def test_two(self):
'''
Lock in results on arbitrary data -- because meaningful runs take too long to run.
'''
fn = "two.txt"
logging.info(fn)
tmpOutfile = self.file_name(fn)
snpreader = self.snpreader_whole[:10, :]
spatial_coor = [[i, -i] for i in xrange(snpreader.iid_count)]
alpha_list = alpha_list_big = [
int(v) for v in np.logspace(2, np.log10(4000), 2)
]
dataframe = heritability_spatial_correction(snpreader,
spatial_coor,
snpreader.iid,
alpha_list,
2,
self.pheno_whole,
jackknife_count=2,
permute_plus_count=1,
permute_times_count=1,
just_testing=False)
dataframe.to_csv(tmpOutfile, sep="\t", index=False)
referenceOutfile = TestFeatureSelection.reference_file(
"heritability_spatial_correction/" + fn)
out, msg = ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(
out,
"msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile,
tmpOutfile))
def blocking_cov_pcs(self,strategy):
currentFolder = os.path.dirname(os.path.realpath(__file__))
cov_fn = currentFolder + "/examples/toydata.cov"
output_dir="tmp"
try:
os.mkdir(output_dir)
except:
pass
output_dir = output_dir + "/feature_selection"
try:
os.mkdir(output_dir)
except:
pass
self.blocking(self.snpreader_bed, cov_fn, num_pcs=3, strategy=strategy, output_prefix=os.path.join(output_dir,strategy))
for outfile in os.listdir(output_dir):
referenceOutfile = TestFeatureSelection.reference_file(outfile)
import fastlmm.util.util as ut
if outfile.lower().endswith(".pdf") or outfile == "output_prefix_report.txt" or outfile.lower().endswith("_k_pcs.txt"):
self.assertTrue(os.path.exists(referenceOutfile))
else:
delimiter = "," if outfile.lower().endswith(".csv") else "\t"
tmpOutfile=os.path.join(output_dir,outfile)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, self.tolerance,delimiter=delimiter)
#if not out:
#import pdb; pdb.set_trace() #This will mess up LocalMultiProc runs
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def runTest(self):
os.chdir( os.path.dirname( os.path.realpath(__file__) ) )
tmpOutfile = self._tmpOutfile()
referenceOutfile = self._referenceOutfile()
with open('inputs/'+self._infile) as f:
filecontent = f.read()
runner = Local()
exec(filecontent)
runner.run(distributable)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def runTest(self):
os.chdir( os.path.dirname( os.path.realpath(__file__) ) )
tmpOutfile = self._tmpOutfile()
referenceOutfile = self._referenceOutfile()
with open('inputs/'+self._infile) as f:
filecontent = f.read()
runner = Local()
exec(filecontent)
runner.run(distributable)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def runTest(self):
os.chdir( os.path.dirname( os.path.realpath(__file__) ) )
tmpOutfile = self._tmpOutfile()
referenceOutfile = self._referenceOutfile()
with open('inputs/'+self._infile) as f:
filecontent = f.read()
runner = Local()
exec(filecontent)
runner.run(distributable)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out,msg)#msg='Files %s and %s are different.' % (tmpOutfile, referenceOutfile))
def test_one(self):
logging.info("TestSnpSet test_one")
fn = "lrt_one_kernel_fixed_mixed_effect_linear_qqfit.N300.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.23.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.txt',
output_file_name = tmpOutfile
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def test_one(self):
logging.info("TestSnpSet test_one")
fn = "lrt_one_kernel_fixed_mixed_effect_linear_qqfit.N300.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.23.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.txt',
output_file_name = tmpOutfile
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def test_two(self):
'''
Lock in results on arbitrary data -- because meaningful runs take too long to run.
'''
fn = "two.txt"
logging.info(fn)
tmpOutfile = self.file_name(fn)
snpreader = self.snpreader_whole[:10,:]
spatial_coor = [[i,-i] for i in xrange(snpreader.iid_count)]
alpha_list = alpha_list_big=[int(v) for v in np.logspace(2,np.log10(4000), 2)]
dataframe = heritability_spatial_correction(snpreader,spatial_coor,snpreader.iid,alpha_list,self.pheno_whole,jackknife_count=2,permute_plus_count=1,permute_times_count=1,just_testing=False)
dataframe.to_csv(tmpOutfile,sep="\t",index=False)
referenceOutfile = TestFeatureSelection.reference_file("heritability_spatial_correction/"+fn)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def test_three(self):
logging.info("TestSnpSet test_three")
fn = "sc_davies_one_kernel_linear_qqfit.N300.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.small.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.txt',
test = "sc_davies",
output_file_name = tmpOutfile
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out,msg)#msg='Files %s and %s are different.' % (tmpOutfile, referenceOutfile))
def test_four(self):
logging.info("TestSnpSet test_four")
fn = "sc_davies_two_kernel_linear_qqfit.N300.noautoselect.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.small.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.randcidorder.txt',
G0 = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.chr22.23.N300.bed',
test = 'sc_davies',
output_file_name = tmpOutfile
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def test_two(self):
logging.info("TestSnpSet test_two")
fn = "lrt_up_two_kernel_mixed_effect_linear_qqfit.N300.fullrank.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.23.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.txt',
G0 = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.chr22.23.N300.bed',
output_file_name = tmpOutfile,
test="lrt"
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out,msg)#msg='Files %s and %s are different.' % (tmpOutfile, referenceOutfile))
def test_four(self):
logging.info("TestSnpSet test_four")
fn = "sc_davies_two_kernel_linear_qqfit.N300.noautoselect.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.small.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.randcidorder.txt',
G0 = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.chr22.23.N300.bed',
test = 'sc_davies',
output_file_name = tmpOutfile
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out, "msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile, tmpOutfile))
def test_two(self):
logging.info("TestSnpSet test_two")
fn = "lrt_up_two_kernel_mixed_effect_linear_qqfit.N300.fullrank.txt"
tmpOutfile = self.file_name(fn)
referenceOutfile = self._referenceOutfile(fn)
result_dataframe = snp_set(
test_snps = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.N300',
set_list = self.currentFolder+'/../../../tests/datasets/set_input.23.txt',
pheno = self.currentFolder+'/../../../tests/datasets/phenSynthFrom22.23.N300.txt',
G0 = self.currentFolder+'/../../../tests/datasets/all_chr.maf0.001.chr22.23.N300.bed',
output_file_name = tmpOutfile,
test="lrt"
)
out,msg=ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(out,msg)#msg='Files %s and %s are different.' % (tmpOutfile, referenceOutfile))
def runTest(self):
os.chdir(os.path.dirname(os.path.realpath(__file__)))
tmpOutfile = self._tmpOutfile()
referenceOutfile = self._referenceOutfile()
with open('inputs/' + self._infile) as f:
filecontent = f.read()
runner = Local()
try:
distributable = eval(filecontent)
except Exception as e:
raise Exception("Can't eval '{0}' because of '{1}'".format(
self._infile, e.message))
runner.run(distributable)
out, msg = ut.compare_files(tmpOutfile, referenceOutfile, tolerance)
self.assertTrue(
out,
"msg='{0}', ref='{1}', tmp='{2}'".format(msg, referenceOutfile,
tmpOutfile))