comparison numeric_clustering.xml @ 13:40f3318b61c2 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 5d71c93a3dd804b1469852240a86021ab9130364

12:3bd31820d63e

import sklearn.cluster
import pandas
from sklearn import metrics
from scipy.io import mmread

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

selected_algorithm = params["input_types"]["algorithm_options"]["selected_algorithm"]

#if $input_types.selected_input_type == "sparse":
data_matrix = mmread(open("$infile", 'r'))
#else:
data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )

start_column = $input_types.start_column
end_column = $input_types.end_column

if end_column and start_column:
    if  end_column >= start_column:
        data_matrix = data.values[:, start_column-1:end_column]
    else:
        data_matrix = data.values
else:
    data_matrix = data.values
#end if

prediction = cluster_object.fit_predict( data_matrix )

if len(np.unique(prediction)) > 1:

                <param name="infile" type="data" format="txt" label="Sparse vector (scipy.sparse.csr_matrix) file:" help="The following clustering algorithms support sparse matrix operations: ''Birch'', ''DBSCAN'', ''KMeans'', ''Mini BatchK Means'', and ''Spectral Clustering''. If your data is in tabular format, please use other clustering algorithms."/>
                <expand macro="clustering_algorithms_options"/>
            </when>
            <when value="tabular">
                <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>
                <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />
                <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />
                <!--expand macro="clustering_algorithms_options"-->
                <conditional name="algorithm_options">
                    <param name="selected_algorithm" type="select" label="Clustering Algorithm">
                        <option value="AgglomerativeClustering">Hierarchical Agglomerative Clustering</option>
                        <option value="AffinityPropagation">Affinity Propagation</option>

    <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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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>
        <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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="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="start_column" value="2" />
            <param name="end_column" value="4" />
            <param name="batch_size" value="10"/>
            <param name="n_clusters" value="4"/>
            <param name="random_state" value="100"/>
            <param name="reassignment_ratio" value="1.0"/>
            <output name="outfile" file="cluster_result15.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="start_column" value="1" />
            <param name="end_column" value="1" />
            <param name="n_clusters" value="4" />
            <param name="random_state" value="100"/>
            <output name="outfile" file="cluster_result16.txt"/>
        </test>
        <test>

13:40f3318b61c2

import sklearn.cluster
import pandas
from sklearn import metrics
from scipy.io import mmread

@COLUMNS_FUNCTION@

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

selected_algorithm = params["input_types"]["algorithm_options"]["selected_algorithm"]

#if $input_types.selected_input_type == "sparse":
data_matrix = mmread(open("$infile", 'r'))
#else:
data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
header = 'infer' if params["input_types"]["header"] else None
column_option = params["input_types"]["column_selector_options"]["selected_column_selector_option"]
if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["input_types"]["column_selector_options"]["col"]
else:
    c = None
data_matrix = read_columns(
    "$infile",
    c = c,
    c_option = column_option,
    sep='\t',
    header=header,
    parse_dates=True,
    encoding=None,
    tupleize_cols=False
)
#end if

prediction = cluster_object.fit_predict( data_matrix )

if len(np.unique(prediction)) > 1:

                <param name="infile" type="data" format="txt" label="Sparse vector (scipy.sparse.csr_matrix) file:" help="The following clustering algorithms support sparse matrix operations: ''Birch'', ''DBSCAN'', ''KMeans'', ''Mini BatchK Means'', and ''Spectral Clustering''. If your data is in tabular format, please use other clustering algorithms."/>
                <expand macro="clustering_algorithms_options"/>
            </when>
            <when value="tabular">
                <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>
                <param name="header" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="True" label="Does the dataset contain header:" />
                <conditional name="column_selector_options">
                    <expand macro="samples_column_selector_options" col_name="col" multiple="true" infile="infile"/>
                </conditional>
                <!--expand macro="clustering_algorithms_options"-->
                <conditional name="algorithm_options">
                    <param name="selected_algorithm" type="select" label="Clustering Algorithm">
                        <option value="AgglomerativeClustering">Hierarchical Agglomerative Clustering</option>
                        <option value="AffinityPropagation">Affinity Propagation</option>

    <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>
        <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"/>
            <param name="reassignment_ratio" value="1.0"/>
            <output name="outfile" file="cluster_result15.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="1" />
            <param name="n_clusters" value="4" />
            <param name="random_state" value="100"/>
            <output name="outfile" file="cluster_result16.txt"/>
        </test>
        <test>