def spin_up_cluster(n_workers):
# set up the cluster before executing the run
env_name = "cmip6_derived_cloud_datasets"
## use the pangeo containerfor the software env
coiled.create_software_environment(
name=env_name,
conda=
'environment.yml', # this will take longer...but I guess thats ok for now?
# couldnt get this to work yet
# container='pangeo/pangeo-notebook:latest', # matches Pangeo Cloud AWS production cluster
)
# Create a Dask cluster which uses
# software environment
cluster = coiled.Cluster(
software=env_name,
n_workers=n_workers,
backend_options={"region": "us-west-2"},
shutdown_on_close=True,
)
client = Client(cluster)
print("Cluster Name:", cluster.name)
print("Dashboard:", client.dashboard_link)
print('\n\n\n----------------------------')
return client, cluster
def __init__(self):
config_file = os.path.join(os.getcwd(), "config", "config.yaml")
if not os.path.isfile(config_file):
raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT),
config_file)
with open(config_file) as file:
self.config_values = yaml.full_load(file)
if not "cluster_name" in self.config_values:
self.config_values["cluster_name"] = "chess-cluster"
if not "software_environment_name" in self.config_values:
self.config_values["software_environment_name"] = "chess-env"
if not "n_workers" in self.config_values:
self.config_values["n_workers"] = 50
if not "worker_cpu" in self.config_values:
self.config_values["worker_cpu"] = 1
if not "worker_memory" in self.config_values:
self.config_values["worker_memory"] = 8
if not "scheduler_memory" in self.config_values:
self.config_values["scheduler_memory"] = 16
if not "scheduler_cpu" in self.config_values:
self.config_values["scheduler_cpu"] = 4
if not "game_batch_size" in self.config_values:
self.config_values["game_batch_size"] = 30
if not "timeout_per_game" in self.config_values:
self.config_values["timeout_per_game"] = 60
if not "debug" in self.config_values:
self.config_values["debug"] = False
if self.config_values["use_local_cluster"]:
cluster = LocalCluster(n_workers=self.config_values["n_workers"],
threads_per_worker=1)
else:
coiled.create_software_environment(
name=self.config_values["software_environment_name"],
pip="requirements.txt")
cluster = coiled.Cluster(
name=self.config_values["cluster_name"],
n_workers=self.config_values["n_workers"],
worker_cpu=self.config_values["worker_cpu"],
worker_memory=str(self.config_values["worker_memory"]) + "GiB",
scheduler_memory=str(self.config_values["scheduler_memory"]) +
"GiB",
scheduler_cpu=self.config_values["scheduler_cpu"],
software=self.config_values["software_environment_name"])
self.client = Client(cluster)
import coiled
# Create cluster software environment
software_name = "examples/optuna-xgboost"
coiled.create_software_environment(
name=software_name,
conda="environment.yaml",
)
# Create notebook job software environment
software_notebook_name = software_name + "-notebook"
coiled.create_software_environment(
name=software_notebook_name,
container="coiled/notebook:latest",
conda="environment.yaml",
)
coiled.create_job_configuration(
name="examples/optuna",
software=software_notebook_name,
command=[
"/bin/bash",
"run.sh",
],
files=["optuna-xgboost.ipynb", "workspace.json", "run.sh"],
ports=[8888],
description="Hyperparameter optimization with Optuna",
)
"python=3.8",
"dask=2021.3.0",
"coiled=0.0.37",
"optuna",
"numpy",
"scikit-learn",
"xgboost",
"joblib",
],
}
# Create cluster software environment
software_name = "examples/optuna-xgboost"
coiled.create_software_environment(
name=software_name,
conda=conda,
pip=["dask-optuna"],
)
# Create notebook job software environment
software_notebook_name = software_name + "-notebook"
coiled.create_software_environment(
name=software_notebook_name,
container="coiled/notebook:latest",
conda=conda,
pip=["dask-optuna"],
)
coiled.create_job_configuration(
name="examples/optuna",
software=software_notebook_name,
import coiled
software_name = "blog-notebooks/xgboost-on-coiled"
coiled.create_software_environment(
name=software_name,
container="coiled/notebook:latest",
conda={
"channels": ["conda-forge"],
"dependencies": [
"python=3.8",
"coiled=0.0.36",
"dask",
"dask-ml",
"dask>=2.23.0",
"fastparquet",
"matplotlib",
"pandas>=1.1.0",
"python-snappy",
"s3fs",
"scikit-learn",
"xgboost>=1.3.0",
"optuna<2.4.0",
"numpy",
"xgboost",
"joblib",
]
},
pip=["dask-optuna"],
)
coiled.create_job_configuration(
name="blog-notebooks/xgboost-on-coiled",
#!/usr/bin/env python3
import coiled
import argparse
coiled.create_software_environment(
name="i2k-2020-mi2",
conda="environment.yml",
)
},
"pytorch": {
"conda": "hyper-parameter-optimmization/environment.yml"
},
}
cluster_configurations = {
"xgboost": {
"worker_cpu": 4,
"worker_memory": "8 GiB"
},
"pangeo": {
"worker_cpu": 4,
"worker_memory": "8 GiB"
},
"pytorch": {
"worker_cpu": 4,
"worker_memory": "16 GiB"
},
}
assert software_environments.keys() == cluster_configurations.keys()
for name, spec in software_environments.items():
full_name = f"coiled-examples/{name}"
print(f"Building {full_name}:")
coiled.create_software_environment(name=full_name, **spec)
coiled.create_cluster_configuration(name=full_name,
software=full_name,
**cluster_configurations[name])
#!/usr/bin/env python3
import coiled
import argparse
# conda=["pip", "nodejs", "graphviz", "compilers"],
coiled.create_software_environment(
name="sc20-pyhpc",
conda="environment.yml",
post_build=[
"jupyter labextension install @jupyter-widgets/jupyterlab-manager jupyter-matplotlib jupyterlab-datawidgets [email protected] dask-labextension [email protected] [email protected]",
"jupyter serverextension enable dask_labextension"
],
)
import coiled
software_name = "examples/quickstart-notebook"
coiled.create_software_environment(
name=software_name,
container="coiled/notebook:latest",
conda={
"channels": ["conda-forge"],
"dependencies": ["python=3.8", "coiled=0.0.37", "dask=2021.3.0"]
},
)
coiled.create_job_configuration(
name="examples/quickstart",
software=software_name,
command=[
"/bin/bash",
"run.sh",
],
files=["quickstart.ipynb", "workspace.json", "run.sh"],
ports=[8888],
description="Quickly launch a Dask cluster on the cloud with Coiled",
)
