client = dask.distributed.Client(processes=True,
n_workers=1,
threads_per_worker=1,
memory_limit="2.9GB")
print("Client created")
file_name = "ggh_delphes.root"
file_path = f"{os.getcwd()}/tests/samples/{file_name}"
datasets = {"ggh_powheg": file_path}
fileset = get_fileset(client, datasets, parameters)
executor_args = {"client": client, "use_dataframes": True, "retries": 0}
executor = DaskExecutor(**executor_args)
run = Runner(executor=executor, schema=DelphesSchema, chunksize=10000)
output = run(fileset,
"Delphes",
processor_instance=DimuonProcessorDelphes())
df = output.compute()
print(df)
elapsed = round(time.time() - tick, 3)
print(f"Finished everything in {elapsed} s.")
dimuon_mass = df.loc[df.event == 20002, "dimuon_mass"].values[0]
jj_mass = df.loc[df.event == 20011, "jj_mass"].values[0]
assert df.shape == (86, 78)
assert almost_equal(dimuon_mass, 124.3369651)
assert almost_equal(jj_mass, 78.593476)
processor_instance=DimuonProcessor(**processor_args),
)
df = load_dataframe(client, parameters, inputs=out_df)
out_hist = to_histograms(client, parameters, df=df)
out_plot = plotter(client, parameters, hist_df=out_hist)
elapsed = round(time.time() - tick, 3)
print(f"Finished everything in {elapsed} s.")
out_df = out_df.compute()
dimuon_mass = out_df.loc[out_df.event == 2, "dimuon_mass"].values[0]
jj_mass = out_df.loc[out_df.event == 2, "jj_mass nominal"].values[0]
assert out_df.shape == (21806, 116)
assert almost_equal(dimuon_mass, 124.16069531)
assert almost_equal(jj_mass, 1478.3898375)
slicer = {
"region": "h-peak",
"channel": "vbf",
"variation": "nominal",
"val_sumw2": "value",
"dimuon_mass": slice(None),
}
assert almost_equal(out_hist["hist"][0][slicer].sum(),
31778.21631,
precision=0.01)
assert almost_equal(sum(out_plot), 31778.21631, precision=0.01)
processor_instance=DimuonProcessorDelphes())
df = load_dataframe(client, parameters, inputs=out_df)
# run_mva(client, parameters, df=df)
out_hist = to_histograms(client, parameters, df=df)
out_plot = plotter(client, parameters, hist_df=out_hist)
out_tmp = to_templates(client, parameters, hist_df=out_hist)
elapsed = round(time.time() - tick, 3)
print(f"Finished everything in {elapsed} s.")
out_df = out_df.compute()
dimuon_mass = out_df.loc[out_df.event == 20002, "dimuon_mass"].values[0]
jj_mass = out_df.loc[out_df.event == 20011, "jj_mass"].values[0]
assert out_df.shape == (86, 78)
assert almost_equal(dimuon_mass, 124.3369651)
assert almost_equal(jj_mass, 78.593476)
slicer = {
"region": "h-peak",
"channel": "ggh_0jets",
"val_sumw2": "value",
"dimuon_mass": slice(None),
}
assert almost_equal(
out_hist.loc[out_hist.var_name == "dimuon_mass",
"hist"].values[0][slicer].sum(),
12426.530232,
)
assert almost_equal(sum(out_plot), 12426.530232)
assert almost_equal(sum(out_tmp), 12426.530232)
samp_info.load("test", use_dask=False)
samp_info.lumi_weights["test"] = 1.0
print(samp_info.fileset)
executor_args = {"client": client, "use_dataframes": True, "retries": 0}
processor_args = {
"samp_info": samp_info,
"do_timer": False,
"do_btag_syst": False
}
executor = DaskExecutor(**executor_args)
run = Runner(executor=executor, schema=NanoAODSchema, chunksize=10000)
output = run(
samp_info.fileset,
"Events",
processor_instance=DimuonProcessor(**processor_args),
)
df = output.compute()
print(df)
elapsed = round(time.time() - tick, 3)
print(f"Finished everything in {elapsed} s.")
dimuon_mass = df.loc[df.event == 2, "dimuon_mass"].values[0]
jj_mass = df.loc[df.event == 2, "jj_mass nominal"].values[0]
assert df.shape == (21806, 116)
assert almost_equal(dimuon_mass, 124.16069531)
assert almost_equal(jj_mass, 1478.3898375)
}
if __name__ == "__main__":
tick = time.time()
client = Client(
processes=True, n_workers=1, threads_per_worker=1, memory_limit="4GB"
)
file_name = "dy_nanoaod_stage1_output.parquet"
path = f"{os.getcwd()}/tests/samples/{file_name}"
df = load_dataframe(client, parameters, inputs=[path])
out_hist = to_histograms(client, parameters, df=df)
out_plot = plotter(client, parameters, hist_df=out_hist)
elapsed = round(time.time() - tick, 3)
print(f"Finished everything in {elapsed} s.")
slicer = {
"region": "h-peak",
"channel": "vbf",
"variation": "nominal",
"val_sumw2": "value",
"dimuon_mass": slice(None),
}
assert almost_equal(out_hist["hist"][0][slicer].sum(), 0.14842246076249055)
assert almost_equal(sum(out_plot), 0.14842246076249055)
}
if __name__ == "__main__":
tick = time.time()
client = Client(processes=True,
n_workers=1,
threads_per_worker=1,
memory_limit="4GB")
file_name = "dy_delphes_stage1_output.parquet"
path = f"{os.getcwd()}/tests/samples/{file_name}"
out_df = load_dataframe(client, parameters, inputs=[path])
out_hist = to_histograms(client, parameters, df=out_df)
out_plot = plotter(client, parameters, hist_df=out_hist)
out_tmp = to_templates(client, parameters, hist_df=out_hist)
elapsed = round(time.time() - tick, 3)
print(f"Finished everything in {elapsed} s.")
slicer = {
"region": "h-peak",
"channel": "ggh_0jets",
"val_sumw2": "value",
"dimuon_mass": slice(None),
}
assert almost_equal(out_hist["hist"][0][slicer].sum(), 3349.189725131393)
assert almost_equal(sum(out_plot), 3349.189725131393)
assert almost_equal(sum(out_tmp), 3349.189725131393)