Amazon SageMaker 組み込みの表形式アルゴリズムを使用したチャーン予測 LightGBM、CatBoost、TabTransformer、および AutoGluon-Tabular

from sagemaker import image_uris, model_uris, script_uris
train_model_id, train_model_version, train_scope = "lightgbm-classification-model", "*", "training"
training_instance_type = "ml.m5.4xlarge"

# Retrieve the docker image
train_image_uri = image_uris.retrieve(region=None,
                                      framework=None,
                                      model_id=train_model_id,
                                      model_version=train_model_version,
                                      image_scope=train_scope,
                                      instance_type=training_instance_type,
                                      )                                      
# Retrieve the training script
train_source_uri = script_uris.retrieve(model_id=train_model_id,
                                        model_version=train_model_version,
                                        script_scope=train_scope
                                        )
# Retrieve the pre-trained model tarball (in the case of tabular modeling, it is a dummy file)
train_model_uri = model_uris.retrieve(model_id=train_model_id,
                                      model_version=train_model_version,
                                      model_scope=train_scope)

from sagemaker import hyperparameters
from sagemaker.tuner import ContinuousParameter, IntegerParameter, HyperparameterTuner

# Retrieve the default hyper-parameters for fine-tuning the model
hyperparameters = hyperparameters.retrieve_default(model_id=train_model_id,
                                                   model_version=train_model_version
                                                   )
# [Optional] Override default hyperparameters with custom values
hyperparameters["num_boost_round"] = "500"
hyperparameters["metric"] = "auc"

# Define search ranges for other hyperparameters
hyperparameter_ranges_lgb = {
    "learning_rate": ContinuousParameter(1e-4, 1, scaling_type="Logarithmic"),
    "num_boost_round": IntegerParameter(2, 30),
    "num_leaves": IntegerParameter(10, 50),
    "feature_fraction": ContinuousParameter(0, 1),
    "bagging_fraction": ContinuousParameter(0, 1),
    "bagging_freq": IntegerParameter(1, 10),
    "max_depth": IntegerParameter(5, 30),
    "min_data_in_leaf": IntegerParameter(5, 50),
}

from sagemaker.estimator import Estimator
from sagemaker.tuner import HyperParameterTuner

# Create SageMaker Estimator instance
tabular_estimator = Estimator(
    role=aws_role,
    image_uri=train_image_uri,
    source_dir=train_source_uri,
    model_uri=train_model_uri,
    entry_point="transfer_learning.py",
    instance_count=1,
    instance_type=training_instance_type,
    max_run=360000,
    hyperparameters=hyperparameters,
)

tuner = HyperparameterTuner(
            tabular_estimator,
            "auc",
            hyperparameter_ranges_lgb,
            [{"Name": "auc", "Regex": "auc: ([0-9.]+)"}],
            max_jobs=10,
            max_parallel_jobs=5,
            objective_type="Maximize",
            base_tuning_job_name="some_name",
        )

tuner.fit({"training": training_dataset_s3_path}, logs=True)

from sagemaker import hyperparameters

# Retrieve the default hyper-parameters for fine-tuning the model
hyperparameters = hyperparameters.retrieve_default(
    model_id=train_model_id, model_version=train_model_version
)
# [Optional] Override default hyperparameters with custom values
hyperparameters["iterations"] = "500"
hyperparameters["eval_metric"] = "AUC"

# Define search ranges for other hyperparameters
hyperparameter_ranges_cat = {
    "learning_rate": ContinuousParameter(0.00001, 0.1, scaling_type="Logarithmic"),
    "iterations": IntegerParameter(50, 1000),
    "depth": IntegerParameter(1, 10),
    "l2_leaf_reg": IntegerParameter(1, 10),
    "random_strength": ContinuousParameter(0.01, 10, scaling_type="Logarithmic"),
}

from sagemaker import hyperparameters
from sagemaker.tuner import CategoricalParameter

# Retrieve the default hyper-parameters for fine-tuning the model
hyperparameters = hyperparameters.retrieve_default(
    model_id=train_model_id, model_version=train_model_version
)
# [Optional] Override default hyperparameters with custom values
hyperparameters["n_epochs"] = 40  # The same hyperparameter is named as "iterations" for CatBoost
hyperparameters["patience"] = 10

# Define search ranges for other hyperparameters
hyperparameter_ranges_tab = {
    "learning_rate": ContinuousParameter(0.001, 0.01, scaling_type="Auto"),
    "batch_size": CategoricalParameter([64, 128, 256, 512]),
    "attn_dropout": ContinuousParameter(0.0, 0.8, scaling_type="Auto"),
    "mlp_dropout": ContinuousParameter(0.0, 0.8, scaling_type="Auto"),
    "input_dim": CategoricalParameter(["16", "32", "64", "128", "256"]),
    "frac_shared_embed": ContinuousParameter(0.0, 0.5, scaling_type="Auto"),
}

from sagemaker import hyperparameters

# Retrieve the default hyper-parameters for fine-tuning the model
hyperparameters = hyperparameters.retrieve_default(
    model_id=train_model_id, model_version=train_model_version
)

hyperparameters["eval_metric"] = "roc_auc"