bechmark_result = []
for dataset, setting in benchmark_settings.items():
print('\n=== Evaluation on %s ===' % dataset)
indir = os.path.join(input_dir, os.path.dirname(setting['log_file']))
log_file = os.path.basename(setting['log_file'])
parser = LenMa.LogParser(log_format=setting['log_format'],
indir=indir,
outdir=output_dir,
rex=setting['regex'],
threshold=setting['threshold'])
parser.parse(log_file)
accuracy_PA, accuracy_exact_string_matching, edit_distance_result, edit_distance_result_median = evaluator.evaluate(
groundtruth=os.path.join(indir, log_file + '_structured.csv'),
parsedresult=os.path.join(output_dir, log_file + '_structured.csv'))
bechmark_result.append([
dataset, accuracy_PA, accuracy_exact_string_matching,
edit_distance_result, edit_distance_result_median
])
print('\n=== Overall evaluation results ===')
df_result = pd.DataFrame(bechmark_result,
columns=[
'Dataset', 'Accuracy_PA',
'Accuracy_ExactMatching', 'Edit_distance',
'Edit_distance_std'
])
df_result.set_index('Dataset', inplace=True)
print(df_result)
'maxChildNum': 4,
'mergeThreshold': 0.002,
'formatLookupThreshold': 0.3,
'superFormatThreshold': 0.85
},
}
bechmark_result = []
for dataset, setting in benchmark_settings.iteritems():
print('\n=== Evaluation on %s ==='%dataset)
indir = os.path.join(input_dir, os.path.dirname(setting['log_file']))
log_file = os.path.basename(setting['log_file'])
parser = SHISO.LogParser(log_format=setting['log_format'], indir=indir, outdir=output_dir, rex=setting['regex'],
maxChildNum=setting['maxChildNum'], mergeThreshold=setting['mergeThreshold'],
formatLookupThreshold=setting['formatLookupThreshold'], superFormatThreshold=setting['superFormatThreshold'])
parser.parse(log_file)
F1_measure, accuracy = evaluator.evaluate(
groundtruth=os.path.join(indir, log_file + '_structured.csv'),
parsedresult=os.path.join(output_dir, log_file + '_structured.csv')
)
bechmark_result.append([dataset, F1_measure, accuracy])
print('\n=== Overall evaluation results ===')
df_result = pd.DataFrame(bechmark_result, columns=['Dataset', 'F1_measure', 'Accuracy'])
df_result.set_index('Dataset', inplace=True)
print(df_result)
df_result.T.to_csv('SHISO_bechmark_result.csv')
import time
from logparser import evaluator
from logparser import ADC
# from logparser.ADC import ADC_Token as ADC
from benchmark.ADC_benchmark import CONFIG_DICT
from logparser.utils.dataset import *
from dataEngineering.token_selection import get_token_list
dataset = DATASET.Android
# ADC.set_TOKEN_LIST(get_token_list(dataset))
parser = ADC.LogParser(
# in_path='/home/zhixin/Desktop/Android.log',
dataset=dataset,
rex=CONFIG_DICT[dataset].rex,
st=CONFIG_DICT[dataset].st,
pre=CONFIG_DICT[dataset].pre)
start = time.perf_counter()
time_elapsed, out_path = parser.parse()
end = time.perf_counter()
F1_measure, accuracy = evaluator.evaluate(
groundtruth=log_path_structured(dataset), parsedresult=out_path)
print(F1_measure, accuracy, time_elapsed.total_seconds())
print(end - start)
