def __init__(
self,
data,
prior_eta=GammaPrior(2., 0.5),
prior_alpha=GammaPrior(0.5, 0.5),
prior_beta=GammaPrior(0.5, 0.5),
p=10,
max_clust_count=300,
):
assert type(data) is MixedData
self.data = data
self.max_clust_count = max_clust_count
self.p = p
self.nCat = self.data.nCat
self.nCol = self.data.nCol
self.nDat = self.data.nDat
self.nCats = self.data.Cats.shape[0]
self.priors = Prior(prior_eta, prior_alpha, prior_beta)
self.set_projection()
self.categorical_considerations()
self.pool = Pool(processes=8, initializer=limit_cpu())
return
import pandas as pd, numpy as np
import os, glob, re
from energy import limit_cpu
from anomaly import ResultFactory
base_path = './simulated/sphere_ad'
model_types = np.array(['sdpppg', 'sdppprg', 'sdpppgln', 'sdppprgln'])
if __name__ == '__main__':
limit_cpu()
paths = glob.glob(os.path.join(base_path, 'results_*.pkl'))
metrics = []
for path in paths:
match = re.search('results_([a-zA-Z]+)_(\d+)_(\d+).pkl', path)
model, nmix, ncol = match.group(1, 2, 3)
print('Processing {} m{} c{}'.format(model, nmix, ncol).ljust(76),
end='')
result = ResultFactory(model, path)
result.pools_open()
metric = result.get_scoring_metrics()
result.pools_closed()
metric['Model'] = model
metric['nMix'] = nmix
metric['nCol'] = ncol
column_order = ['Model', 'nMix', 'nCol', 'Metric'] + list(
result.scoring_metrics.keys())
metrics.append(metric[column_order])
print('Done')
df = pd.concat(metrics)
df.to_csv(os.path.join(base_path, 'performance.csv'), index=False)