def test_map_with_homogenous_and_heterogenous_condition_names(self):
A = [{"name": "gene1", "conditions": [1, 2, 3, 4]}]
B = [{"name": "gene1", "conditions": [7, 8, 9, 0]}]
expn_A = gl.expression(loadable_list=A,
cond_names=["cA", "cB", "cC", "cD"])
expn_B = gl.expression(loadable_list=B,
cond_names=["cA", "cB", "cC",
"cD"]) # same copndition names
m = expn_A.map(genelist=expn_B, key="name")
self.assertEqual(m[0]["name"], "gene1")
self.assertEqual(m[0]["conditions"], [7.0, 8.0, 9.0, 0.0])
self.assertEqual(m.getConditionNames(), ['cA', 'cB', 'cC', 'cD'])
A = [{"name": "gene1", "conditions": [1, 2, 3, 4]}]
C = [{"name": "gene1", "conditions": [7, 8, 9, 0]}]
expn_A = gl.expression(loadable_list=A,
cond_names=["cA", "cB", "cC", "cD"])
expn_C = gl.expression(loadable_list=B,
cond_names=["cE", "cF", "cG",
"cH"]) # now we have differnt names
m = expn_A.map(genelist=expn_C, key="name")
self.assertEqual(m[0]["name"], "gene1")
self.assertEqual(m[0]["conditions"],
[7.0, 8.0, 9.0, 0.0, 1.0, 2.0, 3.0, 4.0])
self.assertEqual(m.getConditionNames(),
['cE', 'cF', 'cG', 'cH', 'cA', 'cB', 'cC', 'cD'])
def test_expression_from_pandas(self):
expn = gl.expression()
expn.from_pandas(self.dfexpn,
condition_names=['expn1', 'expn2', 'expn3'])
self.assertEqual(len(expn), self.dfexpn.shape[0])
self.assertListEqual(list(self.dfexpn['expn1'].values),
list(expn['expn1']))
self.assertListEqual(list(self.dfexpn['expn2'].values),
list(expn['expn2']))
self.assertListEqual(list(self.dfexpn['name'].values),
list(expn['name']))
def test_force_tsvarg(self):
form = dict(tss_loc=1, skiplines=0) # This loads tss_loc as strings
form_delayed = dict(tss_loc=1, skiplines=0) # delayedlists must have skiplines
a = gl.genelist(filename="test_data/mm9_refGene.tsv", force_tsv=True, format=form)
c = gl.delayedlist(filename="test_data/mm9_refGene.tsv", format=form, force_tsv=True)
d = gl.genome(filename="test_data/mm9_refGene.tsv", format=form_delayed, force_tsv=True)
e = gl.expression(filename="test_data/mm9_refGene.tsv", format=form, force_tsv=True, expn="column[5:]") # fake array data # must go last as it modifies format
# Make sure glbase is not just bodging it all in in one key:
self.assertEqual("chr1:134212701-134212701", a[0]["tss_loc"])
self.assertEqual("chr1:134212701-134212701", c[0]["tss_loc"])
self.assertEqual("chr1:134212701-134212701", d[0]["tss_loc"]) # dls should work as __getitem__() will return the zeroth entry.
self.assertEqual("chr1:134212701-134212701", e[0]["tss_loc"])
def setUp(self):
data = [
{
"name": "i1",
"conditions": [1, 2, 3, 4]
},
{
"name": "i2",
"conditions": [1, 1, 2, 1]
},
{
"name": "i3",
"conditions": [4, 3, 2, 1]
},
{
"name": "i4",
"conditions": [1, 2, 3, 1]
},
{
"name": "i5",
"conditions": [2, 1, 5, 1]
},
{
"name": "i6",
"conditions": [3, 3, 3, 1]
},
{
"name": "i7",
"conditions": [4, 2, 3, 1]
},
{
"name": "i8",
"conditions": [2, 1, 5, 1]
},
{
"name": "i9",
"conditions": [3, 2, 3, 1]
},
{
"name": "i10",
"conditions": [4, 3, 3, 1]
},
{
"name": "i11",
"conditions": [1, 1, 5, 1]
},
]
self.expn = gl.expression(loadable_list=data,
cond_names=["a", "b", "c", "d"])
def test_force_tsv_format(self):
form = dict(tss_loc=1, force_tsv=True, chr=1)
form_delayed = dict(tss_loc=1, force_tsv=True, skiplines=0) # delayedlists must have skiplines
a = gl.genelist(filename="test_data/mm9_refGene.tsv", format=form)
c = gl.delayedlist(filename="test_data/mm9_refGene.tsv", format=form_delayed)
d = gl.genome(filename="test_data/mm9_refGene.tsv", format=form)
e = gl.expression(filename="test_data/mm9_refGene.tsv", format=form, expn="column[5:]") # must go last as it modifies format
# Make sure glbase is not just bodging it all in in one key:
self.assertEqual("chr1:134212701-134212701", a[0]["tss_loc"])
self.assertEqual("chr1:134212701-134212701", c[0]["tss_loc"])
self.assertEqual("chr1:134212701-134212701", d[0]["tss_loc"])
self.assertEqual("chr1:134212701-134212701", e[0]["tss_loc"])
def setUp(self):
data = [{
"name": "i1",
"conditions": [1, 2, 3, 4],
"m1": "aaa",
"m2": "bb"
}, {
"name": "i2",
"conditions": [1, 1, 2, 1],
"m1": "zzz",
"m2": "aa"
}, {
"name": "i3",
"conditions": [4, 3, 2, 1],
"m1": "aaa",
"m2": "aa"
}, {
"name": "i4",
"conditions": [1, 2.05, 3, 0.1],
"m1": "zzz",
"m2": "cc"
}]
data_err = [{
"name": "i1",
"conditions": [1, 2, 3, 4],
"err": [1, 2, 3, 4],
"m1": "aaa",
"m2": "bb"
}, {
"name": "i2",
"conditions": [1, 1, 1, 1],
"err": [1, 1, 1, 1],
"m1": "zzz",
"m2": "aa"
}, {
"name": "i3",
"conditions": [4, 3, 2, 1],
"err": [4, 3, 2, 1],
"m1": "aaa",
"m2": "aa"
}, {
"name": "i4",
"conditions": [1, 2.05, 3, 0.1],
"err": [1, 2.05, 3, 0.1],
"m1": "zzz",
"m2": "cc"
}]
data_Z_row = [
{
'name': 0,
'conditions': [1, 2, 3, 4]
},
{
'name': 1,
'conditions': [2, 2, 3, 3]
},
{
'name': 2,
'conditions': [2, 4, 6, 8]
},
{
'name': 3,
'conditions': [10, 8, 6, 4]
},
]
# There is a transpose in this one, so better not to use a x4x4, have an odd matrix.
data_Z = [
{
'name': 0,
'conditions': [1, 2, 3, 4]
},
{
'name': 1,
'conditions': [2, 2, 3, 3]
},
{
'name': 2,
'conditions': [2, 4, 6, 8]
},
{
'name': 3,
'conditions': [10, 8, 6, 4]
},
{
'name': 4,
'conditions': [3, 3, 3, 3]
},
]
self.expn = gl.expression(loadable_list=data,
cond_names=["a", "b", "c", "d"])
self.expn_err = gl.expression(loadable_list=data_err,
cond_names=["a", "b", "c", "d"])
self.expn_Z_row_wise = gl.expression(loadable_list=data_Z_row,
cond_names=["a", "b", "c", "d"])
self.expn_Z_row_all = gl.expression(loadable_list=data_Z_row,
cond_names=["a", "b", "c", "d"])
self.expn_Z_col_wise = gl.expression(loadable_list=data_Z,
cond_names=["a", "b", "c", "d"])
self.expn_Z_col_all = gl.expression(loadable_list=data_Z,
cond_names=["a", "b", "c", "d"])