comparison numeric_clustering.xml @ 40:06d772036a62 draft

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

39:7dd3fb35904f

<tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="20.05">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />

cluster_object.set_params(**options)
if 'n_jobs' in cluster_object.get_params():
    cluster_object.set_params( n_jobs=N_JOBS )

#if $input_types.selected_input_type == "sparse":
data_matrix = mmread("$infile")
#else:
data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None)
header = 'infer' if params["input_types"]["header"] else None
column_option = params["input_types"]["column_selector_options"]["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_types"]["column_selector_options"]["col"]
else:

    <tests>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_algorithm" value="KMeans" />
            <param name="col" value="2,3,4" />
            <param name="n_clusters" value="4" />
            <param name="init" value="k-means++" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result01.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="KMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="n_clusters" value="4" />
            <param name="init" value="random" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result02.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="DBSCAN" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="algorithm" value="kd_tree" />
            <param name="leaf_size" value="10" />
            <param name="eps" value="1.0" />
            <output name="outfile" file="cluster_result03.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="Birch" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="n_clusters" value="4" />
            <param name="threshold" value="0.008" />
            <output name="outfile" file="cluster_result04.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="Birch" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="branching_factor" value="20" />
            <output name="outfile" file="cluster_result05.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AffinityPropagation" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="affinity" value="euclidean" />
            <param name="copy" value="false" />
            <output name="outfile" file="cluster_result06.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AffinityPropagation" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="damping" value="0.8" />
            <output name="outfile" file="cluster_result07.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MeanShift" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="min_bin_freq" value="3" />
            <output name="outfile" file="cluster_result08.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MeanShift" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="cluster_all" value="False" />
            <output name="outfile" file="cluster_result09.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AgglomerativeClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="affinity" value="euclidean" />
            <param name="linkage" value="average" />
            <param name="n_clusters" value="4" />
            <output name="outfile" file="cluster_result10.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AgglomerativeClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="linkage" value="complete" />
            <param name="n_clusters" value="4" />
            <output name="outfile" file="cluster_result11.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="SpectralClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="eigen_solver" value="arpack" />
            <param name="n_neighbors" value="12" />
            <param name="n_clusters" value="4" />
            <param name="assign_labels" value="discretize" />
            <param name="random_state" value="100" />

        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="SpectralClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="assign_labels" value="discretize" />
            <param name="random_state" value="100" />
            <param name="degree" value="2" />
            <output name="outfile" file="cluster_result13.txt" compare="sim_size" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MiniBatchKMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="tol" value="0.5" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result14.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MiniBatchKMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="n_init" value="5" />
            <param name="col" value="2,3,4" />
            <param name="batch_size" value="10" />
            <param name="n_clusters" value="4" />
            <param name="random_state" value="100" />

        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="KMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="1" />
            <param name="n_clusters" value="4" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result16.txt" />
        </test>

40:06d772036a62

<tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="@PROFILE@">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />

cluster_object.set_params(**options)
if 'n_jobs' in cluster_object.get_params():
    cluster_object.set_params( n_jobs=N_JOBS )

header = None
#if $input_types.selected_input_type == "sparse":
data_matrix = mmread("$infile")
#else:
data = pandas.read_csv("$infile", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None)

header = 'infer' if params["input_types"]["header"] else None
column_option = params["input_types"]["column_selector_options"]["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_types"]["column_selector_options"]["col"]
else:

    <tests>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_algorithm" value="KMeans" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="n_clusters" value="4" />
            <param name="init" value="k-means++" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result01.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="KMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="n_clusters" value="4" />
            <param name="init" value="random" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result02.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="DBSCAN" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="algorithm" value="kd_tree" />
            <param name="leaf_size" value="10" />
            <param name="eps" value="1.0" />
            <output name="outfile" file="cluster_result03.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="Birch" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="n_clusters" value="4" />
            <param name="threshold" value="0.008" />
            <output name="outfile" file="cluster_result04.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="Birch" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="branching_factor" value="20" />
            <output name="outfile" file="cluster_result05.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AffinityPropagation" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="affinity" value="euclidean" />
            <param name="copy" value="false" />
            <output name="outfile" file="cluster_result06.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AffinityPropagation" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="damping" value="0.8" />
            <output name="outfile" file="cluster_result07.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MeanShift" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="min_bin_freq" value="3" />
            <output name="outfile" file="cluster_result08.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MeanShift" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="cluster_all" value="False" />
            <output name="outfile" file="cluster_result09.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AgglomerativeClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="affinity" value="euclidean" />
            <param name="linkage" value="average" />
            <param name="n_clusters" value="4" />
            <output name="outfile" file="cluster_result10.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="AgglomerativeClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="linkage" value="complete" />
            <param name="n_clusters" value="4" />
            <output name="outfile" file="cluster_result11.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="SpectralClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="header" value="false" />
            <param name="eigen_solver" value="arpack" />
            <param name="n_neighbors" value="12" />
            <param name="n_clusters" value="4" />
            <param name="assign_labels" value="discretize" />
            <param name="random_state" value="100" />

        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="SpectralClustering" />
            <param name="selected_input_type" value="tabular" />
            <param name="col" value="2,3,4" />
            <param name="header" value="false" />
            <param name="assign_labels" value="discretize" />
            <param name="random_state" value="100" />
            <param name="degree" value="2" />
            <output name="outfile" file="cluster_result13.txt" compare="sim_size" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MiniBatchKMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="2,3,4" />
            <param name="tol" value="0.5" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result14.txt" />
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="MiniBatchKMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="n_init" value="5" />
            <param name="col" value="2,3,4" />
            <param name="batch_size" value="10" />
            <param name="n_clusters" value="4" />
            <param name="random_state" value="100" />

        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular" />
            <param name="selected_algorithm" value="KMeans" />
            <param name="selected_input_type" value="tabular" />
            <param name="header" value="false" />
            <param name="col" value="1" />
            <param name="n_clusters" value="4" />
            <param name="random_state" value="100" />
            <output name="outfile" file="cluster_result16.txt" />
        </test>