comparison pre_process.xml @ 41:a16f33c6ca64 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb

40:80074b842ebd

<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@" profile="20.05">
    <description>raw feature vectors into standardized datasets</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />

        <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
from galaxy_ml.utils import read_columns, SafeEval


safe_eval = SafeEval()

res.to_csv(path_or_buf = "$outfile_transform", sep="\t",
           index=False, header=True if header else False)
#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>
        <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="5" />
        </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="5" />
        </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="5" />
        </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="5" />
        </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="5" />
        </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="5" />
        </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="5" />
        </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="5" />
        </test>
        <test>
            <param name="infile" value="regression_X.tabular" ftype="tabular" />
            <param name="header1" value="true" />
            <param name="selected_column_selector_option" value="all_columns" />

41:a16f33c6ca64

<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@" profile="@PROFILE@">
    <description>raw feature vectors into standardized datasets</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />

        <configfile name="pre_processor_script">
            <![CDATA[
import sys
import json
import pandas

from scipy.io import mmread
from scipy.io import mmwrite
from sklearn import preprocessing
from galaxy_ml.model_persist import dump_model_to_h5
from galaxy_ml.utils import read_columns, SafeEval


safe_eval = SafeEval()

res.to_csv(path_or_buf = "$outfile_transform", sep="\t",
           index=False, header=True if header else False)
#end if

#if $save:
dump_model_to_h5(estimator, "$outfile_fit")
#end if
        ]]>
        </configfile>
    </configfiles>
    <inputs>

        </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="h5mlm" 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="QuantileTransformer" />
            <param name="save" value="true" />
            <param name="random_state" value="200" />
            <param name="n_quantiles" value="10" />
            <param name="subsample" value="100" />
            <output name="outfile_transform" file="prp_result01" ftype="tabular" />
            <output name="outfile_fit" file="prp_model01" ftype="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </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="h5mlm" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="regression_X.tabular" ftype="tabular" />
            <param name="header1" value="true" />
            <param name="selected_column_selector_option" value="all_columns" />