def test_summarize_lengths(self):
lens = {'a': [1, 2, 3], 'b': [3, 4]}
exp = ({
'a':
stat(min=1,
max=3,
std=.81649658092772603,
mean=2.0,
median=2.0,
n=3,
hist=np.array([1, 0, 0, 0, 0, 1, 0, 0, 0, 1]),
hist_edge=np.array(
[1., 1.2, 1.4, 1.6, 1.8, 2, 2.2, 2.4, 2.6, 2.8, 3.])),
'b':
stat(min=3,
max=4,
std=0.5,
mean=3.5,
median=3.5,
n=2,
hist=np.array([1, 0, 0, 0, 0, 0, 0, 0, 0, 1]),
hist_edge=np.array(
[3., 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 4.]))
},
stat(min=1,
max=4,
mean=2.6,
median=3.0,
std=1.019803902718557,
hist=np.array([1, 0, 0, 1, 0, 0, 2, 0, 0, 1]),
n=5,
hist_edge=np.array(
[1., 1.3, 1.6, 1.9, 2.2, 2.5, 2.8, 3.1, 3.4, 3.7,
4.])))
obs_samp, obs_full = _summarize_lengths(lens)
exp_samp, exp_full = exp
self.assertEqual(len(obs_samp), 2)
for k in obs_samp:
self._stat_equal(obs_samp[k], exp_samp[k])
self._stat_equal(obs_full, exp_full)
def test_construct_datasets(self):
lens = {'a': [1, 2, 3], 'b': [3, 4]}
sample_stats, _ = _summarize_lengths(lens)
_construct_datasets(sample_stats, self.hdf5_file)
self.assertEqual(len(self.hdf5_file.keys()), 2)
self.assertTrue('a' in self.hdf5_file)
self.assertTrue('a/sequence' in self.hdf5_file)
self.assertTrue('a/qual' in self.hdf5_file)
self.assertTrue('a/barcode/corrected' in self.hdf5_file)
self.assertTrue('a/barcode/original' in self.hdf5_file)
self.assertTrue('a/barcode/error' in self.hdf5_file)
self.assertTrue(self.hdf5_file['a'].attrs['n'], 3)
self.assertTrue('b' in self.hdf5_file)
self.assertTrue('b/sequence' in self.hdf5_file)
self.assertTrue('b/qual' in self.hdf5_file)
self.assertTrue('b/barcode/corrected' in self.hdf5_file)
self.assertTrue('b/barcode/original' in self.hdf5_file)
self.assertTrue('b/barcode/error' in self.hdf5_file)
self.assertTrue(self.hdf5_file['b'].attrs['n'], 2)
def test_construct_datasets(self):
lens = {'a': [1, 2, 3], 'b': [3, 4]}
sample_stats, _ = _summarize_lengths(lens)
_construct_datasets(sample_stats, self.hdf5_file)
self.assertEqual(len(self.hdf5_file.keys()), 2)
self.assertTrue('a' in self.hdf5_file)
self.assertTrue('a/sequence' in self.hdf5_file)
self.assertTrue('a/qual' in self.hdf5_file)
self.assertTrue('a/barcode/corrected' in self.hdf5_file)
self.assertTrue('a/barcode/original' in self.hdf5_file)
self.assertTrue('a/barcode/error' in self.hdf5_file)
self.assertTrue(self.hdf5_file['a'].attrs['n'], 3)
self.assertTrue('b' in self.hdf5_file)
self.assertTrue('b/sequence' in self.hdf5_file)
self.assertTrue('b/qual' in self.hdf5_file)
self.assertTrue('b/barcode/corrected' in self.hdf5_file)
self.assertTrue('b/barcode/original' in self.hdf5_file)
self.assertTrue('b/barcode/error' in self.hdf5_file)
self.assertTrue(self.hdf5_file['b'].attrs['n'], 2)
def test_summarize_lengths(self):
lens = {'a': [1, 2, 3], 'b': [3, 4]}
exp = ({'a': stat(min=1, max=3, std=.81649658092772603, mean=2.0,
median=2.0, n=3,
hist=np.array([1, 0, 0, 0, 0, 1, 0, 0, 0, 1]),
hist_edge=np.array([1., 1.2, 1.4, 1.6, 1.8, 2, 2.2,
2.4, 2.6, 2.8, 3.])),
'b': stat(min=3, max=4, std=0.5, mean=3.5, median=3.5, n=2,
hist=np.array([1, 0, 0, 0, 0, 0, 0, 0, 0, 1]),
hist_edge=np.array([3., 3.1, 3.2, 3.3, 3.4, 3.5, 3.6,
3.7, 3.8, 3.9, 4.]))},
stat(min=1, max=4, mean=2.6, median=3.0, std=1.019803902718557,
hist=np.array([1, 0, 0, 1, 0, 0, 2, 0, 0, 1]), n=5,
hist_edge=np.array([1., 1.3, 1.6, 1.9, 2.2, 2.5, 2.8, 3.1,
3.4, 3.7, 4.])))
obs_samp, obs_full = _summarize_lengths(lens)
exp_samp, exp_full = exp
self.assertEqual(len(obs_samp), 2)
for k in obs_samp:
self._stat_equal(obs_samp[k], exp_samp[k])
self._stat_equal(obs_full, exp_full)
