Mercurial > repos > pieterlukasse > prims_metabolomics
view test/test_combine_output.py @ 22:cd4f13119afa
Small fix in filters part and improvement in query_metexp time logging
author | pieter.lukasse@wur.nl |
---|---|
date | Thu, 06 Mar 2014 14:29:55 +0100 |
parents | 9d5f4f5f764b |
children |
line wrap: on
line source
''' Created on Mar 27, 2012 @author: marcelk ''' from GCMS import combine_output from pkg_resources import resource_filename # @UnresolvedImport # pylint: disable=E0611 import os import shutil import tempfile import unittest class Test(unittest.TestCase): ''' Tests for the 'combine_output' Galaxy tool ''' def setUp(self): self.rf_output = resource_filename(__name__, "data/RankFilter.txt") self.cl_output = resource_filename(__name__, "data/CasLookup.txt") def test_process_data(self): ''' Tests the processing of the RankFilter and CasLookup files into dictionaries ''' rfdata = combine_output._process_data(self.rf_output) cldata = combine_output._process_data(self.cl_output) self.assertEqual(set([' 18457-04-0', ' 55133-95-4', ' 58-08-2', ' 112-34-5']), set(rfdata['CAS'])) self.assertEqual(set(['C58082', 'C18457040', 'C55133954', 'C112345']), set(cldata['CAS'])) def test_add_hit(self): ''' Tests the combination of two records from both the RankFilter- and CasLookup-tools ''' rfdata = combine_output._process_data(self.rf_output) cldata = combine_output._process_data(self.cl_output) index = 0 rf_record = dict(zip(rfdata.keys(), [rfdata[key][index] for key in rfdata.keys()])) cl_record = dict(zip(cldata.keys(), [cldata[key][index] for key in cldata.keys()])) hit = combine_output._add_hit(rf_record, cl_record) self.assertEqual(len(hit), 27) # Pass empty record, should fail combination self.assertRaises(KeyError, combine_output._add_hit, rf_record, {}) def test_merge_data(self): ''' Tests the merging of the RankFilter and CasLookup data ''' rfdata = combine_output._process_data(self.rf_output) cldata = combine_output._process_data(self.cl_output) merged, _ = combine_output._merge_data(rfdata, cldata) centrotypes = _get_centrotypes(merged) self.failUnless(all(centrotype in centrotypes for centrotype in ('2716','12723', '3403', '12710'))) def _get_centrotypes(merged): ''' returns centrotype codes found in merged set ''' result = [] for item_idx in xrange(len(merged)): item = merged[item_idx] centrotype = item[0][0] result.append(centrotype) return result def test_remove_formula(self): ''' Tests the removal of the Formula from the 'Name' field (RankFilter output) ''' name = "Caffeine C8H10N4O2" compound_name, compound_formula = combine_output._remove_formula(name) self.assertEqual(compound_name, 'Caffeine') self.assertEqual(compound_formula, 'C8H10N4O2') name = "Ethanol C2H6O" compound_name, compound_formula = combine_output._remove_formula(name) self.assertEqual(compound_name, 'Ethanol') self.assertEqual(compound_formula, 'C2H6O') # No formula to remove name = "Butanoic acid, 4-[(trimethylsilyl)oxy]-, trimethylsilyl ester" compound_name, compound_formula = combine_output._remove_formula(name) self.assertEqual(compound_name, name) self.assertEqual(compound_formula, False) def test_save_data(self): ''' Tests the creation of the output tabular files (no content testing) ''' temp_folder = tempfile.mkdtemp(prefix='gcms_combine_output_') saved_single_data = '{0}/{1}'.format(temp_folder, 'output_single.tsv') saved_multi_data = '{0}/{1}'.format(temp_folder, 'output_multi.tsv') rfdata = combine_output._process_data(self.rf_output) cldata = combine_output._process_data(self.cl_output) merged, nhits = combine_output._merge_data(rfdata, cldata) combine_output._save_data(merged, nhits, saved_single_data, saved_multi_data) self.failUnless(os.path.exists(saved_single_data)) self.failUnless(os.path.exists(saved_multi_data)) shutil.rmtree(temp_folder) if __name__ == "__main__": #import sys;sys.argv = ['', 'Test.testName'] unittest.main()