!ray up ./cluster-config.yaml -y # launch the cluster with -y to automatically accept

!aws ec2 authorize-security-group-ingress --group-id {sggroupid} --protocol tcp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !aws ec2 authorize-security-group-ingress --group-id {sggroupid} --protocol udp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !aws ec2 authorize-security-group-egress --group-id {sggroupid} --protocol tcp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !aws ec2 authorize-security-group-egress --group-id {sggroupid} --protocol udp --port 10001 --cidr $(curl ipinfo.io/ip)/24

import time time.sleep(30) # Let's sleep to allow some time for Ray to sort itself out import ray ray.init(address=f'ray://{conn_addr}:10001')

import socket from collections import Counter @ray.remote def check_hosts(): time.sleep(5) return socket.gethostname() for run in range(5): if run != 0: time.sleep(60) # Let nodes in the cluster make progress initialising remote_promises = [check_hosts.remote() for _ in range(10)] ids = ray.get(remote_promises) print(Counter(ids))

import numpy as np from sklearn.datasets import load_breast_cancer from sklearn.model_selection import RandomizedSearchCV from sklearn.ensemble import GradientBoostingClassifier from sklearn.svm import SVC train_x, train_y = load_breast_cancer(return_X_y=True) start = time.time() param_space = { 'learning_rate': np.linspace(0.001, 0.9, 50), 'n_estimators': np.arange(80, 120, 5), 'max_depth': [2,3,4], } model = GradientBoostingClassifier() search = RandomizedSearchCV(model, param_space, cv=10, n_iter=50, verbose=2) search.fit(train_x, train_y) print(f"The total execution time was {time.time()-start:.2f}s")

import joblib from ray.util.joblib import register_ray register_ray() start = time.time() model = GradientBoostingClassifier() search = RandomizedSearchCV(model, param_space, cv=10, n_iter=50, verbose=2) with joblib.parallel_backend('ray'): search.fit(train_x, train_y) print(f"The total execution time was {time.time()-start:.2f}s")

from xgboost_ray import RayDMatrix, RayParams, train from sklearn.datasets import load_breast_cancer train_x, train_y = load_breast_cancer(return_X_y=True) train_set = RayDMatrix(train_x, train_y) evals_result = {} bst = train( { "objective": "binary:logistic", "eval_metric": ["logloss", "error"], }, train_set, evals_result=evals_result, evals=[(train_set, "train")], verbose_eval=False, ray_params=RayParams( num_actors=len(ray.nodes()), # Number of remote actors cpus_per_actor=1)) bst.save_model("model.xgb") print("Final training error: {:.4f}".format( evals_result["train"]["error"][-1]))

!aws ec2 revoke-security-group-ingress --group-id {sggroupid} --protocol tcp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !aws ec2 revoke-security-group-ingress --group-id {sggroupid} --protocol udp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !aws ec2 revoke-security-group-egress --group-id {sggroupid} --protocol tcp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !aws ec2 revoke-security-group-egress --group-id {sggroupid} --protocol udp --port 10001 --cidr $(curl ipinfo.io/ip)/24 !ray down ./cluster-config.yaml -y