Mercurial > repos > nml > csvtk_freq
comparison freq.xml @ 0:a288e0146c2e draft default tip
"planemo upload for repository https://github.com/shenwei356/csvtk commit 3a97e1b79bf0c6cdd37d5c8fb497b85531a563ab"
author | nml |
---|---|
date | Tue, 19 May 2020 17:13:18 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:a288e0146c2e |
---|---|
1 <tool id="csvtk_freq" name="csvtk-freq" version="@VERSION@+@GALAXY_VERSION@"> | |
2 <description>of value in column(s)</description> | |
3 <macros> | |
4 <import>macros.xml</import> | |
5 </macros> | |
6 <expand macro="requirements" /> | |
7 <expand macro="version_cmd" /> | |
8 <command detect_errors="exit_code"><![CDATA[ | |
9 | |
10 ################### | |
11 ## Start Command ## | |
12 ################### | |
13 | |
14 csvtk freq --num-cpus "\${GALAXY_SLOTS:-1}" | |
15 | |
16 ## Add additional flags as specified ## | |
17 ####################################### | |
18 $ignore_case | |
19 $global_param.illegal_rows | |
20 $global_param.empty_rows | |
21 $global_param.header | |
22 $global_param.lazy_quotes | |
23 | |
24 ## Set Tabular input/output flag if input is tabular ## | |
25 ####################################################### | |
26 #if $in_1.is_of_type("tabular"): | |
27 -t -T | |
28 #end if | |
29 | |
30 ## Set Input ## | |
31 ############### | |
32 '$in_1' | |
33 | |
34 ## Specify fields for freq ## | |
35 ############################# | |
36 -F -f '$column_text.in_text' | |
37 | |
38 ## Sorting? ## | |
39 ############## | |
40 #if $sorting.want_sort == 'yes_sort' | |
41 | |
42 #if $sorting.how_sort == 'frequency' | |
43 -n | |
44 #elif $sorting.how_sort == 'alphabetical' | |
45 -k | |
46 #end if | |
47 | |
48 #if $sorting.reverse_sort == 'yes_reverse' | |
49 -r | |
50 #end if | |
51 #end if | |
52 | |
53 ## To output ## | |
54 ############### | |
55 > freq | |
56 | |
57 ]]></command> | |
58 <inputs> | |
59 <expand macro="singular_input" /> | |
60 <expand macro="fields_input" /> | |
61 <expand macro="ignore_case" /> | |
62 <expand macro="global_parameters" /> | |
63 <conditional name="sorting" > | |
64 <param type="select" name="want_sort" | |
65 label="Sort Output Columns?" | |
66 help="Change the order of output column(s)"> | |
67 <option value="no_sort">No</option> | |
68 <option value="yes_sort">Yes</option> | |
69 </param> | |
70 <when value="no_sort" /> | |
71 <when value="yes_sort"> | |
72 <param type="select" name="how_sort" label="How to Sort Output"> | |
73 <option value="frequency">Frequency (Low -> High)</option> | |
74 <option value="alphabetical">Alphabetical</option> | |
75 </param> | |
76 <param type="select" name="reverse_sort" label="Reverse Sort" help="Sort in reverse order. IE. highest to lowest or reverse alphabetical" > | |
77 <option value="no_reverse">No</option> | |
78 <option value="yes_reverse">Yes</option> | |
79 </param> | |
80 </when> | |
81 </conditional> | |
82 </inputs> | |
83 <outputs> | |
84 <data format_source="in_1" name="freq" from_work_dir="freq" label="${in_1.name} frequency of column(s) ${column_text.in_text}" /> | |
85 </outputs> | |
86 <tests> | |
87 <test> | |
88 <param name="in_1" value="blood_type.tsv" /> | |
89 <conditional name="column_text"> | |
90 <param name="select" value="string" /> | |
91 <param name="in_text" value="2,3" /> | |
92 </conditional> | |
93 <conditional name="sorting" > | |
94 <param name="want_sort" value="no_sort" /> | |
95 </conditional> | |
96 <output name="freq" file="frequency.tsv" ftype="tabular" /> | |
97 </test> | |
98 </tests> | |
99 <help><![CDATA[ | |
100 | |
101 Csvtk - Freq Help | |
102 ----------------- | |
103 | |
104 Info | |
105 #### | |
106 Find the frequency of the data based on the selected column(s). | |
107 | |
108 If one column is selected, the frequency will be the number of times each value is found in the column. These can further be sorted if so desired. | |
109 | |
110 Examples can be found in the usage section below! | |
111 | |
112 .. class:: warningmark | |
113 | |
114 Single quotes are not allowed in text inputs! | |
115 | |
116 @HELP_INPUT_DATA@ | |
117 | |
118 | |
119 Usage | |
120 ##### | |
121 | |
122 To run csvtk-freq, all you need is a valid (as defined above) CSV or TSV and the column(s) that you want the frequency of. | |
123 | |
124 **Ex. of frequency with one column:** | |
125 | |
126 +------------+-----------+ | |
127 | Blood Type | Frequency | | |
128 +============+===========+ | |
129 | A | 31 | | |
130 +------------+-----------+ | |
131 | B | 103 | | |
132 +------------+-----------+ | |
133 | etc. | etc. | | |
134 +------------+-----------+ | |
135 | |
136 ---- | |
137 | |
138 **Ex. of frequency with more than one column for frequency:** | |
139 | |
140 +---------+------------+-----------+ | |
141 | Name | Blood Type | Frequency | | |
142 +=========+============+===========+ | |
143 | Bob | A | 4 | | |
144 +---------+------------+-----------+ | |
145 | Jacob | B | 5 | | |
146 +---------+------------+-----------+ | |
147 | Matthew | O | 12 | | |
148 +---------+------------+-----------+ | |
149 | Darian | AB | 1 | | |
150 +---------+------------+-----------+ | |
151 | |
152 With multiple columns, you end up getting the frequency of how many times the values from each column | |
153 are found together. In this example from an input dataset of names and bloodtypes, we can find the frequency that | |
154 each name in our database is a certain bloodtype. | |
155 | |
156 Here, we can note that there are 4 people named bob with blood type A. | |
157 | |
158 ---- | |
159 | |
160 @HELP_COLUMNS@ | |
161 | |
162 | |
163 @HELP_END_STATEMENT@ | |
164 | |
165 | |
166 ]]></help> | |
167 <expand macro="citations" /> | |
168 </tool> |