def test_filter_by_call_rate_in_memory(self):
variations = load_zarr(TEST_DATA_DIR / 'test.zarr')
variations = compute({'vars': variations},
store_variation_to_memory=True)['vars']
pipeline_futures = {}
future_result = remove_low_call_rate_vars(variations,
min_call_rate=0.5)
_add_task_to_pipeline(pipeline_futures, future_result)
future_result2 = remove_low_call_rate_vars(future_result[FLT_VARS],
min_call_rate=0.5,
filter_id='call_rate2')
_add_task_to_pipeline(pipeline_futures, future_result2)
processed = pipeline_futures
self.assertEqual(processed[FLT_STATS]['call_rate'][N_KEPT], 5)
self.assertEqual(processed[FLT_STATS]['call_rate'][N_FILTERED_OUT], 2)
self.assertEqual(processed[FLT_STATS]['call_rate2'][N_KEPT], 5)
self.assertEqual(processed[FLT_STATS]['call_rate2'][N_FILTERED_OUT], 0)
gts = processed[FLT_VARS][GT_FIELD]
self.assertEqual(gts.shape, (5, 3, 2))
self.assertTrue(
np.all(processed[FLT_VARS].samples == variations.samples))
self.assertEqual(processed[FLT_VARS].metadata, variations.metadata)
def test_filter_by_call_rate(self):
variations = create_dask_variations()
pipeline_futures = {}
future_result = remove_low_call_rate_vars(variations,
min_call_rate=0.5)
_add_task_to_pipeline(pipeline_futures, future_result)
future_result2 = remove_low_call_rate_vars(future_result[FLT_VARS],
min_call_rate=0.5,
filter_id='call_rate2')
_add_task_to_pipeline(pipeline_futures, future_result2)
processed = compute(pipeline_futures, store_variation_to_memory=True)
self.assertEqual(processed[FLT_STATS]['call_rate'][N_KEPT], 5)
self.assertEqual(processed[FLT_STATS]['call_rate'][N_FILTERED_OUT], 2)
self.assertEqual(processed[FLT_STATS]['call_rate2'][N_KEPT], 5)
self.assertEqual(processed[FLT_STATS]['call_rate2'][N_FILTERED_OUT], 0)
gts = processed[FLT_VARS][GT_FIELD]
self.assertEqual(gts.shape, (5, 3, 2))
self.assertTrue(
np.all(
processed[FLT_VARS].samples == variations.samples.compute()))
self.assertEqual(processed[FLT_VARS].metadata, variations.metadata)
def _test_filter_samples_by_call_rate(self, variations, do_computation):
tasks = {}
task = remove_low_call_rate_samples(variations,
min_call_rate=0.5,
filter_id='call_rate')
_add_task_to_pipeline(tasks, task)
task2 = remove_low_call_rate_samples(task[FLT_VARS],
min_call_rate=0.5,
filter_id='call_rate2')
_add_task_to_pipeline(tasks, task2)
if do_computation:
processed_tasks = compute(tasks, store_variation_to_memory=True)
else:
processed_tasks = tasks
processed = processed_tasks
self.assertEqual(processed[FLT_STATS]['call_rate'][N_SAMPLES_KEPT], 2)
self.assertEqual(
processed[FLT_STATS]['call_rate'][N_SAMPLES_FILTERED_OUT], 1)
self.assertEqual(processed[FLT_STATS]['call_rate2'][N_SAMPLES_KEPT], 2)
self.assertEqual(
processed[FLT_STATS]['call_rate2'][N_SAMPLES_FILTERED_OUT], 0)
gts = processed[FLT_VARS][GT_FIELD]
self.assertEqual(gts.shape, (7, 2, 2))
self.assertTrue(
np.all(processed[FLT_VARS].samples == ['mu16', 'upv196']))
self.assertEqual(processed[FLT_VARS].metadata, variations.metadata)
def test_filter_and_hist_by_call_rate(self):
variations = load_zarr(TEST_DATA_DIR / 'test.zarr')
pipeline_futures = {}
future_result = remove_low_call_rate_vars(variations,
min_call_rate=0.5,
calc_histogram=True)
_add_task_to_pipeline(pipeline_futures, future_result)
processed = compute(pipeline_futures, store_variation_to_memory=True)
self.assertEqual(len(processed[FLT_STATS]['call_rate'][COUNT]),
DEF_NUM_BINS)
self.assertEqual(len(processed[FLT_STATS]['call_rate'][BIN_EDGES]),
DEF_NUM_BINS + 1)
self.assertEqual(processed[FLT_STATS]['call_rate']['limits'], [0.5])
def test_filter_and_hist_by_call_rate_in_memory(self):
variations = create_dask_variations()
variations = compute({'vars': variations},
store_variation_to_memory=True)['vars']
pipeline_futures = {}
future_result = remove_low_call_rate_vars(variations,
min_call_rate=0.5,
calc_histogram=True)
_add_task_to_pipeline(pipeline_futures, future_result)
processed = pipeline_futures
self.assertEqual(len(processed[FLT_STATS]['call_rate'][COUNT]),
DEF_NUM_BINS)
self.assertEqual(len(processed[FLT_STATS]['call_rate'][BIN_EDGES]),
DEF_NUM_BINS + 1)
self.assertEqual(processed[FLT_STATS]['call_rate']['limits'], [0.5])