def call_experiment(args):
kwargs = {}
print args
model = args['model']['model']
kwargs['model_type'] = model
if model == 'SVM':
kwargs['regularizer'] = args['model']['regularizer_svm']
kwargs['alpha'] = args['model']['C_svm']
elif model == 'LR':
kwargs['regularizer'] = args['model']['regularizer_lr']
kwargs['alpha'] = args['model']['alpha_lr']
feature_list = []
unigrams = 'ngrams,n=1' + \
',binarize=' + args['features']['unigrams']['u_binarize'] + \
',min_doc_threshold=' + str(args['features']['unigrams']['u_min_doc_threshold'])
feature_list.append(unigrams)
if args['features']['bigrams']['use']:
bigrams = 'ngrams,n=2' + \
',binarize=' + args['features']['bigrams']['b_binarize'] + \
',min_doc_threshold=' + str(args['features']['bigrams']['b_min_doc_threshold'])
feature_list.append(bigrams)
print feature_list
result = classify_test.classify(data_filename, label_filename, feature_dir, feature_list, **kwargs)
with codecs.open(log_filename, 'a') as output_file:
output_file.write(str(datetime.datetime.now()) + '\t' + ' '.join(feature_list) + '\t' + ' '.join(kwargs) +
'\t' + str(-result['loss']) + '\n')
return result
def call_experiment(args):
global trial_num
trial_num = trial_num + 1
print model_dir
if line_num: #if reading from file
print 'file'
new_model_dir = model_dir
else:
new_model_dir = model_dir + str(trial_num) + '/'
os.makedirs(new_model_dir)
print new_model_dir
feats_and_args = {}
all_description = []
for i in range(num_models):
feature_list, description, kwargs = wrangle_params(args, str(i))
all_description = all_description + description
feats_and_args[i] = {'feats':feature_list, 'params':kwargs}
result = classify_test.classify(train_data_filename, train_label_filename, dev_data_filename,
dev_label_filename, train_feature_dir, dev_feature_dir,
new_model_dir, word2vec_filename, feats_and_args, folds=num_folds)
with codecs.open(log_filename, 'a') as output_file:
output_file.write(str(datetime.datetime.now()) + '\t' + ' '.join(all_description) +
'\t' + str(-result['loss']) + '\n')
save_model(result)
print("\nFinished iteration " + str(trial_num) + ".\n\n\n")
sys.stdout.flush()
return result
def call_experiment(args):
global trial_num
trial_num = trial_num + 1
feature_list, description, kwargs = wrangle_params(args)
result = classify_test.classify(train_data_filename, train_label_filename, dev_data_filename,
dev_label_filename, train_feature_dir, dev_feature_dir,
feature_list, **kwargs)
with codecs.open(log_filename, 'a') as output_file:
output_file.write(str(datetime.datetime.now()) + '\t' + ' '.join(feature_list) + '\t' + ' '.join(description) +
'\t' + str(-result['loss']) + '\n')
save_model(result['model'], feature_list, kwargs, result)
print("\nFinished iteration " + str(trial_num) + ".\n\n\n")
return result
def call_experiment(args):
global trial_num
trial_num = trial_num + 1
feature_list, description, kwargs = wrangle_params(args)
result = classify_test.classify(train_data_filename, train_label_filename,
dev_data_filename, dev_label_filename,
train_feature_dir, dev_feature_dir,
feature_list, **kwargs)
with codecs.open(log_filename, 'a') as output_file:
output_file.write(
str(datetime.datetime.now()) + '\t' + ' '.join(feature_list) +
'\t' + ' '.join(description) + '\t' + str(-result['loss']) + '\n')
save_model(result['model'], feature_list, kwargs)
print("\nFinished iteration " + str(trial_num) + ".\n\n\n")
return result
def call_experiment(args):
#in case we want to debug the BO algorithms
#import pdb; pdb.set_trace()
debug_mode = False
if debug_mode:
import random
from hyperopt import STATUS_OK
return {'loss': random.random(), 'status': STATUS_OK}
global trial_num
trial_num = trial_num + 1
print model_dir
if line_num: #if reading from file
print 'file'
new_model_dir = model_dir
else:
new_model_dir = model_dir + str(trial_num) + '/'
os.makedirs(new_model_dir)
print new_model_dir
feats_and_args = {}
all_description = []
for i in range(num_models):
feature_list, description, kwargs = wrangle_params(args, str(i))
all_description = all_description + description
feats_and_args[i] = {'feats': feature_list, 'params': kwargs}
result = classify_test.classify(train_data_filename,
train_label_filename,
dev_data_filename,
dev_label_filename,
train_feature_dir,
dev_feature_dir,
new_model_dir,
word2vec_filename,
feats_and_args,
folds=num_folds)
with codecs.open(log_filename, 'a') as output_file:
output_file.write(
str(datetime.datetime.now()) + '\t' + ' '.join(all_description) +
'\t' + str(-result['loss']) + '\n')
save_model(result)
print("\nFinished iteration " + str(trial_num) + ".\n\n\n")
sys.stdout.flush()
return result
