def mock_cws():
os.makedirs("mock", exist_ok=True)
text = ["这是最好的基于深度学习的中文分词系统。", "大王叫我来巡山。", "我党多年来致力于改善人民生活水平。"]
word2id = Vocabulary()
word_list = [ch for ch in "".join(text)]
word2id.update(word_list)
save_pickle(word2id, "./mock/", "word2id.pkl")
class2id = Vocabulary(need_default=False)
label_list = ['B', 'M', 'E', 'S']
class2id.update(label_list)
save_pickle(class2id, "./mock/", "label2id.pkl")
model_args = {
"vocab_size": len(word2id),
"word_emb_dim": 50,
"rnn_hidden_units": 50,
"num_classes": len(class2id)
}
config_file = """
[test_section]
vocab_size = {}
word_emb_dim = 50
rnn_hidden_units = 50
num_classes = {}
""".format(len(word2id), len(class2id))
with open("mock/test.cfg", "w", encoding="utf-8") as f:
f.write(config_file)
model = AdvSeqLabel(model_args)
ModelSaver("mock/cws_basic_model_v_0.pkl").save_pytorch(model)
def mock_pos_tag():
os.makedirs("mock", exist_ok=True)
text = ["这是最好的基于深度学习的中文分词系统。", "大王叫我来巡山。", "我党多年来致力于改善人民生活水平。"]
vocab = Vocabulary()
word_list = [ch for ch in "".join(text)]
vocab.update(word_list)
save_pickle(vocab, "./mock/", "word2id.pkl")
idx2label = Vocabulary(need_default=False)
label_list = ['B-n', 'M-v', 'E-nv', 'S-adj', 'B-v', 'M-vn', 'S-adv']
idx2label.update(label_list)
save_pickle(idx2label, "./mock/", "label2id.pkl")
model_args = {
"vocab_size": len(vocab),
"word_emb_dim": 50,
"rnn_hidden_units": 50,
"num_classes": len(idx2label)
}
config_file = """
[test_section]
vocab_size = {}
word_emb_dim = 50
rnn_hidden_units = 50
num_classes = {}
""".format(len(vocab), len(idx2label))
with open("mock/test.cfg", "w", encoding="utf-8") as f:
f.write(config_file)
model = AdvSeqLabel(model_args)
ModelSaver("mock/pos_tag_model_v_0.pkl").save_pytorch(model)
def train_test():
# Config Loader
train_args = ConfigSection()
ConfigLoader().load_config(config_path, {"POS_infer": train_args})
# define dataset
data_train = TokenizeDataSetLoader().load(cws_data_path)
word_vocab = Vocabulary()
label_vocab = Vocabulary()
data_train.update_vocab(word_seq=word_vocab, label_seq=label_vocab)
data_train.index_field("word_seq",
word_vocab).index_field("label_seq", label_vocab)
data_train.set_origin_len("word_seq")
data_train.rename_field("label_seq", "truth").set_target(truth=False)
train_args["vocab_size"] = len(word_vocab)
train_args["num_classes"] = len(label_vocab)
save_pickle(word_vocab, pickle_path, "word2id.pkl")
save_pickle(label_vocab, pickle_path, "label2id.pkl")
# Trainer
trainer = SeqLabelTrainer(**train_args.data)
# Model
model = SeqLabeling(train_args)
# Start training
trainer.train(model, data_train)
# Saver
saver = ModelSaver("./save/saved_model.pkl")
saver.save_pytorch(model)
del model, trainer
# Define the same model
model = SeqLabeling(train_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, "./save/saved_model.pkl")
# Load test configuration
test_args = ConfigSection()
ConfigLoader().load_config(config_path, {"POS_infer": test_args})
test_args["evaluator"] = SeqLabelEvaluator()
# Tester
tester = SeqLabelTester(**test_args.data)
# Start testing
data_train.set_target(truth=True)
tester.test(model, data_train)
def train_test():
# Config Loader
train_args = ConfigSection()
ConfigLoader().load_config(config_path, {"POS_infer": train_args})
# define dataset
data_train = SeqLabelDataSet(load_func=TokenizeDataSetLoader.load)
data_train.load(cws_data_path)
train_args["vocab_size"] = len(data_train.word_vocab)
train_args["num_classes"] = len(data_train.label_vocab)
save_pickle(data_train.word_vocab, pickle_path, "word2id.pkl")
save_pickle(data_train.label_vocab, pickle_path, "label2id.pkl")
# Trainer
trainer = SeqLabelTrainer(**train_args.data)
# Model
model = SeqLabeling(train_args)
# Start training
trainer.train(model, data_train)
# Saver
saver = ModelSaver("./save/saved_model.pkl")
saver.save_pytorch(model)
del model, trainer
# Define the same model
model = SeqLabeling(train_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, "./save/saved_model.pkl")
# Load test configuration
test_args = ConfigSection()
ConfigLoader().load_config(config_path, {"POS_infer": test_args})
test_args["evaluator"] = SeqLabelEvaluator()
# Tester
tester = SeqLabelTester(**test_args.data)
# Start testing
change_field_is_target(data_train, "truth", True)
tester.test(model, data_train)
def test_seq_label(self):
model_args = {
"vocab_size": 10,
"word_emb_dim": 100,
"rnn_hidden_units": 100,
"num_classes": 5
}
infer_data = [['a', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e'],
['a', 'b', '#', 'd', 'e'], ['a', 'b', 'c', '?', 'e'],
['a', 'b', 'c', 'd', '$'], ['!', 'b', 'c', 'd', 'e']]
vocab = Vocabulary()
vocab.word2idx = {
'a': 0,
'b': 1,
'c': 2,
'd': 3,
'e': 4,
'!': 5,
'@': 6,
'#': 7,
'$': 8,
'?': 9
}
class_vocab = Vocabulary()
class_vocab.word2idx = {"0": 0, "1": 1, "2": 2, "3": 3, "4": 4}
os.system("mkdir save")
save_pickle(class_vocab, "./save/", "class2id.pkl")
save_pickle(vocab, "./save/", "word2id.pkl")
model = SeqLabeling(model_args)
predictor = Predictor("./save/", task="seq_label")
results = predictor.predict(network=model, data=infer_data)
self.assertTrue(isinstance(results, list))
self.assertGreater(len(results), 0)
for res in results:
self.assertTrue(isinstance(res, list))
self.assertEqual(len(res), 5)
self.assertTrue(isinstance(res[0], str))
os.system("rm -rf save")
print("pickle path deleted")
def train():
train_args, model_args = ConfigSection(), ConfigSection()
ConfigLoader.load_config(config_dir, {"text_class": train_args})
# load dataset
print("Loading data...")
data = TextClassifyDataSet(load_func=ClassDataSetLoader.load)
data.load(train_data_dir)
print("vocabulary size:", len(data.word_vocab))
print("number of classes:", len(data.label_vocab))
save_pickle(data.word_vocab, save_dir, "word2id.pkl")
save_pickle(data.label_vocab, save_dir, "label2id.pkl")
model_args["num_classes"] = len(data.label_vocab)
model_args["vocab_size"] = len(data.word_vocab)
# construct model
print("Building model...")
model = CNNText(model_args)
# train
print("Training...")
trainer = ClassificationTrainer(epochs=train_args["epochs"],
batch_size=train_args["batch_size"],
validate=train_args["validate"],
use_cuda=train_args["use_cuda"],
pickle_path=save_dir,
save_best_dev=train_args["save_best_dev"],
model_name=model_name,
loss=Loss("cross_entropy"),
optimizer=Optimizer("SGD", lr=0.001, momentum=0.9))
trainer.train(model, data)
print("Training finished!")
saver = ModelSaver(os.path.join(save_dir, model_name))
saver.save_pytorch(model)
print("Model saved!")
def mock_text_classify():
os.makedirs("mock", exist_ok=True)
text = [
"世界物联网大会明日在京召开龙头股启动在即", "乌鲁木齐市新增一处城市中心旅游目的地",
"朱元璋的大明朝真的源于明教吗？——告诉你一个真实的“明教”"
]
vocab = Vocabulary()
word_list = [ch for ch in "".join(text)]
vocab.update(word_list)
save_pickle(vocab, "./mock/", "word2id.pkl")
idx2label = Vocabulary(need_default=False)
label_list = [
'class_A', 'class_B', 'class_C', 'class_D', 'class_E', 'class_F'
]
idx2label.update(label_list)
save_pickle(idx2label, "./mock/", "label2id.pkl")
model_args = {
"vocab_size": len(vocab),
"word_emb_dim": 50,
"rnn_hidden_units": 50,
"num_classes": len(idx2label)
}
config_file = """
[test_section]
vocab_size = {}
word_emb_dim = 50
rnn_hidden_units = 50
num_classes = {}
""".format(len(vocab), len(idx2label))
with open("mock/test.cfg", "w", encoding="utf-8") as f:
f.write(config_file)
model = CNNText(model_args)
ModelSaver("mock/text_class_model_v0.pkl").save_pytorch(model)
def train():
# Config Loader
train_args = ConfigSection()
test_args = ConfigSection()
ConfigLoader().load_config(cfgfile, {
"train": train_args,
"test": test_args
})
print("loading data set...")
data = SeqLabelDataSet(load_func=TokenizeDataSetLoader.load)
data.load(cws_data_path)
data_train, data_dev = data.split(ratio=0.3)
train_args["vocab_size"] = len(data.word_vocab)
train_args["num_classes"] = len(data.label_vocab)
print("vocab size={}, num_classes={}".format(len(data.word_vocab),
len(data.label_vocab)))
change_field_is_target(data_dev, "truth", True)
save_pickle(data_dev, "./save/", "data_dev.pkl")
save_pickle(data.word_vocab, "./save/", "word2id.pkl")
save_pickle(data.label_vocab, "./save/", "label2id.pkl")
# Trainer
trainer = SeqLabelTrainer(epochs=train_args["epochs"],
batch_size=train_args["batch_size"],
validate=train_args["validate"],
use_cuda=train_args["use_cuda"],
pickle_path=train_args["pickle_path"],
save_best_dev=True,
print_every_step=10,
model_name="trained_model.pkl",
evaluator=SeqLabelEvaluator())
# Model
model = AdvSeqLabel(train_args)
try:
ModelLoader.load_pytorch(model, "./save/saved_model.pkl")
print('model parameter loaded!')
except Exception as e:
print("No saved model. Continue.")
pass
# Start training
trainer.train(model, data_train, data_dev)
print("Training finished!")
# Saver
saver = ModelSaver("./save/trained_model.pkl")
saver.save_pytorch(model)
print("Model saved!")
def test_training():
# Config Loader
trainer_args = ConfigSection()
model_args = ConfigSection()
ConfigLoader().load_config(config_dir, {
"test_seq_label_trainer": trainer_args, "test_seq_label_model": model_args})
data_set = TokenizeDataSetLoader().load(data_path)
word_vocab = Vocabulary()
label_vocab = Vocabulary()
data_set.update_vocab(word_seq=word_vocab, label_seq=label_vocab)
data_set.index_field("word_seq", word_vocab).index_field("label_seq", label_vocab)
data_set.set_origin_len("word_seq")
data_set.rename_field("label_seq", "truth").set_target(truth=False)
data_train, data_dev = data_set.split(0.3, shuffle=True)
model_args["vocab_size"] = len(word_vocab)
model_args["num_classes"] = len(label_vocab)
save_pickle(word_vocab, pickle_path, "word2id.pkl")
save_pickle(label_vocab, pickle_path, "label2id.pkl")
trainer = SeqLabelTrainer(
epochs=trainer_args["epochs"],
batch_size=trainer_args["batch_size"],
validate=False,
use_cuda=False,
pickle_path=pickle_path,
save_best_dev=trainer_args["save_best_dev"],
model_name=model_name,
optimizer=Optimizer("SGD", lr=0.01, momentum=0.9),
)
# Model
model = SeqLabeling(model_args)
# Start training
trainer.train(model, data_train, data_dev)
# Saver
saver = ModelSaver(os.path.join(pickle_path, model_name))
saver.save_pytorch(model)
del model, trainer
# Define the same model
model = SeqLabeling(model_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, os.path.join(pickle_path, model_name))
# Load test configuration
tester_args = ConfigSection()
ConfigLoader().load_config(config_dir, {"test_seq_label_tester": tester_args})
# Tester
tester = SeqLabelTester(batch_size=4,
use_cuda=False,
pickle_path=pickle_path,
model_name="seq_label_in_test.pkl",
evaluator=SeqLabelEvaluator()
)
# Start testing with validation data
data_dev.set_target(truth=True)
tester.test(model, data_dev)
def test_seq_label(self):
model_args = {
"vocab_size": 10,
"word_emb_dim": 100,
"rnn_hidden_units": 100,
"num_classes": 5
}
infer_data = [['a', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e'],
['a', 'b', '#', 'd', 'e'], ['a', 'b', 'c', '?', 'e'],
['a', 'b', 'c', 'd', '$'], ['!', 'b', 'c', 'd', 'e']]
vocab = Vocabulary()
vocab.word2idx = {
'a': 0,
'b': 1,
'c': 2,
'd': 3,
'e': 4,
'!': 5,
'@': 6,
'#': 7,
'$': 8,
'?': 9
}
class_vocab = Vocabulary()
class_vocab.word2idx = {"0": 0, "1": 1, "2": 2, "3": 3, "4": 4}
os.system("mkdir save")
save_pickle(class_vocab, "./save/", "label2id.pkl")
save_pickle(vocab, "./save/", "word2id.pkl")
model = CNNText(model_args)
import fastNLP.core.predictor as pre
predictor = Predictor("./save/", pre.text_classify_post_processor)
# Load infer data
infer_data_set = convert_seq_dataset(infer_data)
infer_data_set.index_field("word_seq", vocab)
results = predictor.predict(network=model, data=infer_data_set)
self.assertTrue(isinstance(results, list))
self.assertGreater(len(results), 0)
self.assertEqual(len(results), len(infer_data))
for res in results:
self.assertTrue(isinstance(res, str))
self.assertTrue(res in class_vocab.word2idx)
del model, predictor
infer_data_set.set_origin_len("word_seq")
model = SeqLabeling(model_args)
predictor = Predictor("./save/", pre.seq_label_post_processor)
results = predictor.predict(network=model, data=infer_data_set)
self.assertTrue(isinstance(results, list))
self.assertEqual(len(results), len(infer_data))
for i in range(len(infer_data)):
res = results[i]
self.assertTrue(isinstance(res, list))
self.assertEqual(len(res), len(infer_data[i]))
os.system("rm -rf save")
print("pickle path deleted")
def train_and_test():
# Config Loader
trainer_args = ConfigSection()
model_args = ConfigSection()
ConfigLoader().load_config(config_dir, {
"test_seq_label_trainer": trainer_args,
"test_seq_label_model": model_args
})
data_set = SeqLabelDataSet()
data_set.load(data_path)
train_set, dev_set = data_set.split(0.3, shuffle=True)
model_args["vocab_size"] = len(data_set.word_vocab)
model_args["num_classes"] = len(data_set.label_vocab)
save_pickle(data_set.word_vocab, pickle_path, "word2id.pkl")
save_pickle(data_set.label_vocab, pickle_path, "label2id.pkl")
trainer = SeqLabelTrainer(
epochs=trainer_args["epochs"],
batch_size=trainer_args["batch_size"],
validate=False,
use_cuda=trainer_args["use_cuda"],
pickle_path=pickle_path,
save_best_dev=trainer_args["save_best_dev"],
model_name=model_name,
optimizer=Optimizer("SGD", lr=0.01, momentum=0.9),
)
# Model
model = SeqLabeling(model_args)
# Start training
trainer.train(model, train_set, dev_set)
print("Training finished!")
# Saver
saver = ModelSaver(os.path.join(pickle_path, model_name))
saver.save_pytorch(model)
print("Model saved!")
del model, trainer
change_field_is_target(dev_set, "truth", True)
# Define the same model
model = SeqLabeling(model_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, os.path.join(pickle_path, model_name))
print("model loaded!")
# Load test configuration
tester_args = ConfigSection()
ConfigLoader().load_config(config_dir,
{"test_seq_label_tester": tester_args})
# Tester
tester = SeqLabelTester(batch_size=4,
use_cuda=False,
pickle_path=pickle_path,
model_name="seq_label_in_test.pkl",
evaluator=SeqLabelEvaluator())
# Start testing with validation data
tester.test(model, dev_set)
print("model tested!")