#!/usr/bin/env python
# -*- coding: utf-8 -*-
import gurobipy as gp
import codecs
from numpy import random
from fei.model.feat_vec import FeatureVector
from fei.model.feat_extr import FeatureExtractor
from fei.model.utils import getLogger
logger = getLogger()
class Decoder(object):
"""
Implement of decoder for structured prediction
"""
def __init__(self):
self.gilp = GurobiILP()
self.weights = FeatureVector()
self.feat_extr = FeatureExtractor()
return
def decode(self,
instance,
oracle_len='nolen',
node_cost=None,
edge_cost=None):
"""
an instance includes:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import codecs
import sys
from fei.model.utils import getLogger
LOG_FILE = 'semantic_summ.log'
if len(sys.argv) > 4: LOG_FILE = 'log_%s_%s_passes_len_%s_exp_%s' % (sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4])
logger = getLogger(log_file=LOG_FILE)
from fei.model.corpus import buildCorpus
from fei.model.decoder import Decoder
from fei.model.learning import ParamEstimator
def train(body_file, summ_file, param_file, loss_func, num_passes, oracle_len, w_exp):
"""
run summarizer, learn structured prediction parameters
"""
logger.debug('start training...')
logger.debug('[settings]: %s_%d_passes_len_%s_exp_%d' % (loss_func, num_passes, oracle_len, w_exp))
corpus = buildCorpus(body_file, summ_file, w_exp)
# learn parameters
decoder = Decoder()
estimator = ParamEstimator()
final_weights = estimator.learnParamsAdaGrad(decoder, corpus, param_file, loss_func, num_passes, oracle_len)
# output parameters to file
with codecs.open(param_file, 'w', 'utf-8') as outfile:
outfile.write('#num_passes#: %d\n' % num_passes)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re
from collections import namedtuple
from collections import Counter
from fei.model.utils import getLogger
logger = getLogger()
# information obtained from file
NodeSource = namedtuple('NodeSource', 'graph_idx, start_idx, end_idx, word_str, filename, line_num, sentence')
EdgeSource = namedtuple('EdgeSource', 'relation, filename, line_num, sentence')
class AmrNode(object):
def __init__(self, graph_idx=None, short_hnd=None, concept=None):
self.graph_idx = graph_idx
self.short_hnd = short_hnd
self.concept = concept
self.sources = [] # list of NodeSource
def __repr__(self):
return '%s %s %s' % (self.graph_idx, self.short_hnd, self.concept)
def toString(self):
"""
convert AmrNode to string, include full node information
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import codecs
import sys
from fei.model.utils import getLogger
LOG_FILE = 'semantic_summ.log'
if len(sys.argv) > 4: LOG_FILE = 'log_%s_%s_passes_len_%s_exp_%s' % (sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4])
logger = getLogger(log_file=LOG_FILE)
from fei.model.corpus import buildCorpus
from fei.model.decoder import Decoder
from fei.model.learning import ParamEstimator
def train(body_file, summ_file, param_file, loss_func, num_passes, oracle_len, w_exp):
"""
run summarizer, learn structured prediction parameters
"""
logger.debug('start training...')
logger.debug('[settings]: %s_%d_passes_len_%s_exp_%d' % (loss_func, num_passes, oracle_len, w_exp))
corpus = buildCorpus(body_file, summ_file, w_exp)
# learn parameters
decoder = Decoder()
estimator = ParamEstimator()
final_weights = estimator.learnParamsAdaGrad(decoder, corpus, param_file, loss_func, num_passes, oracle_len)
# output parameters to file
with codecs.open(param_file, 'w', 'utf-8') as outfile:
outfile.write('#num_passes#: %d\n' % num_passes)