def independent_benchmark(json = 'adult'):
train, test, meta, categoricals, ordinals = load_dataset(json, benchmark=True)
synthesizer = IndependentSynthesizer()
synthesizer.fit(train, categoricals, ordinals)
sampled = synthesizer.sample(300)
print('Sampled Data for 300 records\n')
scores = evaluate(train, test, sampled, meta)
print('\nEvaluation Scores from evaluate function:\n')
return scores
def benchmark(synthesizer, datasets=DEFAULT_DATASETS, repeat=3):
results = list()
for name in datasets:
LOGGER.info('Evaluating dataset %s', name)
train, test, meta, categoricals, ordinals = load_dataset(
name, benchmark=True)
for iteration in range(repeat):
synthesized = synthesizer(train, categoricals, ordinals)
scores = evaluate(train, test, synthesized, meta)
scores['dataset'] = name
scores['iter'] = iteration
results.append(scores)
return pd.concat(results)
def benchCLBNSynthesizer():
from sdgym.synthesizers import CLBNSynthesizer
from sdgym.evaluate import evaluate
from sdgym.data import load_dataset
train, test, meta, categoricals, ordinals = load_dataset('adult',
benchmark=True)
synthesizer = CLBNSynthesizer()
synthesizer.fit(train, categoricals, ordinals)
sampled = synthesizer.sample(300)
scores = evaluate(train, test, sampled, meta)
#scores = scores.append(evaluate(train, test, sampled, meta))
#scores = scores.append(evaluate(train, test, sampled, meta))
print('\nEvaluation Scores from evaluate function:\n')
print(scores)
scores['Synth'] = 'CLBNSynthesizer'
scores.to_csv('CLBNBench.csv')
def benchmark(synthesizer, datasets=DEFAULT_DATASETS, repeat=3, prefix='tmp'):
print(datasets)
results = list()
for name in datasets:
try:
print('Evaluating dataset %s', name)
train, test, meta, categoricals, ordinals = load_dataset(
name, benchmark=True)
for iteration in range(repeat):
synthesized = synthesizer(train, categoricals, ordinals)
scores = evaluate(train, test, synthesized, meta)
scores['dataset'] = name
scores['iter'] = iteration
results.append(scores)
print(results)
with open(f'{prefix}_{name}.pickle', 'wb') as f:
pickle.dump(results, f)
except KeyError:
print("Here is the KeyError")
continue
return pd.concat(results)