def test(body_file, summ_file, param_file, oracle_len, w_exp):
"""
run summarizer, perform structured prediction
"""
logger.debug('start testing...')
logger.debug('[settings]: len_%s_exp_%d' % (oracle_len, w_exp))
corpus = buildCorpus(body_file, summ_file, w_exp)
# load parameters from file
decoder = Decoder()
decoder.weights.load(param_file)
# perform structured prediction
estimator = ParamEstimator()
estimator.predict(decoder, corpus, oracle_len)
return
def test(body_file, summ_file, param_file, oracle_len, w_exp):
"""
run summarizer, perform structured prediction
"""
logger.debug('start testing...')
logger.debug('[settings]: len_%s_exp_%d' % (oracle_len, w_exp))
corpus = buildCorpus(body_file, summ_file, w_exp)
# load parameters from file
decoder = Decoder()
decoder.weights.load(param_file)
# perform structured prediction
estimator = ParamEstimator()
estimator.predict(decoder, corpus, oracle_len)
return
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)
outfile.write('%s\n' % final_weights.toString())
return
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)
outfile.write('%s\n' % final_weights.toString())
return
def summ(body_file, summ_file, param_file, oracle_len, w_exp, jamr=False):
"""
run summarizer, perform structured prediction
"""
logger.debug('start testing...')
logger.debug('[settings]: len_%s_exp_%d' % (oracle_len, w_exp))
corpus = buildCorpus(body_file, summ_file, w_exp)
# load parameters from file
decoder = Decoder()
decoder.weights.load(param_file)
# perform structured prediction
estimator = ParamEstimator()
output_folder = param_file.replace('params', 'summ')
if jamr == True: output_folder = param_file.replace('params', 'jamr_summ')
estimator.summarize(decoder, corpus, oracle_len, output_folder)
return
def summ(body_file, summ_file, param_file, oracle_len, w_exp, jamr=False):
"""
run summarizer, perform structured prediction
"""
logger.debug('start testing...')
logger.debug('[settings]: len_%s_exp_%d' % (oracle_len, w_exp))
corpus = buildCorpus(body_file, summ_file, w_exp)
# load parameters from file
decoder = Decoder()
decoder.weights.load(param_file)
# perform structured prediction
estimator = ParamEstimator()
output_folder = param_file.replace('params', 'summ')
if jamr == True: output_folder = param_file.replace('params', 'jamr_summ')
estimator.summarize(decoder, corpus, oracle_len, output_folder)
return
