def test_build_extraction_dataset(): if os.path.exists(os.path.join(TMP_DIR, 'extraction.data')): os.remove(os.path.join(TMP_DIR, 'extraction.data')) d.build_extraction_dataset(os.path.join(EMAILS_DIR, 'P'), os.path.join(TMP_DIR, 'extraction.data'), 1) test_data = SparseDataSet(os.path.join(TMP_DIR, 'extraction.data'), labelsColumn=-1) # the result is a loadable signature extraction dataset # 32 comes from 3 emails in emails/P folder, 11 lines checked to be # a signature, one email has only 10 lines eq_(test_data.size(), 32) eq_(len(features('')), test_data.numFeatures)