def get_data(self):
process_wmt = PrepareWmt()
data_structure1 = process_wmt.get_data_structure(self.config)
data_structure2 = process_wmt.get_data_structure2(self.config)
process_wmt.print_data_set(self.config, data_structure1)
if 'Parse' in loads(self.config.get("Resources", "processors")):
process_wmt_parse = PrepareWmt(data_type='parse')
data_structure_parse = process_wmt_parse.get_data_structure(self.config)
process_wmt_parse.print_data_set(self.config, data_structure_parse)
f_judgements = self.config.get('WMT', 'human_ranking')
maximum_comparisons = int(self.config.get('WMT', 'maximum_comparisons'))
human_rankings = HumanRanking()
human_rankings.add_human_data(f_judgements, self.config, max_comparisons=maximum_comparisons)
process = Process(self.config)
sents_tgt, sents_ref = process.run_processors()
extractor = FeatureExtractor(self.config)
features_to_extract = FeatureExtractor.read_feature_names(self.config)
extractor.extract_features(features_to_extract, sents_tgt, sents_ref)
return data_structure2, human_rankings, extractor.vals
def prepare_feature_files(self):
process_wmt = PrepareWmt()
data_structure1 = process_wmt.get_data_structure(self.config)
data_structure2 = process_wmt.get_data_structure2(self.config)
process_wmt.print_data_set(self.config, data_structure1)
if 'Parse' in loads(self.config.get("Resources", "processors")):
process_wmt_parse = PrepareWmt(data_type='parse')
data_structure_parse = process_wmt_parse.get_data_structure(self.config)
process_wmt_parse.print_data_set(self.config, data_structure_parse)
process = Process(self.config)
sents_tgt, sents_ref = process.run_processors()
extractor = FeatureExtractor(self.config)
features_to_extract = FeatureExtractor.read_feature_names(self.config)
extractor.extract_features(features_to_extract, sents_tgt, sents_ref)
feature_values = extractor.vals
datasets_language_pairs = set((x[0], x[1]) for x in data_structure2)
dataset_for_all = self.config.get('WMT', 'dataset')
feature_set_name = os.path.basename(self.config.get('Features', 'feature_set')).replace(".txt", "")
f_features_all = open(os.path.expanduser(self.config.get('WMT', 'output_dir')) + '/' + 'x_' + dataset_for_all + '.' + feature_set_name + '.' + 'all' + '.tsv', 'w')
f_meta_data_all = open(os.path.expanduser(self.config.get('WMT', 'output_dir')) + '/' + 'meta_' + dataset_for_all + '.' + feature_set_name + '.' + 'all' + '.tsv', 'w')
for dataset, lp in sorted(datasets_language_pairs):
f_features = open(os.path.expanduser(self.config.get('WMT', 'output_dir')) + '/' + 'x_' + dataset + '.' + feature_set_name + '.' + lp + '.tsv', 'w')
for i, sentence_data in enumerate(data_structure2):
if dataset in sentence_data and lp in sentence_data:
f_features_all.write('\t'.join([str(x) for x in feature_values[i]]) + "\n")
f_meta_data_all.write('\t'.join([str(x) for x in sentence_data]) + "\n")
f_features.write('\t'.join([str(x) for x in feature_values[i]]) + "\n")
f_features.close()
f_features_all.close()
from utils.prepare_wmt import PrepareWmt
# Read configuration files
config_path = os.getcwd() + '/' + 'config' + '/' + 'wmt.cfg'
config = ConfigParser()
config.readfp(open(config_path))
config_path_learning = os.getcwd() + '/' + 'config/learner/logistic.cfg'
with open(config_path_learning, 'r') as cfg_file:
config_learning = yaml.load(cfg_file.read())
# Prepare feature files
# This needs to be done for both training and testing data, changing the names of the datasets in the configuratio file
prepare_wmt = PrepareWmt()
ranking_task = RankingTask(config_path)
ranking_task.prepare_feature_files()
# Create training set for learn to rank
# Comment the above prepare feature files method
dataset_for_all = config.get('WMT', 'dataset')
feature_set_name = os.path.basename(config.get('Features', 'feature_set')).replace(".txt", "")
data_structure2 = prepare_wmt.get_data_structure2(config)
f_judgements = config.get('WMT', 'human_ranking')
human_rankings = HumanRanking()
human_rankings.add_human_data(f_judgements, config)
feature_values = read_features_file(os.path.expanduser(config.get('WMT', 'output_dir')) + '/' + 'x_' + dataset_for_all + '.' + feature_set_name + '.' + 'all' + '.tsv', "\t")
