Repository 'csvtk_replace'
hg clone https://toolshed.g2.bx.psu.edu/repos/nml/csvtk_replace

Changeset 0:1d4ee4308d99 (2020-05-19)
Commit message:
"planemo upload for repository https://github.com/shenwei356/csvtk commit 3a97e1b79bf0c6cdd37d5c8fb497b85531a563ab"
added:
macros.xml
replace.xml
test-data/Animals_More.csv
test-data/XY_converted.csv
test-data/XY_converted.tsv
test-data/XY_with_break.csv
test-data/XY_with_break.tabular
test-data/another.csv
test-data/awk_mutate_input.csv
test-data/awk_mutate_output.csv
test-data/blood_type.tsv
test-data/collapsed.tsv
test-data/concat_1.csv
test-data/concat_2.csv
test-data/corr_1.csv
test-data/corr_2.tsv
test-data/csv-bob.csv
test-data/csv-darian.csv
test-data/csv-jack.csv
test-data/csv.csv
test-data/cut_1.csv
test-data/cut_2.csv
test-data/data.csv
test-data/filtered.tsv
test-data/frequency.tsv
test-data/gathered.csv
test-data/illegal.csv
test-data/illegal_collapse.csv
test-data/joined.csv
test-data/joined_filled.csv
test-data/kv.txt
test-data/line_all_param.png
test-data/mutate_removed.tsv
test-data/mutated.tsv
test-data/other.csv
test-data/plot.csv
test-data/plot.png
test-data/plot_box.png
test-data/plot_scatter.png
test-data/replace_1.csv
test-data/replace_2.csv
test-data/replace_input.csv
test-data/sampled_1.csv
test-data/sampled_2.csv
test-data/separated_1.tsv
test-data/separated_2.tsv
test-data/sort_order.txt
test-data/sorted_1.csv
test-data/test.csv
test-data/uniq.tsv
b
diff -r 000000000000 -r 1d4ee4308d99 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Tue May 19 17:16:05 2020 -0400
b
b'@@ -0,0 +1,337 @@\n+<macros>\n+    <token name="@VERSION@">0.20.0</token>\n+    <token name="@GALAXY_VERSION@">galaxy0</token>\n+    <xml name="requirements">\n+        <requirements>\n+            <requirement type="package" version="@VERSION@">csvtk</requirement>\n+        </requirements>\n+    </xml>\n+    <xml name="version_cmd">\n+        <version_command>csvtk version</version_command>\n+    </xml>\n+    <xml name="text_sanitizer">\n+        <sanitizer>\n+            <valid initial="string.printable">\n+                    <remove value="&apos;"/>\n+            </valid>\n+        </sanitizer>\n+    </xml>\n+    <xml name="multi_input">\n+        <param type="data" name="in_1" format="csv,tabular"\n+            multiple="true" optional="false"\n+            label="Specify TSV or CSV file inputs"\n+            help="Input tsv or csv files to analyze. HOWEVER, they must all be the **same file type** or the tool will fail/not give correct results!"\n+        />\n+    </xml>\n+    <xml name="singular_input">\n+        <param type="data" name="in_1" format="csv,tabular"\n+            multiple="false" optional="false"\n+            label="Specify an input TSV or CSV file"\n+            help="Input a TSV or CSV file to work on"\n+        />\n+    </xml>\n+    <xml name="ignore_case">\n+        <param type="boolean" name="ignore_case"\n+            falsevalue="" truevalue="-i"\n+            checked="false"\n+            argument="-i"\n+            label="Ignore cell case?"\n+            help="ABC == abc"\n+        />\n+    </xml>\n+    <xml name="global_parameters">\n+        <section name="global_param" title="csvtk Global Parameters" expanded="false">\n+            <param type="boolean" name="header"\n+                falsevalue="-H" truevalue=""\n+                checked="true"\n+                argument="-H"\n+                label="Input file has a header line"\n+            />\n+            <param type="boolean" name="illegal_rows"\n+                falsevalue="" truevalue="-I"\n+                checked="false"\n+                argument="-I"\n+                label="Ignore illegal rows"\n+                help="Use if file has illegal rows as defined in the help section"\n+            />\n+            <param type="boolean" name="empty_rows"\n+                falsevalue="" truevalue="-E"\n+                checked="false"\n+                argument="-E"\n+                label="Ignore empty rows"\n+                help="Ignore rows with no data (only needed if input has empty rows)"\n+            />\n+            <param type="boolean" name="lazy_quotes"\n+                falsevalue="" truevalue="-l"\n+                checked="false"\n+                argument="-l"\n+                label="File has Lazy quotes"\n+                help="(TSV files only) If Yes, a quote may appear in an unquoted field and a non-doubled quote may appear in a quoted field"\n+            />\n+        </section>\n+    </xml>\n+    <xml name="fields_input">\n+        <conditional name="column_text" >\n+            <param type="select" name="select" label="Select input column(s) based on" argument="-F -f">\n+                <option value="string">Column Name(s)</option>\n+                <option value="column">Column Number(s)</option>\n+            </param>\n+            <when value="column">\n+                <param type="data_column" name="in_text"\n+                    data_ref="in_1"\n+                    multiple="true"\n+                    label="Input column number(s)"\n+                    help="Select column(s) to use for analysis"\n+                />\n+            </when>\n+            <when value="string">\n+                <param type="text" name="in_text"\n+                    optional="false"\n+                    label="Input column name(s)"\n+                    help="Multiple columns can be given if separated by a \' , \'. \n+                    Column numbers can be given too - ex. \'1,2\' will target columns 1 and 2. \n+                    Please see the help section below for more detailed info">\n+                    <sanit'..b'        <sanitizer>\n+                    <valid initial="string.printable">\n+                        <remove value="&apos;"/>\n+                    </valid>\n+                </sanitizer>\n+            </param>\n+            <param type="float" name="min_x"\n+                argument="--x-min"\n+                optional="true"\n+                label="Minimum value of X-axis (float)"\n+            />\n+            <param type="float" name="max_x"\n+                argument="--x-max"\n+                optional="true"\n+                label="Maximum value of X-axis (float)"\n+            />\n+            <param type="text" name="y_label"\n+                argument="--ylab"\n+                optional="true"\n+                label="Specify Y-axis label">\n+                <sanitizer>\n+                    <valid initial="string.printable">\n+                        <remove value="&apos;"/>\n+                    </valid>\n+                </sanitizer>\n+            </param>\n+            <param type="float" name="min_y"\n+                argument="--y-min"\n+                optional="true"\n+                label="Minimum value of Y-axis (float)"\n+            />\n+            <param type="float" name="max_y"\n+                argument="--y-max"\n+                optional="true"\n+                label="Maximum value of Y-axis (float)"\n+            />\n+        </section>\n+    </xml>\n+    <token name="@HELP_COLUMNS@">\n+Column Name Input Help\n+######################\n+\n+- Multiple names can be given if separated by a \' , \'.\n+\n+    - ex. \'ID,Organism\' would target the columns named ID and Organism for the function \n+\n+- Column names are case SeNsitive\n+\n+- Column numbers can also be given:\n+\n+    -ex. \'1,2,3\' or \'1-3\' for inputting columns 1-3.\n+\n+- You can also specify all but unwanted column(s) with a \' - \'.\n+\n+    - ex. \'-ID\' would target all columns but the ID column\n+\n+----\n+    </token>\n+    <token name="@HELP_INPUT_DATA@">\n+Input Data\n+##########\n+\n+::\n+\n+    **Limitations of Input Data**\n+\n+    1. The CSV parser requires all the lines have same number of fields/columns.\n+        If your file has illegal rows, set the "Illegal Rows" parameter to "Yes" to pass your data through\n+        Even lines with spaces will cause error.\n+        Example bad table below.\n+\n+    2. By default, csvtk thinks files have header rows. If your file does not, set global parameter\n+        "Has Header Row" to "No"\n+\n+    3. Column names should be unique and are case sensitive!\n+\n+    4. Lines starting with "#" or "$" will be ignored, if in the header row\n+\n+    5. If " exists in tab-delimited files, set Lazy quotes global parameter to "Yes"\n+\n+Example bad table:\n+\n++--------+--------+--------+--------+\n+| Head 1 | Head 2 | Head 3 | Head 3 |\n++========+========+========+========+\n+| 1      | 2      | 3      |        |\n++--------+--------+--------+--------+\n+| this   | will   |        | break  |\n++--------+--------+--------+--------+\n+\n+Bad tables may work if both the "Ignore Illegal Rows" and "Ignore Empty Rows" global parameters are set to "Yes",\n+But there is no guarentee of that!\n+\n+----\n+    </token>\n+    <token name="@HELP_END_STATEMENT@">\n+More Information\n+################\n+For information from the creators of csvtk, please visit their site at: https://bioinf.shenwei.me/csvtk/\n+\n+Although be aware that some features may not be available and some small changes were made to work with Galaxy.\n+\n+**Notable changes from their documentation:**\n+\n+- Cannot specify multiple file header names (IE cannot use "name;username" as a valid column match)\n+\n+- No single quotes / apostrophes allowed in text inputs\n+    </token>\n+    <xml name="citations">\n+        <citations>\n+            <citation type="bibtex">@ARTICLE{a1,\n+                title = {csvtk - CSV/TSV Toolkit},\n+                author = {Wei Shen},\n+                url = {https://github.com/shenwei356/csvtk}\n+                }\n+            }</citation>\n+        </citations>\n+    </xml>\n+</macros>\n\\ No newline at end of file\n'
b
diff -r 000000000000 -r 1d4ee4308d99 replace.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/replace.xml Tue May 19 17:16:05 2020 -0400
[
b'@@ -0,0 +1,256 @@\n+<tool id="csvtk_replace" name="csvtk-replace" version="@VERSION@+@GALAXY_VERSION@">\n+    <description> data of selected columns by regular expression</description>\n+    <macros>\n+        <import>macros.xml</import>\n+    </macros>\n+    <expand macro="requirements" />\n+    <expand macro="version_cmd" />\n+    <command detect_errors="exit_code"><![CDATA[\n+\n+###################\n+## Start Command ##\n+###################\n+csvtk replace --num-cpus "\\${GALAXY_SLOTS:-1}"\n+\n+    ## Add additional flags as specified ##\n+    #######################################\n+    $ignore_case\n+    $global_param.illegal_rows\n+    $global_param.empty_rows\n+    $global_param.header\n+    $global_param.lazy_quotes\n+\n+    ## Set Tabular input/output flag if first input is tabular ##\n+    #############################################################\n+    #if $in_1.is_of_type("tabular"):\n+        -t -T\n+    #end if\n+\n+    ## Set input files ##\n+    #####################\n+    \'$in_1\'\n+\n+    ## Specify fields to use ##\n+    ###########################\n+    -F -f \'${column_text.in_text}\'\n+    \n+    ## Specific Commands ##\n+    #######################\n+    -p \'($pattern_string)\'\n+    -r \'$replacement_string\'\n+\n+    #if $input_kv\n+        -k \'$input_kv\'\n+    #end if\n+\n+    #if $fill.how_fill == "key"\n+        -K\n+    #elif $fill.how_fill == "string"\n+        --key-miss-repl \'$fill.fill_string\'\n+    #end if\n+    \n+    ## To output ##\n+    ###############\n+    > replaced\n+\n+    ]]></command>\n+    <inputs>\n+        <expand macro="singular_input"/>\n+        <expand macro="fields_input" />\n+        <param name="pattern_string" type="text" argument="-p"\n+            label="Pattern Regex"\n+            help="Regex to search column for. Input is structured as \'(YOUR_INPUT_HERE)\' so if your regex was just a period it would look like \'(.)\' as an input.">\n+            <expand macro="text_sanitizer" />\n+        </param>\n+        <param name="replacement_string" type="text" argument="-r"\n+            label="Replacement String">\n+            <help>\n+                <![CDATA[\n+        String to replace found data. Supports capture variables and special replacement symbols.\n+\n+        - Capture Variables: $1 represents the text of the first submatch\n+        - {nr} inserts a record number starting from 1\n+        - {kv} uses corresponding value of the key (captured variable $n) of a key-value file\n+\n+        If using the special replacement symbols, the capture variable must be specified as ${1}!\n+            ]]>\n+            </help>\n+            <expand macro="text_sanitizer" />\n+        </param>\n+        <param name="input_kv" type="data" format="tsv,tabular" argument="-k"\n+            optional="true"\n+            label="Key/Value file for replacement string"\n+            help="Only specify a file if using {kv} in replacement string. The file must be tab delimited with one key/value pair per line.\n+            An example can be found in the help section below"\n+        />\n+        <conditional name="fill">\n+            <param name="how_fill" type="select" label="Fill columns that don\'t get any regex matches">\n+                <option value="no">No</option>\n+                <option value="key">Yes - Fill with Original Value</option>\n+                <option value="string">Yes - Fill with String</option>\n+            </param>\n+            <when value="no" />\n+            <when value="key" />\n+            <when value="string" >\n+                <param name="fill_string" type="text" value="NA" argument="--key-miss-repl" label="Fill string">\n+                    <expand macro="text_sanitizer" />\n+                </param>\n+            </when>\n+        </conditional>\n+        <expand macro="ignore_case" />\n+        <expand macro="global_parameters" />\n+    </inputs>\n+    <outputs>\n+        <data format_source="in_1" name="replaced" from_work_dir="replaced" label=\'${in_1.name} with column ${column_text.in_text} replaced\' />\n+    </outputs>\n+    <tests>\n+        <tes'..b'>\n+            <output name="replaced" value="replace_1.csv" />\n+        </test>\n+        <test>\n+            <param name="in_1" value="replace_input.csv" />\n+            <conditional name="column_text">\n+                <param name="select" value="string" />\n+                <param name="in_text" value="2" />\n+            </conditional>\n+            <param name="pattern_string" value=".+" />\n+            <param name="replacement_string" value="{kv}" />\n+            <param name="input_kv" value="kv.txt" />\n+            <conditional name="fill">\n+                <param name="how_fill" value="key" />\n+            </conditional>\n+            <output name="replaced" value="replace_2.csv" />\n+        </test>\n+    </tests>\n+    <help><![CDATA[\n+    \n+Csvtk - Replace Help\n+--------------------\n+\n+Info\n+####\n+Csvtk-replace is a tool that uses Regular Expressions (Regex) to match data in the specified column and replace it with the replacement string.\n+Non-matched columns can be kept or filled with the Regex key or an input string\n+\n+The regex input for this tool is structured such that your regular expression **does not** need to start with with quotes or brackets. You can\n+start your expression with a `^` or just go straight into it\n+\n+For example:\n+\n+::\n+\n+    Using `.+` as an input would be used in the code as \'(.+)\'\n+\n+    Using ^(.+)$ as an input would yield an input in the code as \'(^(.+)$)\'\n+\n+.. class:: warningmark\n+\n+    Single quotes are not allowed in text inputs!\n+\n+-----\n+\n+\n+@HELP_INPUT_DATA@\n+\n+\n+Usage\n+#####\n+You can use csvtk replace to any matched regex expressions with your input replacement string.\n+\n+The replacement string has some unique properties that you can use too to better replace your data:\n+\n+- Replacement supports capture variables, like $1 which represents the text of the first submatch of the Regex\n+\n+- \\{nr} can be used to assign ascending numbers starting from 1 to each column\n+\n+- \\{kv} can be used to get the value of the key (captured variable $n) or a key-value file\n+\n+A good Regular expressions cheat sheet that you can use to help yourself build regular expressions can be found at:\n+https://regexr.com/\n+\n+**Replace Examples**\n+\n+1. Replacement with {nr} and $1\n+\n+Input file:\n+\n++---------+--------+\n+| Name    | Animal |\n++=========+========+\n+| Bud     | Dog    |\n++---------+--------+\n+| Mittens | Cat    |\n++---------+--------+\n+\n+Now if our regex was set to \'.*\' on column 2 and our replacement string was set to \'{nr}-$1\', the following output would be observed:\n+\n++---------+--------+\n+| Name    | Animal |\n++=========+========+\n+| Bud     | 1-Dog  |\n++---------+--------+\n+| Mittens | 2-Cat  |\n++---------+--------+\n+\n+---------------\n+\n+2. Replacement with {kv} file\n+\n+Suppose you set up a key-value TAB separated file that looked as such:\n+\n+::\n+\n+    Key     Value\n+    Dog     Big\n+    Cat     Small\n+\n+And had a similar input file:\n+\n++---------+--------+\n+| Name    | Animal |\n++=========+========+\n+| Bud     | Dog    |\n++---------+--------+\n+| Mittens | Cat    |\n++---------+--------+\n+| Fuzzy   | Gerbil |\n++---------+--------+\n+\n+Now if the regex was \'.*\' on column 2 with the replacement string as \'{kv}\'. Your output would look as such with \'No\' fill specified:\n+\n++---------+--------+\n+| Name    | Animal |\n++=========+========+\n+| Bud     | Big    |\n++---------+--------+\n+| Mittens | Small  |\n++---------+--------+\n+| Fuzzy   |        |\n++---------+--------+\n+\n+If you wanted to fill the blank cell you could set it to either:\n+\n+- String - the string you input (ex. \'NA\') would fill up the blank cell.\n+\n+- Original value - would change the blank cell to \'Gerbil\'\n+\n+----\n+\n+If your having trouble with the regular expressions, please play around with a builder, there are many others online \n+and they are great resources to improve your regex statements or test them before use!\n+\n+----\n+\n+@HELP_END_STATEMENT@\n+\n+\n+    ]]></help>\n+    <expand macro="citations" />\n+</tool>\n\\ No newline at end of file\n'
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/Animals_More.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/Animals_More.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,10 @@
+Name,Animal,Random_Number
+Spots,Dog,1
+Fred,Dog,5
+Mittens,Cat,16
+Slippers,Cat,11
+Gravy,Cat,6
+Stripes,Zebra,7
+Muffin,Cat,7
+Earl,Dog,2
+Sir-Wags-A-Lot,Dog,44
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/XY_converted.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/XY_converted.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,12 @@
+X,Y
+1,2
+2,4
+4,8
+8,16
+16,32
+32,64
+64,128
+128,256
+256,512
+1024,2048
+2048,5096
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/XY_converted.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/XY_converted.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,12 @@
+X Y
+1 2
+2 4
+4 8
+8 16
+16 32
+32 64
+64 128
+128 256
+256 512
+1024 2048
+2048 5096
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/XY_with_break.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/XY_with_break.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,13 @@
+X,Y
+1,2
+2,4
+4,8
+8,16
+16,32
+32,64
+64,128
+128,256
+256,512
+,
+1024,2048
+2048,5096
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/XY_with_break.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/XY_with_break.tabular Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,13 @@
+X Y
+1 2
+2 4
+4 8
+8 16
+16 32
+32 64
+64 128
+128 256
+256 512
+
+1024 2048
+2048 5096
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/another.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/another.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Name,Food,Age
+Joe,Beets,33
+Steven,Eggplant,36
+Jacob,Kale,59
\ No newline at end of file
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/awk_mutate_input.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/awk_mutate_input.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Culture Label,Cell Count,Dilution
+ECo-1,2523,1000
+LPn-1,100,1000000
+LPn-2,4,1000
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/awk_mutate_output.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/awk_mutate_output.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Culture Label,Cell Count,Dilution,CFU/ml
+ECo-1,2523,1000,2523000
+LPn-1,100,1000000,100000000
+LPn-2,4,1000,4000
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/blood_type.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/blood_type.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,11 @@
+Name Blood_Type Favourite_Colour Height
+Darian AB Blue 175cm
+Fred AB- Orange 185cm
+Jacob AB Blue 160cm
+Adrian O Blue 2000cm
+Tim O- Green 20cm
+Matthew O Green 140cm
+Patrick O Green 1cm
+Chester O Blue 22cm
+Kim B Teal 11cm
+Sarah A Blue 123cm
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/collapsed.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapsed.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,7 @@
+Blood_Type Name
+AB- Fred
+AB Darian; Jacob
+O- Tim
+O Adrian; Matthew; Patrick; Chester
+B Kim
+A Sarah
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/concat_1.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/concat_1.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,11 @@
+Name,Colour,Food
+Eric,Blue,Apples
+Darian,Blue,Pancakes
+Daniel,Red,Apples
+Emily,Blue,Apples
+Fred,-,-
+Adrian,-,-
+Steven,-,-
+Joe,-,Beets
+Steven,-,Eggplant
+Jacob,-,Kale
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/concat_2.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/concat_2.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,11 @@
+Name,Colour,Food
+Eric,Blue,Apples
+Darian,Blue,Pancakes
+Daniel,Red,Apples
+Emily,Blue,Apples
+Fred,,
+Adrian,,
+Steven,,
+Joe,,Beets
+Steven,,Eggplant
+Jacob,,Kale
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/corr_1.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/corr_1.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,1 @@
+X,Y,0.9960
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/corr_2.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/corr_2.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,1 @@
+X Y 0.9997
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/csv-bob.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/csv-bob.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,2 @@
+Person,Favourite Food,Favourite Colour,Height,BloodType
+Bob,Protein,All of them,250cm,O-
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/csv-darian.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/csv-darian.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,2 @@
+Person,Favourite Food,Favourite Colour,Height,BloodType
+Darian,Potatos,Blue,175cm,O
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/csv-jack.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/csv-jack.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,2 @@
+Person,Favourite Food,Favourite Colour,Height,BloodType
+Jack,Pineapple,Off White,165cm,O
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/csv.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/csv.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Person,Favourite Food,Favourite Colour,Height,BloodType
+Jack,Pineapple,Off White,165cm,O
+Bob,Protein,All of them,250cm,O-
+Darian,Potatos,Blue,175cm,O
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/cut_1.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cut_1.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,33 @@
+Length,GC Content
+100,50.00
+100,50.05
+100,49.95
+110,50.60
+105,50.50
+101,49.05
+99,49.95
+95,50.95
+100,50.00
+100,50.00
+90,66.00
+100,66.60
+100,65.05
+101,65.95
+101,65.55
+99,66.00
+95,66.05
+100,66.55
+105,65.55
+100,65.55
+110,66.55
+110,70.00
+100,70.00
+90,45.65
+99,45.60
+99,45.50
+95,45.20
+95,45.55
+100,45.55
+100,45.20
+100,45.55
+100,45.50
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/cut_2.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cut_2.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,33 @@
+Group,GC Content
+A,50.00
+A,50.05
+A,49.95
+A,50.60
+A,50.50
+A,49.05
+A,49.95
+A,50.95
+A,50.00
+A,50.00
+B,66.00
+B,66.60
+B,65.05
+B,65.95
+B,65.55
+B,66.00
+B,66.05
+B,66.55
+B,65.55
+B,65.55
+B,66.55
+C,70.00
+C,70.00
+D,45.65
+D,45.60
+D,45.50
+D,45.20
+D,45.55
+D,45.55
+D,45.20
+D,45.55
+D,45.50
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/data.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/data.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Person,Height,Sport,Job
+Fred,140cm,Diving,Accountant
+Darian,175cm,Running,Student
+Jake,188cm,Shotput,Moving Heavy Objects
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/filtered.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtered.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Blood_Type Favourite_Colour frequency
+AB Blue 2
+O Green 2
+O Blue 2
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/frequency.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/frequency.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,8 @@
+Blood_Type Favourite_Colour frequency
+AB- Orange 1
+AB Blue 2
+O- Green 1
+O Green 2
+O Blue 2
+B Teal 1
+A Blue 1
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/gathered.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gathered.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Favourite Food,Favourite Colour,Height,BloodType,1,2
+Pineapple,Off White,165cm,O,Person,Jack
+Protein,All of them,250cm,O-,Person,Bob
+Potatos,Blue,175cm,O,Person,Darian
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/illegal.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/illegal.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,6 @@
+Test,A,B,C
+D,,S,C
+F,F,F,F
+F,F,F,
+TT,TT,TT,TT
+Agh,Ol,As,TT
\ No newline at end of file
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/illegal_collapse.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/illegal_collapse.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,5 @@
+C,Test
+C,D
+F,F
+,F
+TT,TT; Agh
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/joined.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/joined.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,2 @@
+Person,Favourite Food,Favourite Colour,Height,BloodType,Height,Sport,Job
+Darian,Potatos,Blue,175cm,O,175cm,Running,Student
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/joined_filled.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/joined_filled.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,6 @@
+Person,Favourite Food,Favourite Colour,Height,BloodType,Height,Sport,Job
+Jack,Pineapple,Off White,165cm,O,a,a,a
+Bob,Protein,All of them,250cm,O-,a,a,a
+Darian,Potatos,Blue,175cm,O,175cm,Running,Student
+Fred,a,a,a,a,140cm,Diving,Accountant
+Jake,a,a,a,a,188cm,Shotput,Moving Heavy Objects
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/kv.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/kv.txt Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,3 @@
+Key Value
+Dog Big
+Cat Small
\ No newline at end of file
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/line_all_param.png
b
Binary file test-data/line_all_param.png has changed
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/mutate_removed.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mutate_removed.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,11 @@
+Blood_Type Favourite_Colour Height new_column
+AB Blue 175cm Darian
+AB- Orange 185cm
+AB Blue 160cm
+O Blue 2000cm
+O- Green 20cm
+O Green 140cm
+O Green 1cm
+O Blue 22cm
+B Teal 11cm
+A Blue 123cm
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/mutated.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mutated.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,11 @@
+Name Blood_Type Favourite_Colour Height new_column
+Darian AB Blue 175cm Darian
+Fred AB- Orange 185cm Fred
+Jacob AB Blue 160cm Jacob
+Adrian O Blue 2000cm Adrian
+Tim O- Green 20cm Tim
+Matthew O Green 140cm Matthew
+Patrick O Green 1cm Patrick
+Chester O Blue 22cm Chester
+Kim B Teal 11cm Kim
+Sarah A Blue 123cm Sarah
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/other.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/other.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Name,Sport,Job
+Fred,Volleyball,Molecular Biologist
+Adrian,Basketball,Computational Biologist
+Steven,Football,Microbiologist
\ No newline at end of file
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/plot.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/plot.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,33 @@
+Group,Length,GC Content
+A,100,50.00
+A,100,50.05
+A,100,49.95
+A,110,50.60
+A,105,50.50
+A,101,49.05
+A,99,49.95
+A,95,50.95
+A,100,50.00
+A,100,50.00
+B,90,66.00
+B,100,66.60
+B,100,65.05
+B,101,65.95
+B,101,65.55
+B,99,66.00
+B,95,66.05
+B,100,66.55
+B,105,65.55
+B,100,65.55
+B,110,66.55
+C,110,70.00
+C,100,70.00
+D,90,45.65
+D,99,45.60
+D,99,45.50
+D,95,45.20
+D,95,45.55
+D,100,45.55
+D,100,45.20
+D,100,45.55
+D,100,45.50
\ No newline at end of file
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/plot.png
b
Binary file test-data/plot.png has changed
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/plot_box.png
b
Binary file test-data/plot_box.png has changed
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/plot_scatter.png
b
Binary file test-data/plot_scatter.png has changed
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/replace_1.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/replace_1.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Name,Animal
+Shirley,1-Dog
+Mittens,2-Cat
+Fuzzy,3-Chinchilla
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/replace_2.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/replace_2.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Name,Animal
+Shirley,Big
+Mittens,Small
+Fuzzy,Chinchilla
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/replace_input.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/replace_input.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,4 @@
+Name,Animal
+Shirley,Dog
+Mittens,Cat
+Fuzzy,Chinchilla
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/sampled_1.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sampled_1.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,16 @@
+Group,Length,GC Content
+A,100,50.00
+A,101,49.05
+A,100,50.00
+A,100,50.00
+B,90,66.00
+B,100,66.60
+B,101,65.55
+B,99,66.00
+B,105,65.55
+D,90,45.65
+D,99,45.60
+D,99,45.50
+D,95,45.20
+D,95,45.55
+D,100,45.20
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/sampled_2.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sampled_2.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,25 @@
+n,Group,Length,GC Content
+1,A,100,50.00
+4,A,110,50.60
+5,A,105,50.50
+6,A,101,49.05
+9,A,100,50.00
+10,A,100,50.00
+11,B,90,66.00
+12,B,100,66.60
+13,B,100,65.05
+14,B,101,65.95
+15,B,101,65.55
+16,B,99,66.00
+19,B,105,65.55
+20,B,100,65.55
+22,C,110,70.00
+24,D,90,45.65
+25,D,99,45.60
+26,D,99,45.50
+27,D,95,45.20
+28,D,95,45.55
+29,D,100,45.55
+30,D,100,45.20
+31,D,100,45.55
+32,D,100,45.50
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/separated_1.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/separated_1.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,7 @@
+Blood_Type 1 2
+AB- Fred NA
+AB Darian Jacob
+O- Tim NA
+O Adrian Matthew
+B Kim NA
+A Sarah NA
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/separated_2.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/separated_2.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,7 @@
+Blood_Type Name 1 2
+AB- Fred Fred N/A
+AB Darian; Jacob Darian Jacob
+O- Tim Tim N/A
+O Adrian; Matthew; Patrick; Chester Adrian Matthew; Patrick; Chester
+B Kim Kim N/A
+A Sarah Sarah N/A
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/sort_order.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sort_order.txt Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,3 @@
+Zebra
+Cat
+Dog
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/sorted_1.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sorted_1.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,10 @@
+Name,Animal,Random_Number
+Stripes,Zebra,7
+Mittens,Cat,16
+Slippers,Cat,11
+Muffin,Cat,7
+Gravy,Cat,6
+Sir-Wags-A-Lot,Dog,44
+Fred,Dog,5
+Earl,Dog,2
+Spots,Dog,1
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/test.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test.csv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,5 @@
+Name,Colour,Food
+Eric,Blue,Apples
+Darian,Blue,Pancakes
+Daniel,Red,Apples
+Emily,Blue,Apples
\ No newline at end of file
b
diff -r 000000000000 -r 1d4ee4308d99 test-data/uniq.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/uniq.tsv Tue May 19 17:16:05 2020 -0400
b
@@ -0,0 +1,8 @@
+Name Blood_Type Favourite_Colour Height
+Darian AB Blue 175cm
+Fred AB- Orange 185cm
+Adrian O Blue 2000cm
+Tim O- Green 20cm
+Matthew O Green 140cm
+Kim B Teal 11cm
+Sarah A Blue 123cm