'BERT_VERSION': 1,
'BATCH_SIZE': 16,
'EPOCHS': 3,
'OPTIMIZER': 'adam',
'LEARNING_RATE': 2e-6,
'PREPROCESSING_ALGORITHM_UUID': algorithm_id,
'PREPROCESSING_ALGORITHM': preprocessing_algorithm,
'KFOLD_HISTORY': []
}
kfold = StratifiedKFold(n_splits=KFOLD, shuffle=True, random_state=SEED)
if algorithm_id != 'None':
train_data['preprocessed'] = tweets_preprocessor.preprocess(
train_data.text,
preprocessing_algorithm,
keywords=train_data.keyword,
locations=train_data.location)
test_data['preprocessed'] = tweets_preprocessor.preprocess(
test_data.text,
preprocessing_algorithm,
keywords=test_data.keyword,
locations=test_data.location)
else:
train_data['preprocessed'] = train_data.text
test_data['preprocessed'] = test_data.text
inputs = train_data['preprocessed']
targets = train_data['target']
if USE_GLOVE:
MODEL['GLOVE'] = {'SIZE': 200}
GLOVE = f'glove.twitter.27B.{MODEL["GLOVE"]["SIZE"]}d.txt'
GLOVE_FILE_PATH = f'./data/glove/{GLOVE}'
GLOVE_EMBEDDINGS = get_glove_embeddings(GLOVE_FILE_PATH)
MODEL['UUID'] = str(uuid.uuid4())
MODEL['PREPROCESSING_ALGORITHM'] = PREPROCESSING_ALGORITHM
MODEL['PREPROCESSING_ALGORITHM_UUID'] = PREPROCESSING_ALGORITHM_ID
MODEL['DIR'] = f'./data-saved-models/glove-false/{NETWORK_KEY}/'
ensure_path_exists(MODEL['DIR'])
MODEL['PREFIX'] = f'{NETWORK_KEY}-{PREPROCESSING_ALGORITHM_ID}-SEED-{SEED}'
train_data['preprocessed'] = tweets_preprocessor.preprocess(
train_data.text,
PREPROCESSING_ALGORITHM,
keywords=train_data.keyword,
locations=train_data.location)
test_data['preprocessed'] = tweets_preprocessor.preprocess(
test_data.text,
PREPROCESSING_ALGORITHM,
keywords=test_data.keyword,
locations=test_data.location)
train_inputs, val_inputs, train_targets, val_targets = train_test_split(
train_data['preprocessed'],
train_data['target'],
test_size=0.3,
random_state=SEED)