comparison discriminant.xml @ 41:d769d83ec796 draft

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

40:4335cec181ba

<tool id="sklearn_discriminant_classifier" name="Discriminant Analysis" version="@VERSION@" profile="20.05">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
        <!--macro name="priors"-->
    </macros>

import pandas
import pickle
import sklearn.discriminant_analysis
import sys

from galaxy_ml.utils import load_model, get_X_y


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

#if $selected_tasks.selected_task == "load":

with open("$infile_model", 'rb') as model_handler:
    classifier_object = load_model(model_handler)

header = 'infer' if params["selected_tasks"]["header"] else None
data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None)
prediction = classifier_object.predict(data)
prediction_df = pandas.DataFrame(prediction)

selected_algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"]

my_class = getattr(sklearn.discriminant_analysis, selected_algorithm)
classifier_object = my_class(**options)
classifier_object.fit(X, y)
with open("$outfile_fit", 'wb') as out_handler:
    pickle.dump(classifier_object, out_handler, pickle.HIGHEST_PROTOCOL)

#end if
]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="sl_Conditional" model="zip">
            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="LinearDiscriminantAnalysis" selected="true">Linear Discriminant Classifier</option>
                <option value="QuadraticDiscriminantAnalysis">Quadratic Discriminant Classifier</option>
            </param>
            <when value="LinearDiscriminantAnalysis">

    <expand macro="output" />
    <tests>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis" />
            <param name="solver" value="svd" />

            <output name="outfile_fit" file="lda_model01" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis" />
            <param name="solver" value="lsqr" />
            <output name="outfile_fit" file="lda_model02" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="QuadraticDiscriminantAnalysis" />
            <output name="outfile_fit" file="qda_model01" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile_model" value="lda_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="lda_prediction_result01.tabular" />
        </test>
        <test>
            <param name="infile_model" value="lda_model02" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="lda_prediction_result02.tabular" />
        </test>
        <test>
            <param name="infile_model" value="qda_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="qda_prediction_result01.tabular" />
        </test>
    </tests>
    <help><![CDATA[

41:d769d83ec796

<tool id="sklearn_discriminant_classifier" name="Discriminant Analysis" version="@VERSION@" profile="@PROFILE@">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
        <!--macro name="priors"-->
    </macros>

import pandas
import pickle
import sklearn.discriminant_analysis
import sys

from galaxy_ml.model_persist import dump_model_to_h5, load_model_from_h5
from galaxy_ml.utils import clean_params, get_X_y


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

#if $selected_tasks.selected_task == "load":

classifier_object = load_model_from_h5('$infile_model')
classifier_object = clean_params(classifier_object)

header = 'infer' if params["selected_tasks"]["header"] else None
data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None)
prediction = classifier_object.predict(data)
prediction_df = pandas.DataFrame(prediction)

selected_algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"]

my_class = getattr(sklearn.discriminant_analysis, selected_algorithm)
classifier_object = my_class(**options)
classifier_object.fit(X, y)
dump_model_to_h5(classifier_object, '$outfile_fit')

#end if
]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="sl_Conditional" model="h5mlm">
            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="LinearDiscriminantAnalysis" selected="true">Linear Discriminant Classifier</option>
                <option value="QuadraticDiscriminantAnalysis">Quadratic Discriminant Classifier</option>
            </param>
            <when value="LinearDiscriminantAnalysis">

    <expand macro="output" />
    <tests>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis" />
            <param name="solver" value="svd" />

            <output name="outfile_fit" file="lda_model01" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis" />
            <param name="solver" value="lsqr" />
            <output name="outfile_fit" file="lda_model02" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="QuadraticDiscriminantAnalysis" />
            <output name="outfile_fit" file="qda_model01" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile_model" value="lda_model01" ftype="h5mlm" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="lda_prediction_result01.tabular" />
        </test>
        <test>
            <param name="infile_model" value="lda_model02" ftype="h5mlm" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="lda_prediction_result02.tabular" />
        </test>
        <test>
            <param name="infile_model" value="qda_model01" ftype="h5mlm" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="qda_prediction_result01.tabular" />
        </test>
    </tests>
    <help><![CDATA[