view pre_process.xml @ 19:f196d4715cfb draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit d00173591e4a783a4c1cb2664e4bb192ab5414f7

<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@">
    <description>raw feature vectors into standardized datasets</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command>
        <![CDATA[
        python "$pre_processor_script" '$inputs'
        ]]>
    </command>
    <configfiles>
        <inputs name="inputs" />
        <configfile name="pre_processor_script">
            <![CDATA[
import sys
import json
import pandas
import pickle
from scipy.io import mmread
from scipy.io import mmwrite
from sklearn import preprocessing

execfile("$__tool_directory__/utils.py")

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

#if $input_type.selected_input_type == "sparse":
X = mmread("$infile")
#else:
header = 'infer' if params["input_type"]["header1"] else None
column_option = params["input_type"]["column_selector_options_1"]["selected_column_selector_option"]
if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["input_type"]["column_selector_options_1"]["col1"]
else:
    c = None
X = read_columns(
        "$input_type.infile",
        c = c,
        c_option = column_option,
        sep='\t',
        header=header,
        parse_dates=True,
        encoding=None,
        index_col=None,
        tupleize_cols=False
)
#end if

preprocessor = params["input_type"]["pre_processors"]["selected_pre_processor"]
options = params["input_type"]["pre_processors"]["options"]

my_class = getattr(preprocessing, preprocessor)
estimator = my_class(**options)
estimator.fit(X)
result = estimator.transform(X)

#if $input_type.selected_input_type == "sparse":
with open("$outfile_transform", "w+") as transform_handler:
    mmwrite(transform_handler, result)
#else:
res = pandas.DataFrame(result)
res.to_csv(path_or_buf = "$outfile_transform", sep="\t", index=False, header=None)
#end if

#if $save:
with open("$outfile_fit", 'wb') as out_handler:
    pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)
#end if
        ]]>
        </configfile>
    </configfiles>
    <inputs>
        <conditional name="input_type">
            <param name="selected_input_type" type="select" label="Select the type of your input data:">
                <option value="tabular" selected="true">Tabular</option>
                <option value="sparse">Sparse</option>
            </param>
            <when value="tabular">
                <param name="infile" type="data" format="tabular" label="Select a tabular file you want to train your preprocessor on its data:" />
                <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
                <conditional name="column_selector_options_1">
                    <expand macro="samples_column_selector_options" multiple="true" column_option="selected_column_selector_option" col_name="col1" infile="infile"/>
                </conditional>
                <conditional name="pre_processors">
                    <expand macro="sparse_preprocessors_ext" />
                    <expand macro="sparse_preprocessor_options_ext" />
                </conditional>
            </when>
            <when value="sparse">
                <param name="infile" type="data" format="txt" label="Select a sparse representation you want to train your preprocessor on its data:"/>
                <conditional name="pre_processors">
                    <expand macro="sparse_preprocessors"/>
                    <expand macro="sparse_preprocessor_options"/>
                </conditional>
            </when>
        </conditional>
        <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolflase" checked="false"
            label="Save the preprocessor"
            help="Saves the preprocessor after fitting to the data. The preprocessor can then be passed to other tools and used in later operations."/>
    </inputs>
    <outputs>
        <data format="tabular" name="outfile_transform" from_work_dir="./output"/>
        <data format="zip" name="outfile_fit">
            <filter>save</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="KernelCenterer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result01" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model01" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="MinMaxScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result02" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model02" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="PolynomialFeatures"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result03" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model03" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="RobustScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result04" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model04" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Binarizer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result05" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Imputer"/>
            <param name="save" value="true"/>
            <param name="axis" value="true"/>
            <output name="outfile_transform" file="prp_result06" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model06" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_pre_processor" value="StandardScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result07" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model07" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="MaxAbsScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result08" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model08" ftype="zip" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Normalizer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result09" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="500"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

This tool provides several transformer classes to change raw feature vectors into a representation that is more suitable for the downstream estimators. The library is provided by sklearn.preprocessing package.

For information about preprocessing classes and parameter settings please refer to `Scikit-learn preprocessing`_.

.. _`Scikit-learn preprocessing`: http://scikit-learn.org/stable/modules/preprocessing.html
        ]]>
    </help>
    <expand macro="sklearn_citation"/>
</tool>