def witnesscheck_test(): category_results_nowc = svcomp15.read_category('static/results-xml-raw', 'mixed-examples', False) category_results = svcomp15.read_category('static/results-xml-raw', 'mixed-examples', True) nt.assert_equal(category_results_nowc['smack'].iloc[0]['status'], svcomp15.Status.false) nt.assert_equal(category_results['smack'].iloc[0]['status'], svcomp15.Status.unknown) nt.assert_equal(category_results_nowc['cbmc'].iloc[0]['status'], svcomp15.Status.true) nt.assert_equal(category_results['cbmc'].iloc[0]['status'], svcomp15.Status.true)
def derive_total_benchmark_order_test(): category_results = svcomp15.read_category('static/results-xml-raw', 'mixed-examples') r = utils.derive_total_benchmark_order( category_results, 'static/sv-benchmarks/c/mixed-examples/data_structures_set_multi_proc_false-unreach-call_ground.i', svcomp15.compare_results) nt.assert_equal(r, ['cpachecker', 'smack', 'cbmc'])
def create_features_labels_df_test(): cr = svcomp15.read_category('static/results-xml-raw', 'mixed-examples') sourcefiles = {i for k in cr.keys() for i in cr[k].index} features_df = f.create_feature_df(sourcefiles) # RPC dataset ranking_df = ranking.create_ranking_df(cr, svcomp15.compare_results) features_ranking_df = f.create_features_labels_df(features_df, ranking_df) # Learning via Utility Functions datasets score_dfdict = classification.create_benchmark_score_dfdict(cr, svcomp15.score) features_score_dfdict = {b: f.create_features_labels_df(features_df, score_dfdict[b]) for b in score_dfdict.keys()} cputime_dfdict = regression.create_benchmark_cputime_dfdict(cr) features_cputime_dfdict = {b: f.create_features_labels_df(features_df, cputime_dfdict[b]) for b in cputime_dfdict.keys()}
def extract_ranking_df(xml_dir, category, max_size): results = svcomp15.read_category(xml_dir, category, max_size) return ranking.create_ranking_df(results, svcomp15.compare_results)
def create_benchmark_best_tool_df_test(): category_results = svcomp15.read_category('static/results-xml-raw', 'mixed-examples') df = classification.create_benchmark_best_tool_df(category_results, svcomp15.compare_results) df.to_csv('best_tool_df.csv')
def create_benchmark_cputime_df_test(): category_results = svcomp15.read_category('static/results-xml-raw', 'mixed-examples') df = regression.create_benchmark_cputime_dfdict(category_results) df['cbmc'].to_csv('cmbc_cputime_df.csv') df['cpachecker'].to_csv('cpachecker_cputime_df.csv') df['smack'].to_csv('smack_cputime_df.csv')
def create_benchmark_score_df_test(): category_results = svcomp15.read_category('static/results-xml-raw', 'mixed-examples') df = classification.create_benchmark_score_dfdict(category_results, svcomp15.score) df['cbmc'].to_csv('cmbc_score_df.csv') df['cpachecker'].to_csv('cpachecker_score_df.csv') df['smack'].to_csv('smack_score_df.csv')
def create_benchmark_ranking_df_test(): category_results = svcomp15.read_category('static/results-xml-raw', 'mixed-examples') df = ranking.create_ranking_df(category_results, svcomp15.compare_results) df.to_csv('ranking_df.csv')