def run_and_evaluate_dBoost(params):
model = params['model']
final_file = generate_dBoost_result_file_name(
model, params['data'], params['parameter_grid_dict'], params['keys'])
if not os.path.isfile(final_file):
model = params['model']
model(**params['parameter_grid_dict'])
result_file = str(params['parameter_grid_dict']['result_file'])
del params['parameter_grid_dict']['sample_file']
del params['parameter_grid_dict']['result_file']
run = DBoostMe(params['data'], result_file)
run.write_detected_matrix(final_file)
def search_mixture_stat(data,
data_sample,
data_sample_ground_truth,
sample_file,
result_file,
n_subpops_s,
threshold_s,
statistical_range,
write_out=False):
best_params = {}
best_fscore = 0.0
precision = 0.0
recall = 0.0
for p in n_subpops_s:
for t in threshold_s:
for s in statistical_range:
run_mixture_stat(p, t, s, sample_file, result_file)
our_sample_data = DataSetBasic(
data.name + " random" + str(data_sample.shape[0]),
data_sample, data_sample_ground_truth)
run = DBoostMe(our_sample_data, result_file)
current_fscore = run.calculate_total_fscore()
current_precision = run.calculate_total_precision()
current_recall = run.calculate_total_recall()
if write_out:
run.write_detected_matrix(
Config.get("logging.folder") + "/out/dboost" +
'/dboost_' + data.name + '_mixture_subpop' + str(p) +
'_threshold_' + str(t) + '_stat_' + str(s) + '.npy')
print "n_subpops: " + str(p) + " threshold: " + str(
t) + " --statistical " + str(s)
print "Fscore: " + str(current_fscore)
print "Precision: " + str(run.calculate_total_precision())
print "Recall: " + str(run.calculate_total_recall())
if current_fscore >= best_fscore:
best_fscore = current_fscore
precision = current_precision
recall = current_recall
best_params['n_subpops'] = p
best_params['threshold'] = t
best_params['statistical'] = s
return best_params, best_fscore, precision, recall
def search_histogram_stat(data,
data_sample,
data_sample_ground_truth,
sample_file,
result_file,
peak_s,
outlier_s,
statistical_range,
write_out=False):
best_params = {}
best_fscore = 0.0
precision = 0.0
recall = 0.0
for p in peak_s:
for o in outlier_s:
for s in statistical_range:
run_histogram_stat(p, o, s, sample_file, result_file)
our_sample_data = DataSetBasic(
data.name + " random" + str(data_sample.shape[0]),
data_sample, data_sample_ground_truth)
run = DBoostMe(our_sample_data, result_file)
current_fscore = run.calculate_total_fscore()
current_precision = run.calculate_total_precision()
current_recall = run.calculate_total_recall()
if write_out:
run.write_detected_matrix(
Config.get("logging.folder") + "/out/dboost" +
'/dboost_histogram_' + data.name + '_peak' + str(p) +
'_outlier_' + str(o) + '_stat_' + str(s) + '.npy')
print "peak: " + str(p) + " outlier: " + str(
o) + " --statistical " + str(s)
print "Fscore: " + str(current_fscore)
print "Precision: " + str(run.calculate_total_precision())
print "Recall: " + str(run.calculate_total_recall())
if current_fscore >= best_fscore:
best_fscore = current_fscore
precision = current_precision
recall = current_recall
best_params['peak'] = p
best_params['outlier'] = o
best_params['statistical'] = s
return best_params, best_fscore, precision, recall
def search_gaussian_stat(data,
data_sample,
data_sample_ground_truth,
sample_file,
result_file,
gaussian_range,
statistical_range,
write_out=False):
best_params = {}
best_fscore = 0.0
precision = 0.0
recall = 0.0
for g in gaussian_range:
for s in statistical_range:
run_gaussian_stat(g, s, sample_file, result_file)
our_sample_data = DataSetBasic(
data.name + " random" + str(data_sample.shape[0]), data_sample,
data_sample_ground_truth)
run = DBoostMe(our_sample_data, result_file)
current_fscore = run.calculate_total_fscore()
current_precision = run.calculate_total_precision()
current_recall = run.calculate_total_recall()
if write_out:
run.write_detected_matrix(
Config.get("logging.folder") + "/out/dboost" +
'/dboost_gausian_' + data.name + '_gausian' + str(g) +
'_stat_' + str(s) + '.npy')
print "--gaussian " + str(g) + " --statistical " + str(s)
print "Fscore: " + str(current_fscore)
print "Precision: " + str(run.calculate_total_precision())
print "Recall: " + str(run.calculate_total_recall())
if current_fscore >= best_fscore:
best_fscore = current_fscore
precision = current_precision
recall = current_recall
best_params['gaussian'] = g
best_params['statistical'] = s
return best_params, best_fscore, precision, recall
data_sample_ground_truth = data.matrix_is_error[random_index]
sample_file = "/tmp/data_sample.csv"
result_file = "/tmp/dboostres.csv"
data_sample.to_csv(sample_file, index=False)
total_start_time = time.time()
gaus = 0.8
stat = 0.5
command = "python3 /home/felix/dBoost/dboost/dboost-stdin.py -F ',' --gaussian " + str(
gaus) + " --statistical " + str(
stat) + " " + sample_file + " > " + result_file
os.system(command)
our_sample_data = DataSetBasic(data.name + " random" + str(n), data_sample,
data_sample_ground_truth)
run = DBoostMe(our_sample_data, result_file)
print "--gaussian " + str(gaus) + " --statistical " + str(
stat) + " -> Fscore: " + str(run.calculate_total_fscore())
print "Precision: " + str(run.calculate_total_precision())
print "Recall: " + str(run.calculate_total_recall())
runtime = (time.time() - total_start_time)
print runtime
from ml.datasets.blackOak.BlackOakDataSet import BlackOakDataSet
from ml.tools.dboost.DBoostMe import DBoostMe
tool = DBoostMe(BlackOakDataSet(), "/tmp/test_format.csv")
print "Fscore: " + str(tool.calculate_total_fscore())
print "Precision: " + str(tool.calculate_total_precision())
print "Recall: " + str(tool.calculate_total_recall())
#data = BlackOakDataSet()
#data.dirty_pd.to_csv("blackOak_clear.csv",index=False, quotechar="\"")