def test_write_hgt_list(self):
me = Analyze()
me.output = self.tmpdir
makedirs(join(me.output, 'hgts'), exist_ok=True)
me.donor_name = False
me.donor_rank = None
me.taxdump = taxdump_from_text(taxdump_proteo)
add_children(me.taxdump)
me.df = pd.DataFrame(
[['S1', 'P1', 0.85, '562', True], ['S1', 'P2', 0.95, '622', True],
['S1', 'P3', 1.05, '0', True], ['S2', 'P4', 0.80, '766', True],
['S2', 'P5', 0.20, '0', False]],
columns=['sample', 'protein', 'silh', 'match', 'hgt'])
# default
me.write_hgt_list('S1')
with open(join(me.output, 'hgts', 'S1.txt'), 'r') as f:
obs = f.read()
exp = ('P1\t0.85\t562\n' 'P2\t0.95\t622\n' 'P3\t1.05\t0\n')
self.assertEqual(obs, exp)
# number format and negative result
me.write_hgt_list('S2')
with open(join(me.output, 'hgts', 'S2.txt'), 'r') as f:
self.assertEqual(f.read(), 'P4\t0.8\t766\n')
# raise to family
me.donor_rank = 'family'
me.write_hgt_list('S1')
with open(join(me.output, 'hgts', 'S1.txt'), 'r') as f:
obs = f.read()
exp = ('P1\t0.85\t543\n' 'P2\t0.95\t543\n' 'P3\t1.05\t0\n')
self.assertEqual(obs, exp)
# report taxon name
me.donor_rank = None
me.donor_name = True
me.write_hgt_list('S1')
with open(join(me.output, 'hgts', 'S1.txt'), 'r') as f:
obs = f.read()
exp = ('P1\t0.85\tEscherichia coli\n'
'P2\t0.95\tShigella dysenteriae\n'
'P3\t1.05\tN/A\n')
self.assertEqual(obs, exp)
rmtree(join(me.output, 'hgts'))
def test_predict_hgt(self):
me = Analyze()
# populate score table
n = 1000
data = {
'sample': ['S1'] * n,
'protein': [f'P{x}' for x in range(n)],
'self':
np.random.choice(self.dist_gamma, n),
'close':
np.concatenate((np.random.choice(self.dist_norm1, int(n / 2)) / 3,
np.random.choice(self.dist_norm2, int(n / 2)))),
'distal':
np.concatenate(
(np.random.choice(self.dist_lognorm, int(n * 3 / 4)),
np.random.choice(self.dist_gamma, int(n / 4)) / 2)),
'match': ['0'] * n
}
me.df = pd.DataFrame(data)
# default setting
me.output = self.tmpdir
me.self_low = False
me.bandwidth = 'auto'
me.bw_steps = 20
me.low_part = 75
me.fixed = 25
me.noise = 50
me.silhouette = 0.5
me.taxdump = {}
me.donor_name = False
me.donor_rank = None
# run prediction
self.assertEqual(me.predict_hgt(), 96)
groups = ['self', 'close', 'distal']
for group in groups[1:]:
fp = join(self.tmpdir, f'{group}.hist.png')
self.assertTrue(isfile(fp))
remove(fp)
fp = join(self.tmpdir, 'scatter.png')
self.assertTrue(isfile(fp))
remove(fp)
fp = join(self.tmpdir, 'hgts')
self.assertTrue(isfile(join(fp, 'S1.txt')))
rmtree(fp)
# constant values
me.df['close'] = 1
me.df.drop('hgt', axis=1, inplace=True)
self.assertEqual(me.predict_hgt(), 0)
self.assertNotIn('hgt', me.df.columns)
remove(join(self.tmpdir, 'close.hist.png'))
