def _generate_data_set(self, params: DataSetParameters) -> DataSet:
if self._verbose:
print(params)
publishers = []
publisher_size = params.largest_publisher_size
publisher_size_decay_rate = (1 if params.num_publishers == 1 else
params.largest_to_smallest_publisher_ratio
**(1 / float(params.num_publishers - 1)))
for publisher in range(params.num_publishers):
publishers.append(
PublisherData.generate_publisher_data(
params.impression_generator_params.generator(
**{
"n": publisher_size,
"random_generator": self._random_generator,
**params.impression_generator_params.params,
}),
params.pricing_generator_params.generator(
**params.pricing_generator_params.params),
str(publisher + 1),
))
publisher_size = math.floor(publisher_size *
publisher_size_decay_rate)
overlap_params = {**params.overlap_generator_params.params}
if "random_generator" in overlap_params:
overlap_params["random_generator"] = self._random_generator
return params.overlap_generator_params.generator(publishers,
name=str(params),
**overlap_params)
def test_generate_publisher_data(self):
pdf = PublisherData.generate_publisher_data(
HomogeneousImpressionGenerator(3, 5), FixedPriceGenerator(0.01), "test"
)
self.assertEqual(pdf.max_reach, 3)