def h5(cls,
h5_file,
out_dir,
dsets=None,
group=None,
process_size=None,
max_workers=None,
plot_type='plotly',
cmap='viridis',
**kwargs):
"""
Run QA/QC by computing summary stats from dsets in h5_file and
plotting scatters plots of compatible summary stats
Parameters
----------
h5_file : str
Path to .h5 file to run QA/QC on
out_dir : str
Directory path to save summary tables and plots too
dsets : str | list, optional
Datasets to summarize, by default None
group : str, optional
Group within h5_file to summarize datasets for, by default None
process_size : int, optional
Number of sites to process at a time, by default None
max_workers : int, optional
Number of workers to use when summarizing 2D datasets,
by default None
plot_type : str, optional
plot_type of plot to create 'plot' or 'plotly', by default 'plotly'
cmap : str, optional
Colormap name, by default 'viridis'
kwargs : dict
Additional plotting kwargs
"""
try:
qa_qc = cls(out_dir)
SummarizeH5.run(h5_file,
out_dir,
group=group,
dsets=dsets,
process_size=process_size,
max_workers=max_workers)
qa_qc.create_scatter_plots(plot_type=plot_type,
cmap=cmap,
**kwargs)
except Exception as e:
logger.exception(
'QAQC failed on file: {}. Received exception:\n{}'.format(
os.path.basename(h5_file), e))
raise e
else:
logger.info(
'Finished QAQC on file: {} output directory: {}'.format(
os.path.basename(h5_file), out_dir))
def h5(ctx, h5_file, dsets, group, process_size, max_workers):
"""
Summarize datasets in .h5 file
"""
SummarizeH5.run(h5_file,
ctx.obj['OUT_DIR'],
group=group,
dsets=dsets,
process_size=process_size,
max_workers=max_workers)
def test_summarize(dataset):
"""Run QA/QC Summarize and compare with baseline"""
summary = SummarizeH5(H5_FILE)
if dataset is None:
baseline = os.path.join(SUMMARY_DIR,
'ri_wind_gen_profiles_2010_summary.csv')
baseline = pd.read_csv(baseline)
test = summary.summarize_means()
elif dataset == 'cf_mean':
baseline = os.path.join(SUMMARY_DIR, 'cf_mean_summary.csv')
baseline = pd.read_csv(baseline, index_col=0)
test = summary.summarize_dset(dataset,
process_size=None,
max_workers=1)
elif dataset == 'cf_profile':
baseline = os.path.join(SUMMARY_DIR, 'cf_profile_summary.csv')
baseline = pd.read_csv(baseline, index_col=0)
test = summary.summarize_dset(dataset,
process_size=None,
max_workers=1)
assert_frame_equal(test, baseline, check_dtype=False)