Add OrderHistory.make_real_time_time_series()

- the method slices out a real-time time series from the data within
  an `OrderHistory` object

tests/forecasts/timify/test_make_time_series.py

@@ -1,4 +1,8 @@
-"""Test the time series related code."""
+"""Test the code generating time series with the order totals.
+
+Unless otherwise noted, each `time_step` is 60 minutes long implying
+12 time steps per day (i.e., we use `LONG_TIME_STEP` by default).
+"""
 # pylint:disable=no-self-use,unused-argument
 
 import datetime
@@ -63,7 +67,11 @@ def good_predict_at():
     or `train_horizon=2` works.
     """
     return datetime.datetime(
-        test_config.END.year, test_config.END.month, test_config.END.day, 12, 0,
+        test_config.END.year,
+        test_config.END.month,
+        test_config.END.day,
+        test_config.NOON,
+        0,
     )
 
 
@@ -76,7 +84,7 @@ def bad_predict_at():
     """
     predict_day = test_config.END - datetime.timedelta(weeks=1, days=1)
     return datetime.datetime(
-        predict_day.year, predict_day.month, predict_day.day, 12, 0,
+        predict_day.year, predict_day.month, predict_day.day, test_config.NOON, 0,
     )
 
 
@@ -282,3 +290,156 @@ class TestMakeVerticalTimeSeries:
                 predict_day=good_predict_at.date(),
                 train_horizon=999,
             )
+
+
+class TestMakeRealTimeTimeSeries:
+    """Test the `OrderHistory.make_real_time_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_real_time_time_series(
+                pixel_id=999_999,
+                predict_at=good_predict_at,
+                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_real_time_time_series(
+            pixel_id=good_pixel_id,
+            predict_at=good_predict_at,
+            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_length1(
+        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; however, this assertion only holds if
+        we predict the first `time_step` of the day.
+
+        The time series with the actual order counts always holds `1` value.
+        """
+        predict_at = datetime.datetime(
+            good_predict_at.year,
+            good_predict_at.month,
+            good_predict_at.day,
+            config.SERVICE_START,
+            0,
+        )
+        result = order_history.make_real_time_time_series(
+            pixel_id=good_pixel_id, predict_at=predict_at, 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) == 1
+
+    @pytest.mark.parametrize('train_horizon', test_config.TRAIN_HORIZONS)
+    def test_time_series_have_correct_length2(
+        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; however, this assertion only holds if
+        we predict the first `time_step` of the day. Predicting any other `time_step`
+        means that the training time series becomes longer by the number of time steps
+        before the one being predicted.
+
+        The time series with the actual order counts always holds `1` value.
+        """
+        assert good_predict_at.hour == test_config.NOON
+
+        result = order_history.make_real_time_time_series(
+            pixel_id=good_pixel_id,
+            predict_at=good_predict_at,
+            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
+        )
+        n_time_steps_before = (
+            60 * (test_config.NOON - config.SERVICE_START) // test_config.LONG_TIME_STEP
+        )
+
+        assert (
+            len(training_df)
+            == 7 * n_daily_time_steps * train_horizon + n_time_steps_before
+        )
+        assert len(actual_df) == 1
+
+    @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_real_time_time_series(
+            pixel_id=good_pixel_id,
+            predict_at=good_predict_at,
+            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_real_time_time_series(
+                pixel_id=good_pixel_id,
+                predict_at=bad_predict_at,
+                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_real_time_time_series(
+                pixel_id=good_pixel_id, predict_at=good_predict_at, train_horizon=999,
+            )