def _merge_models(feat, is_header, is_before_proj, is_gs, ds, covariance_type, dataset_name, model_name):
""" merge all models and datasets to one csv
Parameters
----------
feat
is_header
is_gs
d
Returns
-------
"""
res_ = {}
vs = [] # store for csv
for i, d_tup in enumerate(ds):
_, d = d_tup
if "OCSVM" in model_name:
pth_cfg = (feat, is_header, is_before_proj, is_gs, d, None, model_name)
data = _merge_datasets([dataset_name], pth_cfg)
res_[d_tup] = data
elif 'GMM' in model_name:
pth_cfg = (feat, is_header, is_before_proj, is_gs, d, covariance_type, model_name)
data = _merge_datasets([dataset_name], pth_cfg)
res_[d_tup] = data
else:
msg = d_tup
raise NotImplementedError(msg)
# store for csv
if i == 0:
vs = copy.deepcopy(data)
else:
vs.extend(data)
# print(vs)
# 'feat-header_false-before_proj_False-gs_True-diag-std_False_center_False-d_5'
out_file_ = pth.join(in_dir, feat + "-header_" + str(is_header),
"before_proj_" + str(is_before_proj) + "-gs_" + str(is_gs),
f"std_False_center_False-{str(covariance_type)}",
f'{dataset_name}-{model_name}.csv')
print(f'data_models: {out_file_}')
check_path(out_file_)
out_file_dat = out_file_ + '.dat'
dump_data(res_, out_file=out_file_dat)
# save as csv
pd.DataFrame(vs).to_csv(out_file_, index=False, encoding='utf-8-sig')
# # save as xlsx
# out_xlsx = dat2xlxs_new(out_file_dat, out_file=out_file_dat + '.xlsx', models=models)
# # compute ratio OCSVM/GMM
# out_xlsx_ratio = improvement(out_xlsx, feat_set=feat,
# out_file=os.path.splitext(out_file_dat)[0] + '-ratio.xlsx')
# print(out_xlsx)
#
# # for paper
# out_latex = dat2latex(out_xlsx_ratio, out_file=os.path.splitext(out_file_dat)[0] + '-latex.xlsx')
# print(out_latex)
# show(in_file=out_file_) # show model separately
return out_file_
def main():
res = {}
feat_set = 'iat_size'
# in_dir = 'speedup/out/kjl_serial_ind_32_threads-cProfile_perf_counter'
in_dir = 'speedup/out/kjl_joblib_parallel_30'
# Load models and evaluate them on test data
for i, (data_name,
model_name) in enumerate(itertools.product(DATASETS, MODELS)):
out = _main(in_dir, data_name, model_name, feat_set)
if data_name not in res.keys():
res[data_name] = {model_name: out}
else:
res[data_name][model_name] = out
# if model_name not in res.keys():
# res[model_name] = [out]
# else:
# res[model_name].append(out)
lg.debug(res)
# Save results
out_file = f'{in_dir}/res.csv'
check_path(out_file)
# save as csv
_, outs = res2csv(res, out_file, feat_set=feat_set)
out_file_dat = out_file + '.dat'
dump_data(outs, out_file=out_file_dat)
lg.info(out_file)
# save as xlsx
out_xlsx = dat2xlxs_new(out_file_dat,
out_file=out_file_dat + '.xlsx',
models=MODELS)
# compute ratio OCSVM/GMM
out_xlsx_ratio = improvement(out_xlsx,
feat_set=feat_set,
out_file=os.path.splitext(out_file_dat)[0] +
'-ratio.xlsx')
print(out_xlsx_ratio)
lg.info('finish!')