def configure_ermlp_training_pipeline(model_name: str):
"""Configure ERMLP from pipeline.
:param model_name: name of the model
:rtype: OrderedDict
:return: configuration dictionary
"""
config = get_config_dict(model_name)
# Step 1: Query embedding dimension
print_training_embedding_dimension_message()
print_embedding_dimension_info_message()
embedding_dimension = select_integer_value(
print_msg=EMBEDDING_DIMENSION_PRINT_MSG,
prompt_msg=EMBEDDING_DIMENSION_PROMPT_MSG,
error_msg=EMBEDDING_DIMENSION_ERROR_MSG)
config[EMBEDDING_DIM] = embedding_dimension
print_section_divider()
# Step 2: Query margin loss
print_training_margin_loss_message()
magin_loss = select_float_value(print_msg=MARGIN_LOSS_PRINT_MSG,
prompt_msg=MARGIN_LOSS_PROMPT_MSG,
error_msg=MARGIN_LOSS_ERROR_MSG)
config[MARGIN_LOSS] = magin_loss
print_section_divider()
# Step 3: Query learning rate
print_learning_rate_message()
learning_rate = select_float_value(print_msg=LEARNING_RATE_PRINT_MSG,
prompt_msg=LEARNING_RATE_PROMPT_MSG,
error_msg=LEARNING_RATE_ERROR_MSG)
config[LEARNING_RATE] = learning_rate
print_section_divider()
# Step 4: Query batch size
print_batch_size_message()
batch_size = select_integer_value(print_msg=BATCH_SIZE_PRINT_MSG,
prompt_msg=BATCH_SIZE_PROMPT_MSG,
error_msg=BATCH_SIZE_ERROR_MSG)
config[BATCH_SIZE] = batch_size
print_section_divider()
# Step 5: Query number of epochs
print_number_epochs_message()
number_epochs = select_integer_value(print_msg=EPOCH_PRINT_MSG,
prompt_msg=EPOCH_PROMPT_MSG,
error_msg=EPOCH_ERROR_MSG)
config[NUM_EPOCHS] = number_epochs
print_section_divider()
return config
def prompt_random_seed(config) -> None:
"""Query random seed."""
print_random_seed_message()
config[SEED] = select_integer_value(
print_msg=SEED_PRINT_MSG,
prompt_msg=SEED_PROMPT_MSG,
error_msg=SEED_ERROR_MSG,
default=0,
)
def prompt_execution_parameters(config: Dict, model_name: str) -> None:
"""Prompt the user for execution mode parameters."""
pykeen_exec_mode = config[EXECUTION_MODE]
if pykeen_exec_mode == TRAINING_MODE:
config.update(_configure_training_pipeline(model_name))
elif pykeen_exec_mode == HPO_MODE:
config.update(_configure_hpo_pipeline(model_name))
# Query number of HPO iterations
hpo_iter = select_integer_value(
print_msg=HPO_ITERS_PRINT_MSG,
prompt_msg=HPO_ITERS_PROMPT_MSG,
error_msg=HPO_ITERS_ERROR_MSG,
)
config[NUM_OF_HPO_ITERS] = hpo_iter
print_section_divider()
def configure_um_training_pipeline(model_name: str):
config = OrderedDict()
config[KG_EMBEDDING_MODEL_NAME] = model_name
# Step 1: Query embedding dimension
print_training_embedding_dimension_message()
print_embedding_dimension_info_message()
embedding_dimension = select_integer_value(print_msg=EMBEDDING_DIMENSION_PRINT_MSG,
prompt_msg=EMBEDDING_DIMENSION_PROMPT_MSG,
error_msg=EMBEDDING_DIMENSION_ERROR_MSG)
config[EMBEDDING_DIM] = embedding_dimension
print_section_divider()
# Step 2: Query margin loss
print_training_margin_loss_message()
magin_loss = select_float_value(print_msg=MARGIN_LOSS_PRINT_MSG,
prompt_msg=MARGIN_LOSS_PROMPT_MSG,
error_msg=MARGIN_LOSS_ERROR_MSG)
config[MARGIN_LOSS] = magin_loss
print_section_divider()
# Step 3: Query L_p norm as scoring function
print_scoring_fct_message()
scoring_fct_norm = select_integer_value(print_msg=NORM_SCORING_FUNCTION_PRINT_MSG,
prompt_msg=NORM_SCORING_FUNCTION_PROMPT_MSG,
error_msg=NORM_SCORING_FUNCTION_ERROR_MSG)
config[SCORING_FUNCTION_NORM] = scoring_fct_norm
print_section_divider()
# Step 4: Query L_p norm for normalizing the entities
print_entity_normalization_message()
entity_normalization_norm = select_integer_value(print_msg=ENTITIES_NORMALIZATION_PRINT_MSG,
prompt_msg=ENTITIES_NORMALIZATION_PROMPT_MSG,
error_msg=ENTITIES_NORMALIZATION_ERROR_MSG)
config[NORM_FOR_NORMALIZATION_OF_ENTITIES] = entity_normalization_norm
print_section_divider()
# Step 5: Query learning rate
print_learning_rate_message()
learning_rate = select_float_value(print_msg=LEARNING_RATE_PRINT_MSG,
prompt_msg=LEARNING_RATE_PROMPT_MSG,
error_msg=LEARNING_RATE_ERROR_MSG)
config[LEARNING_RATE] = learning_rate
print_section_divider()
# Step 6: Query batch size
print_batch_size_message()
batch_size = select_integer_value(print_msg=BATCH_SIZE_PRINT_MSG,
prompt_msg=BATCH_SIZE_PROMPT_MSG,
error_msg=BATCH_SIZE_ERROR_MSG)
config[BATCH_SIZE] = batch_size
print_section_divider()
# Step 7: Query number of epochs
print_number_epochs_message()
number_epochs = select_integer_value(print_msg=EPOCH_PRINT_MSG,
prompt_msg=EPOCH_PROMPT_MSG,
error_msg=EPOCH_ERROR_MSG)
config[NUM_EPOCHS] = number_epochs
print_section_divider()
return config
def configure_trans_d_training_pipeline(model_name: str):
"""Configure Trans D from pipeline.
:param model_name: name of the model
:return: configuration dictionary
"""
config = get_config_dict(model_name)
# Step 1: Query embedding dimension for entities
print_entities_embedding_dimension_message()
embedding_dimension = select_integer_value(
print_msg=ENTITIES_EMBEDDING_DIMENSION_PRINT_MSG,
prompt_msg=ENTITIES_EMBEDDING_DIMENSION_PROMPT_MSG,
error_msg=ENTITIES_EMBEDDING_DIMENSION_ERROR_MSG,
)
config[EMBEDDING_DIM] = embedding_dimension
print_section_divider()
# Step 2: Query embedding dimension for relations
print_relations_embedding_dimension_message()
relation_embedding_dimension = select_integer_value(
print_msg=RELATION_EMBEDDING_DIMENSION_PRINT_MSG,
prompt_msg=RELATION_EMBEDDING_DIMENSION_PROMPT_MSG,
error_msg=RELATION_EMBEDDING_DIMENSION_ERROR_MSG,
)
config[RELATION_EMBEDDING_DIM] = relation_embedding_dimension
print_section_divider()
# Step 2: Query margin loss
print_training_margin_loss_message()
magin_loss = select_float_value(print_msg=MARGIN_LOSS_PRINT_MSG,
prompt_msg=MARGIN_LOSS_PROMPT_MSG,
error_msg=MARGIN_LOSS_ERROR_MSG)
config[MARGIN_LOSS] = magin_loss
print_section_divider()
# Step 3: Query L_p norm as scoring function
print_scoring_fct_message()
scoring_fct_norm = select_integer_value(
print_msg=NORM_SCORING_FUNCTION_PRINT_MSG,
prompt_msg=NORM_SCORING_FUNCTION_PROMPT_MSG,
error_msg=NORM_SCORING_FUNCTION_ERROR_MSG)
config[SCORING_FUNCTION_NORM] = scoring_fct_norm
print_section_divider()
# Step 5: Query learning rate
print_learning_rate_message()
learning_rate = select_float_value(print_msg=LEARNING_RATE_PRINT_MSG,
prompt_msg=LEARNING_RATE_PROMPT_MSG,
error_msg=LEARNING_RATE_ERROR_MSG)
config[LEARNING_RATE] = learning_rate
print_section_divider()
# Step 6: Query batch size
print_batch_size_message()
batch_size = select_integer_value(print_msg=BATCH_SIZE_PRINT_MSG,
prompt_msg=BATCH_SIZE_PROMPT_MSG,
error_msg=BATCH_SIZE_ERROR_MSG)
config[BATCH_SIZE] = batch_size
print_section_divider()
# Step 7: Query number of epochs
print_number_epochs_message()
number_epochs = select_integer_value(print_msg=EPOCH_PRINT_MSG,
prompt_msg=EPOCH_PROMPT_MSG,
error_msg=EPOCH_ERROR_MSG)
config[NUM_EPOCHS] = number_epochs
print_section_divider()
return config
def configure_trans_h_training_pipeline(model_name: str) -> Dict:
"""Prompt the user to configure Trans H from pipeline."""
config = get_config_dict(model_name)
# Step 1: Query embedding dimension
print_training_embedding_dimension_message()
print_embedding_dimension_info_message()
embedding_dimension = select_integer_value(
print_msg=EMBEDDING_DIMENSION_PRINT_MSG,
prompt_msg=EMBEDDING_DIMENSION_PROMPT_MSG,
error_msg=EMBEDDING_DIMENSION_ERROR_MSG,
)
config[EMBEDDING_DIM] = embedding_dimension
print_section_divider()
# Step 2: Query margin loss
print_training_margin_loss_message()
magin_loss = select_float_value(
print_msg=MARGIN_LOSS_PRINT_MSG,
prompt_msg=MARGIN_LOSS_PROMPT_MSG,
error_msg=MARGIN_LOSS_ERROR_MSG,
)
config[MARGIN_LOSS] = magin_loss
print_section_divider()
# Step 3: Query L_p norm as scoring function
print_scoring_fct_message()
scoring_fct_norm = select_integer_value(
print_msg=NORM_SCORING_FUNCTION_PRINT_MSG,
prompt_msg=NORM_SCORING_FUNCTION_PROMPT_MSG,
error_msg=NORM_SCORING_FUNCTION_ERROR_MSG
)
config[SCORING_FUNCTION_NORM] = scoring_fct_norm
print_section_divider()
# Step 4: Query weight for the soft constraints
print_trans_h_soft_constraints_weight_message()
soft_constraints_weight = select_float_value(
print_msg=WEIGHTS_SOFT_CONSTRAINT_TRANS_H_PRINT_MSG,
prompt_msg=WEIGHTS_SOFT_CONSTRAINT_TRANS_H_PROMPT_MSG,
error_msg=WEIGHTS_SOFT_CONSTRAINT_TRANS_H_ERROR_MSG,
)
config[WEIGHT_SOFT_CONSTRAINT_TRANS_H] = soft_constraints_weight
print_section_divider()
# Step 5: Query learning rate
print_learning_rate_message()
learning_rate = select_float_value(
print_msg=LEARNING_RATE_PRINT_MSG,
prompt_msg=LEARNING_RATE_PROMPT_MSG,
error_msg=LEARNING_RATE_ERROR_MSG,
)
config[LEARNING_RATE] = learning_rate
print_section_divider()
# Step 6: Query batch size
print_batch_size_message()
batch_size = select_integer_value(
print_msg=BATCH_SIZE_PRINT_MSG,
prompt_msg=BATCH_SIZE_PROMPT_MSG,
error_msg=BATCH_SIZE_ERROR_MSG,
)
config[BATCH_SIZE] = batch_size
print_section_divider()
# Step 7: Query number of epochs
print_number_epochs_message()
number_epochs = select_integer_value(
print_msg=EPOCH_PRINT_MSG,
prompt_msg=EPOCH_PROMPT_MSG,
error_msg=EPOCH_ERROR_MSG,
)
config[NUM_EPOCHS] = number_epochs
print_section_divider()
return config
def configure_conv_e_training_pipeline(model_name: str):
"""Configure ConvE.
:param str model_name: name of the model
:return: configuration dictionary
"""
config = get_config_dict(model_name)
# Step 1: Query embedding dimension
print_training_embedding_dimension_message()
print_embedding_dimension_info_message()
embedding_dimension = select_integer_value(
print_msg=EMBEDDING_DIMENSION_PRINT_MSG,
prompt_msg=EMBEDDING_DIMENSION_PROMPT_MSG,
error_msg=EMBEDDING_DIMENSION_ERROR_MSG,
)
config[EMBEDDING_DIM] = embedding_dimension
print_section_divider()
# Step 2: Query height and width
print_conv_e_width_height_message()
height, width = query_height_and_width_for_conv_e(embedding_dimension)
config[CONV_E_HEIGHT] = height
config[CONV_E_WIDTH] = width
print_section_divider()
# Step 3: Query number of input channels
print_conv_input_channels_message()
num_input_channels = select_integer_value(
CONV_E_INPUT_CHANNEL_PRINT_MSG,
CONV_E_INPUT_CHANNEL_PROMPT_MSG,
CONV_E_INPUT_CHANNEL_ERROR_MSG,
)
config[CONV_E_INPUT_CHANNELS] = num_input_channels
print_section_divider()
# Step 4: Query number of output channels
print_conv_e_output_channels_message()
num_output_channels = select_integer_value(
CONV_E_OUT_CHANNEL_PRINT_MSG,
CONV_E_OUT_CHANNEL_PROMPT_MSG,
CONV_E_OUT_CHANNEL_ERROR_MSG,
)
config[CONV_E_OUTPUT_CHANNELS] = num_output_channels
print_section_divider()
# Step 4: Query kernel height
print_conv_kernel_height_message()
kernel_height = query_kernel_param(
depending_param=height,
print_msg=CONV_E_KERNEL_HEIGHT_PRINT_MSG,
prompt_msg=CONV_E_KERNEL_HEIGHT_PROMPT_MSG,
error_msg=CONV_E_KERNEL_HEIGHT_ERROR_MSG,
)
config[CONV_E_KERNEL_HEIGHT] = kernel_height
print_section_divider()
# Step 5: Query kernel width
print_conv_kernel_width_message()
kernel_width = query_kernel_param(
depending_param=width,
print_msg=CONV_E_KERNEL_WIDTH_PRINT_MSG,
prompt_msg=CONV_E_KERNEL_WIDTH_PROMPT_MSG,
error_msg=CONV_E_KERNEL_WIDTH_ERROR_MSG,
)
config[CONV_E_KERNEL_WIDTH] = kernel_width
print_section_divider()
# Step 6: Query dropout for input layer
print_hpo_input_dropout_message()
input_dropout = select_zero_one_float_value(
print_msg=CONV_E_INPUT_DROPOUT_PRINT_MSG,
prompt_msg=CONV_E_INPUT_DROPOUT_PROMPT_MSG,
error_msg=CONV_E_INPUT_DROPOUT_ERROR_MSG,
)
config[CONV_E_INPUT_DROPOUT] = input_dropout
print_section_divider()
# Step 7: Query dropout for output layer
print_output_dropout_message()
output_dropout = select_zero_one_float_value(
print_msg=CONV_E_OUTPUT_DROPOUT_PRINT_MSG,
prompt_msg=CONV_E_OUTPUT_DROPOUT_PROMPT_MSG,
error_msg=CONV_E_OUTPUT_DROPOUT_ERROR_MSG,
)
config[CONV_E_OUTPUT_DROPOUT] = output_dropout
print_section_divider()
# Step 8: Query feature map dropout for output layer
print_feature_map_dropout_message()
feature_map_dropout = select_zero_one_float_value(
print_msg=CONV_E_FEATURE_MAP_DROPOUT_PRINT_MSG,
prompt_msg=CONV_E__FEATURE_MAP_DROPOUT_PROMPT_MSG,
error_msg=CONV_E_FEATURE_MAP_DROPOUT_ERROR_MSG,
)
config[CONV_E_FEATURE_MAP_DROPOUT] = feature_map_dropout
print_section_divider()
# Step 5: Query learning rate
print_learning_rate_message()
learning_rate = select_float_value(print_msg=LEARNING_RATE_PRINT_MSG,
prompt_msg=LEARNING_RATE_PROMPT_MSG,
error_msg=LEARNING_RATE_ERROR_MSG)
config[LEARNING_RATE] = learning_rate
print_section_divider()
# Step 6: Query batch size
print_batch_size_message()
batch_size = select_integer_value(print_msg=BATCH_SIZE_PRINT_MSG,
prompt_msg=BATCH_SIZE_PROMPT_MSG,
error_msg=BATCH_SIZE_ERROR_MSG)
config[BATCH_SIZE] = batch_size
print_section_divider()
# Step 7: Query number of epochs
print_number_epochs_message()
number_epochs = select_integer_value(print_msg=EPOCH_PRINT_MSG,
prompt_msg=EPOCH_PROMPT_MSG,
error_msg=EPOCH_ERROR_MSG)
config[NUM_EPOCHS] = number_epochs
print_section_divider()
return config