def test_update(self):
for dataset_name in self.TEST_DATASETS:
dataset = Dataset.create(self.test_dataset_ids[dataset_name])
self.assertFalse('field' in dataset)
Dataset.update(dataset, {'field': {'key': 'value'}})
dataset = Dataset.find_one(self.test_dataset_ids[dataset_name])
self.assertTrue('field' in dataset)
self.assertEqual(dataset['field'], {'key': 'value'})
def summarize(dataset, query, select, group):
"""
Return a summary for the rows/values filtered by *query* and *select*
and grouped by *group* or the overall summary if no group is specified.
"""
# narrow list of observations via query/select
dframe = Observation.find(dataset, query, select, as_df=True)
# do not allow group by numeric types
# TODO check schema for valid groupby columns once included
_type = dframe.dtypes.get(group)
if group != ALL and (_type is None or _type.type != np.object_):
return {ERROR: "group: '%s' is not categorical." % group}
# check cached stats for group and update as necessary
stats = dataset.get(STATS, {})
if not stats.get(group):
stats = {ALL: summarize_df(dframe)} if group == ALL \
else summarize_with_groups(dframe, stats, group)
Dataset.update(dataset, {STATS: stats})
stats_to_return = stats.get(group)
return dict_from_mongo(stats_to_return if group == ALL else {group:
stats_to_return})
except ParseError, err:
# do not save record, return error
return {ERROR: err}
record = {
DATASET_ID: dataset[DATASET_ID],
cls.FORMULA: formula,
cls.NAME: name,
}
cls.collection.insert(record)
# invalidate summary ALL since we have a new column
stats = dataset.get(STATS)
if stats:
del stats[ALL]
del dataset[STATS]
Dataset.update(dataset, {STATS: stats})
# call remote calculate and pass calculation id
calculate_column.delay(dataset, dframe, formula, name)
return mongo_remove_reserved_keys(record)
@classmethod
def find(cls, dataset):
"""
Return the calculations for given *dataset*.
"""
return [mongo_remove_reserved_keys(record) for record in cls.collection.find({
DATASET_ID: dataset[DATASET_ID],
})]