def train_pos(args):
######################################################
#
# Data preprocessing
#
######################################################
datasets = {
args.datasetName: #Name of the dataset
{
'columns': {
0: 'tokens',
1: 'POS',
2: 'chunk_BIO'
}, #CoNLL format for the input data. Column 1 contains tokens, column 3 contains POS information
'label': 'POS', #Which column we like to predict
'evaluate': True, #Should we evaluate on this task? Set true always for single task setups
'commentSymbol': None
} #Lines in the input data starting with this string will be skipped. Can be used to skip comments
}
# :: Path on your computer to the word embeddings. Embeddings by Komninos et al. will be downloaded automatically ::
embeddingsPath = args.embeddings
#'komninos_english_embeddings.gz'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
pickleFile = perpareDataset(embeddingsPath, datasets)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [100],
'dropout': (0.25, 0.25)
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.modelSavePath = args.model_save + '/[ModelName]_[Epoch].h5'
model.fit(epochs=25)
fpath = args.model_save + '/' + args.datasetName + '_1.h5'
save_dir, model_init = os.path.split(fpath)
print(save_dir)
print(model_init)
remove_except_last_model(save_dir, model_init)
def run_experiment(dataset_id, dataset_dict, task, embeddings, mappings, data):
# set network hyperparameters and mappings/datasets
model = BiLSTM(network_params)
model.setMappings(mappings, embeddings)
model.setDataset(dataset_dict, data)
# path to store the trained model and model results
experiment_name = f'{dataset_id}_{task.lower()}'
model.modelSavePath = models_dir / f'{experiment_name}.h5'
model.storeResults(results_dir / f'{experiment_name}.csv')
# build and train the model
model.buildModel()
model.fit(
epochs=500) # do not limit training by epochs - use early stopping
def run_experiment(datasets_dict, lang, task, embeddings, mappings, data):
# set network hyperparameters and mappings/datasets
model = BiLSTM(network_params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets_dict, data)
# define the experiment name
lang_prefix = f'{lang.lower()}_' if lang is not None else ''
task_suffix = f'_{task.lower()}' if task is not None else ''
experiment_name = lang_prefix + 'datasets' + task_suffix
# path to store the trained model and model results
model.modelSavePath = models_dir / f'{experiment_name}.h5'
model.storeResults(results_dir / f'{experiment_name}.csv')
# build and train the model
model.buildModel()
model.fit(
epochs=500) # do not limit training by epochs - use early stopping
def train_and_eval_model(cfg):
"""
Load data and train model
args:
cfg (YACS YAML config)
"""
# Data preprocessing
dataset = {
"columns": {
0: "raw_tokens",
1: "boundaries"
},
# CoNLL format (tab-delineated)
# Column 0: phones
# Column 1: syllable boundary
"label": "boundaries", # Which column we like to predict
}
# Load the embeddings and the dataset. Choose whether or not to pad the words.
# Right now, padding must be done if CRF is chosen for output layer.
# The CRF layer does not support masking.
embeddings, data, mappings, vocab_size, n_class_labels, word_length = load_dataset(
dataset, dataset_name=cfg.TRAINING.DATASET, do_pad_words=True)
create_directory(cfg.CONFIG_NAME)
logger.info(
f"Starting training of `{cfg.CONFIG_NAME}` on dataset `{dataset}`")
for training_repeat in range(cfg.TRAINING.TRAINING_REPEATS):
model = BiLSTM(cfg)
model.set_vocab(vocab_size, n_class_labels, word_length, mappings)
model.set_dataset(dataset, data)
# Path to store performance scores for dev / test
model.store_results(PATH + "/" + cfg.CONFIG_NAME + "/" +
str(training_repeat) + ".csv")
model.fit(epochs=cfg.TRAINING.EPOCHS)
# TODO Replace customClassifier dengan main task + auxiliary task
custom_classifier = {}
custom_classifier[target_task] = [('LSTM', 100), 'CRF']
for task in aux_task:
custom_classifier[task] = ['CRF']
params = {
'classifier': ['CRF'],
'LSTM-Size': [100],
'dropout': (0.25, 0.25),
'charEmbeddings': 'CNN',
'customClassifier': custom_classifier
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.storeResults("/".join(
[args.root_dir_result, args.directory_name,
"performance.out"])) # Path to store performance scores for dev / test
model.predictionSavePath = "/".join([
args.root_dir_result, args.directory_name, "predictions",
"[ModelName]_[Data].conll"
]) # Path to store predictions
model.modelSavePath = "/".join(
[args.root_dir_result, args.directory_name,
"models/[ModelName].h5"]) # Path to store models
model.fit(epochs=args.nb_epoch)
}
# :: Path on your computer to the word embeddings. Embeddings by Reimers et al. will be downloaded automatically ::
embeddingsPath = 'final.txt'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
pickleFile = perpareDataset(embeddingsPath, datasets)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [100, 100],
'dropout': (0.25, 0.25),
'charEmbeddings': 'LSTM',
'maxCharLength': 30
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5"
model.fit(epochs=25)
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
# :: 数据预处理,并保存为cPickle文件
pickleFile = prepareDataset(embeddingsPath, datasets)
############################################################################################################
#
# 2.Network training
#
############################################################################################################
# :: Load the embeddings and the dataset ::
# :: 加载词向量和训练数据 ::
embeddings, mappings, data = loadDatasetPickle(pickleFile)
params = {'classifier': ['CRF'], 'LSTM-Size': [100], 'dropout': (0.25, 0.25)}
print("***** Train the model with 1 Epoch and store to disk")
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.modelSavePath = "models/my_model_[Epoch].h5"
model.fit(epochs=1)
print("\n\n\n\n------------------------")
print("***** Load the model and continue training")
newModel = BiLSTM.loadModel('models/my_model_1.h5')
newModel.setDataset(datasets, data)
newModel.modelSavePath = "models/my_reloaded_model_[Epoch].h5"
newModel.fit(epochs=1)
print("***** retrained model store at "+newModel.modelSavePath)
pickleFile = perpareDataset(embeddingsPath, datasets)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [500],
'dropout': (0.25, 0.25),
'charEmbeddings': 'LSTM',
'maxCharLength': 150,
'charEmbeddingsSize': 200,
'charLSTMSize': 200,
'charFilterLength': 20
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.storeResults('results/sentiment_results.csv'
) #Path to store performance scores for dev / test
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5" #Path to store models
model.fit(epochs=70)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [100, 100],
'dropout': (0.25, 0.25),
'charEmbeddings': 'CNN',
'maxCharLength': 50
}
print('#######################' + args.mod + ' #######################')
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.modelSavePath = "/datastore/liu121/nosqldb2/emnlp_ukplab/models/[ModelName]_bbn.h5"
eval_result = model.fit(epochs=100)
def report(eval_result, filePath):
with open(filePath, 'w+') as f:
for key in eval_result:
info = eval_result[key]
f.write('====================' + key + '====================')
f.write(info['epoch'] + '\n')
f.write(info["per_f1"] + "\n")
f.write(info['per_pre'] + '\n')
f.write(info['per_recall'] + '\n')
f.write(info["micro_f1"] + '\n')
f.write(info["micro_pre"] + '\n')
f.write(info["micro_recall"] + '\n')
f.write(info["macro_f1"] + '\n')
'evaluate': True, # Set true always for single task setups
'commentSymbol': None
} # Lines in the input data starting with this string will be skipped
}
# :: Path on your computer to the word embeddings. Embeddings by Komninos et al. will be downloaded automatically ::
# :: 词向量文件地址,采样Komninos词向量;没有则自动下载
embeddingsPath = 'komninos_english_embeddings.gz'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
# :: 数据预处理,并保存为cPickle文件
pickleFile = prepareDataset(embeddingsPath, datasets)
############################################################################################################
#
# 2.Network training
#
############################################################################################################
# :: Load the embeddings and the dataset ::
# :: 加载词向量和训练数据 ::
embeddings, mappings, data = loadDatasetPickle(pickleFile)
params = {'classifier': ['CRF'], 'LSTM-Size': [100], 'dropout': (0.25, 0.25)}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.storeResults('results/unidep_pos_results.csv'
) # Path to store performance scores for dev/test
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5" # Path to store models
model.fit(epochs=10)
# embeddingsPath = 'embeddings.vec'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
pickleFile = perpareDataset(embeddingsPath, datasets, useExistent=False)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {'classifier': ['CRF'], 'LSTM-Size': [100, 100], 'dropout': (0.5, 0.5), 'charEmbeddings':'LSTM',
'optimizer': 'adam', 'featureNames': ['tokens', 'casing']}
MODEL = BiLSTM(params)
MODEL.setMappings(mappings, embeddings)
MODEL.setDataset(datasets, data)
MODEL.storeResults('results/Jurica_NER.csv') #Path to store performance scores for dev / test
MODEL.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5"
MODEL.fit(epochs=100)
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [100],
'dropout': (0.25, 0.25),
'charEmbeddings': 'CNN'
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data,
mainModelName='MIT_Restaurant') # KHUSUS MULTITSAK
model.storeResults("/".join(
["results", args.directory_name,
"performance.out"])) #Path to store performance scores for dev / test
model.predictionSavePath = "/".join([
"results", args.directory_name, "predictions",
"[ModelName]_[Epoch]_[Data].conll"
]) #Path to store predictions
model.modelSavePath = "/".join([
"results", args.directory_name,
"models/model_[DevScore]_[TestScore]_[Epoch].h5"
]) #Path to store models
model.fit(epochs=50)
'commentSymbol': None
},
}
embeddingsPath = 'more_embedding.tsv' #Word embeddings by Levy et al: https://levyomer.wordpress.com/2014/04/25/dependency-based-word-embeddings/
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
pickleFile = perpareDataset(embeddingsPath, datasets)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['Softmax'],
'LSTM-Size': [500],
'dropout': (0.25, 0.25)
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.modelSavePath = "models/multi_[ModelName]_[DevScore]_[TestScore]_[Epoch].h5"
model.fit(epochs=60)
# :: Path on your computer to the word embeddings. Embeddings by Komninos et al. will be downloaded automatically ::
embeddingsPath = 'komninos_english_embeddings.gz'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
pickleFile = perpareDataset(embeddingsPath, datasets)
######################################################
#
# The training of the network starts here
#
######################################################
#Load the embeddings and the dataset
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [100, 100],
'dropout': (0.25, 0.25)
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.storeResults('results/quote_direct.csv'
) #Path to store performance scores for dev / test
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5" #Path to store models
model.fit(epochs=20)
embeddings, mappings, data = loadDatasetPickle(pickleFile)
# Some network hyperparameters
params = {
'classifier': ['CRF'],
'LSTM-Size': [100, 100],
'dropout': (0.25, 0.25),
'charEmbeddings': 'CNN',
'maxCharLength': 50
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5"
history = model.fit(epochs=30)
with open('training_history.json', 'w') as outfile:
json.dump(history, outfile)
# # Visualize training
# import matplotlib.pyplot as plt
# hist = pd.DataFrame(history)
# plt.style.use("ggplot")
# plt.figure(figsize=(7,5))
# plt.plot(hist["epoch"], hist["dev"])
# plt.plot(hist["epoch"], hist["test"])
# plt.xlabel('Epoch')
# plt.ylabel('F1 score')
# plt.ylim(0, 1)
# plt.legend(['dev', 'test'], loc='upper left')
# :: Path on your computer to the word embeddings. Embeddings by Komninos et al. will be downloaded automatically ::
# :: 词向量文件地址,采样Komninos词向量;没有则自动下载
embeddingsPath = 'komninos_english_embeddings.gz'
# :: Prepares the dataset to be used with the LSTM-network. Creates and stores cPickle files in the pkl/ folder ::
# :: 数据预处理,并保存为cPickle文件
pickleFile = prepareDataset(embeddingsPath, datasets)
############################################################################################################
#
# 2.Network training
#
############################################################################################################
# :: Load the embeddings and the dataset ::
# :: 加载词向量和训练数据 ::
embeddings, mappings, data = loadDatasetPickle(pickleFile)
params = {
'classifier': ['CRF'],
'LSTM-Size': [100, 100],
'dropout': (0.25, 0.25)
}
model = BiLSTM(params)
model.setMappings(mappings, embeddings)
model.setDataset(datasets, data)
model.storeResults('results/conll2000_chunking.csv'
) # Path to store performance scores for dev / test
model.modelSavePath = "models/[ModelName]_[DevScore]_[TestScore]_[Epoch].h5"
model.fit(epochs=5)
