def infer():
# Config Loader
test_args = ConfigSection()
ConfigLoader().load_config(cfgfile, {"POS_test": test_args})
# fetch dictionary size and number of labels from pickle files
word2index = load_pickle(pickle_path, "word2id.pkl")
test_args["vocab_size"] = len(word2index)
index2label = load_pickle(pickle_path, "label2id.pkl")
test_args["num_classes"] = len(index2label)
# Define the same model
model = AdvSeqLabel(test_args)
try:
ModelLoader.load_pytorch(model, "./save/trained_model.pkl")
print('model loaded!')
except Exception as e:
print('cannot load model!')
raise
# Data Loader
infer_data = SeqLabelDataSet(load_func=BaseLoader.load_lines)
infer_data.load(data_infer_path,
vocabs={"word_vocab": word2index},
infer=True)
print('data loaded')
# Inference interface
infer = SeqLabelInfer(pickle_path)
results = infer.predict(model, infer_data)
print(results)
print("Inference finished!")
def test_case_1(self):
def loader(path):
labeled_data_list = [
[["a", "b", "e", "d"], ["1", "2", "3", "4"]],
[["a", "b", "e", "d"], ["1", "2", "3", "4"]],
[["a", "b", "e", "d"], ["1", "2", "3", "4"]],
]
return labeled_data_list
data_set = SeqLabelDataSet(load_func=loader)
data_set.load("any_path")
self.assertEqual(len(data_set), len(self.labeled_data_list))
self.assertTrue(len(data_set) > 0)
self.assertTrue(hasattr(data_set[0], "fields"))
self.assertTrue("word_seq" in data_set[0].fields)
self.assertTrue(hasattr(data_set[0].fields["word_seq"], "text"))
self.assertTrue(hasattr(data_set[0].fields["word_seq"], "_index"))
self.assertEqual(data_set[0].fields["word_seq"].text, self.labeled_data_list[0][0])
self.assertTrue("truth" in data_set[0].fields)
self.assertTrue(hasattr(data_set[0].fields["truth"], "text"))
self.assertTrue(hasattr(data_set[0].fields["truth"], "_index"))
self.assertEqual(data_set[0].fields["truth"].text, self.labeled_data_list[0][1])
self.assertTrue("word_seq_origin_len" in data_set[0].fields)
def infer():
# Load infer configuration, the same as test
test_args = ConfigSection()
ConfigLoader().load_config(config_path, {"POS_infer": test_args})
# fetch dictionary size and number of labels from pickle files
word2index = load_pickle(pickle_path, "word2id.pkl")
test_args["vocab_size"] = len(word2index)
index2label = load_pickle(pickle_path, "label2id.pkl")
test_args["num_classes"] = len(index2label)
# Define the same model
model = SeqLabeling(test_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, "./save/saved_model.pkl")
print("model loaded!")
# Load infer data
infer_data = SeqLabelDataSet(load_func=BaseLoader.load)
infer_data.load(data_infer_path, vocabs={"word_vocab": word2index}, infer=True)
# inference
infer = SeqLabelInfer(pickle_path)
results = infer.predict(model, infer_data)
print(results)
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_case_1(self):
args = {
"epochs": 3,
"batch_size": 2,
"validate": False,
"use_cuda": False,
"pickle_path": "./save/",
"save_best_dev": True,
"model_name": "default_model_name.pkl",
"loss": Loss("cross_entropy"),
"optimizer": Optimizer("Adam", lr=0.001, weight_decay=0),
"vocab_size": 10,
"word_emb_dim": 100,
"rnn_hidden_units": 100,
"num_classes": 5,
"evaluator": SeqLabelEvaluator()
}
trainer = SeqLabelTrainer(**args)
train_data = [
[['a', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', '@', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', '#', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', 'c', '?', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', 'c', 'd', '$'], ['a', '@', 'c', 'd', 'e']],
[['!', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
]
vocab = {
'a': 0,
'b': 1,
'c': 2,
'd': 3,
'e': 4,
'!': 5,
'@': 6,
'#': 7,
'$': 8,
'?': 9
}
label_vocab = {'a': 0, '@': 1, 'c': 2, 'd': 3, 'e': 4}
data_set = SeqLabelDataSet()
for example in train_data:
text, label = example[0], example[1]
x = TextField(text, False)
x_len = LabelField(len(text), is_target=False)
y = TextField(label, is_target=False)
ins = Instance(word_seq=x, truth=y, word_seq_origin_len=x_len)
data_set.append(ins)
data_set.index_field("word_seq", vocab)
data_set.index_field("truth", label_vocab)
model = SeqLabeling(args)
trainer.train(network=model, train_data=data_set, dev_data=data_set)
# If this can run, everything is OK.
os.system("rm -rf save")
print("pickle path deleted")
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_case_2(self):
def loader(path):
unlabeled_data_list = [
["a", "b", "e", "d"],
["a", "b", "e", "d"],
["a", "b", "e", "d"]
]
return unlabeled_data_list
data_set = SeqLabelDataSet(load_func=loader)
data_set.load("any_path", vocabs={"word_vocab": self.word_vocab}, infer=True)
self.assertEqual(len(data_set), len(self.labeled_data_list))
self.assertTrue(len(data_set) > 0)
self.assertTrue(hasattr(data_set[0], "fields"))
self.assertTrue("word_seq" in data_set[0].fields)
self.assertTrue(hasattr(data_set[0].fields["word_seq"], "text"))
self.assertTrue(hasattr(data_set[0].fields["word_seq"], "_index"))
self.assertEqual(data_set[0].fields["word_seq"].text, self.labeled_data_list[0][0])
self.assertEqual(data_set[0].fields["word_seq"]._index,
[self.word_vocab[c] for c in self.labeled_data_list[0][0]])
self.assertTrue("word_seq_origin_len" in data_set[0].fields)
def infer():
# Load infer configuration, the same as test
test_args = ConfigSection()
ConfigLoader().load_config(config_dir, {"POS_infer": test_args})
# fetch dictionary size and number of labels from pickle files
word_vocab = load_pickle(pickle_path, "word2id.pkl")
label_vocab = load_pickle(pickle_path, "label2id.pkl")
test_args["vocab_size"] = len(word_vocab)
test_args["num_classes"] = len(label_vocab)
print("vocabularies loaded")
# Define the same model
model = SeqLabeling(test_args)
print("model defined")
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, os.path.join(pickle_path, model_name))
print("model loaded!")
# Data Loader
infer_data = SeqLabelDataSet(load_func=BaseLoader.load)
infer_data.load(data_infer_path,
vocabs={
"word_vocab": word_vocab,
"label_vocab": label_vocab
},
infer=True)
print("data set prepared")
# Inference interface
infer = SeqLabelInfer(pickle_path)
results = infer.predict(model, infer_data)
for res in results:
print(res)
print("Inference finished!")
def _create_data_set(self, infer_input):
"""Create a DataSet object given the raw inputs.
:param infer_input: 2-D lists of strings
:return data_set: a DataSet object
"""
if self.infer_type == "seq_label":
data_set = SeqLabelDataSet()
data_set.load_raw(infer_input, {"word_vocab": self.word_vocab})
return data_set
elif self.infer_type == "text_class":
data_set = TextClassifyDataSet()
data_set.load_raw(infer_input, {"word_vocab": self.word_vocab})
return data_set
else:
raise RuntimeError("fail to make outputs with infer type {}".format(self.infer_type))
def test_case_1(self):
model_args = {
"vocab_size": 10,
"word_emb_dim": 100,
"rnn_hidden_units": 100,
"num_classes": 5
}
valid_args = {
"save_output": True,
"validate_in_training": True,
"save_dev_input": True,
"save_loss": True,
"batch_size": 2,
"pickle_path": "./save/",
"use_cuda": False,
"print_every_step": 1,
"evaluator": SeqLabelEvaluator()
}
train_data = [
[['a', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', '@', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', '#', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', 'c', '?', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', 'c', 'd', '$'], ['a', '@', 'c', 'd', 'e']],
[['!', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
]
vocab = {
'a': 0,
'b': 1,
'c': 2,
'd': 3,
'e': 4,
'!': 5,
'@': 6,
'#': 7,
'$': 8,
'?': 9
}
label_vocab = {'a': 0, '@': 1, 'c': 2, 'd': 3, 'e': 4}
data_set = SeqLabelDataSet()
for example in train_data:
text, label = example[0], example[1]
x = TextField(text, False)
x_len = LabelField(len(text), is_target=False)
y = TextField(label, is_target=True)
ins = Instance(word_seq=x, truth=y, word_seq_origin_len=x_len)
data_set.append(ins)
data_set.index_field("word_seq", vocab)
data_set.index_field("truth", label_vocab)
model = SeqLabeling(model_args)
tester = SeqLabelTester(**valid_args)
tester.test(network=model, dev_data=data_set)
# If this can run, everything is OK.
os.system("rm -rf save")
print("pickle path deleted")
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 = TextClassifyDataSet(load_func=BaseLoader.load)
infer_data_set.convert_for_infer(infer_data,
vocabs={"word_vocab": vocab.word2idx})
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
model = SeqLabeling(model_args)
predictor = Predictor("./save/", pre.seq_label_post_processor)
infer_data_set = SeqLabelDataSet(load_func=BaseLoader.load)
infer_data_set.convert_for_infer(infer_data,
vocabs={"word_vocab": vocab.word2idx})
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!")