def profiler_with_unrealistic_expectations(
dataset: PandasDataset) -> ExpectationSuite:
# need to create dataframe with corrupted data first
df = pd.DataFrame()
df["current_balance"] = [-100]
df["avg_passenger_count"] = [0]
other_ds = PandasDataset(df)
other_ds.expect_column_max_to_be_between("current_balance", -1000, -100)
other_ds.expect_column_values_to_be_in_set("avg_passenger_count",
value_set={0})
# this should pass
other_ds.expect_column_min_to_be_between("avg_passenger_count", 0, 1000)
return other_ds.get_expectation_suite()
def test_pandas_datetime_evaluation_parameter():
evaluation_parameters = {
"now": pd.Timestamp.now(),
"now_minus_48h": pd.Timestamp.now() - pd.to_timedelta(2, unit="d"),
}
test_data = {
"data_refresh": [
pd.Timestamp.now(),
(pd.Timestamp.now() - pd.to_timedelta(1, unit="d")),
]
}
_df = pd.DataFrame(test_data)
df = PandasDataset(_df)
for param in evaluation_parameters:
df.set_evaluation_parameter(param, evaluation_parameters[param])
df.expect_column_max_to_be_between(
column="data_refresh", min_value={"$PARAMETER": "now_minus_48h"})
result = df.validate()
assert result.success
