def main():
print("读取数据...")
train_word_lists, train_tag_lists, word2id, tag2id = \
build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test", make_vocab=False)
dev_word_lists_, dev_word_lists_raw, article_id = loadDevFile("development_2.txt")
print("加载并评估hmm模型...")
hmm_model = load_model(HMM_MODEL_PATH)
#hmm_pred = hmm_model.test(test_word_lists,
# word2id,
# tag2id)
hmm_pred_dev = hmm_model.test(dev_word_lists_,
word2id,
tag2id)
output_pred(hmm_pred_dev, article_id, dev_word_lists_raw)
metrics = Metrics(test_tag_lists, hmm_pred, remove_O=REMOVE_O)
metrics.report_scores() # 打印每个标记的精确度、召回率、f1分数
metrics.report_confusion_matrix() # 打印混淆矩阵
# 加载并评估CRF模型
print("加载并评估crf模型...")
crf_model = load_model(CRF_MODEL_PATH)
crf_pred = crf_model.test(test_word_lists)
metrics = Metrics(test_tag_lists, crf_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
# bilstm模型
print("加载并评估bilstm模型...")
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
bilstm_model = load_model(BiLSTM_MODEL_PATH)
bilstm_model.model.bilstm.flatten_parameters() # remove warning
lstm_pred, target_tag_list = bilstm_model.test(test_word_lists, test_tag_lists,
bilstm_word2id, bilstm_tag2id)
metrics = Metrics(target_tag_list, lstm_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
print("加载并评估bilstm+crf模型...")
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
bilstm_model = load_model(BiLSTMCRF_MODEL_PATH)
bilstm_model.model.bilstm.bilstm.flatten_parameters() # remove warning
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True
)
lstmcrf_pred, target_tag_list = bilstm_model.test(test_word_lists, test_tag_lists,
crf_word2id, crf_tag2id)
metrics = Metrics(target_tag_list, lstmcrf_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
ensemble_evaluate(
[hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
test_tag_lists
)
def main():
"""训练模型，评估结果"""
# 读取数据
print("读取数据...")
train_word_lists, train_tag_lists, word2id, tag2id = \
build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test", make_vocab=False)
#### # 训练评估ｈｍｍ模型
#### print("正在训练评估HMM模型...")
#### hmm_pred = hmm_train_eval(
#### (train_word_lists, train_tag_lists),
#### (test_word_lists, test_tag_lists),
#### word2id,
#### tag2id
#### )
####
#### # 训练评估CRF模型
#### print("正在训练评估CRF模型...")
#### crf_pred = crf_train_eval(
#### (train_word_lists, train_tag_lists),
#### (test_word_lists, test_tag_lists)
#### )
####
#### # 训练评估BI-LSTM模型
#### print("正在训练评估双向LSTM模型...")
#### # LSTM模型训练的时候需要在word2id和tag2id加入PAD和UNK
#### bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
#### lstm_pred = bilstm_train_and_eval(
#### (train_word_lists, train_tag_lists),
#### (dev_word_lists, dev_tag_lists),
#### (test_word_lists, test_tag_lists),
#### bilstm_word2id, bilstm_tag2id,
#### crf=False
#### )
print("正在训练评估Bi-LSTM+CRF模型...")
# 如果是加了CRF的lstm还要加入<start>和<end> (解码的时候需要用到)
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
# 还需要额外的一些数据处理
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists), (dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists), crf_word2id, crf_tag2id)
ensemble_evaluate(
# [hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
[lstmcrf_pred],
test_tag_lists)
def main():
"""训练模型，评估结果"""
# 读取数据
print("读取数据...")
data_folder = "./data123"
train_word_lists, train_tag_lists, word2id, tag2id = \
build_corpus("train", data_dir=data_folder)
dev_word_lists, dev_tag_lists = build_corpus("dev",
make_vocab=False,
data_dir=data_folder)
test_word_lists, test_tag_lists = build_corpus("test",
make_vocab=False,
data_dir=data_folder)
# 训练评估ｈｍｍ模型
print("正在训练评估HMM模型...")
hmm_pred = hmm_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists), word2id,
tag2id)
# 训练评估CRF模型
print("正在训练评估CRF模型...")
crf_pred = crf_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists))
# 训练评估BI-LSTM模型
print("正在训练评估双向LSTM模型...")
# LSTM模型训练的时候需要在word2id和tag2id加入PAD和UNK
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
lstm_pred = bilstm_train_and_eval((train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
bilstm_word2id,
bilstm_tag2id,
crf=False)
print("正在训练评估Bi-LSTM+CRF模型...")
# 如果是加了CRF的lstm还要加入<start>和<end> (解码的时候需要用到)
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
# 还需要额外的一些数据处理
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists), (dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists), crf_word2id, crf_tag2id)
ensemble_evaluate([hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
test_tag_lists)
def main():
print("Read data...")
train_word_lists, train_tag_lists, word2id, tag2id = \
build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test", make_vocab=False)
print("Load and evaluate the hmm model...")
hmm_model = load_model(HMM_MODEL_PATH)
hmm_pred = hmm_model.test(test_word_lists, word2id, tag2id)
metrics = Metrics(test_tag_lists, hmm_pred, remove_O=REMOVE_O)
metrics.report_scores(
) # Print the accuracy of each mark, recall rate, f1 score
metrics.report_confusion_matrix() #Print confusion matrix
# Load and evaluate the CRF model
print("Load and evaluate the crf model...")
crf_model = load_model(CRF_MODEL_PATH)
crf_pred = crf_model.test(test_word_lists)
metrics = Metrics(test_tag_lists, crf_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
# bilstm Model
print("Load and evaluate the bilstm model...")
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
bilstm_model = load_model(BiLSTM_MODEL_PATH)
bilstm_model.model.bilstm.flatten_parameters() # remove warning
lstm_pred, target_tag_list = bilstm_model.test(test_word_lists,
test_tag_lists,
bilstm_word2id,
bilstm_tag2id)
metrics = Metrics(target_tag_list, lstm_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
print("Load and evaluate the bilstm+crf model...")
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
bilstm_model = load_model(BiLSTMCRF_MODEL_PATH)
bilstm_model.model.bilstm.bilstm.flatten_parameters() # remove warning
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred, target_tag_list = bilstm_model.test(test_word_lists,
test_tag_lists,
crf_word2id, crf_tag2id)
metrics = Metrics(target_tag_list, lstmcrf_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
ensemble_evaluate([hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
test_tag_lists)
def main():
"""模型训练与评估"""
# 读取数据
print("读取数据中...")
train_word_lists, train_tag_lists, word2id, tag2id = build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test", make_vocab=False)
#训练并评估hmm模型
print("正在训练评估HMM模型")
hmm_pred = hmm_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists), word2id,
tag2id)
# 训练并评估crf模型
crf_pred = crf_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists))
#训练并评估bilstm模型
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
lstm_pred = bilstm_train_and_eval((train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
bilstm_word2id,
bilstm_tag2id,
crf=False)
print("正在训练评估Bi-LSTM+CRF模型...")
# 如果是加了CRF的lstm还要加入<start>和<end> (解码的时候需要用到)
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
print(' '.join([i[0] for i in crf_tag2id.items()]))
# 还需要额外的一些数据处理
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists), (dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists), crf_word2id, crf_tag2id)
ensemble_evaluate([hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
test_tag_lists)
def decode(input_status, output_file):
print("读取数据...")
train_word_lists, train_tag_lists, word2id1, tag2id = build_corpus(
"train", make_vocab=True)
decode_word_lists, decode_tag_lists, word2id2, tag2id1 = build_corpus(
input_status, make_vocab=True)
lists = train_word_lists + decode_word_lists
word2id = build_map(lists)
print("加载并评估hmm模型...")
hmm_model = load_model(HMM_MODEL_PATH)
hmm_pred = hmm_model.test(decode_word_lists, word2id, tag2id)
print("加载并评估crf模型...")
crf_model = load_model(CRF_MODEL_PATH)
crf_pred = crf_model.test(decode_word_lists)
print("加载并评估bilstm模型...")
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
bilstm_model = load_model(BiLSTM_MODEL_PATH)
bilstm_model.model.bilstm.flatten_parameters() # remove warning
lstm_pred, target_tag_list = bilstm_model.test(decode_word_lists,
decode_tag_lists,
bilstm_word2id,
bilstm_tag2id)
print("加载并评估bilstm+crf模型...")
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
bilstm_model = load_model(BiLSTMCRF_MODEL_PATH)
bilstm_model.model.bilstm.bilstm.flatten_parameters() # remove warning
decode_word_lists, decode_tag_lists = prepocess_data_for_lstmcrf(
decode_word_lists, decode_tag_lists, test=True)
lstmcrf_pred, target_tag_list = bilstm_model.test(decode_word_lists,
decode_tag_lists,
crf_word2id, crf_tag2id)
print("加载并评估lattice lstm模型...")
latticelstm_pred = run(status='decode')
print("加载并评估ensemble模型...")
predict_results = ensemble_evaluate(hmm_pred,
crf_pred,
lstm_pred,
lstmcrf_pred,
latticelstm_pred,
decode_tag_lists,
status='decode')
print("输出解码结果...")
write_decoded_results(output_file, predict_results, decode_word_lists)
def main(args):
"""训练模型，评估结果"""
output_directory = os.path.join('ckpts', args.name)
if not os.path.isdir(output_directory):
os.makedirs(output_directory)
os.chmod(output_directory, 0o775)
shutil.copy2('models/config.py', output_directory)
# 读取数据
print("读取数据...")
train_word_lists, train_tag_lists, word2id, tag2id = build_corpus("train", fix_length=-1)
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test", make_vocab=False)
# 训练评估HMM模型
print("正在训练评估HMM模型...")
hmm_pred = hmm_train_eval(
(train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists),
word2id,
tag2id,
output_directory
)
# 训练评估CRF模型
print("正在训练评估CRF模型...")
crf_pred = crf_train_eval(
(train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists),
output_directory
)
# 训练评估BI-LSTM模型
print("正在训练评估双向LSTM模型...")
# LSTM模型训练的时候需要在word2id和tag2id加入PAD和UNK
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
lstm_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
bilstm_word2id, bilstm_tag2id,
output_directory,
crf=False
)
print("正在训练评估Bi-LSTM+CRF模型...")
# 如果是加了CRF的lstm还要加入<start>和<end> (解码的时候需要用到)
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
# 还需要额外的一些数据处理
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists
)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists
)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True
)
lstmcrf_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
crf_word2id, crf_tag2id,
output_directory
)
ensemble_evaluate(
[hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
test_tag_lists
)
def main():
"""训练模型，评估结果"""
# 读取数据
print("读取数据...")
train_word_lists, train_tag_lists, word2id, tag2id = build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
#test_word_lists, test_tag_lists = build_corpus("test", make_vocab=False)
test_word_lists, test_tag_lists, article_id = loadDevFile(
"development_2.txt")
# # 训练评估ｈｍｍ模型
# # print("正在训练评估HMM模型...")
# # hmm_pred = hmm_train_eval(
# # (train_word_lists, train_tag_lists),
# # (dev_word_lists_, test_tag_lists),
# # word2id,
# # tag2id,
# # remove_O=True
# # )
# # output_pred(hmm_pred, article_id, dev_word_lists_raw)
# # 训练评估CRF模型
# print("正在训练评估CRF模型...")
# crf_pred = crf_train_eval(
# (train_word_lists, train_tag_lists),
# (dev_word_lists_, test_tag_lists),
# remove_O=True
# )
# output_pred(crf_pred, article_id, dev_word_lists_raw,output_path = 'output_crf.tsv')
# 训练评估BI-LSTM模型
print("正在训练评估双向LSTM模型...")
# LSTM模型训练的时候需要在word2id和tag2id加入PAD和UNK
bilstm_word2id, bilstm_tag2id = extend_maps(word2id, tag2id, for_crf=False)
lstm_pred = bilstm_train_and_eval((train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
bilstm_word2id,
bilstm_tag2id,
crf=False,
remove_O=True)
print("正在训练评估Bi-LSTM+CRF模型...")
# 如果是加了CRF的lstm还要加入<start>和<end> (解码的时候需要用到)
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
# 还需要额外的一些数据处理
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred = bilstm_train_and_eval((train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
crf_word2id,
crf_tag2id,
remove_O=True)
ensemble_evaluate([hmm_pred, crf_pred, lstm_pred, lstmcrf_pred],
test_tag_lists)
def main():
"""Training model and evaluating results!"""
# selecting model
do_hmm_in_main = False
do_crf_in_main = False
do_bilstm_in_main = False
do_bilstmcrf_in_main = True
do_ensemble_in_main = False
ensemble_model_list = []
# Data
print("Reading data:")
ner_data_dir = "./datasets/FA_NER_Data_IOB"
train_word_lists, train_tag_lists, word2id, tag2id = build_corpus(
"train", data_dir=ner_data_dir)
dev_word_lists, dev_tag_lists = build_corpus("dev",
make_vocab=False,
data_dir=ner_data_dir)
test_word_lists, test_tag_lists = build_corpus("test",
make_vocab=False,
data_dir=ner_data_dir)
print("len(train_word_lists):", len(train_word_lists))
print("len(word2id=vocab):", len(word2id))
if do_hmm_in_main:
# Training and Evaluating HMM model
print("Training and Evaluating HMM model:")
hmm_pred = hmm_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists), word2id,
tag2id)
ensemble_model_list.append(hmm_pred)
if do_crf_in_main:
# Training and evaluating CRF model
print("Training and evaluating CRF model:")
crf_pred = crf_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists))
ensemble_model_list.append(crf_pred)
if do_bilstm_in_main:
# Training and evaluating BI-LSTM model
print("Training and evaluating Bi-LSTM model:")
# We need to put 'PAD' and 'UNK' in word2id and tag2id, when we train LSTM model.
bilstm_word2id, bilstm_tag2id = extend_maps(word2id,
tag2id,
for_crf=False)
lstm_pred = bilstm_train_and_eval((train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
bilstm_word2id,
bilstm_tag2id,
crf=False)
ensemble_model_list.append(lstm_pred)
if do_bilstmcrf_in_main:
# Training and evaluating Bi-LSTM+CRF model
print("Training and evaluating Bi-LSTM-CRF model:")
# We need to add <start> and <end>, when we use lstm model with CRF (will be used during decoder processing).
crf_word2id, crf_tag2id = extend_maps(word2id, tag2id, for_crf=True)
# data processing
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists), (test_word_lists, test_tag_lists),
crf_word2id,
crf_tag2id,
remove_O=False,
reload_model=True)
ensemble_model_list.append(lstmcrf_pred)
if do_ensemble_in_main:
ensemble_evaluate(ensemble_model_list, test_tag_lists)
def main_rep1(x, y):
if x == 'train':
# select data according to args.process
print("Read data...")
train_word_lists, train_tag_lists, word2id, tag2id = \
build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test",
make_vocab=False)
######
if y == 'crf':
crf_pred = crf_train_eval((train_word_lists, train_tag_lists),
(test_word_lists, test_tag_lists))
ensemble_evaluate([crf_pred], test_tag_lists)
elif y == 'bilstm':
bilstm_word2id, bilstm_tag2id = extend_maps(word2id,
tag2id,
for_crf=False)
lstm_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists),
bilstm_word2id,
bilstm_tag2id,
crf=False)
ensemble_evaluate([lstm_pred], test_tag_lists)
elif y == 'bilstm-crf':
crf_word2id, crf_tag2id = extend_maps(word2id,
tag2id,
for_crf=True)
# more data processing
train_word_lists, train_tag_lists = prepocess_data_for_lstmcrf(
train_word_lists, train_tag_lists)
dev_word_lists, dev_tag_lists = prepocess_data_for_lstmcrf(
dev_word_lists, dev_tag_lists)
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred = bilstm_train_and_eval(
(train_word_lists, train_tag_lists),
(dev_word_lists, dev_tag_lists),
(test_word_lists, test_tag_lists), crf_word2id, crf_tag2id)
ensemble_evaluate([lstmcrf_pred], test_tag_lists)
else:
HMM_MODEL_PATH = './ckpts/hmm.pkl'
CRF_MODEL_PATH = './ckpts/crf.pkl'
BiLSTM_MODEL_PATH = './ckpts/bilstm.pkl'
BiLSTMCRF_MODEL_PATH = './ckpts/bilstm_crf.pkl'
REMOVE_O = False # Whether to remove the O mark at the time of evaluation
# select data according to args.process
print("Read data...")
train_word_lists, train_tag_lists, word2id, tag2id = \
build_corpus("train")
dev_word_lists, dev_tag_lists = build_corpus("dev", make_vocab=False)
test_word_lists, test_tag_lists = build_corpus("test",
make_vocab=False)
if y == 'crf':
crf_model = load_model_1(CRF_MODEL_PATH)
crf_pred = crf_model.test(test_word_lists)
metrics = Metrics(test_tag_lists, crf_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
elif y == 'bilstm':
bilstm_word2id, bilstm_tag2id = extend_maps(word2id,
tag2id,
for_crf=False)
bilstm_model = load_model_1(BiLSTM_MODEL_PATH)
bilstm_model.model.bilstm.flatten_parameters() # remove warning
lstm_pred, target_tag_list = bilstm_model.test(
test_word_lists, test_tag_lists, bilstm_word2id, bilstm_tag2id)
metrics = Metrics(target_tag_list, lstm_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
elif y == 'bilstm-crf':
crf_word2id, crf_tag2id = extend_maps(word2id,
tag2id,
for_crf=True)
bilstm_model = load_model_1(BiLSTMCRF_MODEL_PATH)
bilstm_model.model.bilstm.bilstm.flatten_parameters(
) # remove warning
test_word_lists, test_tag_lists = prepocess_data_for_lstmcrf(
test_word_lists, test_tag_lists, test=True)
lstmcrf_pred, target_tag_list = bilstm_model.test(
test_word_lists, test_tag_lists, crf_word2id, crf_tag2id)
metrics = Metrics(target_tag_list, lstmcrf_pred, remove_O=REMOVE_O)
metrics.report_scores()
metrics.report_confusion_matrix()
exit()
