def train_xgb_asha(config):
train_set = xgb.DMatrix(x_tr, label=y_tr)
test_set = xgb.DMatrix(x_te, label=y_te)
xgb.train(config,
train_set,
100,
evals=[(test_set, 'eval')],
verbose_eval=False,
early_stopping_rounds=10,
callbacks=[TuneReportCheckpointCallback(filename='model.xgb')])
def train_breast_cancer(config: dict):
# This is a simple training function to be passed into Tune
# Load dataset
# Split into train and test set
# Build input matrices for XGBoost
train_set = xgb.DMatrix(train_x, label=train_y)
test_set = xgb.DMatrix(test_x, label=test_y)
# Train the classifier, using the Tune callback
xgb.train(
config,
train_set,
evals=[(test_set, "eval")],
verbose_eval=False,
callbacks=[TuneReportCheckpointCallback(filename="model.xgb")])
def train_breast_cancer(config):
# Load dataset
data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)
# Split into train and test set
train_x, test_x, train_y, test_y = train_test_split(
data, labels, test_size=0.25)
# Build input matrices for XGBoost
train_set = xgb.DMatrix(train_x, label=train_y)
test_set = xgb.DMatrix(test_x, label=test_y)
# Train the classifier
xgb.train(
config,
train_set,
evals=[(test_set, "eval")],
verbose_eval=False,
callbacks=[TuneReportCheckpointCallback(filename="model.xgb")])
def train_breast_cancer(config: dict):
# This is a simple training function to be passed into Tune
# Load dataset
data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)
# Split into train and test set
train_x, test_x, train_y, test_y = train_test_split(
data, labels, test_size=0.25)
# Build input matrices for XGBoost
train_set = xgb.DMatrix(train_x, label=train_y)
test_set = xgb.DMatrix(test_x, label=test_y)
# HyperOpt returns a tuple
config = config.copy()
config["eval_metric"] = ["logloss", "error"]
config["objective"] = "binary:logistic"
# Train the classifier, using the Tune callback
xgb.train(
config,
train_set,
evals=[(test_set, "eval")],
verbose_eval=False,
callbacks=[TuneReportCheckpointCallback(filename="model.xgb")])
def train_breast_cancer(config: dict, checkpoint_dir=None):
# This is a simple training function to be passed into Tune
# Load dataset
data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)
# Split into train and test set
train_x, test_x, train_y, test_y = train_test_split(data,
labels,
test_size=0.25)
# Build input matrices for XGBoost
train_set = xgb.DMatrix(train_x, label=train_y)
test_set = xgb.DMatrix(test_x, label=test_y)
# Checkpointing needs to be set up in order for dynamic
# resource allocation to work as intended
xgb_model = None
if checkpoint_dir:
xgb_model = xgb.Booster()
xgb_model.load_model(os.path.join(checkpoint_dir, CHECKPOINT_FILENAME))
# we can obtain current trial resources through
# tune.get_trial_resources()
config["nthread"] = int(tune.get_trial_resources().head_cpus)
print(f"nthreads: {config['nthread']} xgb_model: {xgb_model}")
# Train the classifier, using the Tune callback
xgb.train(
config,
train_set,
evals=[(test_set, "eval")],
verbose_eval=False,
xgb_model=xgb_model,
callbacks=[
TuneReportCheckpointCallback(
filename=CHECKPOINT_FILENAME,
# checkpointing should happen every iteration
# with dynamic resource allocation
frequency=1,
)
],
)
def train_breast_cancer(config: dict):
# This is a simple training function to be passed into Tune
# Load dataset
data, labels = sklearn.datasets.load_breast_cancer(return_X_y=True)
# Split into train and test set
train_x, test_x, train_y, test_y = train_test_split(data,
labels,
test_size=0.25)
# Build input matrices for XGBoost
train_set = xgb.DMatrix(train_x, label=train_y)
test_set = xgb.DMatrix(test_x, label=test_y)
# Train the classifier, using the Tune callback
xgb.train(
config,
train_set,
evals=[(test_set, "test")],
verbose_eval=False,
callbacks=[TuneReportCheckpointCallback(filename="model.xgb")],
)
