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):
# 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
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
ngram_size=1,
positional=False,
stem_words=False)
extractors = [
unigram_bow_window,
unigram_window_stemmed,
biigram_window_stemmed,
#trigram_window_stemmed,
extract_brown_cluster,
#extract_dependency_relation
]
comp_feat_extactor = fact_composite_feature_extractor(extractors)
code_freq = tally_code_frequencies(train_tagged_essays)
folds = [(train_tagged_essays, test_tagged_essays)]
for feat_poss_state in [False]:
for feat_poss_transitions in [True]:
for c2 in [1.0]: # different to CB
cv_wd_td_ys_by_tag, cv_wd_td_predictions_by_tag = defaultdict(
list), defaultdict(list)
cv_wd_vd_ys_by_tag, cv_wd_vd_predictions_by_tag = defaultdict(
list), defaultdict(list)
training_opt = {
"feature.possible_states": feat_poss_state,
"feature.possible_transitions": feat_poss_transitions,
"c2": c2
}
unigram_bow_window = fact_extract_ngram_features(offset=offset, ngram_size=1, positional=False, stem_words=False)
extractors = [
unigram_bow_window,
unigram_window_stemmed,
biigram_window_stemmed,
#trigram_window_stemmed,
extract_brown_cluster,
#extract_dependency_relation
]
comp_feat_extactor = fact_composite_feature_extractor(extractors)
code_freq = tally_code_frequencies(train_tagged_essays)
folds = [(train_tagged_essays, test_tagged_essays)]
for feat_poss_state in [False]:
for feat_poss_transitions in [True]:
for c2 in [1.0]: # different to CB
cv_wd_td_ys_by_tag, cv_wd_td_predictions_by_tag = defaultdict(list), defaultdict(list)
cv_wd_vd_ys_by_tag, cv_wd_vd_predictions_by_tag = defaultdict(list), defaultdict(list)
training_opt = {"feature.possible_states" : feat_poss_state,
"feature.possible_transitions": feat_poss_transitions,
"c2": c2
}
training_opt_copy = dict([(k.replace(".", "_"),v) for k,v in training_opt.items()])