alexander/urban-meal-delivery
1
1
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity Actions

Add OrderHistory.make_vertical_time_series()

Browse source 
- the method slices out a vertical time series from the data within
  an `OrderHistory` object
This commit is contained in:
Alexander Hess 2021-01-09 17:00:10 +01:00
parent b61db734b6
commit 5330ceb771
Signed by: alexander
GPG key ID: 344EA5AB10D868E0
2 changed files with 194 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

82
src/urban_meal_delivery/forecasts/timify.py
View file

@ -212,3 +212,85 @@ class OrderHistory:
actual_df = intra_pixel.loc[[predict_at]]
return training_df, frequency, actual_df
def make_vertical_time_series( # noqa:WPS210
self, pixel_id: int, predict_day: dt.date, train_horizon: int,
) -> Tuple[pd.DataFrame, int, pd.DataFrame]:
"""Slice a vertical time series out of the `.totals`.
Create a time series covering `train_horizon` weeks that can be used
for training a forecasting model to predict the demand on the `predict_day`.
For explanation of the terms "horizontal", "vertical", and "real-time"
in the context of time series, see section 3.2 in the following paper:
https://github.com/webartifex/urban-meal-delivery-demand-forecasting/blob/main/paper.pdf
Args:
pixel_id: pixel in which the time series is aggregated
predict_day: day for which predictions are made
train_horizon: weeks of historic data used to predict `predict_at`
Returns:
training time series, frequency, actual order counts on `predict_day`
Raises:
LookupError: `pixel_id` is not in the `grid`
RuntimeError: desired time series slice is not entirely in `.totals`
"""
try:
intra_pixel = self.totals.loc[pixel_id]
except KeyError:
raise LookupError('The `pixel_id` is not in the `grid`') from None
if predict_day >= config.CUTOFF_DAY.date(): # pragma: no cover
raise RuntimeError('Internal error: cannot predict beyond the given data')
# The first and last training day are just before the `predict_day`
# and span exactly `train_horizon` weeks covering all times of the day.
first_train_day = predict_day - dt.timedelta(weeks=train_horizon)
first_start_at = dt.datetime(
first_train_day.year,
first_train_day.month,
first_train_day.day,
config.SERVICE_START,
0,
)
last_train_day = predict_day - dt.timedelta(days=1)
last_start_at = dt.datetime(
last_train_day.year,
last_train_day.month,
last_train_day.day,
config.SERVICE_END, # subtract one `time_step` below
0,
) - dt.timedelta(minutes=self._time_step)
# The frequency is the number of weekdays times the number of daily time steps.
frequency = 7 * self._n_daily_time_steps
# Take all the counts between `first_train_day` and `last_train_day`.
training_df = intra_pixel.loc[
first_start_at:last_start_at # type: ignore
]
if len(training_df) != frequency * train_horizon:
raise RuntimeError('Not enough historic data for `predict_day`')
first_prediction_at = dt.datetime(
predict_day.year,
predict_day.month,
predict_day.day,
config.SERVICE_START,
0,
)
last_prediction_at = dt.datetime(
predict_day.year,
predict_day.month,
predict_day.day,
config.SERVICE_END, # subtract one `time_step` below
0,
) - dt.timedelta(minutes=self._time_step)
actuals_df = intra_pixel.loc[
first_prediction_at:last_prediction_at # type: ignore
]
return training_df, frequency, actuals_df

113
tests/forecasts/timify/test_make_time_series.py
View file

@ -117,7 +117,7 @@ class TestMakeHorizontalTimeSeries:
):
"""The length of a training time series must be a multiple of `7` ...
whereas the time series with the actual order counts always holds `1` value.
... whereas the time series with the actual order counts has only `1` value.
"""
result = order_history.make_horizontal_time_series(
pixel_id=good_pixel_id,
@ -171,3 +171,114 @@ class TestMakeHorizontalTimeSeries:
order_history.make_horizontal_time_series(
pixel_id=good_pixel_id, predict_at=good_predict_at, train_horizon=999,
)
class TestMakeVerticalTimeSeries:
"""Test the `OrderHistory.make_vertical_time_series()` method."""
@pytest.mark.parametrize('train_horizon', test_config.TRAIN_HORIZONS)
def test_wrong_pixel(self, order_history, good_predict_at, train_horizon):
"""A `pixel_id` that is not in the `grid`."""
with pytest.raises(LookupError):
order_history.make_vertical_time_series(
pixel_id=999_999,
predict_day=good_predict_at.date(),
train_horizon=train_horizon,
)
@pytest.mark.parametrize('train_horizon', test_config.TRAIN_HORIZONS)
def test_time_series_are_dataframes(
self, order_history, good_pixel_id, good_predict_at, train_horizon,
):
"""The time series come in a one-column `pd.DataFrame`."""
result = order_history.make_vertical_time_series(
pixel_id=good_pixel_id,
predict_day=good_predict_at.date(),
train_horizon=train_horizon,
)
training_df, _, actual_df = result
assert isinstance(training_df, pd.DataFrame)
assert training_df.columns == ['total_orders']
assert isinstance(actual_df, pd.DataFrame)
assert actual_df.columns == ['total_orders']
@pytest.mark.parametrize('train_horizon', test_config.TRAIN_HORIZONS)
def test_time_series_have_correct_length(
self, order_history, good_pixel_id, good_predict_at, train_horizon,
):
"""The length of a training time series is the product of the ...
... weekly time steps (i.e., product of `7` and the number of daily time steps)
and the `train_horizon` in weeks.
The time series with the actual order counts always holds one observation
per time step of a day.
"""
result = order_history.make_vertical_time_series(
pixel_id=good_pixel_id,
predict_day=good_predict_at.date(),
train_horizon=train_horizon,
)
training_df, _, actual_df = result
n_daily_time_steps = (
60
* (config.SERVICE_END - config.SERVICE_START)
// test_config.LONG_TIME_STEP
)
assert len(training_df) == 7 * n_daily_time_steps * train_horizon
assert len(actual_df) == n_daily_time_steps
@pytest.mark.parametrize('train_horizon', test_config.TRAIN_HORIZONS)
def test_frequency_is_number_number_of_weekly_time_steps(
self, order_history, good_pixel_id, good_predict_at, train_horizon,
):
"""The `frequency` is the number of weekly time steps."""
result = order_history.make_vertical_time_series(
pixel_id=good_pixel_id,
predict_day=good_predict_at.date(),
train_horizon=train_horizon,
)
_, frequency, _ = result # noqa:WPS434
n_daily_time_steps = (
60
* (config.SERVICE_END - config.SERVICE_START)
// test_config.LONG_TIME_STEP
)
assert frequency == 7 * n_daily_time_steps
@pytest.mark.parametrize('train_horizon', test_config.TRAIN_HORIZONS)
def test_no_long_enough_history1(
self, order_history, good_pixel_id, bad_predict_at, train_horizon,
):
"""If the `predict_at` day is too early in the `START`-`END` horizon ...
... the history of order totals is not long enough.
"""
with pytest.raises(RuntimeError):
order_history.make_vertical_time_series(
pixel_id=good_pixel_id,
predict_day=bad_predict_at.date(),
train_horizon=train_horizon,
)
def test_no_long_enough_history2(
self, order_history, good_pixel_id, good_predict_at,
):
"""If the `train_horizon` is longer than the `START`-`END` horizon ...
... the history of order totals can never be long enough.
"""
with pytest.raises(RuntimeError):
order_history.make_vertical_time_series(
pixel_id=good_pixel_id,
predict_day=good_predict_at.date(),
train_horizon=999,
)