def run(rundate, pipeline, *args, **kwargs):
"""Run a Where pipeline for a given date and session
Args:
rundate: Rundate of analysis.
pipeline: Pipeline used for analysis.
session: Session in analysis.
"""
if not setup.has_config(rundate, pipeline, *args, **kwargs):
log.fatal(
f"No configuration found for {pipeline.upper()} {rundate.strftime(config.FMT_date)}"
)
# Set up config
config.init(rundate, pipeline, **kwargs)
# Register filekey suffix
filekey_suffix = config.tech.filekey_suffix.list
if filekey_suffix:
config.files.profiles = filekey_suffix
# Validate input arguments
try:
prefix = plugins.call(package_name=__name__,
plugin_name=pipeline,
part="validate_args",
rundate=rundate,
**kwargs)
except mg_exceptions.UnknownPluginError:
log.warn(
f"Pipeline {pipeline} has not defined function 'validate_args'")
except exceptions.InvalidArgsError as err:
from where.tools import delete
# Clean up {placeholder} directories created by config
delete.delete_analysis(rundate, pipeline, **kwargs)
log.fatal(err)
# Set up console logger and start file logger
try:
prefix = plugins.call(package_name=__name__,
plugin_name=pipeline,
part="log_prefix",
rundate=rundate,
**kwargs)
except mg_exceptions.UnknownPluginError:
log.warn(f"Pipeline {pipeline} has not defined function 'log_prefix'")
prefix = ""
log_cfg = config.where.log
log.init(log_level=log_cfg.default_level.str, prefix=prefix)
if log_cfg.log_to_file.bool:
log.file_init(
file_path=config.files.path("log"),
log_level=log_cfg.default_level.str,
prefix=prefix,
rotation=log_cfg.number_of_log_backups.int,
)
# Update analysis config and file variables
config.set_analysis(rundate, pipeline=pipeline, **kwargs)
config.set_file_vars(file_vars())
log.blank() # Empty line for visual clarity
# Read which stages that should be executed once for each iterable
skip_stages = config.tech.skip_stages.list
stage_iterate = config.tech.stage_iterate.list
dset_list = []
dset = None
if stage_iterate:
# Read which list should be iterated over and the placeholder name of each entry
iterate_over, _, var_name = config.tech.stage_iterate_over.str.partition(
":")
var_name = var_name.strip()
# Iterate
for item in config.tech[iterate_over].list:
kwargs[var_name] = item
log.blank()
log.info(f"***** Running {item} *****")
for prev_stage, stage in zip([None] + stage_iterate,
stage_iterate):
if stage not in skip_stages:
dset = run_stage(rundate, pipeline, dset, stage,
prev_stage, **kwargs)
if dset is not None:
dset_list.append(dset)
dset = None
kwargs[var_name] = "combined"
if dset_list:
dset_list[0].merge_with(*dset_list[1:], sort_by="time")
dset = dset_list[0]
if len(dset_list) > 1:
log.info(f"Combining dataset for {len(dset_list)} {iterate_over}")
dset.write_as(stage=stage_iterate[-1], label=2, **kwargs)
# Read which stages that should be executed once
stage_once = config.tech.stage_once.list
# Find which stages we will run analysis for
if not stage_once and not stage_iterate:
stage_list = [s for s in stages(pipeline)]
prev_stage_start = None
else:
stage_list = [s for s in stage_once]
prev_stage_start = stage_iterate[-1] if stage_iterate else None
for prev_stage, stage in zip([prev_stage_start] + stage_list, stage_list):
if stage not in skip_stages:
dset = run_stage(rundate, pipeline, dset, stage, prev_stage,
**kwargs)
log.blank()
if dset is not None and dset.num_obs == 0:
log.warn(f"No observations in dataset after {stage} stage.")
break
# Store configuration to library
setup.store_config_to_library(rundate, pipeline, **kwargs)
# Write requirements to file for reproducibility
util.write_requirements()
def run(rundate, pipeline, session=""):
"""Run a Where pipeline for a given date and session
Args:
rundate: Rundate of analysis.
pipeline: Pipeline used for analysis.
session: Session in analysis.
"""
if not setup.has_config(rundate, pipeline, session):
log.fatal(
f"No configuration found for {pipeline.upper()} {session} {rundate.strftime(config.FMT_date)}"
)
# Set up session config
config.init(rundate=rundate, tech_name=pipeline, session=session)
# Set up prefix for console logger and start file logger
log_cfg = config.where.log
prefix = f"{pipeline.upper()} {session} {rundate:%Y-%m-%d}"
log.init(log_level=log_cfg.default_level.str, prefix=prefix)
if log_cfg.log_to_file.bool:
log.file_init(
file_path=files.path("log"),
log_level=log_cfg.default_level.str,
prefix=prefix,
rotation=log_cfg.number_of_log_backups.int,
)
# Read which stages to skip from technique configuration file.
skip_stages = config.tech.get("skip_stages", default="").list
# Register filekey suffix
filekey_suffix = config.tech.filekey_suffix.list
if filekey_suffix:
config.files.profiles = filekey_suffix
# Find which stages we will run analysis for
# TODO: Specify stage_list in config
stage_list = [s for s in stages(pipeline) if s not in skip_stages]
# Start file logging and reporting
reports.report.init(sessions=[session])
reports.report.start_session(session)
reports.report.text("header", session.replace("_", " ").title())
# Update analysis config and file variables
config.set_analysis(rundate=rundate,
tech=pipeline,
analysis=pipeline,
session=session)
config.set_file_vars(file_vars())
# Log the name of the session
log.blank() # Empty line for visual clarity
log.info(f"Start session {session}")
session_timer = timer(f"Finish session {session} in")
session_timer.start()
# Run stages, keep track of previous stage
dset = None
dep_fast = config.where.files.dependencies_fast.bool
for prev_stage, stage in zip([None] + stage_list, stage_list):
# Skip stages where no dependencies have changed
dep_path = files.path("depends", file_vars=dict(stage=stage))
if not (dependencies.changed(dep_path, fast_check=dep_fast)
or util.check_options("-F", "--force")):
log.info(
f"Not necessary to run {stage} for {pipeline.upper()} {rundate.strftime(config.FMT_date)}"
)
continue
elif dset is None:
# Create or read dataset
empty = stage == stage_list[0]
dset = dataset.Dataset(rundate,
tech=pipeline,
stage=prev_stage,
dataset_name=session,
dataset_id="last",
empty=empty)
# Report on the stage
reports.report.start_section(stage)
reports.report.text("header", stage.replace("_", " ").title())
if prev_stage:
log.blank() # Empty line for visual clarity
# Set up dependencies. Add dependencies to previous stage and config file
dependencies.init(dep_path, fast_check=dep_fast)
dependencies.add(files.path("depends",
file_vars=dict(stage=prev_stage)),
label="depends")
dependencies.add(*config.tech.sources, label="config")
# Delete old datasets for this stage
dset.delete_from_file(stage=stage, dataset_id="all")
# Call the current stage. Skip rest of stages if current stage returns False (compare with is since by
# default stages return None)
plugins.call(package_name=__name__,
plugin_name=pipeline,
part=stage,
stage=stage,
dset=dset,
plugin_logger=log.info)
dependencies.write()
if dset.num_obs == 0:
log.warn(
f"No observations in dataset after {stage} stage. Exiting pipeline"
)
break
else: # Only done if loop does not break (all stages finish normally)
# Publish files for session
files.publish_files()
session_timer.end()
# Store configuration to library
setup.store_config_to_library(rundate, pipeline, session)
# Write reports specified in config
reports.write(rundate, pipeline)
# Write requirements to file for reproducibility
util.write_requirements()
def run(rundate, pipeline, session=""):
"""Run a Where pipeline for a given date and session
Args:
rundate: Rundate of analysis.
pipeline: Pipeline used for analysis.
session: Session in analysis.
"""
if not setup.has_config(rundate, pipeline, session):
log.fatal(
f"No configuration found for {pipeline.upper()} {session} {rundate.strftime(config.FMT_date)}"
)
# Set up tech config and file logging
config.init(rundate=rundate, tech_name=pipeline, session=session)
log.file_init(log_path=files.path("log"))
# Read which stages to skip from technique configuration file.
skip_stages = config.tech.get("skip_stages", default="").list
# Register filekey suffix
filekey_suffix = config.tech.filekey_suffix.list
if filekey_suffix:
files.use_filelist_profiles(*filekey_suffix)
# Find which stages we will run analysis for
stage_list = [s for s in stages(pipeline) if s not in skip_stages]
# Start file logging and reporting
reports.report.init(sessions=[session])
reports.report.start_session(session)
reports.report.text("header", session.replace("_", " ").title())
# Update analysis config and file variables
config.set_analysis(rundate=rundate,
tech=pipeline,
analysis=pipeline,
session=session)
config.set_file_vars(file_vars())
# Log the name of the session
log.blank() # Empty line for visual clarity
log.info(f"Start session {session}")
session_timer = timer(f"Finish session {session} in")
session_timer.start()
# Run stages, keep track of previous stage
dep_fast = config.where.files.dependencies_fast.bool
for prev_stage, stage in zip([None] + stage_list, stage_list):
# Skip stages where no dependencies have changed
if not (dependencies.changed(fast_check=dep_fast,
rundate=rundate,
tech=pipeline,
session=session,
stage=stage)
or util.check_options("-F", "--force")):
log.info(
f"Not necessary to run {stage} for {pipeline.upper()} {rundate.strftime(config.FMT_date)}"
)
continue
# Report on the stage
reports.report.start_section(stage)
reports.report.text("header", stage.replace("_", " ").title())
if prev_stage:
log.blank() # Empty line for visual clarity
# Set up dependencies. Add dependencies to previous stage and config file
dependencies.init(fast_check=dep_fast, session=session, stage=stage)
dependencies.add(
files.path("model_run_depends",
file_vars=dict(session=session, stage=prev_stage)))
dependencies.add(*config.tech.sources)
# Call the current stage. Skip rest of stages if current stage returns False (compare with is since by
# default stages return None)
do_next_stage = call(pipeline,
stage,
rundate=rundate,
session=session,
prev_stage=prev_stage,
stage=stage,
logger=log.info)
dependencies.write()
if do_next_stage is False:
break # TODO, this does not work together with dependencies changed ...
# Publish files for session
files.publish_files()
session_timer.end()
# Store configuration to library
setup.store_config_to_library(rundate, pipeline, session)
# Write reports specified in config
reports.write(rundate, pipeline)
# Write requirements to file for reproducibility
util.write_requirements()