical]
|
|
|
110 Numeric metadata column to use as prediction target.
|
|
|
111 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
112 Fraction of input samples to exclude from training set and use for
|
|
|
113 classifier testing.
|
|
|
114 random_state : Int, optional
|
|
|
115 Seed used by random number generator.
|
|
|
116 stratify : Bool, optional
|
|
|
117 Evenly stratify training and test data among metadata categories. If
|
|
|
118 True, all values in column must match at least two samples.
|
|
|
119 missing_samples : Str % Choices('error', 'ignore'), optional
|
|
|
120 How to handle missing samples in metadata. "error" will fail if missing
|
|
|
121 samples are detected. "ignore" will cause the feature table and
|
|
|
122 metadata to be filtered, so that only samples found in both files are
|
|
|
123 retained.
|
|
|
124
|
|
|
125 Returns
|
|
|
126 -------
|
|
|
127 training_table : FeatureTable[Frequency¹ | RelativeFrequency² | PresenceAbsence³ | Balance⁴ | PercentileNormalized⁵ | Design⁶]
|
|
|
128 Feature table containing training samples
|
|
|
129 test_table : FeatureTable[Frequency¹ | RelativeFrequency² | PresenceAbsence³ | Balance⁴ | PercentileNormalized⁵ | Design⁶]
|
|
|
130 Feature table containing test samples
|
|
|
131 ]]></help>
|
|
|
132 <macros>
|
|
|
133 <import>qiime_citation.xml</import>
|
|
|
134 </macros>
|
|
|
135 <expand macro="qiime_citation"/>
|
|
|
136 </tool> |
