def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold):
projection = lambda x: x
if STEM:
projection = stem
# Start Training
print("Fold %i Training code" % fold)
# For training
td_sents = to_label_powerset_tagged_sentences(essays_TD, regular_tags, projection=projection)
vd_sents = to_label_powerset_tagged_sentences(essays_VD, regular_tags, projection=projection)
trainer = HiddenMarkovModelTrainer()
model = trainer.train_supervised(td_sents)
td_predictions = model.tag_sents(to_sentences(td_sents))
vd_predictions = model.tag_sents(to_sentences(vd_sents))
# for evaluation - binary tags
# YS (ACTUAL)
wd_td_ys_bytag = to_flattened_binary_tags_by_code(td_sents, regular_tags)
wd_vd_ys_bytag = to_flattened_binary_tags_by_code(vd_sents, regular_tags)
# YS (PREDICTED)
td_wd_predictions_by_code = to_flattened_binary_tags_by_code(td_predictions, regular_tags)
vd_wd_predictions_by_code = to_flattened_binary_tags_by_code(vd_predictions, regular_tags)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold):
td_sents_by_code = to_tagged_sentences_by_code(essays_TD, regular_tags)
vd_sents_by_code = to_tagged_sentences_by_code(essays_VD, regular_tags)
wd_td_ys_bytag = dict()
wd_vd_ys_bytag = dict()
td_wd_predictions_by_code = dict()
vd_wd_predictions_by_code = dict()
for code in sorted(regular_tags):
print("Fold %i Training code: %s" % (fold, code))
td, vd = td_sents_by_code[code], vd_sents_by_code[code]
model_filename = models_folder + "/" + "%i_%s__%s" % (fold, code, str(randint(0, 9999999)))
# documentation: http://www.chokkan.org/software/crfsuite/manual.html
training_opt = {"feature.possible_states": False,
"feature.possible_transitions": False,
"c2": 2.0
}
model = CRFTagger(feature_func=comp_feat_extactor, verbose=False, training_opt=training_opt)
model.train(td, model_filename)
wd_td_ys_bytag[code] = to_flattened_binary_tags(td)
wd_vd_ys_bytag[code] = to_flattened_binary_tags(vd)
td_predictions = model.tag_sents(to_sentences(td))
vd_predictions = model.tag_sents(to_sentences(vd))
# Delete model file now predictions obtained
# Note, we are randomizing name above, so we need to clean up here
os.remove(model_filename)
td_wd_predictions_by_code[code] = to_flattened_binary_tags(td_predictions)
vd_wd_predictions_by_code[code] = to_flattened_binary_tags(vd_predictions)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold):
projection = lambda x: x
if STEM:
projection = stem
# Start Training
print("Fold %i Training code" % fold)
# Important - only compute code frequency from training data (NO CHEATING)
code_freq = tally_code_frequencies(essays_TD)
# For training
td_sents = to_most_common_code_tagged_sentences(essays_TD, regular_tags, code_freq, projection=projection)
vd_sents = to_most_common_code_tagged_sentences(essays_VD, regular_tags, code_freq, projection=projection)
trainer = HiddenMarkovModelTrainer()
model = trainer.train_supervised(td_sents)
td_predictions = model.tag_sents(to_sentences(td_sents))
vd_predictions = model.tag_sents(to_sentences(vd_sents))
# for evaluation - binary tags
# YS (ACTUAL)
td_sents_pset = to_label_powerset_tagged_sentences(essays_TD, regular_tags)
vd_sents_pset = to_label_powerset_tagged_sentences(essays_VD, regular_tags)
wd_td_ys_bytag = to_flattened_binary_tags_by_code(td_sents_pset, regular_tags)
wd_vd_ys_bytag = to_flattened_binary_tags_by_code(vd_sents_pset, regular_tags)
# YS (PREDICTED)
td_wd_predictions_by_code = to_flattened_binary_tags_by_code(td_predictions, regular_tags)
vd_wd_predictions_by_code = to_flattened_binary_tags_by_code(vd_predictions, regular_tags)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold):
projection = lambda x: x
if STEM:
projection = stem
# Start Training
print("Fold %i Training code" % fold)
# For training
td_sents = to_label_powerset_tagged_sentences(essays_TD, regular_tags, projection=projection)
vd_sents = to_label_powerset_tagged_sentences(essays_VD, regular_tags, projection=projection)
trainer = HiddenMarkovModelTrainer()
model = trainer.train_supervised(td_sents)
td_predictions = model.tag_sents(to_sentences(td_sents))
vd_predictions = model.tag_sents(to_sentences(vd_sents))
# for evaluation - binary tags
# YS (ACTUAL)
wd_td_ys_bytag = to_flattened_binary_tags_by_code(td_sents, regular_tags)
wd_vd_ys_bytag = to_flattened_binary_tags_by_code(vd_sents, regular_tags)
# YS (PREDICTED)
td_wd_predictions_by_code = to_flattened_binary_tags_by_code(td_predictions, regular_tags)
vd_wd_predictions_by_code = to_flattened_binary_tags_by_code(vd_predictions, regular_tags)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold, code_freq, training_opt):
# Start Training
# Start Training
print("Fold %i Training code" % fold)
# For training
td_sents = to_most_common_code_tagged_sentences(essays_TD, regular_tags, code_freq)
vd_sents = to_most_common_code_tagged_sentences(essays_VD, regular_tags, code_freq)
model_filename = models_folder + "/" + "%i_%s__%s" % (fold, "most_freq_code", str(randint(0, 9999999)))
model = CRFTagger(feature_func=comp_feat_extactor, verbose=False, training_opt=training_opt)
model.train(td_sents, model_filename)
td_predictions = model.tag_sents(to_sentences(td_sents))
vd_predictions = model.tag_sents(to_sentences(vd_sents))
# for evaluation - binary tags
# YS (ACTUAL)
td_sents_pset = to_label_powerset_tagged_sentences(essays_TD, regular_tags)
vd_sents_pset = to_label_powerset_tagged_sentences(essays_VD, regular_tags)
wd_td_ys_bytag = to_flattened_binary_tags_by_code(td_sents_pset, regular_tags)
wd_vd_ys_bytag = to_flattened_binary_tags_by_code(vd_sents_pset, regular_tags)
# YS (PREDICTED)
td_wd_predictions_by_code = to_flattened_binary_tags_by_code(td_predictions, regular_tags)
vd_wd_predictions_by_code = to_flattened_binary_tags_by_code(vd_predictions, regular_tags)
os.remove(model_filename)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold):
td_sents_by_code = to_tagged_sentences_by_code(essays_TD, regular_tags)
vd_sents_by_code = to_tagged_sentences_by_code(essays_VD, regular_tags)
wd_td_ys_bytag = dict()
wd_vd_ys_bytag = dict()
td_wd_predictions_by_code = dict()
vd_wd_predictions_by_code = dict()
for code in sorted(regular_tags):
print("Fold %i Training code: %s" % (fold, code))
td, vd = td_sents_by_code[code], vd_sents_by_code[code]
model_filename = models_folder + "/" + "%i_%s__%s" % (fold, code, str(randint(0, 9999999)))
# documentation: http://www.chokkan.org/software/crfsuite/manual.html
model = CRFTagger(feature_func=comp_feat_extactor, verbose=False)
model.train(td, model_filename)
wd_td_ys_bytag[code] = to_flattened_binary_tags(td)
wd_vd_ys_bytag[code] = to_flattened_binary_tags(vd)
td_predictions = model.tag_sents(to_sentences(td))
vd_predictions = model.tag_sents(to_sentences(vd))
# Delete model file now predictions obtained
# Note, we are randomizing name above, so we need to clean up here
os.remove(model_filename)
td_wd_predictions_by_code[code] = to_flattened_binary_tags(td_predictions)
vd_wd_predictions_by_code[code] = to_flattened_binary_tags(vd_predictions)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold,
training_opt):
# Start Training
print("Fold %i Training code" % fold)
# For training
td_sents = to_label_powerset_tagged_sentences(essays_TD, regular_tags)
vd_sents = to_label_powerset_tagged_sentences(essays_VD, regular_tags)
model_filename = models_folder + "/" + "%i_%s__%s" % (
fold, "power_set", str(randint(0, 9999999)))
model = CRFTagger(feature_func=comp_feat_extactor,
verbose=False,
training_opt=training_opt)
model.train(td_sents, model_filename)
td_predictions = model.tag_sents(to_sentences(td_sents))
vd_predictions = model.tag_sents(to_sentences(vd_sents))
# for evaluation - binary tags
# YS (ACTUAL)
wd_td_ys_bytag = to_flattened_binary_tags_by_code(td_sents, regular_tags)
wd_vd_ys_bytag = to_flattened_binary_tags_by_code(vd_sents, regular_tags)
# YS (PREDICTED)
td_wd_predictions_by_code = to_flattened_binary_tags_by_code(
td_predictions, regular_tags)
vd_wd_predictions_by_code = to_flattened_binary_tags_by_code(
vd_predictions, regular_tags)
os.remove(model_filename)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
def train_classifer_on_fold(essays_TD, essays_VD, regular_tags, fold):
# Start Training
print("Fold %i Training code" % fold)
# Important - only compute code frequency from training data (NO CHEATING)
code_freq = tally_code_frequencies(essays_TD)
# For training
td_sents = to_most_common_code_tagged_sentences(essays_TD, regular_tags,
code_freq)
vd_sents = to_most_common_code_tagged_sentences(essays_VD, regular_tags,
code_freq)
model_filename = models_folder + "/" + "%i_%s__%s" % (
fold, "most_freq_code", str(randint(0, 9999999)))
model = CRFTagger(feature_func=comp_feat_extactor, verbose=False)
model.train(td_sents, model_filename)
td_predictions = model.tag_sents(to_sentences(td_sents))
vd_predictions = model.tag_sents(to_sentences(vd_sents))
# for evaluation - binary tags
# YS (ACTUAL)
td_sents_pset = to_label_powerset_tagged_sentences(essays_TD, regular_tags)
vd_sents_pset = to_label_powerset_tagged_sentences(essays_VD, regular_tags)
wd_td_ys_bytag = to_flattened_binary_tags_by_code(td_sents_pset,
regular_tags)
wd_vd_ys_bytag = to_flattened_binary_tags_by_code(vd_sents_pset,
regular_tags)
# YS (PREDICTED)
td_wd_predictions_by_code = to_flattened_binary_tags_by_code(
td_predictions, regular_tags)
vd_wd_predictions_by_code = to_flattened_binary_tags_by_code(
vd_predictions, regular_tags)
os.remove(model_filename)
return wd_td_ys_bytag, wd_vd_ys_bytag, td_wd_predictions_by_code, vd_wd_predictions_by_code
wd_vd_ys_bytag = dict()
td_wd_predictions_by_code = dict()
vd_wd_predictions_by_code = dict()
for code in sorted(regular_tags):
print("Fold %i Training code: %s" % (fold, code))
td, vd = td_sents_by_code[code], vd_sents_by_code[code]
trainer = HiddenMarkovModelTrainer()
model = trainer.train_supervised(td)
code2model[code] = model
wd_td_ys_bytag[code] = to_flattened_binary_tags(td)
wd_vd_ys_bytag[code] = to_flattened_binary_tags(vd)
td_predictions = model.tag_sents(to_sentences(td))
vd_predictions = model.tag_sents(to_sentences(vd))
td_wd_predictions_by_code[code] = to_flattened_binary_tags(td_predictions)
vd_wd_predictions_by_code[code] = to_flattened_binary_tags(vd_predictions)
merge_dictionaries(wd_td_ys_bytag, cv_wd_td_ys_by_tag)
merge_dictionaries(wd_vd_ys_bytag, cv_wd_vd_ys_by_tag)
merge_dictionaries(td_wd_predictions_by_code, cv_wd_td_predictions_by_tag)
merge_dictionaries(vd_wd_predictions_by_code, cv_wd_vd_predictions_by_tag)
logger.info("Training completed")
""" Persist Results to Mongo DB """
wd_algo = "HMM_BR"
wd_vd_ys_bytag = dict()
td_wd_predictions_by_code = dict()
vd_wd_predictions_by_code = dict()
for code in sorted(regular_tags):
print("Fold %i Training code: %s" % (fold, code))
td, vd = td_sents_by_code[code], vd_sents_by_code[code]
trainer = HiddenMarkovModelTrainer()
model = trainer.train_supervised(td)
code2model[code] = model
wd_td_ys_bytag[code] = to_flattened_binary_tags(td)
wd_vd_ys_bytag[code] = to_flattened_binary_tags(vd)
td_predictions = model.tag_sents(to_sentences(td))
vd_predictions = model.tag_sents(to_sentences(vd))
td_wd_predictions_by_code[code] = to_flattened_binary_tags(
td_predictions)
vd_wd_predictions_by_code[code] = to_flattened_binary_tags(
vd_predictions)
merge_dictionaries(wd_td_ys_bytag, cv_wd_td_ys_by_tag)
merge_dictionaries(wd_vd_ys_bytag, cv_wd_vd_ys_by_tag)
merge_dictionaries(td_wd_predictions_by_code, cv_wd_td_predictions_by_tag)
merge_dictionaries(vd_wd_predictions_by_code, cv_wd_vd_predictions_by_tag)
logger.info("Training completed")
""" Persist Results to Mongo DB """
