def test_datetime_column_with_min_max_constraints_ok():
assert (
validate_constraints(
DataFrame(
{
"datetime": [Timestamp("2021-03-14T12:34:56")],
"datetime_utc_min_max_no_tz": [Timestamp("2021-03-14T12:34:56Z")],
"datetime_utc_min_max_same_tz": [Timestamp("2021-03-14T12:34:56Z")],
"datetime_utc_min_max_from_different_tz": [Timestamp("2021-03-14T12:34:56Z")],
}
),
pandas_columns=[
PandasColumn.datetime_column(
"datetime_utc_min_max_no_tz",
tz="UTC",
min_datetime=Timestamp.min,
max_datetime=Timestamp.max,
),
PandasColumn.datetime_column(
"datetime_utc_min_max_same_tz",
tz="UTC",
min_datetime=Timestamp("2021-01-01T00:00:00Z"),
max_datetime=Timestamp("2021-12-01T00:00:00Z"),
),
PandasColumn.datetime_column(
"datetime_utc_min_max_from_different_tz",
tz="UTC",
min_datetime=Timestamp("2021-01-01T00:00:00Z", tz="US/Eastern"),
max_datetime=Timestamp("2021-12-01T00:00:00Z"),
),
],
)
is None
)
def test_datetime_column_with_tz_validation_fails_when_incorrect_tz():
with pytest.raises(ConstraintViolationException):
validate_constraints(
DataFrame(
{
"datetime_utc": [Timestamp("2021-03-14T12:34:56")],
}
),
pandas_columns=[
PandasColumn.datetime_column("datetime_utc", tz="UTC"),
],
)
def test_datetime_column_with_tz_validation_ok():
assert (
validate_constraints(
DataFrame(
{
"datetime": [Timestamp("2021-03-14T12:34:56")],
"datetime_utc": [Timestamp("2021-03-14T12:34:56Z")],
"datetime_dublin": [Timestamp("2021-03-14T12:34:56", tz="Europe/Dublin")],
"datetime_est": [Timestamp("2021-03-14T12:34:56", tz="US/Eastern")],
"datetime_chatham": [Timestamp("2021-03-14T12:34:56", tz="Pacific/Chatham")],
"datetime_utc_with_min_max": [Timestamp("2021-03-14T12:34:56Z")],
}
),
pandas_columns=[
PandasColumn.datetime_column("datetime"),
PandasColumn.datetime_column("datetime_utc", tz="UTC"),
PandasColumn.datetime_column("datetime_dublin", tz="Europe/Dublin"),
PandasColumn.datetime_column("datetime_est", tz="US/Eastern"),
PandasColumn.datetime_column("datetime_chatham", tz="Pacific/Chatham"),
],
)
is None
)
"min_start_time",
"Date data collection started",
),
EventMetadataEntry.text(str(max(dataframe["end_time"])),
"max_end_time", "Timestamp of last trip"),
EventMetadataEntry.text(str(len(dataframe)), "n_rows",
"Number of rows seen in the dataframe"),
EventMetadataEntry.text(str(dataframe.columns), "columns",
"Keys of columns seen in the dataframe"),
]
TripDataFrameSchema = [
PandasColumn.integer_column("bike_id", min_value=0),
PandasColumn.datetime_column(
"start_time",
min_datetime=Timestamp(year=2017, month=1, day=1),
),
PandasColumn.datetime_column(
"end_time",
min_datetime=Timestamp(year=2017, month=1, day=1),
),
PandasColumn.string_column("interval_date"),
]
RawTripDataFrame = create_dagster_pandas_dataframe_type(
name="RawTripDataFrame",
columns=[
PandasColumn(column.name) for column in TripDataFrameSchema
if column.name != "interval_date"
],
)
'min_start_time',
'Date data collection started',
),
EventMetadataEntry.text(str(max(dataframe['end_time'])),
'max_end_time', 'Timestamp of last trip'),
EventMetadataEntry.text(str(len(dataframe)), 'n_rows',
'Number of rows seen in the dataframe'),
EventMetadataEntry.text(str(dataframe.columns), 'columns',
'Keys of columns seen in the dataframe'),
]
TripDataFrameSchema = [
PandasColumn.integer_column('bike_id', min_value=0),
PandasColumn.datetime_column(
'start_time',
min_datetime=Timestamp(year=2018, month=1, day=1),
),
PandasColumn.datetime_column(
'end_time',
min_datetime=Timestamp(year=2018, month=1, day=1),
),
PandasColumn.string_column('interval_date'),
]
RawTripDataFrame = create_dagster_pandas_dataframe_type(
name='RawTripDataFrame',
columns=[
PandasColumn(column.name) for column in TripDataFrameSchema
if column.name != 'interval_date'
],
)
