def create_from_list_or_dict(cls, dataset, calculations):
calculations = to_list(calculations)
if not len(calculations) or not isinstance(calculations, list):
raise ArgumentError('Improper format for JSON calculations.')
parsed_calculations = []
# Pull out args to check JSON format
try:
for c in calculations:
groups = c.get("groups")
if not isinstance(groups, list):
groups = [groups]
for group in groups:
parsed_calculations.append([
c[cls.FORMULA],
c[cls.NAME], group])
except KeyError as e:
raise ArgumentError('Required key %s not found in JSON' % e)
calculations = [cls().save(dataset, formula, name, group)
for formula, name, group in parsed_calculations]
call_async(calculate_task, calculations, dataset.clear_cache())
def create_from_list_or_dict(cls, dataset, calculations):
calculations = to_list(calculations)
if not len(calculations) or not isinstance(calculations, list) or\
any([not isinstance(e, dict) for e in calculations]):
raise ArgumentError('Improper format for JSON calculations.')
parsed_calculations = []
# Pull out args to check JSON format
try:
for c in calculations:
groups = c.get("groups")
if not isinstance(groups, list):
groups = [groups]
for group in groups:
parsed_calculations.append(
[c[cls.FORMULA], c[cls.NAME], group])
except KeyError as e:
raise ArgumentError('Required key %s not found in JSON' % e)
# Save instead of create so that we calculate on all at once.
calculations = [
cls().save(dataset, formula, name, group)
for formula, name, group in parsed_calculations
]
call_async(calculate_task, calculations, dataset.clear_cache())
def add_observations(self, new_data):
"""Update `dataset` with `new_data`."""
update_id = uuid.uuid4().hex
self.add_pending_update(update_id)
new_data = to_list(new_data)
# fetch data before other updates
new_dframe_raw = dframe_from_update(self, new_data)
call_async(calculate_updates, self, new_data,
new_dframe_raw=new_dframe_raw, update_id=update_id)
def __slugify_data(new_data, labels_to_slugs):
slugified_data = []
new_data = to_list(new_data)
for row in new_data:
for key, value in row.iteritems():
if labels_to_slugs.get(key) and key != MONGO_ID:
del row[key]
row[labels_to_slugs[key]] = value
slugified_data.append(row)
return slugified_data
def add_observations(self, new_data):
"""Update `dataset` with `new_data`."""
update_id = uuid.uuid4().hex
self.add_pending_update(update_id)
new_data = to_list(new_data)
# fetch data before other updates
new_dframe_raw = dframe_from_update(self, new_data)
call_async(calculate_updates,
self,
new_data,
new_dframe_raw=new_dframe_raw,
update_id=update_id)
def add_observations(self, new_data):
"""Update `dataset` with `new_data`."""
update_id = uuid.uuid4().hex
self.add_pending_update(update_id)
new_data = to_list(new_data)
calculator = Calculator(self)
new_dframe_raw = calculator.dframe_from_update(
new_data, self.schema.labels_to_slugs)
calculator._check_update_is_valid(new_dframe_raw)
calculator.dataset.clear_cache()
call_async(calculator.calculate_updates, calculator, new_data,
new_dframe_raw=new_dframe_raw, update_id=update_id)
def delete_columns(self, columns):
"""Delete column `column` from this dataset.
:param column: The column to delete.
"""
columns = set(self.schema.keys()).intersection(set(to_list(columns)))
if not len(columns):
raise ArgumentError("Columns: %s not in dataset.")
Observation.delete_columns(self, columns)
new_schema = self.schema
[new_schema.pop(c) for c in columns]
self.set_schema(new_schema, set_num_columns=True)
return columns
def delete_columns(self, columns):
"""Delete column `column` from this dataset.
:param column: The column to delete.
"""
columns = set(self.schema.keys()).intersection(set(to_list(columns)))
if not len(columns):
raise ArgumentError("Columns: %s not in dataset.")
Observation.delete_columns(self, columns)
new_schema = self.schema
[new_schema.pop(c) for c in columns]
self.set_schema(new_schema, set_num_columns=True)
return columns
def aggregated_dataset(self, groups):
groups = to_list(groups)
_id = self.aggregated_datasets_dict.get(self.join_groups(groups))
return self.find_one(_id) if _id else None
def aggregated_dataset(self, groups):
groups = to_list(groups)
_id = self.aggregated_datasets_dict.get(self.join_groups(groups))
return self.find_one(_id) if _id else None