def main():
# Load dataset
data, labels = 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)
train_set = RayDMatrix(train_x, train_y)
test_set = RayDMatrix(test_x, test_y)
# Set config
config = {
"tree_method": "approx",
"objective": "binary:logistic",
"eval_metric": ["logloss", "error"],
"max_depth": 3,
}
evals_result = {}
# Train the classifier
bst = train(config,
train_set,
evals=[(test_set, "eval")],
evals_result=evals_result,
ray_params=RayParams(max_actor_restarts=1),
verbose_eval=False)
bst.save_model("simple.xgb")
print("Final validation error: {:.4f}".format(
evals_result["eval"]["error"][-1]))
def train_model(config):
# Load dataset
data, labels = 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)
train_set = RayDMatrix(train_x, train_y)
test_set = RayDMatrix(test_x, test_y)
evals_result = {}
bst = train(params=config,
dtrain=train_set,
evals=[(test_set, "eval")],
evals_result=evals_result,
verbose_eval=False,
ray_params=RayParams(num_actors=num_actors,
cpus_per_actor=num_cpus_per_actor))
bst.save_model("model.xgb")
