comparison numeric_clustering.xml @ 4:7c1794e0f9c2 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/numeric_clustering commit adf077b912ddebd97b07b947b855cdd2862ed8ef-dirty

3:6bfbaf81b8f4

import json
import numpy as np
import sklearn.cluster
import pandas

data = pandas.read_csv("$infile", sep='\t', header=0, index_col=0, parse_dates=True, encoding=None, tupleize_cols=False )
my_class = getattr(sklearn.cluster, "$algorithm_options.selected_algorithm")
cluster_object = my_class()

params = json.loads( sys.argv[1] )
cluster_object.set_params(**params)

#else:
data_matrix = data.values
#end if
prediction = cluster_object.fit_predict( data_matrix )
data[len(data.columns)] = prediction
data.to_csv(path_or_buf = "$outfile", sep="\t")
]]>
        </configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="tabular" label="Data file with numeric values" />

            <param name="selected_algorithm" value="AgglomerativeClustering"/>
            <param name="start_column" value="2" />
            <param name="end_column" value="4" />
            <param name="affinity" value="euclidean"/>
            <param name="linkage" value="average"/>
            <output name="outfile" file="cluster_result10.txt"/>
        </test>
        <test>
            <param name="infile" value="numeric_values.tabular" ftype="tabular"/>
            <param name="selected_algorithm" value="AgglomerativeClustering"/>

4:7c1794e0f9c2

import json
import numpy as np
import sklearn.cluster
import pandas

data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
my_class = getattr(sklearn.cluster, "$algorithm_options.selected_algorithm")
cluster_object = my_class()

params = json.loads( sys.argv[1] )
cluster_object.set_params(**params)

#else:
data_matrix = data.values
#end if
prediction = cluster_object.fit_predict( data_matrix )
prediction_df = pandas.DataFrame(prediction)
res = pandas.concat([data, prediction_df], axis=1)
res.to_csv(path_or_buf = "$outfile", sep="\t", index=False)
]]>
        </configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="tabular" label="Data file with numeric values" />

            <param name="selected_algorithm" value="AgglomerativeClustering"/>
            <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"/>