def _initGP(self,colCovarType,rank_r,rank_g,rank_n):
"""
Initializes genetic and noise LIMIX trait covar
Args:
colCovarType_g: genetic trait covariance type
colCovarType_n: noise trait covariance type
rank_r: rank of region trait covar
rank_g: rank of genetic trait covar
rank_n: rank of noise trait covar
"""
if self.P==1:
self.rank_r = 1
self.rank_g = 1
self.rank_n = 1
# ideally should be diag
colCovarType = 'freeform'
elif colCovarType is None:
colCovarType='freeform'
self.rank_r = rank_r
self.rank_g = rank_g
self.rank_n = rank_n
self.colCovarType = colCovarType
self.Cg = self._buildTraitCovar(colCovarType,rank_g)
self.Cn = self._buildTraitCovar(colCovarType,rank_n)
XXnotNone = self.XX is not None
SUnotNone = self.S_XX is not None and self.U_XX is not None
# build mean
if self.bgRE:
self.gp = gp3kronSum(self.mean,self.Cg,self.Cn,XX=self.XX,S_XX=self.S_XX,U_XX=self.U_XX,rank=self.rank_r)
else:
self.gp = gp2kronSumLR(self.Y,self.Cn,F=self.F,rank=self.rank_r)
def fitNull(self,verbose=True,cache=False,out_dir='./cache',fname=None,rewrite=False,seed=None,n_times=10,factr=1e3,init_method=None):
"""
Fit null model
"""
if seed is not None: SP.random.seed(seed)
read_from_file = False
if cache:
assert fname is not None, 'MultiTraitSetTest:: specify fname'
if not os.path.exists(out_dir):
os.makedirs(out_dir)
out_file = os.path.join(out_dir,fname)
read_from_file = os.path.exists(out_file) and not rewrite
RV = {}
if read_from_file:
f = h5py.File(out_file,'r')
for key in f.keys():
RV[key] = f[key][:]
f.close()
self.setNull(RV)
else:
start = TIME.time()
if self.bgRE:
self.gpNull = gp2kronSum(self.mean,self.Cg,self.Cn,XX=self.XX,S_XX=self.S_XX,U_XX=self.U_XX)
else:
self.gpNull = gp2kronSumLR(self.Y,self.Cn,Xr=SP.ones((self.N,1)),F=self.F)
for i in range(n_times):
params0,Ifilter=self._initParams(init_method=init_method)
conv,info = OPT.opt_hyper(self.gpNull,params0,Ifilter=Ifilter,factr=factr)
if conv: break
if not conv: warnings.warn("not converged")
LMLgrad = SP.concatenate([self.gpNull.LMLgrad()[key]**2 for key in self.gpNull.LMLgrad().keys()]).mean()
LML = self.gpNull.LML()
if 'mean' in params0.keys():
RV['params_mean'] = self.gpNull.mean.getParams()
RV['params0_g'] = self.Cg.getParams()
RV['params0_n'] = self.Cn.getParams()
RV['Cg'] = self.Cg.K()
RV['Cn'] = self.Cn.K()
RV['conv'] = SP.array([conv])
RV['time'] = SP.array([TIME.time()-start])
RV['NLL0'] = SP.array([LML])
RV['LMLgrad'] = SP.array([LMLgrad])
RV['nit'] = SP.array([info['nit']])
RV['funcalls'] = SP.array([info['funcalls']])
if self.bgRE:
RV['h2'] = self.gpNull.h2()
RV['h2_ste'] = self.gpNull.h2_ste()
RV['Cg_ste'] = self.gpNull.ste('Cg')
RV['Cn_ste'] = self.gpNull.ste('Cn')
self.null = RV
if cache:
f = h5py.File(out_file,'w')
dumpDictHdf5(RV,f)
f.close()
return RV
def _initGP(self, colCovarType, rank_r, rank_g, rank_n):
"""
Initializes genetic and noise LIMIX trait covar
Args:
colCovarType_g: genetic trait covariance type
colCovarType_n: noise trait covariance type
rank_r: rank of region trait covar
rank_g: rank of genetic trait covar
rank_n: rank of noise trait covar
"""
if self.P == 1:
self.rank_r = 1
self.rank_g = 1
self.rank_n = 1
# ideally should be diag
colCovarType = 'freeform'
elif colCovarType is None:
colCovarType = 'freeform'
self.rank_r = rank_r
self.rank_g = rank_g
self.rank_n = rank_n
self.colCovarType = colCovarType
self.Cg = self._buildTraitCovar(colCovarType, rank_g)
self.Cn = self._buildTraitCovar(colCovarType, rank_n)
XXnotNone = self.XX is not None
SUnotNone = self.S_XX is not None and self.U_XX is not None
# build mean
if self.bgRE:
self.gp = gp3kronSum(self.mean,
self.Cg,
self.Cn,
XX=self.XX,
S_XX=self.S_XX,
U_XX=self.U_XX,
rank=self.rank_r)
else:
self.gp = gp2kronSumLR(self.Y, self.Cn, F=self.F, rank=self.rank_r)
def fitNull(self,
verbose=True,
cache=False,
out_dir='./cache',
fname=None,
rewrite=False,
seed=None,
n_times=10,
factr=1e3,
init_method=None):
"""
Fit null model
"""
if seed is not None: SP.random.seed(seed)
read_from_file = False
if cache:
assert fname is not None, 'MultiTraitSetTest:: specify fname'
if not os.path.exists(out_dir):
os.makedirs(out_dir)
out_file = os.path.join(out_dir, fname)
read_from_file = os.path.exists(out_file) and not rewrite
RV = {}
if read_from_file:
f = h5py.File(out_file, 'r')
for key in f.keys():
RV[key] = f[key][:]
f.close()
self.setNull(RV)
else:
start = TIME.time()
if self.bgRE:
self.gpNull = gp2kronSum(self.mean,
self.Cg,
self.Cn,
XX=self.XX,
S_XX=self.S_XX,
U_XX=self.U_XX)
else:
self.gpNull = gp2kronSumLR(self.Y,
self.Cn,
Xr=SP.ones((self.N, 1)),
F=self.F)
for i in range(n_times):
params0, Ifilter = self._initParams(init_method=init_method)
conv, info = OPT.opt_hyper(self.gpNull,
params0,
Ifilter=Ifilter,
factr=factr)
if conv: break
if not conv: warnings.warn("not converged")
LMLgrad = SP.concatenate([
self.gpNull.LMLgrad()[key]**2
for key in self.gpNull.LMLgrad().keys()
]).mean()
LML = self.gpNull.LML()
if 'mean' in params0.keys():
RV['params_mean'] = self.gpNull.mean.getParams()
RV['params0_g'] = self.Cg.getParams()
RV['params0_n'] = self.Cn.getParams()
RV['Cg'] = self.Cg.K()
RV['Cn'] = self.Cn.K()
RV['conv'] = SP.array([conv])
RV['time'] = SP.array([TIME.time() - start])
RV['NLL0'] = SP.array([LML])
RV['LMLgrad'] = SP.array([LMLgrad])
RV['nit'] = SP.array([info['nit']])
RV['funcalls'] = SP.array([info['funcalls']])
if self.bgRE:
RV['h2'] = self.gpNull.h2()
RV['h2_ste'] = self.gpNull.h2_ste()
RV['Cg_ste'] = self.gpNull.ste('Cg')
RV['Cn_ste'] = self.gpNull.ste('Cn')
self.null = RV
if cache:
f = h5py.File(out_file, 'w')
dumpDictHdf5(RV, f)
f.close()
return RV