def test_movie_split(self):
N_RECORDS = 1745161
N_RECORDS_1 = 959539
N_RECORDS_2 = 785622
test_file_1 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2372215/0007/Analysis_Results/m150404_101626_42"
"267_c100807920800000001823174110291514_s1_p0.al"
"l.subreadset.xml")
test_file_2 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2590980/0008/Analysis_Results/m141115_075238_et"
"han_c100699872550000001823139203261572_s1_p0.al"
"l.subreadset.xml")
ds1 = SubreadSet(test_file_1, test_file_2)
# used to get total:
#self.assertEqual(sum(1 for _ in ds1), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
dss = ds1.split_movies(1)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
self.assertFalse(ds1.filters)
dss = ds1.split_movies(12)
self.assertEqual(len(dss), 2)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
self.assertEqual(len(set(dss[0].index.qId)), 1)
self.assertEqual(len(set(dss[-1].index.qId)), 1)
self.assertEqual(
dss[0].qid2mov[list(set(dss[0].index.qId))[0]],
'm150404_101626_42267_c100807920800000001823174110291514_s1_p0')
self.assertEqual(len(dss[0]), N_RECORDS_1)
self.assertEqual(
dss[-1].qid2mov[list(set(dss[-1].index.qId))[0]],
'm141115_075238_ethan_c100699872550000001823139203261572_s1_p0')
self.assertEqual(len(dss[-1]), N_RECORDS_2)
def test_multi_movie_split_zmws_with_existing_movie_filter(self):
# TODO: test with three movies and two chunks
N_RECORDS = 959539
test_file_1 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2372215/0007/Analysis_Results/m150404_101626_42"
"267_c100807920800000001823174110291514_s1_p0.al"
"l.subreadset.xml")
test_file_2 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2590980/0008/Analysis_Results/m141115_075238_et"
"han_c100699872550000001823139203261572_s1_p0.al"
"l.subreadset.xml")
ds1 = SubreadSet(test_file_1, test_file_2)
dss = ds1.split_movies(2)
self.assertEqual(len(dss), 2)
ds1 = dss[0]
# used to get total:
#self.assertEqual(sum(1 for _ in ds1), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
dss = ds1.split(chunks=1, zmws=True)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
dss = ds1.split(chunks=12, zmws=True)
self.assertEqual(len(dss), 12)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
for ds in dss:
self.assertEqual(
ds.zmwRanges[0][0],
'm150404_101626_42267_c100807920800000001823174110291514_s1_p0'
)
def test_multi_movie_split_zmws_with_existing_movie_filter(self):
# TODO: test with three movies and two chunks
N_RECORDS = 959539
test_file_1 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2372215/0007/Analysis_Results/m150404_101626_42"
"267_c100807920800000001823174110291514_s1_p0.al"
"l.subreadset.xml")
test_file_2 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2590980/0008/Analysis_Results/m141115_075238_et"
"han_c100699872550000001823139203261572_s1_p0.al"
"l.subreadset.xml")
ds1 = SubreadSet(test_file_1, test_file_2)
dss = ds1.split_movies(2)
self.assertEqual(len(dss), 2)
ds1 = dss[0]
# used to get total:
#self.assertEqual(sum(1 for _ in ds1), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
dss = ds1.split(chunks=1, zmws=True)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
dss = ds1.split(chunks=12, zmws=True)
self.assertEqual(len(dss), 12)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
for ds in dss:
self.assertEqual(
ds.zmwRanges[0][0],
'm150404_101626_42267_c100807920800000001823174110291514_s1_p0')
def test_movie_split(self):
N_RECORDS = 1745161
N_RECORDS_1 = 959539
N_RECORDS_2 = 785622
test_file_1 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2372215/0007/Analysis_Results/m150404_101626_42"
"267_c100807920800000001823174110291514_s1_p0.al"
"l.subreadset.xml")
test_file_2 = ("/pbi/dept/secondary/siv/testdata/SA3-DS/lambda/"
"2590980/0008/Analysis_Results/m141115_075238_et"
"han_c100699872550000001823139203261572_s1_p0.al"
"l.subreadset.xml")
ds1 = SubreadSet(test_file_1, test_file_2)
# used to get total:
#self.assertEqual(sum(1 for _ in ds1), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
dss = ds1.split_movies(1)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
self.assertFalse(ds1.filters)
dss = ds1.split_movies(12)
self.assertEqual(len(dss), 2)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
self.assertEqual(len(set(dss[0].index.qId)), 1)
self.assertEqual(len(set(dss[-1].index.qId)), 1)
self.assertEqual(
dss[0].qid2mov[list(set(dss[0].index.qId))[0]],
'm150404_101626_42267_c100807920800000001823174110291514_s1_p0')
self.assertEqual(len(dss[0]), N_RECORDS_1)
self.assertEqual(
dss[-1].qid2mov[list(set(dss[-1].index.qId))[0]],
'm141115_075238_ethan_c100699872550000001823139203261572_s1_p0')
self.assertEqual(len(dss[-1]), N_RECORDS_2)
