def test_smooth(get_dataframe):
"""
Test that iterated median filter matches an independently calculated result.
"""
sl = SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat"),
hours=(20, 0),
)
ds = DistanceSeries(subscriber_locations=sl, statistic="min")
smoothed_df = get_dataframe(
IterativeMedianFilter(
query_to_filter=ImputedDistanceSeries(distance_series=ds),
filter_window_size=3,
)
)
assert smoothed_df.set_index("subscriber").loc[
"038OVABN11Ak4W5P"
].value.tolist() == pytest.approx(
[
9343367.56611,
9343367.56611,
9343367.56611,
9343367.56611,
9343367.56611,
9221492.17419,
]
)
def test_returns_expected_values(stat, sub_a_expected, sub_b_expected,
get_dataframe):
"""
Test that we get expected return values for the various statistics
"""
sub_a_id, sub_b_id = "j6QYNbMJgAwlVORP", "NG1km5NzBg5JD8nj"
rl = daily_location("2016-01-01",
spatial_unit=make_spatial_unit("lon-lat"))
df = get_dataframe(
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat"),
),
reference_location=rl,
statistic=stat,
))
df = (df.assign(datetime=pd.to_datetime(df.datetime)).set_index(
["subscriber", "datetime"]).sort_index())
sub = df.loc[sub_a_id]
assert df.loc[sub_a_id].loc["2016-01-01"].value == pytest.approx(
sub_a_expected)
assert df.loc[(sub_b_id,
datetime(2016, 1,
6))].value == pytest.approx(sub_b_expected)
def test_error_when_subs_locations_not_point_geom():
"""
Test that error is raised if the spatial unit of the subscriber locations isn't point.
"""
with pytest.raises(ValueError,
match="does not have longitude/latitude columns"):
DistanceSeries(subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("admin", level=3),
))
def test_no_cast_for_below_day(get_dataframe):
"""
Test that results aren't cast to date for smaller time buckets.
"""
df = get_dataframe(
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-02",
spatial_unit=make_spatial_unit("lon-lat")),
time_bucket="hour",
))
assert isinstance(df.datetime[0], datetime)
def test_invalid_statistic_raises_error():
"""
Test that passing an invalid statistic raises an error.
"""
with pytest.raises(ValueError,
match="'NOT_A_STATISTIC' is not a valid statistic"):
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat")),
statistic="NOT_A_STATISTIC",
)
def test_invalid_time_bucket_raises_error():
"""
Test that passing an invalid time bucket raises an error.
"""
with pytest.raises(
ValueError,
match="'NOT_A_BUCKET' is not a valid value for time_bucket"):
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat")),
time_bucket="NOT_A_BUCKET",
)
def test_invalid_reference_raises_error():
"""
Test that passing an invalid reference location raises an error.
"""
with pytest.raises(
ValueError,
match=
"Argument 'reference_location' should be an instance of BaseLocation class or a tuple of two floats. Got: str",
):
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat")),
reference_location="NOT_A_LOCATION",
)
def test_bad_window(size, match):
"""
Test some median unfriendly window sizes raise errors.
"""
with pytest.raises(ValueError, match=match):
sl = SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat"),
hours=(20, 0),
)
ds = DistanceSeries(subscriber_locations=sl, statistic="min")
IterativeMedianFilter(
query_to_filter=ImputedDistanceSeries(distance_series=ds),
filter_window_size=size,
)
def test_column_must_exist(column_arg):
"""
Check errors for required columns.
"""
with pytest.raises(ValueError, match=column_arg):
sl = SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat"),
hours=(20, 0),
)
ds = DistanceSeries(subscriber_locations=sl, statistic="min")
IterativeMedianFilter(
query_to_filter=ImputedDistanceSeries(distance_series=ds),
filter_window_size=3,
**{column_arg: "NOT_A_VALID_COLUMN"},
)
def test_returns_expected_values_fixed_point(stat, sub_a_expected,
sub_b_expected, get_dataframe):
"""
Test that we get expected return values for the various statistics with 0, 0 reference
"""
sub_a_id, sub_b_id = "j6QYNbMJgAwlVORP", "NG1km5NzBg5JD8nj"
df = get_dataframe(
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat")),
statistic=stat,
)).set_index(["subscriber", "datetime"])
assert df.loc[(sub_a_id, date(2016, 1,
1))].value == pytest.approx(sub_a_expected)
assert df.loc[(sub_b_id, date(2016, 1,
6))].value == pytest.approx(sub_b_expected)
def test_impute(get_dataframe):
sl = SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat"),
hours=(20, 0),
)
ds = DistanceSeries(subscriber_locations=sl, statistic="min")
ds_df = get_dataframe(ds)
sql = get_dataframe(ImputedDistanceSeries(distance_series=ds))
all_subs = ds_df.subscriber.drop_duplicates()
for sub in all_subs:
print(sub)
if ds_df[ds_df.subscriber == sub].datetime.nunique() > 3:
to_be_imputed = ds_df[ds_df.subscriber == sub].sort_values(
"datetime")
imputed = fill_in_dates(to_be_imputed, 3, sl.start, sl.stop)
assert imputed.value.values.tolist() == pytest.approx(
sql[sql.subscriber == sub].value.tolist())
def test_error_on_spatial_unit_mismatch():
"""
Test that error is raised if the spatial unit of the subscriber locations isn't point.
"""
rl = daily_location("2016-01-01",
spatial_unit=make_spatial_unit("admin", level=3))
with pytest.raises(
ValueError,
match=
"reference_location must have the same spatial unit as subscriber_locations.",
):
DistanceSeries(
subscriber_locations=SubscriberLocations(
"2016-01-01",
"2016-01-07",
spatial_unit=make_spatial_unit("lon-lat")),
reference_location=rl,
)
