def main(argv):
# reading the command line
helpString = 'python python_script_JAD_paper -a <trainingSet> -b <testSet> -t <timeForEachWorker> -n <numWorkers>'
try:
opts, args = getopt.getopt(argv, "ha:b:t:n:")
except getopt.GetoptError:
print(helpString)
sys.exit(2)
# collecting the arguments
for opt, arg in opts:
if opt == '-h':
print(helpString)
sys.exit()
elif opt == '-a':
training_set = arg
elif opt == '-b':
test_set = arg
elif opt == '-t':
time_left_for_this_task = int(arg)
elif opt == '-n':
n_processes = int(arg)
# starting counting the time
start_time = time.time()
# folders
tmp_folder = './tmp/autosklearn_tmp/' + training_set
output_folder = './tmp/autosklearn_out/' + training_set
# ensuring the folders are empty (?)
for tmpDir in [tmp_folder, output_folder]:
try:
shutil.rmtree(tmpDir)
except OSError as e:
pass
# reading the training data
trainingData = pandas.read_csv(filepath_or_buffer='./tmp/data/' +
training_set + '.csv',
index_col=False)
y_train = trainingData['target']
X_train = trainingData.drop('target', 1)
# reading the test data
testData = pandas.read_csv(filepath_or_buffer='./tmp/data/' + test_set +
'.csv',
index_col=False)
y_test = testData['target']
X_test = testData.drop('target', 1)
# main block
try:
# creating the sub-process function
processes = []
spawn_classifier = get_spawn_classifier(X_train, y_train, training_set,
time_left_for_this_task,
tmp_folder, output_folder)
# spawning the subprocesses
for i in range(small_constant, small_constant + n_processes):
p = multiprocessing.Process(target=spawn_classifier, args=[i])
p.start()
processes.append(p)
# waiting until all processes are done
for p in processes:
p.join()
# retrieving the csRes and concatenating in a single data frame
csvFiles = glob.glob('./tmp/results/' + training_set + '/*.csv')
cvRes = pandas.read_csv(filepath_or_buffer=csvFiles[0], index_col=0)
for csvFile in csvFiles[1:]:
cvRes_tmp = pandas.read_csv(filepath_or_buffer=csvFile,
index_col=0)
cvRes = pandas.concat([cvRes, cvRes_tmp], axis=0, sort=False)
# writing the cvRes on file
cvRes.to_csv('./tmp/results/' + training_set + '/cvRes.csv',
index=False)
# building the ensemble
automl_ensemble = AutoSklearnClassifier(
time_left_for_this_task=
time_left_for_this_task, # sec., how long should this seed fit process run
delete_tmp_folder_after_terminate=False,
delete_output_folder_after_terminate=False,
seed=12345,
shared_mode=True,
ensemble_size=50,
ensemble_nbest=50,
tmp_folder=tmp_folder,
output_folder=output_folder)
automl_ensemble.fit_ensemble(y_train.copy(),
task=BINARY_CLASSIFICATION,
metric=autosklearn.metrics.roc_auc)
# building the best model
automl_bestModel = AutoSklearnClassifier(
time_left_for_this_task=
time_left_for_this_task, # sec., how long should this seed fit process run
delete_tmp_folder_after_terminate=False,
delete_output_folder_after_terminate=False,
shared_mode=True,
ensemble_size=1,
ensemble_nbest=1,
tmp_folder=tmp_folder,
output_folder=output_folder)
automl_bestModel.fit_ensemble(y_train.copy(),
task=BINARY_CLASSIFICATION,
metric=autosklearn.metrics.roc_auc)
# refitting on the whole dataset
automl_bestModel.refit(X_train.copy(), y_train.copy())
automl_ensemble.refit(X_train.copy(), y_train.copy())
# extracting the performances on test set
automl_bestModel.target_type = 'multilabel-indicator'
automl_ensemble.target_type = 'multilabel-indicator'
predictions_bestModel = automl_bestModel.predict_proba(X_test.copy())
predictions_ensemble = automl_ensemble.predict_proba(X_test.copy())
# saving the results on file
toSave = pandas.DataFrame({'outcome': y_test})
toSave['prob_ensemble'] = predictions_ensemble[:, 0]
toSave['prob_bestModel'] = predictions_bestModel[:, 0]
toSave.to_csv('./tmp/results/' + training_set + '/holdoutRes.csv')
# stopping counting the time
end_time = time.time()
# saving total time
total_time = end_time - start_time
time_file = open('./tmp/results/' + training_set + '/etime.txt', "w+")
tmp = time_file.write('Total time in seconds: %d\n' % total_time)
time_file.close()
except Exception as e:
print(e)
finally:
# removing the tmp results folder
shutil.rmtree(tmp_folder + '/.auto-sklearn/models')
