def test_iterate_segmented_dataset_with_processor(dataset, segmentation):
feature_processor_segment_names = []
def feature_processor(segment_name,
dataset,
column_mapping=None): # rename some columns
feature_processor_segment_names.append(segment_name)
return dataset.rename(columns=column_mapping).assign(weight=1)
iterator = iterate_segmented_dataset(
dataset,
segmentation=segmentation,
feature_processor=feature_processor,
feature_processor_kwargs={"column_mapping": {
"a": "c",
"b": "d"
}},
feature_processor_segment_name_mapping={
"jan": "jan2",
"feb": "feb2"
},
)
segment_name, data = next(iterator)
assert feature_processor_segment_names == ["jan2"]
assert segment_name == "jan"
assert list(data.columns) == ["c", "d", "weight"]
assert data.shape == (1000, 3)
assert data.sum().sum() == 4000.0
segment_name, data = next(iterator)
assert feature_processor_segment_names == ["jan2", "feb2"]
assert segment_name == "feb"
assert list(data.columns) == ["c", "d", "weight"]
assert data.shape == (1000, 3)
assert data.sum().sum() == 4000.0
def test_iterate_segmented_dataset_no_segmentation(dataset):
iterator = iterate_segmented_dataset(dataset, segmentation=None)
segment_name, data = next(iterator)
assert segment_name is None
assert list(data.columns) == ["a", "b", "weight"]
assert data.shape == (1000, 3)
assert data.sum().sum() == 4000
with pytest.raises(StopIteration):
next(iterator)
def create_caltrack_hourly_segmented_design_matrices(preliminary_design_matrix,
segmentation,
occupancy_lookup,
temperature_bins):
return {
segment_name: segmented_data
for segment_name, segmented_data in iterate_segmented_dataset(
preliminary_design_matrix,
segmentation=segmentation,
feature_processor=caltrack_hourly_fit_feature_processor,
feature_processor_kwargs={
"occupancy_lookup": occupancy_lookup,
"temperature_bins": temperature_bins,
},
)
}
def create_caltrack_hourly_segmented_design_matrices(
preliminary_design_matrix,
segmentation,
occupancy_lookup,
occupied_temperature_bins,
unoccupied_temperature_bins,
):
"""A helper function which calls basic feature creation methods to create a
design matrix suitable for use with segmented CalTRACK hourly models.
Parameters
----------
preliminary_design_matrix : :any:`pandas.DataFrame`
A dataframe of the form returned by
:any:`eemeter.create_caltrack_hourly_preliminary_design_matrix`.
segmentation : :any:`pandas.DataFrame`
Weights for each segment. This is a dataframe of the form returned by
:any:`eemeter.segment_time_series` on the `preliminary_design_matrix`.
occupancy_lookup : any:`pandas.DataFrame`
Occupancy for each segment. This is a dataframe of the form returned by
:any:`eemeter.estimate_hour_of_week_occupancy`.
occupied_temperature_bins : :any:``
Occupied temperature bin settings for each segment. This is a dataframe of the
form returned by :any:`eemeter.fit_temperature_bins`.
unoccupied_temperature_bins : :any:``
Ditto, for unoccupied.
Returns
-------
design_matrix : :any:`dict` of :any:`pandas.DataFrame`
A dict of design matrixes created using the
:any:`eemeter.caltrack_hourly_fit_feature_processor`.
"""
return {
segment_name: segmented_data
for segment_name, segmented_data in iterate_segmented_dataset(
preliminary_design_matrix,
segmentation=segmentation,
feature_processor=caltrack_hourly_fit_feature_processor,
feature_processor_kwargs={
"occupancy_lookup": occupancy_lookup,
"occupied_temperature_bins": occupied_temperature_bins,
"unoccupied_temperature_bins": unoccupied_temperature_bins,
},
)
}
def test_iterate_segmented_dataset_with_segmentation(dataset, segmentation):
iterator = iterate_segmented_dataset(dataset, segmentation=segmentation)
segment_name, data = next(iterator)
assert segment_name == "jan"
assert list(data.columns) == ["a", "b", "weight"]
assert data.shape == (744, 3)
assert data.sum().sum() == 2976.0
segment_name, data = next(iterator)
assert segment_name == "feb"
assert list(data.columns) == ["a", "b", "weight"]
assert data.shape == (256, 3)
assert data.sum().sum() == 1024.0
segment_name, data = next(iterator)
assert segment_name == "mar"
assert list(data.columns) == ["a", "b", "weight"]
assert data.shape == (0, 3)
assert data.sum().sum() == 0.0