'Check if the utterance is true given the KB. Only work for simulated data.'
)
add_scenario_arguments(parser)
add_lexicon_arguments(parser)
add_dataset_arguments(parser)
add_neural_system_arguments(parser)
add_heuristic_system_arguments(parser)
args = parser.parse_args()
logstats.init(args.stats_file)
if args.random_seed:
random.seed(args.random_seed)
np.random.seed(args.random_seed)
schema = Schema(args.schema_path)
scenario_db = ScenarioDB.from_dict(schema, read_json(args.scenarios_path))
lexicon = Lexicon(schema, args.learned_lex, stop_words=args.stop_words)
if args.inverse_lexicon:
realizer = InverseLexicon(schema, args.inverse_lexicon)
else:
realizer = None
if args.train_max_examples is None:
args.train_max_examples = scenario_db.size
if args.test_max_examples is None:
args.test_max_examples = scenario_db.size
def get_system(name):
if name == 'simple':
return SimpleSystem(lexicon, realizer=realizer)
elif name == 'heuristic':
type=str)
parser.add_argument("--transcripts",
help="Json file of all transcripts collected")
parser.add_argument("--output", help="Output path")
add_lexicon_arguments(parser)
args = parser.parse_args()
path = args.schema
schema = Schema(path)
re_pattern = r"[\w*\']+|[(\w*&)]+|[\w]+|\.|\(|\)|\\|\"|\/|;|\#|\$|\%|\@|\{|\}|\:"
lexicon = Lexicon(schema,
learned_lex=False,
entity_ranker=None,
scenarios_json=args.scenarios_json,
stop_words=args.stop_words)
with open(args.annotated_examples_path, "r") as f:
annotated_examples = json.load(f)
with open(args.transcripts, "r") as f:
examples = json.load(f)
if not args.output:
fout = open("inverse_lexicon_data.txt", "w")
else:
fout = open(args.output, 'w')
# Process annotated examples
raw_chats = read_json(args.dialogue_transcripts)
uuid_to_chat = {chat['uuid']: chat for chat in raw_chats}
schema = Schema(args.schema_path)
scenario_db = ScenarioDB.from_dict(schema, read_json(args.scenarios_path))
dialogue_ids = filter(raw_eval, uuid_to_chat)
for eval_ in raw_eval:
read_eval(eval_, question_scores, mask=dialogue_ids)
if args.hist:
hist(question_scores, args.outdir, partner=args.partner)
if args.summary:
summary = summarize(question_scores)
write_json(summary, args.stats)
if args.analyze:
schema = Schema(args.schema_path)
lexicon = Lexicon(schema,
False,
scenarios_json=args.scenarios_path,
stop_words=args.stop_words)
preprocessor = Preprocessor(schema, lexicon, 'canonical', 'canonical',
'canonical')
analyze(question_scores, uuid_to_chat, preprocessor)
# Visualize
if args.html_output:
visualize(args.viewer_mode, args.html_output, question_scores,
uuid_to_chat)
__author__ = 'anushabala'
from argparse import ArgumentParser
from src.basic.scenario_db import ScenarioDB, add_scenario_arguments
from src.basic.schema import Schema
import json
from get_data_statistics import add_statistics_arguments, compute_statistics
from visualize_data import add_visualization_arguments, visualize_transcripts
if __name__ == "__main__":
parser = ArgumentParser()
add_scenario_arguments(parser)
add_statistics_arguments(parser)
add_visualization_arguments(parser)
parser.add_argument('--transcripts',
type=str,
default='transcripts.json',
help='Path to directory containing transcripts')
parser.add_argument('--domain',
type=str,
choices=['MutualFriends', 'Matchmaking'])
args = parser.parse_args()
schema = Schema(args.schema_path, args.domain)
scenario_db = ScenarioDB.from_dict(schema, read_json(args.scenarios_path))
transcripts = json.load(open(args.transcripts, 'r'))
lexicon = Lexicon(schema, False, scenarios_json=args.scenarios_path)
visualize_transcripts(args, scenario_db, transcripts)
compute_statistics(args, lexicon, schema, scenario_db, transcripts)