},
# HTCondor submit script
job_extra={
"universe": "docker",
# To be used with coffea-casa:0.1.11
"encrypt_input_files": "/etc/cmsaf-secrets/xcache_token",
#"docker_network_type": "host",
"docker_image": "coffeateam/coffea-casa-analysis:0.1.11",
"container_service_names": "dask",
"dask_container_port": "8787",
"should_transfer_files": "YES",
"when_to_transfer_output": "ON_EXIT",
"+DaskSchedulerAddress": '"129.93.183.33:8787"',
})
cluster.adapt(minimum_jobs=5, maximum_jobs=100, maximum_memory="4 GB"
) # auto-scale between 5 and 100 jobs (maximum_memory="4 GB")
client = Client(cluster)
exe_args = {
'client': client,
}
output = processor.run_uproot_job(fileset,
treename='Events',
processor_instance=METProcessor(),
executor=processor.dask_executor,
executor_args=exe_args)
# Generates a 1D histogram from the data output to the 'MET' key. fill_opts are optional, to fill the graph (default is a line).
hist.plot1d(output['MET'],
from tdub import setup_logging
from tdub.train import prepare_from_root
from tdub.utils import get_selection, get_features, quick_files
import lightgbm as lgbm
from sklearn.model_selection import train_test_split
from dask_jobqueue import HTCondorCluster
from dask.distributed import Client
from dask_ml.model_selection import GridSearchCV
cluster = HTCondorCluster(cores=2, disk="4GB", memory="8GB")
client = Client(cluster)
cluster.adapt(maximum_jobs=200)
setup_logging()
qf = quick_files("/atlasgpfs01/usatlas/data/ddavis/wtloop/v29_20191111")
df, y, w = prepare_from_root(qf["tW_DR"], qf["ttbar"], "1j1b")
X_train, X_test, y_train, y_test, w_train, w_test = train_test_split(
df, y, w, train_size=0.8, random_state=414, shuffle=True)
n_sig = y_train[y_train == 1].shape[0]
n_bkg = y_train[y_train == 0].shape[0]
spw = n_bkg / n_sig
n_sig = y[y == 1].shape[0]
n_bkg = y[y == 0].shape[0]
spw = n_bkg / n_sig