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 get_data(self):
human_scores = read_reference_file(os.path.expanduser(self.config.get('Data', 'human_scores')), '\t')
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 extractor.vals, human_scores
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()
def feature_extraction(config_features_path):
config = ConfigParser()
config.readfp(open(config_features_path))
wd = config.get('WMT', 'working_directory')
if not os.path.exists(wd):
os.mkdir(wd)
data = RankingData(config)
data.read_dataset()
process = Process(config)
sentences_tgt, sentences_ref = process.run_processors()
feature_names = FeatureExtractor.read_feature_names(config)
feature_values = FeatureExtractor.extract_features_static(feature_names, sentences_tgt, sentences_ref)
write_feature_file(wd + '/' + 'x' + '_' + data.datasets[0].name + '.tsv', feature_values)
my_dataset = data.plain[0].dataset
my_lp = data.plain[0].lp
f_path = wd + '/' + 'x' + '_' + my_dataset + '_' + my_lp + '.tsv'
f_file = open(f_path, 'w')
for i, instance in enumerate(data.plain):
if instance.dataset == my_dataset and instance.lp == my_lp:
f_file.write('\t'.join([str(x) for x in feature_values[i]]) + "\n")
else:
f_file.close()
my_dataset = instance.dataset
my_lp = instance.lp
f_path = wd + '/' + 'x' + '_' + my_dataset + '_' + my_lp + '.tsv'
f_file = open(f_path, 'w')
f_judgements = config.get('WMT', 'human_ranking')
human_rankings = HumanRanking()
human_rankings.add_human_data(f_judgements, config)
human_rankings.get_sentence_ids(data)
learn_to_rank(feature_values, human_rankings, wd + '/' + 'x_learn_to_rank.tsv', wd + '/' + 'y_learn_to_rank.tsv')
import sys
import os
from configparser import ConfigParser
from utils.ranking_data import RankingData
from utils.write_parsed import write_parsed
from utils.human_ranking import HumanRanking
from processors.process import Process
from features.feature_extractor import FeatureExtractor
from utils.wmt import write_wmt_format
from utils.process_semeval import process_semeval
from nltk.corpus import stopwords
# Read configuration file
config = ConfigParser()
config.readfp(open('test.cfg'))
# Prepare dataset
ranking_data = RankingData(config)
ranking_data.read_dataset()
ranking_data.write_dataset()
write_parsed(config.get('Data', 'input_dir').replace('plain', 'parse'), config.get('Data', 'working_dir'), ['cs-en'])
# Process dataset
process = Process(config)
sentences_target, sentences_reference = process.run_processors()
cobalt_scores = FeatureExtractor.extract_features_static(['cobalt'], sentences_target, sentences_reference)
# print(str(cobalt_scores[-1][0]))
ranking_data.write_scores_wmt_format(cobalt_scores, metric='cobalt', output_path='output/cobalt.scores')
