def test_no_groupby_columns(self, config, dataset_columns):
config["groupby_columns"] = []
config["groupby_column"] = "country"
groupby_colums = check_and_get_groupby_columns(config, dataset_columns)
assert len(groupby_colums) == 1
config.pop("groupby_columns")
groupby_colums = check_and_get_groupby_columns(config, dataset_columns)
assert len(groupby_colums) == 1
def test_check_and_get_groupby_columns(self, config):
dataset_columns = ["value1", "country", "old"]
groupby_colums = check_and_get_groupby_columns(config, dataset_columns)
assert groupby_colums == ["country", "old"]
config.pop("groupby_columns")
config["groupby_column"] = "country"
groupby_colums = check_and_get_groupby_columns(config, dataset_columns)
assert groupby_colums == ["country"]
def test_invalid_groupby_columns(self, config, dataset_columns):
config["groupby_columns"] = ["country", ""]
restricted_dataset_columns = ["value1", "country"]
with pytest.raises(ValueError) as err:
_ = check_and_get_groupby_columns(config, restricted_dataset_columns)
assert "Invalid time series identifiers selection" in str(err.value)
with pytest.raises(ValueError) as err:
_ = check_and_get_groupby_columns(config, restricted_dataset_columns)
assert "Invalid time series identifiers selection" in str(err.value)
config.pop("groupby_columns")
with pytest.raises(ValueError) as err:
_ = check_and_get_groupby_columns(config, restricted_dataset_columns)
assert "Long format is activated but no time series identifiers have been provided" in str(err.value)
config["groupby_column"] = "not_ok"
with pytest.raises(ValueError) as err:
_ = check_and_get_groupby_columns(config, dataset_columns)
assert "Invalid time series identifiers selection" in str(err.value)
from dataiku.customrecipe import get_recipe_config
from dku_timeseries import Resampler
from io_utils import get_input_output
from recipe_config_loading import check_and_get_groupby_columns, check_time_column_parameter, check_python_version, get_resampling_params
check_python_version()
# --- Setup
(input_dataset, output_dataset) = get_input_output()
recipe_config = get_recipe_config()
input_dataset_columns = [
column["name"] for column in input_dataset.read_schema()
]
check_time_column_parameter(recipe_config, input_dataset_columns)
groupby_columns = check_and_get_groupby_columns(recipe_config,
input_dataset_columns)
datetime_column = recipe_config.get('datetime_column')
params = get_resampling_params(recipe_config)
# --- Run
df = input_dataset.get_dataframe()
resampler = Resampler(params)
output_df = resampler.transform(df,
datetime_column,
groupby_columns=groupby_columns)
# --- Write output
output_dataset.write_with_schema(output_df)
def test_two_identifiers_fields(self, config, dataset_columns):
config["groupby_column"] = "notice"
config["groupby_columns"] = ["country"]
groupby_colums = check_and_get_groupby_columns(config, dataset_columns)
assert groupby_colums == ["country"]