diff tools/filters/uniq.xml @ 0:9071e359b9a3

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/filters/uniq.xml	Fri Mar 09 19:37:19 2012 -0500
@@ -0,0 +1,75 @@
+<tool id="Count1" name="Count">
+  <description>occurrences of each record</description>
+  <command interpreter="python">uniq.py -i $input -o $out_file1 -c "$column" -d $delim</command>
+  <inputs>
+    <param name="input" type="data" format="tabular" label="from dataset" help="Dataset missing? See TIP below"/>
+    <param name="column" type="data_column" data_ref="input" multiple="True" numerical="False" label="Count occurrences of values in column(s)" help="Multi-select list - hold the appropriate key while clicking to select multiple columns" />
+    <param name="delim" type="select" label="Delimited by">
+      <option value="T">Tab</option>
+      <option value="Sp">Whitespace</option>
+      <option value="Dt">Dot</option>
+      <option value="C">Comma</option>
+      <option value="D">Dash</option>
+      <option value="U">Underscore</option>
+      <option value="P">Pipe</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="tabular" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="input" value="1.bed"/>
+      <output name="out_file1" file="uniq_out.dat"/>
+      <param name="column" value="1"/>
+      <param name="delim" value="T"/>
+    </test>
+  </tests>
+  <help>
+  
+ .. class:: infomark
+
+**TIP:** If your data is not TAB delimited, use *Text Manipulation-&gt;Convert*
+
+-----
+
+**Syntax**
+
+This tool counts occurrences of unique values in selected column(s).
+
+- If multiple columns are selected, counting is performed on each unique group of all values in the selected columns.
+- The first column of the resulting dataset will be the count of unique values in the selected column(s) and will be followed by each value.
+
+-----
+
+**Example**
+
+- Input file::
+     
+       chr1   10  100  gene1
+       chr1  105  200  gene2
+       chr1  205  300  gene3
+       chr2   10  100  gene4
+       chr2 1000 1900  gene5
+       chr3   15 1656  gene6
+       chr4   10 1765  gene7
+       chr4   10 1765  gene8
+
+- Counting unique values in column c1 will result in::
+
+       3 chr1
+       2 chr2
+       1 chr3
+       2 chr4   
+
+- Counting unique values in the grouping of columns c2 and c3 will result in::
+
+       2    10    100
+       2    10    1765
+       1    1000  1900
+       1    105   200
+       1    15    1656
+       1    205   300
+
+</help>
+</tool>