Mercurial > repos > nml > biohansel_bionumeric_converter

changeset 1:07dfb8fd47f4 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
author nml
date Mon, 13 May 2019 12:59:15 -0400
parents b000a3130db8
children
files bionumeric_convert.xml bionumeric_converter.py test-data/Biohansel_Bionumerics.csv test-data/Output.csv test-data/results.tab
diffstat 5 files changed, 37 insertions(+), 33 deletions(-) [+]
line wrap: on
line diff
--- a/bionumeric_convert.xml	Mon Mar 18 13:15:57 2019 -0400
+++ b/bionumeric_convert.xml	Mon May 13 12:59:15 2019 -0400
@@ -1,38 +1,41 @@
-<tool id="bionumeric_convert" name="biohansel2bionumerics" version="0.1.0">
+<tool id="bionumeric_convert" name="biohansel2bionumerics" version="0.2.0">
     <description>compliant results</description>
     <requirements>
         <requirement type="package" version="0.24.1">pandas</requirement>
     </requirements>
     <command detect_errors="exit_code"><![CDATA[
-        $__tool_directory__/bionumeric_converter.py -f '$Input' -o '$output'
+        $__tool_directory__/bionumeric_converter.py -f '$Input' -o '$Output'
     ]]></command>
     <inputs>
         <param type="data" name="Input" format="tabular"/>
     </inputs>
     <outputs>
-        <data name="output" format="csv" from_work_dir="output" label="Output.csv"/>
+        <data name="Output" format="csv" from_work_dir="output" label="Biohansel_Bionumerics"/>
     </outputs>
     <tests>
         <test>
             <param name="Input" value="results.tab"/>
-            <output name="output" value="Output.csv"/>
+            <output name="Output" value="Biohansel_Bionumerics.csv"/>
         </test>
     </tests>
     <help><![CDATA[
         **What it does**
 
-        This tool is a supplementary script that takes *only* BioHansel output data and converts it into a format compatible with bionumerics.
+        This tool is a supplementary script that takes Biohansel output data and converts it into a format compatible with Bionumerics.
 
-        **How to run it**
+        **Inputs:**
+
+        - *Individual* output or *Collection* of outputs for any of the three Biohansel results files (tech_results.tab, match_results.tab, or results.tab)
 
-        1. Input any of your BioHansel output files (tech_results.tab, match_results.tab, and results.tab)
-        2. Click Execute
+        **Outputs:**
 
-        **Specific modifications done on the data**
+        - A .CSV file or a collection of .CSV files called "*Output*" that can be renamed and downloaded as required.
+
+        **Specific modifications done to the data**
 
         1. Converts all commas in the output to "/"
-        2. Shortens BioHansel qc_messages if they are over 150 characters
-        3. Converts the .tab file to a .csv file
+        2. Splits Biohansel qc_message column into multiple columns if the message is longer than 150 characters
+        3. Converts the .tab or .tsv file to a .csv file
 
     ]]></help>
     <citations>
--- a/bionumeric_converter.py	Mon Mar 18 13:15:57 2019 -0400
+++ b/bionumeric_converter.py	Mon May 13 12:59:15 2019 -0400
@@ -14,7 +14,7 @@
         '-f',
         '--filename',
         required=True,
-        help='Specify your tsv input')
+        help='Specify your biohansel tsv or other tabular separated input')
     parser.add_argument(
         '-o',
         '--output',
@@ -24,30 +24,27 @@
     tsv_file = args.filename
     out_name = args.output
 
-    no_comma_tsv = comma_remover(tsv_file)
-    df = qc_shortener(no_comma_tsv)
-    df.to_csv(out_name, index=False)
-
-# Remove comma function:
-
+    df_input = pd.read_csv(tsv_file, sep='\t')
 
-def comma_remover(tsv_file):
-    # Create a table from the tsv file as an input into the dataframe.
-    df = pd.read_csv(tsv_file, sep='\t')
-    # Change all commas to / in the QC message
-    no_comma_tsv = df.replace(',', '/', regex=True)
-    return no_comma_tsv
+    df_no_comma = df_input.replace(',', '/', regex=True)
+    df = qc_shortener(df_no_comma)
+    df.to_csv(out_name, index=False)
 
 # Shorten QC results:
 
 
+def splittingstrings(string, length):
+    return (string[0+i:length+i] for i in range(0, len(string), length))
+
+
 def qc_shortener(df):
-    for count in df.index:
-        message = str(df.at[count, 'qc_message'])
+    for i, row in df.iterrows():
+        message = str(row['qc_message'])
         if len(message) > 150:
-            results = message.find('|')
-            new_message = "Truncated after first '|' : " + message[0:results]
-            df['qc_message'] = df['qc_message'].replace(message, new_message)
+            message_list = list(splittingstrings(message, 150))
+            df.at[i, 'qc_message'] = message_list[0]
+            for val in range(1, len(message_list)):
+                df.at[i, 'qc_message_{}'.format(val)] = message_list[val]
     return df
 
 
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/Biohansel_Bionumerics.csv	Mon May 13 12:59:15 2019 -0400
@@ -0,0 +1,4 @@
+sample,subtype,avg_tile_coverage,qc_status,qc_message,qc_message_1
+SRR1645238,1.3,43.345,PASS,,
+SRR1753252,1.1,32.33,PASS,FAIL: This is a test of the cut off system. The data is good and as such I have to manually type this message in to get it to cut off. I am adding in ,5 comas /////
+SRR1928313,1.1.1,555.11,PASS,,
--- a/test-data/Output.csv	Mon Mar 18 13:15:57 2019 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,2 +0,0 @@
-sample,scheme,scheme_version,subtype,all_subtypes,tiles_matching_subtype,are_subtypes_consistent,inconsistent_subtypes,n_tiles_matching_all,n_tiles_matching_all_expected,n_tiles_matching_positive,n_tiles_matching_positive_expected,n_tiles_matching_subtype,n_tiles_matching_subtype_expected,file_path,avg_tile_coverage,qc_status,qc_message
-2019C-111,heidelberg,0.5.0,2.2.3.1.2,2; 2.2; 2.2.3; 2.2.3.1; 2.2.3.1.2,2.2.3.1.2,True,,202,202,14,14,3,3,['2019C-111_1.fastq'/ '2019C-111_2.fastq'],30.07,PASS,Truncated after first '|' : This is a trial to the cut /off/ system as this data all passed the checks. 
--- a/test-data/results.tab	Mon Mar 18 13:15:57 2019 -0400
+++ b/test-data/results.tab	Mon May 13 12:59:15 2019 -0400
@@ -1,2 +1,4 @@
-sample	scheme	scheme_version	subtype	all_subtypes	tiles_matching_subtype	are_subtypes_consistent	inconsistent_subtypes	n_tiles_matching_all	n_tiles_matching_all_expected	n_tiles_matching_positive	n_tiles_matching_positive_expected	n_tiles_matching_subtype	n_tiles_matching_subtype_expected	file_path	avg_tile_coverage	qc_status	qc_message
-2019C-111	heidelberg	0.5.0	2.2.3.1.2	2; 2.2; 2.2.3; 2.2.3.1; 2.2.3.1.2	2.2.3.1.2	True		202	202	14	14	3	3	['2019C-111_1.fastq', '2019C-111_2.fastq']	30.070	PASS	This is a trial to the cut ,off, system as this data all passed the checks. | I will attemp to get 150 characters into here in a way that is not awful and sounds decent. We can try counting the letters and as of now, it should be ok!
+sample	subtype	avg_tile_coverage	qc_status	qc_message
+SRR1645238	1.3	43.345	PASS
+SRR1753252	1.1	32.33	PASS	"FAIL: This is a test of the cut off system. The data is good and as such I have to manually type this message in to get it to cut off. I am adding in 5 comas ,,,,,"
+SRR1928313	1.1.1	555.11	PASS