Mercurial > repos > bgruening > numeric_clustering

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

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/numeric_clustering commit adf077b912ddebd97b07b947b855cdd2862ed8ef-dirty
author bgruening
date Fri, 01 Jan 2016 18:00:23 -0500
parents 6bfbaf81b8f4
children
comparison
equal deleted inserted replaced
3:6bfbaf81b8f4 4:7c1794e0f9c2
74 import json 74 import json
75 import numpy as np 75 import numpy as np
76 import sklearn.cluster 76 import sklearn.cluster
77 import pandas 77 import pandas
78 78
79 data = pandas.read_csv("$infile", sep='\t', header=0, index_col=0, parse_dates=True, encoding=None, tupleize_cols=False ) 79 data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
80 my_class = getattr(sklearn.cluster, "$algorithm_options.selected_algorithm") 80 my_class = getattr(sklearn.cluster, "$algorithm_options.selected_algorithm")
81 cluster_object = my_class() 81 cluster_object = my_class()
82 82
83 params = json.loads( sys.argv[1] ) 83 params = json.loads( sys.argv[1] )
84 cluster_object.set_params(**params) 84 cluster_object.set_params(**params)
91 91
92 #else: 92 #else:
93 data_matrix = data.values 93 data_matrix = data.values
94 #end if 94 #end if
95 prediction = cluster_object.fit_predict( data_matrix ) 95 prediction = cluster_object.fit_predict( data_matrix )
96 data[len(data.columns)] = prediction 96 prediction_df = pandas.DataFrame(prediction)
97 data.to_csv(path_or_buf = "$outfile", sep="\t") 97 res = pandas.concat([data, prediction_df], axis=1)
98 res.to_csv(path_or_buf = "$outfile", sep="\t", index=False)
98 ]]> 99 ]]>
99 </configfile> 100 </configfile>
100 </configfiles> 101 </configfiles>
101 <inputs> 102 <inputs>
102 <param name="infile" type="data" format="tabular" label="Data file with numeric values" /> 103 <param name="infile" type="data" format="tabular" label="Data file with numeric values" />
296 <param name="selected_algorithm" value="AgglomerativeClustering"/> 297 <param name="selected_algorithm" value="AgglomerativeClustering"/>
297 <param name="start_column" value="2" /> 298 <param name="start_column" value="2" />
298 <param name="end_column" value="4" /> 299 <param name="end_column" value="4" />
299 <param name="affinity" value="euclidean"/> 300 <param name="affinity" value="euclidean"/>
300 <param name="linkage" value="average"/> 301 <param name="linkage" value="average"/>
302 <param name="n_clusters" value="4"/>
301 <output name="outfile" file="cluster_result10.txt"/> 303 <output name="outfile" file="cluster_result10.txt"/>
302 </test> 304 </test>
303 <test> 305 <test>
304 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 306 <param name="infile" value="numeric_values.tabular" ftype="tabular"/>
305 <param name="selected_algorithm" value="AgglomerativeClustering"/> 307 <param name="selected_algorithm" value="AgglomerativeClustering"/>