def test_do_not_drop_changed_probabilistic_belief(setup_beliefs):
"""Trying to save a changed probabilistic belief should result in saving the whole belief.
For example, given a belief that defines both cp=0.2 and cp=0.5,
if that belief becomes more certain (e.g. cp=0.3 and cp=0.5),
we expect to see the full new belief stored, rather than just the cp=0.3 value.
"""
# Set a reference for the number of beliefs stored
sensor = Sensor.query.filter_by(name="epex_da").one_or_none()
bdf = sensor.search_beliefs(source="ENTSO-E",
most_recent_beliefs_only=False)
num_beliefs_before = len(bdf)
# See what happens when storing a belief with more certainty one hour later
old_belief = bdf.loc[(bdf.index.get_level_values("event_start") ==
pd.Timestamp("2021-03-28 16:00:00+00:00"))
& (bdf.index.get_level_values("belief_time") ==
pd.Timestamp("2021-03-27 9:00:00+00:00"))]
new_belief = tb_utils.replace_multi_index_level(old_belief,
"cumulative_probability",
pd.Index([0.3, 0.5]))
new_belief = tb_utils.replace_multi_index_level(
new_belief, "belief_time",
new_belief.belief_times + pd.Timedelta("1H"))
save_to_db(new_belief)
# Verify that the whole probabilistic belief was added
bdf = sensor.search_beliefs(source="ENTSO-E",
most_recent_beliefs_only=False)
num_beliefs_after = len(bdf)
assert num_beliefs_after == num_beliefs_before + len(new_belief)
def test_drop_unchanged_beliefs(setup_beliefs):
"""Trying to save beliefs that are already in the database shouldn't raise an error.
Even after updating the belief time, we expect to persist only the older belief time.
"""
# Set a reference for the number of beliefs stored and their belief times
sensor = Sensor.query.filter_by(name="epex_da").one_or_none()
bdf = sensor.search_beliefs(most_recent_beliefs_only=False)
num_beliefs_before = len(bdf)
belief_times_before = bdf.belief_times
# See what happens when storing all existing beliefs verbatim
save_to_db(bdf)
# Verify that no new beliefs were saved
bdf = sensor.search_beliefs(most_recent_beliefs_only=False)
assert len(bdf) == num_beliefs_before
# See what happens when storing all beliefs with their belief time updated
bdf = tb_utils.replace_multi_index_level(
bdf, "belief_time", bdf.belief_times + pd.Timedelta("1H"))
save_to_db(bdf)
# Verify that no new beliefs were saved
bdf = sensor.search_beliefs(most_recent_beliefs_only=False)
assert len(bdf) == num_beliefs_before
assert list(bdf.belief_times) == list(belief_times_before)
def fixed_viewpoint(
self,
belief_time: datetime = None,
belief_time_window: Tuple[Optional[datetime], Optional[datetime]] = (
None,
None,
),
update_belief_times: bool = False,
) -> "BeliefsDataFrame":
"""Select the most recent belief about each event at a given belief time.
NB: with a fixed viewpoint the horizon increases as you look further ahead.
Alternatively, select the most recent belief formed within a certain time window. This allows setting a maximum
freshness of the data.
:Example:
>>> # Select the latest beliefs formed before June 6th 2018 about each event
>>> df.fixed_viewpoint(belief_time=datetime(2018, 6, 6))
>>> # Or equivalently:
>>> df.fixed_viewpoint(belief_time_window=(None, datetime(2018, 6, 6, tzinfo=utc)))
>>> # Select the latest beliefs formed from June 1st to June 6th (up to June 6th 0:00 AM)
>>> df.fixed_viewpoint(belief_time_window=(datetime(2018, 6, 1, tzinfo=utc), datetime(2018, 6, 6, tzinfo=utc)))
:param belief_time: datetime indicating the belief should be formed at least before this time
:param belief_time_window: optional tuple specifying a time window within which beliefs should have been formed
:param update_belief_times: if True, update the belief time of each belief with the given fixed viewpoint
"""
if belief_time is not None:
if belief_time_window != (None, None):
raise ValueError(
"Cannot pass both a belief time and belief time window.")
belief_time_window = (None, belief_time)
df = self
if "belief_time" not in df.index.names:
df = df.convert_index_from_belief_horizon_to_time()
if belief_time_window[0] is not None:
df = df[df.index.get_level_values("belief_time") >=
tb_utils.enforce_utc(belief_time_window[0])]
if belief_time_window[1] is not None:
df = df[df.index.get_level_values("belief_time") <=
tb_utils.enforce_utc(belief_time_window[1])]
df = belief_utils.select_most_recent_belief(df)
if update_belief_times is True:
return tb_utils.replace_multi_index_level(
df,
"belief_time",
pd.DatetimeIndex(data=[belief_time_window[1]] * len(df.index)),
)
else:
return df
def test_replace_index_level_with_intersect(df_4323):
"""Test replacing an index level.
First test deterministic beliefs, then probabilistic beliefs."""
df = df_4323.xs(0.5, level="cumulative_probability", drop_level=False)
df = replace_multi_index_level(
df,
"event_start",
pd.date_range(
start=df.index.get_level_values(0)[0],
periods=1,
freq=df.sensor.event_resolution,
),
intersection=True,
)
assert len(df.index) == 6 # 2 sources each having 3 deterministic beliefs
df = replace_multi_index_level(df, "event_start", pd.Index([]), intersection=True)
assert len(df.index) == 0
# Todo: uncomment below to test probabilistic beliefs
df = df_4323
df = replace_multi_index_level(
df,
"event_start",
pd.date_range(
start=df.index.get_level_values(0)[0],
periods=1,
freq=df.sensor.event_resolution,
),
intersection=True,
)
assert (
len(df.index) == 18
) # 2 sources each having 3 probabilistic beliefs with 3 probabilistic values
df = replace_multi_index_level(df, "event_start", pd.Index([]), intersection=True)
assert len(df.index) == 0
def respect_event_resolution(grouper: DataFrameGroupBy, resolution):
"""Resample to make sure the df slice contains events with the same frequency as the given resolution.
The input BeliefsDataFrame (see below) should represent beliefs about sequential sub-events formed by a single source
at a single unique belief time.
Extra beliefs are added with nan values.
:Example:
>>> df = df.groupby([pd.Grouper(freq="1D", level="event_start"), "belief_time", "source"]).pipe(respect_event_resolution, timedelta(hours=1))
So don't pass a BeliefsDataFrame directly, but pipe it so that we receive a DataFrameGroupBy object, which we can
iterate over to obtain a BeliefsDataFrame slice for a unique belief time, source and (in our example) day of
events. We then make sure an event is stated explicitly for (in our example) each hour.
"""
# We need to loop over each belief time in this slice, and reindex such that each subslice has rows for each event. Then recombine.
# Get a list of n groups, one group for each belief_time with info about how we sliced and the actual slice
groups = list(grouper.__iter__())
# Describe the event_start bin for the slices (we take the first, because the slices share the same event_start bin)
bin_size = grouper.keys[0].freq
bin_start = groups[0][0][0]
bin_end = bin_start + bin_size
# Build up our new BeliefsDataFrame (by copying over and emptying the rows, the metadata should be copied over)
df = groups[0][1].copy().iloc[0:0]
for (group) in (
groups
): # Loop over the groups (we grouped by unique belief time and unique source)
# Get the BeliefsDataFrame for a unique belief time and source
df_slice = group[1]
if not df_slice.empty:
lvl0 = pd.date_range(
start=bin_start,
end=bin_end,
freq=to_offset(resolution).freqstr,
closed="left",
name="event_start",
)
df = df.append(
tb_utils.replace_multi_index_level(df_slice,
level="event_start",
index=lvl0,
intersection=True))
return df
def test_do_not_drop_beliefs_copied_by_another_source(setup_beliefs):
"""Trying to copy beliefs from one source to another should double the number of beliefs."""
# Set a reference for the number of beliefs stored
sensor = Sensor.query.filter_by(name="epex_da").one_or_none()
bdf = sensor.search_beliefs(most_recent_beliefs_only=False)
num_beliefs_before = len(bdf)
# See what happens when storing all belief with their source updated
new_source = DataSource(name="Not Seita", type="demo script")
bdf = tb_utils.replace_multi_index_level(
bdf, "source", pd.Index([new_source] * num_beliefs_before))
save_to_db(bdf)
# Verify that all the new beliefs were added
bdf = sensor.search_beliefs(most_recent_beliefs_only=False)
num_beliefs_after = len(bdf)
assert num_beliefs_after == 2 * num_beliefs_before
def set_truth(
grouped: DataFrameGroupBy,
right_source: "classes.BeliefSource") -> "classes.BeliefsDataFrame":
"""Overwrite the beliefs of each source by those of the given source.
Terminology-wise, we say the given source is considered to be right,
so it's beliefs contain the truth to be used as a reference for accuracy calculations.
"""
# Pick out the group that is considered to contain the true observations
gr_dict = dict(grouped.__iter__())
if right_source in gr_dict:
truth_group = gr_dict[right_source]
else:
raise KeyError("Source %s not found in BeliefsDataFrame." %
right_source)
# Replace each original group with the truth group, while adding back the source for each original group
gr_list = [
tb_utils.replace_multi_index_level(truth_group, "source",
pd.Index([key] * len(truth_group)))
for key, group in grouped
]
return pd.concat(gr_list)
def convert_index_from_event_start_to_end(self) -> "BeliefsDataFrame":
return tb_utils.replace_multi_index_level(self, "event_start",
self.event_ends)
def convert_index_from_belief_horizon_to_time(self) -> "BeliefsDataFrame":
return tb_utils.replace_multi_index_level(self, "belief_horizon",
self.belief_times)