def __init__(
self,
start: str,
stop: str,
*,
spatial_unit: Optional[LonLatSpatialUnit] = None,
departure_rate: Union[pd.DataFrame, float] = 0.1,
hours: Union[str, Tuple[int, int]] = "all",
method: str = "last",
table: Union[str, List[str]] = "all",
subscriber_identifier: str = "msisdn",
subscriber_subset: Optional[Query] = None,
):
warnings.warn(
"The PopulationWeightedOpportunities model is currently **experimental**. "
+ "Please review Yan X-Y et al. " +
"(http://dx.doi.org/10.1098/rsif.2014.0834) " +
"before using this model in production.")
if isinstance(departure_rate, pd.DataFrame):
# Rename the columns to match what we'll join to
# sort the dataframe so we'll have a consistent md5
self.departure_rate = departure_rate.rename(
columns=lambda x: x if x == "rate" else f"{x}_from").apply(
lambda x: x.sort_values().values)
self.departure_rate = self.departure_rate.reindex(
columns=sorted(self.departure_rate.columns))
elif isinstance(departure_rate, float):
self.departure_rate = departure_rate
else:
raise TypeError(f"{departure_rate} must be a float or dataframe")
self.start = start
self.stop = stop
if spatial_unit is None:
self.spatial_unit = make_spatial_unit("versioned-site")
else:
self.spatial_unit = spatial_unit
self.distance_matrix = DistanceMatrix(spatial_unit=self.spatial_unit,
return_geometry=True)
self.population_object = ModalLocation(*[
daily_location(
d,
spatial_unit=self.spatial_unit,
hours=hours,
method=method,
table=table,
subscriber_identifier=subscriber_identifier,
ignore_nulls=True,
subscriber_subset=subscriber_subset,
) for d in list_of_dates(self.start, self.stop)
]).aggregate()
self.population_buffer_object = _PopulationBuffer(
population_object=self.population_object,
distance_matrix=self.distance_matrix,
)
def __init__(
self,
start,
stop,
statistic="avg",
*,
hours="all",
tables="all",
direction: Union[str, Direction] = Direction.BOTH,
subscriber_subset=None,
exclude_self_calls=True,
):
self.tables = tables
self.start = standardise_date(start)
self.stop = standardise_date(stop)
self.hours = hours
self.direction = Direction(direction)
self.exclude_self_calls = exclude_self_calls
self.statistic = statistic.lower()
if self.statistic not in valid_stats:
raise ValueError(
"{} is not a valid statistic. Use one of {}".format(
self.statistic, valid_stats))
column_list = [
"msisdn", "msisdn_counterpart", "id", "location_id", "outgoing"
]
self.tables = tables
# EventsTablesUnion will only subset on the subscriber identifier,
# which means that we need to query for a unioned table twice. That has
# a considerable negative impact on execution time.
self.unioned_from_query = EventsTablesUnion(
self.start,
self.stop,
columns=column_list,
tables=self.tables,
subscriber_identifier="msisdn",
hours=hours,
subscriber_subset=subscriber_subset,
)
self.unioned_to_query = EventsTablesUnion(
self.start,
self.stop,
columns=column_list,
tables=self.tables,
subscriber_identifier="msisdn_counterpart",
hours=hours,
subscriber_subset=subscriber_subset,
)
self.distance_matrix = DistanceMatrix()
super().__init__()
def distance_matrix(get_dataframe):
""" Calculates the distance matrix between cells. """
return get_dataframe(DistanceMatrix())