annotate netcdf_read.xml @ 0:8da8ec7da45f draft default tip

Uploaded

<tool id="netcdf_read" name="Netcdf Reader" version="0.2.0">
    <description>extracts variable values with custom conditions on dimensions</description>
    <requirements>
        <requirement type="package" version="2.1.0">matplotlib</requirement>
        <requirement type="package" version="1.3.1">netCDF4</requirement>
        <requirement type="package" version="1.0.0">scipy</requirement>
        <requirement type="package" version="1.1.0">datamash</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
    mkdir output_dir && 

    #if $condi_source_coord.coord_source=="coord_from_file"
        i=0 &&
        re='^[-+]?[0-9]+\.?[0-9]*$' && 
        while read line; do 
            lat=\$(echo \$line | cut -d' ' -f1) 
            lon=\$(echo \$line | cut -d' ' -f2)
            && 
            if ! [[ \$lat =~ \$re ]] || ! [[ \$lon =~ \$re ]] ; then continue ;fi
            &&
            i=\$((\$i+1)) &&
            python '$__tool_directory__/netcdf_read.py' '$input' '$var_tab' $var
            #for $i,$uc in enumerate($user_choice)
                #if $uc.condi_between.comparator=="bi"
                    ${uc.dim} ${uc.condi_between.comparator} ${uc.condi_between.t1}-${uc.condi_between.t2}
                #elif $uc.condi_between.comparator=="be"
                    ${uc.dim} ${uc.condi_between.comparator} ${uc.condi_between.t1}-${uc.condi_between.t2}
                #else
                    ${uc.dim} ${uc.condi_between.comparator} ${uc.condi_between.value}
                #end if
            #end for   
            '$condi_source_coord.lat_dim'
            \$lat
            '$condi_source_coord.lon_dim'
            \$lon
        
            &&
            cat 'header' | sed 's/array(\[//g' | sed 's/], dtype=float32)//g'| sed 's/,\s/_/g' | sed 's/(//g' | sed 's/)//g' > 'header_cleaned'
            &&
            cat 'header_cleaned' 'sortie.tabular' > 'supersortie.tabular'
            &&
            datamash transpose < 'supersortie.tabular' > 'supersortie_transposed.tabular'
            &&
            sed -i 's/_/\t/g' 'supersortie_transposed.tabular'
            &&
            cat 'header_names' 'supersortie_transposed.tabular' | sed 's/\s/\t/g' > 'output_dir/coord'\$i'.tabular'; 
        done<'$coord_tabular'

    #else

        python '$__tool_directory__/netcdf_read.py' '$input' '$var_tab' $var
        #for $i,$uc in enumerate($user_choice)
            #if $uc.condi_between.comparator=="bi"
                ${uc.dim} ${uc.condi_between.comparator} ${uc.condi_between.t1}-${uc.condi_between.t2}
            #elif $uc.condi_between.comparator=="be"
                ${uc.dim} ${uc.condi_between.comparator} ${uc.condi_between.t1}-${uc.condi_between.t2}
            #else
                ${uc.dim} ${uc.condi_between.comparator} ${uc.condi_between.value}
            #end if
        #end for
        #if $condi_source_coord.condi_coord.coord=='yes_cust_coord'
            $condi_source_coord.condi_coord.lat_dim $condi_source_coord.condi_coord.lat_val $condi_source_coord.condi_coord.lon_dim $condi_source_coord.condi_coord.lon_val
        #end if
        &&
        cat 'header' | sed 's/array(\[//g' | sed 's/], dtype=float32)//g'| sed 's/,\s/_/g' | sed 's/(//g' | sed 's/)//g' > 'header_cleaned'
        &&
        cat 'header_cleaned' 'sortie.tabular' > 'supersortie.tabular'
        &&
        datamash transpose < 'supersortie.tabular' > 'supersortie_transposed.tabular'
        &&
        sed -i 's/_/\t/g' 'supersortie_transposed.tabular'
        &&
        cat 'header_names' 'supersortie_transposed.tabular' | sed 's/\s/\t/g' > 'final.tabular'

    #end if


    ]]></command>
    <inputs>
        <param type="data" name="input" label="Input netcdf file" format="netcdf,h5"/>
        <param type="data" label="Tabular of variables" name="var_tab" format="tabular" help="Select the tabular file which summarize the available variables and dimensions."/>

        <param name="var" type="select" label="Chose the variable to extract">
            <options from_dataset="var_tab">
                <column name="name" index="0"/>
                <column name="value" index="0"/>
                <column name="n_dim" index="1"/>
            </options>
        </param>

        <conditional name="condi_source_coord">
            <param name="coord_source" type="select" label="Source of coordinates">
                <option value="coord_from_file">Use coordinates from input file</option>
                <option value="coord_from_stdin">Manually enter coordinate</option>
            </param>

            <when value="coord_from_file">
                <param type="data" label="Tabular of coord" name="coord_tabular" format="tabular" help="Format : Latitude	Longitude"/>
                <param name="lat_dim" type="select" label="Select latitude" >
                    <options from_dataset="var_tab">
                        <column name="value" index="0"/>
                    </options>
                </param>
                <param name="lon_dim" type="select" label="Select longitude" >
                    <options from_dataset="var_tab">
                        <column name="value" index="0"/>
                    </options>
                </param>
            </when>

            <when value="coord_from_stdin">
                <conditional name="condi_coord">
                    <param name="coord" type="boolean" label="Search values for custom coordinates" truevalue="yes_cust_coord" checked="true" falsevalue="nope" help="Use this option to get valid values at your custom coordinates. If only NA values are availables the tool will search for the next closest coordinate until valid values."/>
                    <when value="yes_cust_coord">
                        <param name="lat_dim" type="select" label="Select latitude" >
                            <options from_dataset="var_tab">
                                <column name="value" index="0"/>
                            </options>
                        </param>
                        <param name="lat_val" type="float" value="0" label="Latitude"/>
                        <param name="lon_dim" type="select" label="Select longitude" >
                            <options from_dataset="var_tab">
                                <column name="value" index="0"/>
                            </options>
                        </param>
                        <param name="lon_val" type="float" value="0" label="Longitude"/>
                    </when>

                    <when value="nope"></when>
                </conditional>
            </when>

        </conditional>

        <repeat name="user_choice" title="Filter">
            <param name="dim" type="select" label="Dimensions">
                <options from_dataset="var_tab">
                    <column name="value" index="0"/>
                </options>
            </param>
            <conditional name="condi_between">
                <param name="comparator" type="select" label="Comparator">
                    <option value="e">Equal</option>
                    <option value="g">Greater</option>
                    <option value="ge">Greater or equal</option>
                    <option value="l">Less</option>
                    <option value="le">Less or equal</option>
                    <option value="be">Between-exclude ]threshold1,threshold2[</option>
                    <option value="bi">Between-include [threshold1,threshold2]</option>
                </param>
                <when value="bi">
                    <param name="t1" type="float" value="0" label="Inferior threshold"/>
                    <param name="t2" type="float" value="0" label="Superior threshold"/>
                </when>
                <when value="be">
                    <param name="t1" type="float" value="0" label="Inferior threshold"/>
                    <param name="t2" type="float" value="0" label="Superior threshold"/>
                </when>
                <when value="e">
                    <param name="value" type="float" value="0" label="Value"/>
                </when>
                <when value="g">
                    <param name="value" type="float" value="0" label="Value"/>
                </when>
                <when value="ge">
                    <param name="value" type="float" value="0" label="Value"/>
                </when>
                <when value="l">
                    <param name="value" type="float" value="0" label="Value"/>
                </when>
                <when value="le">
                    <param name="value" type="float" value="0" label="Value"/>
                </when>
            </conditional>
        </repeat>

    </inputs>        

    <outputs>
        <collection type="list" name="output">
            <discover_datasets pattern="__designation_and_ext__" visible="false" format="tabular" directory="output_dir"/>
            <filter>condi_source_coord['coord_source'] == 'coord_from_file'</filter>
        </collection>
        <data name="simpleoutput" from_work_dir="final.tabular" format="tabular">
            <filter>condi_source_coord['coord_source'] == 'coord_from_stdin'</filter>
        </data>
    </outputs>


    <tests>
        <test>
             <param name="input" value="dataset-ibi-reanalysis-bio-005-003-monthly-regulargrid_1510914389133.nc"/>
             <param name="var_tab" value="var_tab_dataset-ibi"/>
             <param name="var" value="phy"/>
             <param name="dim_tab" value="tab_dim_phy_dataset-ibi"/>
             <param name="coord" value="yes_cut_coord"/>
             <param name="lat_dim" value="latitude"/>
             <param name="lat_val" value="44.0"/>
             <param name="lon_dim" value="longitude"/>
             <param name="lon_val" value="-2.0"/>
             <param name="output" value="Test1.tabular"/>
        </test>
        <test>
             <param name="input" value="dataset-ibi-reanalysis-bio-005-003-monthly-regulargrid_1510914389133.nc"/>
             <param name="var_tab" value="var_tab_dataset-ibi"/>
             <param name="var" value="nh4"/>
             <param name="dim_tab" value="tab_dim_nh4_dataset-ibi"/>
             <param name="coord" value="nope"/>
             <param name="dim" value="time"/>
             <param name="comparator" value="e"/>
             <param name="value" value="7272.0"/>
             <param name="dim" value="latitude"/>
             <param name="comparator" value="ge"/>
             <param name="value" value="45.0"/>
             <param name="output" value="Test2.tabular"/>
        </test>




    </tests>

    <help><![CDATA[
**What it does**

This tool extracts variable values with custom conditions on dimensions.

It can use manualy given coordinates or automaticaly take them from a tabular file to filter informations.

If no values are availables at a coordinate X, the tool will search the closest coordinate with a non NA value.

Filter can be set on every dimension. Available filtering operations are : =, >, <, >=, <=, [interval], ]interval[.



**Input**

A netcdf file (.nc).

Variable tabular file from 'Netcdf Metadate Info'.

Tabular file with coordinates and the following structure : 'lat'	'lon'.


**Outputs**

A single output with values for the wanted variable if there is only one coordinate.

A data collection where one file is created for every coordinate, if multiple coordinates from tabular file.


------------------------------------------------- 

The Netcdf Read tool can be used after the Netcdf Info. 
    ]]></help>
</tool>