def ioput_baseline_predict(ff):
with open(ff, 'r') as f:
text = f.read().splitlines()
output_yaml = {}
for i, orig_text in enumerate(text):
rp = RParser()
#Preprocess
pre_p = PreProcessor()
process_text, sub_table = pre_p.process([orig_text.strip()])
sen = process_text[0]
#RParse
verb_parent, method_parent = rp.parse_v_method(sen)
ioput_phrases = rp.parse_input_output(sen, verb_parent, method_parent)
NPs = rp.return_NPs(sen)
#Postprocess
#post_p = PostProcessor(verb_parent, method_parent, ioput_phrases, orig_text.strip(), sub_table)
#summary = post_p.process()
summary = {}
summary['action1'] = {}
for ioput_seq_num, np in enumerate(NPs):
summary['action1']['input_output_{}'.format(ioput_seq_num+1)] = repr(np)
output_yaml['sen{}'.format(i+1)] = summary
file_path = ff.split('/')
output_file_name_list = file_path[-1].split('.')
output_file_name_list[1] = 'ioput_baseline'
output_file_name_list[2] = 'yaml'
file_path[-1] = '.'.join(output_file_name_list)
output_file_path = '/'.join(file_path)
with open(output_file_path, 'w') as f:
f.write(yaml.dump(output_yaml, default_flow_style=False))
def ioput_baseline_predict(ff):
with open(ff, 'r') as f:
text = f.read().splitlines()
output_yaml = {}
for i, orig_text in enumerate(text):
rp = RParser()
#Preprocess
pre_p = PreProcessor()
process_text, sub_table = pre_p.process([orig_text.strip()])
sen = process_text[0]
#RParse
verb_parent, method_parent = rp.parse_v_method(sen)
ioput_phrases = rp.parse_input_output(sen, verb_parent, method_parent)
NPs = rp.return_NPs(sen)
#Postprocess
#post_p = PostProcessor(verb_parent, method_parent, ioput_phrases, orig_text.strip(), sub_table)
#summary = post_p.process()
summary = {}
summary['action1'] = {}
for ioput_seq_num, np in enumerate(NPs):
summary['action1']['input_output_{}'.format(ioput_seq_num +
1)] = repr(np)
output_yaml['sen{}'.format(i + 1)] = summary
file_path = ff.split('/')
output_file_name_list = file_path[-1].split('.')
output_file_name_list[1] = 'ioput_baseline'
output_file_name_list[2] = 'yaml'
file_path[-1] = '.'.join(output_file_name_list)
output_file_path = '/'.join(file_path)
with open(output_file_path, 'w') as f:
f.write(yaml.dump(output_yaml, default_flow_style=False))
__author__ = 'Shaun Rong'
__version__ = '0.1'
__maintainer__ = 'Shaun Rong'
__email__ = '*****@*****.**'
with open('environ.yaml', 'r') as f:
env = yaml.load(f)
stanford_parser_folder = env['stanford_parser_folder']
os.environ['STANFORD_PARSER'] = stanford_parser_folder
os.environ['STANFORD_MODELS'] = stanford_parser_folder
cfuf = PreProcessor()
with open('data/3.raw.txt', 'r') as f:
text = f.read().splitlines()
process_text, sub_table = cfuf.process(text)
sen = process_text[3]
rp = RParser()
verb_parent, method_parent = rp.parse_v_method(sen)
print verb_parent
print method_parent
stanford_parser_folder = env['stanford_parser_folder']
os.environ['STANFORD_PARSER'] = stanford_parser_folder
os.environ['STANFORD_MODELS'] = stanford_parser_folder
tree_parser = stanford.StanfordParser(model_path=env['model_path'])
for ff in train_file:
with open(os.path.join(args.f, "{}.raw.txt".format(ff)), 'r') as f:
text = f.read().splitlines()
with open(os.path.join(args.f, "{}.gold.yaml".format(ff)), 'r') as f:
gold_ticket = yaml.load(f)
for i, orig_text in enumerate(text):
rp = RParser()
#Preprocess
pre_p = PreProcessor()
process_text, sub_table = pre_p.process([orig_text.strip()])
sen = process_text[0]
#RParse
NPs = rp.return_NPs(sen)
gold_NPs = extract_gold_NPs(gold_ticket['sen{}'.format(i+1)], sub_table, tree_parser)
for NP in NPs:
if NP in gold_NPs:
train_summary['input_output'].append(repr(NP))
else:
train_summary['else'].append(repr(NP))
from PreProcessor import PreProcessor
from RParser import RParser
__author__ = 'Shaun Rong'
__version__ = '0.1'
__maintainer__ = 'Shaun Rong'
__email__ = '*****@*****.**'
with open('environ.yaml', 'r') as f:
env = yaml.load(f)
stanford_parser_folder = env['stanford_parser_folder']
os.environ['STANFORD_PARSER'] = stanford_parser_folder
os.environ['STANFORD_MODELS'] = stanford_parser_folder
cfuf = PreProcessor()
with open('data/3.raw.txt', 'r') as f:
text = f.read().splitlines()
process_text, sub_table = cfuf.process(text)
sen = process_text[3]
rp = RParser()
verb_parent, method_parent = rp.parse_v_method(sen)
print verb_parent
print method_parent
