def work_sequence(self):
# is it OK to do the intersect and the linear regression 23 extra times?
# clear
G, y, snp_name, _ = load_intersect(self.snp_reader, self.pheno_fn)
# compute linear regression
_, p_values_lin = f_regression(G, y, center=True)
# set up empty return structures
#self.rs = snp_name
#self.p_values = -np.ones(len(snp_name))
# get chr names/id
chr_ids = self.snp_reader.pos[:,0]
#self.pos = self.snp_reader.pos
#loco = [[range(0,5000), range(5000,10000)]]
loco = LeaveOneChromosomeOut(chr_ids, indices=True)
if len(loco) is not self.chrom_count : raise Exception("The snp reader has {0} chromosome, not {1} as specified".format(len(loco),self.chrom_count))
for i, (train_snp_idx, test_snp_idx) in enumerate(loco):
if i == 0:
result = {"p_values":-np.ones(len(snp_name)),
"p_values_lin": p_values_lin,
"rs":snp_name,
"pos":self.snp_reader.pos}
else:
result = None
yield lambda i=i, train_snp_idx=train_snp_idx,test_snp_idx=test_snp_idx,result=result,G=G,y=y: self.dowork(i,train_snp_idx,test_snp_idx,result,G,y) # the 'i=i',etc is need to get around a strangeness in Python
def test_loco(self):
"""
test leave one chromosome out iterator
"""
names = ["a", "b", "a", "c", "b", "c", "b"]
loco = LeaveOneChromosomeOut(names)
expect = [[[1, 3, 4, 5, 6], [0, 2]], [[0, 2, 3, 5], [1, 4, 6]],
[[0, 1, 2, 4, 6], [3, 5]]]
for i, (train_idx, test_idx) in enumerate(loco):
assert (expect[i][0] == train_idx).all()
assert (expect[i][1] == test_idx).all()