def test_writeToFile(self):
"""FlowgramCollection.writeToFile should write in correct format"""
a = [
Flowgram('0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0',
Name='a',
header_info={
'Bases': 'TACCCCTTGG',
'Name Length': '14'
}),
Flowgram('1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0',
Name='b',
header_info={
'Bases': 'TTATTTACCG',
'Name Length': '14'
})
]
f = FlowgramCollection(a, header_info={'Flow Chars': 'TACG'})
fn = mktemp(suffix='.sff')
f.writeToFile(fn)
result = open(fn, 'U').read()
self.assertEqual(
result,
"""Common Header:\n Flow Chars:\tTACG\n\n>a\n Name Length:\t14\nBases:\tTACCCCTTGG\nFlowgram:\t0.5\t1.0\t4.0\t0.0\t1.5\t0.0\t0.0\t2.0\n\n>b\n Name Length:\t14\nBases:\tTTATTTACCG\nFlowgram:\t1.5\t1.0\t0.0\t0.0\t2.5\t1.0\t2.0\t1.0\n"""
)
remove(fn)
def test_getFlow(self):
"""FlowgramCollection.getFlow should return specified flow"""
a = [('a','0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0'),
('b','1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0'),
('c','2.5 0.0 4.0 0.0 0.5 1.0 0.0 1.0')]
f = FlowgramCollection(a)
self.assertEqual(f.getFlow('a'), '0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0')
self.assertRaises(KeyError, f.getFlow, 'd')
def test_getFlow(self):
"""FlowgramCollection.getFlow should return specified flow"""
a = [('a','0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0'),
('b','1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0'),
('c','2.5 0.0 4.0 0.0 0.5 1.0 0.0 1.0')]
f = FlowgramCollection(a)
self.assertEqual(f.getFlow('a'), '0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0')
self.assertRaises(KeyError, f.getFlow, 'd')
def test_createCommonHeader(self):
"""create_commor_header should return lines for sff common header"""
a = [Flowgram('0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0', Name='a',
header_info = {'Bases':'TACCCCTTGG','Name Length':'14'}),
Flowgram('1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0', Name = 'b',
header_info = {'Bases':'TTATTTACCG','Name Length':'14'})]
f = FlowgramCollection(a, header_info = {'Flow Chars':'TACG'})
self.assertEqual('\n'.join(f.createCommonHeader()),
"""Common Header:\n Flow Chars:\tTACG""")
def test_createCommonHeader(self):
"""create_commor_header should return lines for sff common header"""
a = [Flowgram('0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0', Name='a',
header_info = {'Bases':'TACCCCTTGG','Name Length':'14'}),
Flowgram('1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0', Name = 'b',
header_info = {'Bases':'TTATTTACCG','Name Length':'14'})]
f = FlowgramCollection(a, header_info = {'Flow Chars':'TACG'})
self.assertEqual('\n'.join(f.createCommonHeader()),
"""Common Header:\n Flow Chars:\tTACG""")
def test_getFlow(self):
"""FlowgramCollection.getFlow should return specified flow"""
a = [
("a", "0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0"),
("b", "1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0"),
("c", "2.5 0.0 4.0 0.0 0.5 1.0 0.0 1.0"),
]
f = FlowgramCollection(a)
self.assertEqual(f.getFlow("a"), "0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0")
self.assertRaises(KeyError, f.getFlow, "d")
def test_writeToFile(self):
"""FlowgramCollection.writeToFile should write in correct format"""
a = [Flowgram('0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0', Name='a',
header_info = {'Bases':'TACCCCTTGG','Name Length':'14'}),
Flowgram('1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0', Name = 'b',
header_info = {'Bases':'TTATTTACCG','Name Length':'14'})]
f = FlowgramCollection(a, header_info = {'Flow Chars':'TACG'})
fn = mktemp(suffix='.sff')
f.writeToFile(fn)
result = open(fn, 'U').read()
self.assertEqual(result, """Common Header:\n Flow Chars:\tTACG\n\n>a\n Name Length:\t14\nBases:\tTACCCCTTGG\nFlowgram:\t0.5\t1.0\t4.0\t0.0\t1.5\t0.0\t0.0\t2.0\n\n>b\n Name Length:\t14\nBases:\tTTATTTACCG\nFlowgram:\t1.5\t1.0\t0.0\t0.0\t2.5\t1.0\t2.0\t1.0\n""")
remove(fn)
def test_average_flowgrams(self):
"""_average_flowgrams computes an averaged flowgram for each cluster."""
fc = FlowgramCollection({'a':'1.0 0.0 0.0 1.0 1.0 1.2 1.2 0.8',
'b':'1.2 1.0 0.0 0.8 1.2 2.4 1.0 0.0'})
#return the centroid unmodified if sample_mapping = 1
actual = list(_average_flowgrams({'a':'b'}, fc, {'a':['a']}))
self.assertEqual(actual , [(fc.getFlow('a'), 'a')])
actual = list(_average_flowgrams({'a':'b'}, fc, {'a':['a','b']}))
self.assertEqual(actual , [(Flowgram(['1.1 0.5 0.0 0.9 1.1 1.8 1.1 0.4']), 'a')])
def test_createCommonHeader(self):
"""create_commor_header should return lines for sff common header"""
a = [
Flowgram(
"0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0", Name="a", header_info={"Bases": "TACCCCTTGG", "Name Length": "14"}
),
Flowgram(
"1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0", Name="b", header_info={"Bases": "TTATTTACCG", "Name Length": "14"}
),
]
f = FlowgramCollection(a, header_info={"Flow Chars": "TACG"})
self.assertEqual("\n".join(f.createCommonHeader()), """Common Header:\n Flow Chars:\tTACG""")
def test_average_flowgrams(self):
"""_average_flowgrams computes an averaged flowgram for each cluster."""
fc = FlowgramCollection({
'a': '1.0 0.0 0.0 1.0 1.0 1.2 1.2 0.8',
'b': '1.2 1.0 0.0 0.8 1.2 2.4 1.0 0.0'
})
#return the centroid unmodified if sample_mapping = 1
actual = list(_average_flowgrams({'a': 'b'}, fc, {'a': ['a']}))
self.assertEqual(actual, [(fc.getFlow('a'), 'a')])
actual = list(_average_flowgrams({'a': 'b'}, fc, {'a': ['a', 'b']}))
self.assertEqual(
actual, [(Flowgram(['1.1 0.5 0.0 0.9 1.1 1.8 1.1 0.4']), 'a')])
def test_len(self):
"""len(FlowgramCollection) returns length of longest sequence"""
a = [('a','0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0'),
('b','1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0'),
('c','2.5 0.0 4.0 0.0 0.5 1.0 0.0 1.0')]
f = FlowgramCollection(a)
self.assertEqual(len(f), 3)
def test_flows_from_flowCollection(self):
"""flows_from_flowCollection should init from existing collection"""
c = FlowgramCollection({'a':'0.0 1.1 3.0 1.0','b':'0.5 1.0 4.0 0.0'})
obs_a, obs_labels, obs_info = flows_from_flowCollection(c)
self.assertEqual(map(str,obs_a), ['0.0\t1.1\t3.0\t1.0',
'0.5\t1.0\t4.0\t0.0'])
self.assertEqual(obs_labels, ['a','b'])
self.assertEqual(obs_info, [None,None])
def test_str(self):
"""FlowgramCollection __str__ should return sff format"""
a = [Flowgram('0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0', Name='a',
header_info = {'Bases':'TACCCCTTGG','Name Length':'14'}),
Flowgram('1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0', Name = 'b',
header_info = {'Bases':'TTATTTACCG','Name Length':'14'})]
f = FlowgramCollection(a, header_info = {'Flow Chars':'TACG'})
self.assertEqual(str(f), """Common Header:\n Flow Chars:\tTACG\n\n>a\n Name Length:\t14\nBases:\tTACCCCTTGG\nFlowgram:\t0.5\t1.0\t4.0\t0.0\t1.5\t0.0\t0.0\t2.0\n\n>b\n Name Length:\t14\nBases:\tTTATTTACCG\nFlowgram:\t1.5\t1.0\t0.0\t0.0\t2.5\t1.0\t2.0\t1.0\n""")
def test_writeToFile(self):
"""FlowgramCollection.writeToFile should write in correct format"""
a = [
Flowgram(
"0.5 1.0 4.0 0.0 1.5 0.0 0.0 2.0", Name="a", header_info={"Bases": "TACCCCTTGG", "Name Length": "14"}
),
Flowgram(
"1.5 1.0 0.0 0.0 2.5 1.0 2.0 1.0", Name="b", header_info={"Bases": "TTATTTACCG", "Name Length": "14"}
),
]
f = FlowgramCollection(a, header_info={"Flow Chars": "TACG"})
fn = mktemp(suffix=".sff")
f.writeToFile(fn)
result = open(fn, "U").read()
self.assertEqual(
result,
"""Common Header:\n Flow Chars:\tTACG\n\n>a\n Name Length:\t14\nBases:\tTACCCCTTGG\nFlowgram:\t0.5\t1.0\t4.0\t0.0\t1.5\t0.0\t0.0\t2.0\n\n>b\n Name Length:\t14\nBases:\tTTATTTACCG\nFlowgram:\t1.5\t1.0\t0.0\t0.0\t2.5\t1.0\t2.0\t1.0\n""",
)
remove(fn)
def test_container(self):
"""FlowgramContainerArray works as expectected"""
fc = FlowgramCollection({'a':'1.0 0.0 0.0 1.0 1.0 1.2 1.2 0.8',
'b':'1.2 1.0 0.0 0.8 1.2 2.4 1.0 0.0'})
f_container = FlowgramContainerArray(header)
for f in fc:
f_container.add(f)
for f_obs, f_exp in zip(f_container,fc):
self.assertEqual(str(f_obs), str(f_exp))
def test_container(self):
"""FlowgramContainerFile works as expected"""
fc = FlowgramCollection({'a':'1.0 0.0 0.0 1.0 1.0 1.2 1.2 0.8',
'b':'1.2 1.0 0.0 0.8 1.2 2.4 1.0 0.0'})
f_container = FlowgramContainerFile(header)
for f in fc:
f_container.add(f)
for f_obs, f_exp in zip(f_container,fc):
self.assertEqual(str(f_obs), str(f_exp))
# adding after iter started raises errror
self.assertRaises(ValueError, f_container.add,f_obs)
def test_prefix_filter_flowgrams(self):
"""prefix_filter_flowgrams maps all flowgrams which are exact prefixe."""
fc = FlowgramCollection({
'a': '1.0 0.0 0.0 1.0 1.0 1.2 1.2 0.8',
'b': '1.2 1.0 0.0 0.8 1.2 2.4 1.0 0.0',
'c': '2.0 0.0 0.0 1.0',
'd': '1.1 0.3 0.0 1.1'
})
expected_squeeze_map = {'a': ['c', 'd'], 'b': []}
expected_map = {'a': ['d'], 'b': [], 'c': []}
obs = prefix_filter_flowgrams(fc)
self.assertEqual(obs, (3, 4, expected_map))
obs = prefix_filter_flowgrams(fc, squeeze=True)
self.assertEqual(obs, (2, 4, expected_squeeze_map))