def parse_columns(dataset, formula, name, dframe=None, no_index=False):
"""Parse a formula and return columns resulting from its functions.
Parse a formula into a list of functions then apply those functions to
the Data Frame and return the resulting columns.
:param formula: The formula to parse.
:param name: Name of the formula.
:param dframe: A DataFrame to apply functions to.
:param no_index: Drop the index on result columns.
"""
functions = Parser.parse_functions(formula)
dependent_columns = Parser.dependent_columns(formula, dataset)
# make select from dependent_columns
if dframe is None:
select = {col: 1 for col in dependent_columns or [MONGO_ID]}
dframe = dataset.dframe(
query_args=QueryArgs(select=select),
keep_mongo_keys=True).set_index(MONGO_ID_ENCODED)
if not dependent_columns:
# constant column, use dummy
dframe['dummy'] = 0
return __build_columns(dataset, dframe, functions, name, no_index)
def parse_columns(dataset, formula, name, dframe=None, no_index=False):
"""Parse a formula and return columns resulting from its functions.
Parse a formula into a list of functions then apply those functions to
the Data Frame and return the resulting columns.
:param formula: The formula to parse.
:param name: Name of the formula.
:param dframe: A DataFrame to apply functions to.
:param no_index: Drop the index on result columns.
"""
functions = Parser.parse_functions(formula)
dependent_columns = Parser.dependent_columns(formula, dataset)
# make select from dependent_columns
if dframe is None:
select = {col: 1 for col in dependent_columns or [MONGO_ID]}
dframe = dataset.dframe(
query_args=QueryArgs(select=select),
keep_mongo_keys=True).set_index(MONGO_ID_ENCODED)
if not dependent_columns:
# constant column, use dummy
dframe['dummy'] = 0
return __build_columns(dataset, dframe, functions, name, no_index)
def __create_aggregator(dataset, formula, name, groups, dframe=None):
# TODO this should work with index eventually
columns = parse_columns(dataset, formula, name, dframe, no_index=True)
dependent_columns = Parser.dependent_columns(formula, dataset)
aggregation = Parser.parse_aggregation(formula)
# get dframe with only the necessary columns
select = combine_dicts({group: 1 for group in groups},
{col: 1 for col in dependent_columns})
# ensure at least one column (MONGO_ID) for the count aggregation
query_args = QueryArgs(select=select or {MONGO_ID: 1})
dframe = dataset.dframe(query_args=query_args, keep_mongo_keys=not select)
return Aggregator(dframe, groups, aggregation, name, columns)
def calculate_task(calculations, dataset):
"""Background task to run a calculation.
Set calculation to failed and raise if an exception occurs.
:param calculation: Calculation to run.
:param dataset: Dataset to run calculation on.
"""
# block until other calculations for this dataset are finished
calculations[0].restart_if_has_pending(dataset, calculations[1:])
calculate_columns(dataset.reload(), calculations)
for calculation in calculations:
calculation.add_dependencies(
dataset, Parser.dependent_columns(calculation.formula, dataset))
if calculation.aggregation is not None:
aggregated_id = dataset.aggregated_datasets_dict[calculation.group]
calculation.set_aggregation_id(aggregated_id)
calculation.ready()
def calculate_task(calculations, dataset):
"""Background task to run a calculation.
Set calculation to failed and raise if an exception occurs.
:param calculation: Calculation to run.
:param dataset: Dataset to run calculation on.
"""
# block until other calculations for this dataset are finished
calculations[0].restart_if_has_pending(dataset, calculations[1:])
calculate_columns(dataset.reload(), calculations)
for calculation in calculations:
calculation.add_dependencies(
dataset, Parser.dependent_columns(calculation.formula, dataset))
if calculation.aggregation is not None:
aggregated_id = dataset.aggregated_datasets_dict[calculation.group]
calculation.set_aggregation_id(aggregated_id)
calculation.ready()
def test_parse_formula_dependent_columns(self):
formulas_to_deps = combine_dicts(AGG_CALCS_TO_DEPS, CALCS_TO_DEPS)
for formula, column_list in formulas_to_deps.iteritems():
columns = Parser.dependent_columns(formula, self.dataset)
self.assertEqual(set(column_list), columns)
def test_parse_formula_dependent_columns(self):
formulas_to_deps = combine_dicts(AGG_CALCS_TO_DEPS, CALCS_TO_DEPS)
for formula, column_list in formulas_to_deps.iteritems():
columns = Parser.dependent_columns(formula, self.dataset)
self.assertEqual(set(column_list), columns)
