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 test_match_cpp(self):
'''
match
FaSTLMM.207\Data\DemoData>..\.cd.\bin\windows\cpp_mkl\fastlmmc -bfile snps -extract topsnps.txt -bfileSim snps -extractSim ASout.snps.txt -pheno pheno.txt -covar covariate.txt -out topsnps.singlesnp.txt -logDelta 0 -verbose 100
'''
logging.info("TestSingleSnp test_match_cpp")
snps = Bed(os.path.join(self.pythonpath, "tests/datasets/selecttest/snps"), count_A1=False)
pheno = os.path.join(self.pythonpath, "tests/datasets/selecttest/pheno.txt")
covar = os.path.join(self.pythonpath, "tests/datasets/selecttest/covariate.txt")
sim_sid = ["snp26250_m0_.19m1_.19","snp82500_m0_.28m1_.28","snp63751_m0_.23m1_.23","snp48753_m0_.4m1_.4","snp45001_m0_.26m1_.26","snp52500_m0_.05m1_.05","snp75002_m0_.39m1_.39","snp41253_m0_.07m1_.07","snp11253_m0_.2m1_.2","snp86250_m0_.33m1_.33","snp3753_m0_.23m1_.23","snp75003_m0_.32m1_.32","snp30002_m0_.25m1_.25","snp26252_m0_.19m1_.19","snp67501_m0_.15m1_.15","snp63750_m0_.28m1_.28","snp30001_m0_.28m1_.28","snp52502_m0_.35m1_.35","snp33752_m0_.31m1_.31","snp37503_m0_.37m1_.37","snp15002_m0_.11m1_.11","snp3751_m0_.34m1_.34","snp7502_m0_.18m1_.18","snp52503_m0_.3m1_.3","snp30000_m0_.39m1_.39","isnp4457_m0_.11m1_.11","isnp23145_m0_.2m1_.2","snp60001_m0_.39m1_.39","snp33753_m0_.16m1_.16","isnp60813_m0_.2m1_.2","snp82502_m0_.34m1_.34","snp11252_m0_.13m1_.13"]
sim_idx = snps.sid_to_index(sim_sid)
test_sid = ["snp26250_m0_.19m1_.19","snp63751_m0_.23m1_.23","snp82500_m0_.28m1_.28","snp48753_m0_.4m1_.4","snp45001_m0_.26m1_.26","snp52500_m0_.05m1_.05","snp75002_m0_.39m1_.39","snp41253_m0_.07m1_.07","snp86250_m0_.33m1_.33","snp15002_m0_.11m1_.11","snp33752_m0_.31m1_.31","snp26252_m0_.19m1_.19","snp30001_m0_.28m1_.28","snp11253_m0_.2m1_.2","snp67501_m0_.15m1_.15","snp3753_m0_.23m1_.23","snp52502_m0_.35m1_.35","snp30000_m0_.39m1_.39","snp30002_m0_.25m1_.25"]
test_idx = snps.sid_to_index(test_sid)
for G0,G1 in [(snps[:,sim_idx],KernelIdentity(snps.iid)),(KernelIdentity(snps.iid),snps[:,sim_idx])]:
frame_h2 = single_snp(test_snps=snps[:,test_idx], pheno=pheno, G0=G0,G1=G1, covar=covar,h2=.5,leave_out_one_chrom=False,count_A1=False)
frame_log_delta = single_snp(test_snps=snps[:,test_idx], pheno=pheno, G0=G0,G1=G1, covar=covar,log_delta=0,leave_out_one_chrom=False,count_A1=False)
for frame in [frame_h2, frame_log_delta]:
referenceOutfile = TestFeatureSelection.reference_file("single_snp/topsnps.single.txt")
reference = pd.read_table(referenceOutfile,sep="\t") # We've manually remove all comments and blank lines from this file
assert len(frame) == len(reference)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
reldiff = abs(row.Pvalue - pvalue)/row.Pvalue
assert reldiff < .035, "'{0}' pvalue_list differ too much {4} -- {2} vs {3}".format(sid,None,row.Pvalue,pvalue,reldiff)
def compare_files(self, sid0_list, sid1_list, pvalue_list, ref_base):
reffile = TestFeatureSelection.reference_file("epistasis/" + ref_base +
".txt")
pair_to_pvalue = {}
for index, sid0 in enumerate(sid0_list):
sid1 = sid1_list[index]
if sid0 < sid1:
key = (sid0, sid1)
else:
key = (sid1, sid0)
pair_to_pvalue[key] = pvalue_list[index]
reference = sp.loadtxt(reffile, dtype='str', comments=None, skiprows=1)
assert len(pvalue_list) == len(
reference), "# of pairs differs from file '{0}'".format(reffile)
for row in reference:
sid0 = row[0]
sid1 = row[4]
if sid0 < sid1:
key = (sid0, sid1)
else:
key = (sid1, sid0)
assert abs(
float(row[8]) - pair_to_pvalue[key]
) < 1e-5, "pair {0} differs too much from file '{1}'".format(
key, reffile)
def compare_files(self, frame, ref_base):
reffile = TestFeatureSelection.reference_file("single_snp/" +
ref_base + ".txt")
#sid_list,pvalue_list = frame['SNP'].values,frame['Pvalue'].values
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference = pd.read_csv(reffile,
delimiter='\s',
comment=None,
engine='python')
assert len(frame) == len(
reference), "# of pairs differs from file '{0}'".format(reffile)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
diff = abs(row.PValue - pvalue)
if diff > 1e-5 or np.isnan(diff):
raise Exception(
"pair {0} differs too much from file '{1}'".format(
sid, reffile))
assert abs(row.PValue - pvalue) < 1e-5, "wrong"
def compare_files(self, frame, ref_base):
reffile = TestFeatureSelection.reference_file("single_snp_select/" +
ref_base + ".txt")
#sid_list,pvalue_list = frame['SNP'].values,frame['Pvalue'].values
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference = pd.read_csv(reffile,
delimiter='\s',
comment=None,
engine='python')
if 'Pvalue' in reference.columns:
reference[
'PValue'] = reference.Pvalue #add a new column with different capitalization if it is there
assert len(frame) == len(
reference), "# of pairs differs from file '{0}'".format(reffile)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
assert abs(
row.PValue - pvalue
) < 1e-5, "pair {0} differs too much from file '{1}'".format(
sid, reffile)
def compare_files(self,answer,ref_base):
reffile = TestFeatureSelection.reference_file("fastlmm/"+ref_base+".dat") #Uses same results folder as lmm_train
reference=Dat(reffile).read()
assert np.array_equal(answer.col,reference.col), "sid differs. File '{0}'".format(reffile)
assert np.array_equal(answer.row,reference.row), "iid differs. File '{0}'".format(reffile)
for iid_index in range(reference.row_count):
for sid_index in range(reference.col_count):
a_v = answer.val[iid_index,sid_index]
r_v = reference.val[iid_index,sid_index]
assert abs(a_v - r_v) < 1e-4, "Value at {0},{1} differs too much from file '{2}'".format(iid_index,sid_index,reffile)
def compare_files(self,answer,ref_base):
reffile = TestFeatureSelection.reference_file("fastlmm/"+ref_base+".dat") #Uses same results folder as lmm_train
reference=Dat(reffile).read()
assert np.array_equal(answer.col,reference.col), "sid differs. File '{0}'".format(reffile)
assert np.array_equal(answer.row,reference.row), "iid differs. File '{0}'".format(reffile)
for iid_index in xrange(reference.row_count):
for sid_index in xrange(reference.col_count):
a_v = answer.val[iid_index,sid_index]
r_v = reference.val[iid_index,sid_index]
assert abs(a_v - r_v) < 1e-4, "Value at {0},{1} differs too much from file '{2}'".format(iid_index,sid_index,reffile)
def compare_files(self,frame,ref_base):
reffile = TestFeatureSelection.reference_file("single_snp/"+ref_base+".txt")
#sid_list,pvalue_list = frame['SNP'].values,frame['Pvalue'].values
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference=pd.read_csv(reffile,delimiter='\s',comment=None,engine='python')
assert len(frame) == len(reference), "# of pairs differs from file '{0}'".format(reffile)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
assert abs(row.PValue - pvalue) < 1e-5, "pair {0} differs too much from file '{1}'".format(sid,reffile)
def compare_files(self,frame,ref_base):
reffile = TestFeatureSelection.reference_file("single_snp/"+ref_base+".txt") #Results are in single_snp, not single_snp_lin_reg
#sid_list,pvalue_list = frame['SNP'].as_matrix(),frame['Pvalue'].as_matrix()
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference=pd.read_csv(reffile,delimiter='\s',comment=None,engine='python')
assert len(frame) == len(reference), "# of pairs differs from file '{0}'".format(reffile)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
assert abs(row.PValue - pvalue) < 1e-5, "pair {0} differs too much from file '{1}'".format(sid,reffile)
def compare_files(self,frame,ref_base):
reffile = TestFeatureSelection.reference_file("single_snp/"+ref_base+".txt")
#sid_list,pvalue_list = frame['SNP'].values,frame['Pvalue'].values
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference=pd.read_csv(reffile,delimiter='\s',comment=None,engine='python')
assert len(frame) == len(reference), "# of pairs differs from file '{0}'".format(reffile)
frame.set_index('SNP',inplace=True)
reference.set_index('SNP',inplace=True)
diff = (frame.PValue-reference.PValue)
bad = diff[np.abs(diff)>1e-5]
if len(bad) > 0:
raise Exception("snps differ too much from file '{0}' at these snps {1}".format(reffile,bad))
def compare_files(self,frame,ref_base):
reffile = TestFeatureSelection.reference_file("single_snp_all_plus_select/"+ref_base+".txt")
#sid_list,pvalue_list = frame['SNP'].as_matrix(),frame['Pvalue'].as_matrix()
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference=pd.read_csv(reffile,delimiter='\s',comment=None,engine='python')
if 'Pvalue' in reference.columns: reference['PValue']=reference.Pvalue #add a new column with different capitalization if it is there
assert len(frame) == len(reference), "# of pairs differs from file '{0}'".format(reffile)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
assert abs(row.PValue - pvalue) < 1e-5, "pair {0} differs too much from file '{1}'".format(sid,reffile)
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 compare_files(self,sid0_list,sid1_list,pvalue_list,ref_base):
reffile = TestFeatureSelection.reference_file("epistasis/"+ref_base+".txt")
pair_to_pvalue = {}
for index, sid0 in enumerate(sid0_list):
sid1 = sid1_list[index]
if sid0 < sid1:
key = (sid0, sid1)
else:
key = (sid1, sid0)
pair_to_pvalue[key] = pvalue_list[index]
reference=sp.loadtxt(reffile,dtype='str',comments=None,skiprows=1)
assert len(pvalue_list) == len(reference), "# of pairs differs from file '{0}'".format(reffile)
for row in reference:
sid0 = row[0]
sid1 = row[4]
if sid0 < sid1:
key = (sid0, sid1)
else:
key = (sid1, sid0)
assert abs(float(row[8])-pair_to_pvalue[key]) < 1e-5, "pair {0} differs too much from file '{1}'".format(key,reffile)
def test_match_cpp(self):
'''
match
FaSTLMM.207\Data\DemoData>fastlmmc -snpPairs -bfile snps -extract topsnps.txt -bfileSim snps -extractSim ASout.snps.txt -pheno pheno.txt -covar covariate.txt -out topsnps.pairs.txt -logDelta 0 -verbose 100
'''
logging.info("TestEpistasis test_match_cpp")
from pysnptools.snpreader import Bed
snps = Bed(os.path.join(self.pythonpath, "tests/datasets/selecttest/snps"))
pheno = os.path.join(self.pythonpath, "tests/datasets/selecttest/pheno.txt")
covar = os.path.join(self.pythonpath, "tests/datasets/selecttest/covariate.txt")
sim_sid = ["snp26250_m0_.19m1_.19","snp82500_m0_.28m1_.28","snp63751_m0_.23m1_.23","snp48753_m0_.4m1_.4","snp45001_m0_.26m1_.26","snp52500_m0_.05m1_.05","snp75002_m0_.39m1_.39","snp41253_m0_.07m1_.07","snp11253_m0_.2m1_.2","snp86250_m0_.33m1_.33","snp3753_m0_.23m1_.23","snp75003_m0_.32m1_.32","snp30002_m0_.25m1_.25","snp26252_m0_.19m1_.19","snp67501_m0_.15m1_.15","snp63750_m0_.28m1_.28","snp30001_m0_.28m1_.28","snp52502_m0_.35m1_.35","snp33752_m0_.31m1_.31","snp37503_m0_.37m1_.37","snp15002_m0_.11m1_.11","snp3751_m0_.34m1_.34","snp7502_m0_.18m1_.18","snp52503_m0_.3m1_.3","snp30000_m0_.39m1_.39","isnp4457_m0_.11m1_.11","isnp23145_m0_.2m1_.2","snp60001_m0_.39m1_.39","snp33753_m0_.16m1_.16","isnp60813_m0_.2m1_.2","snp82502_m0_.34m1_.34","snp11252_m0_.13m1_.13"]
sim_idx = snps.sid_to_index(sim_sid)
test_sid = ["snp26250_m0_.19m1_.19","snp63751_m0_.23m1_.23","snp82500_m0_.28m1_.28","snp48753_m0_.4m1_.4","snp45001_m0_.26m1_.26","snp52500_m0_.05m1_.05","snp75002_m0_.39m1_.39","snp41253_m0_.07m1_.07","snp86250_m0_.33m1_.33","snp15002_m0_.11m1_.11","snp33752_m0_.31m1_.31","snp26252_m0_.19m1_.19","snp30001_m0_.28m1_.28","snp11253_m0_.2m1_.2","snp67501_m0_.15m1_.15","snp3753_m0_.23m1_.23","snp52502_m0_.35m1_.35","snp30000_m0_.39m1_.39","snp30002_m0_.25m1_.25"]
test_idx = snps.sid_to_index(test_sid)
frame = epistasis(snps[:,test_idx], pheno,covar=covar, G0 = snps[:,sim_idx],log_delta=0)
sid0,sid1,pvalue_list =np.array(frame['SNP0']),np.array(frame['SNP1']),np.array(frame['PValue'])
referenceOutfile = TestFeatureSelection.reference_file("epistasis/topsnps.pairs.txt")
import pandas as pd
table = pd.read_table(referenceOutfile,sep="\t") # We've manually remove all comments and blank lines from this file
assert len(pvalue_list) == len(table)
for row in table.iterrows():
snp0cpp,snp1cpp,pvaluecpp,i1,i2 = row[1]
for i in xrange(len(pvalue_list)):
found = False
pvaluepy = pvalue_list[i]
snp0py = sid0[i]
snp1py = sid1[i]
if (snp0py == snp0cpp and snp1py == snp1cpp) or (snp0py == snp1cpp and snp1py == snp0cpp):
found = True
diff = abs(pvaluecpp - pvaluepy)/pvaluecpp
assert diff < .035, "'{0}' '{1}' pvalue_list differ too much {4} -- {2} vs {3}".format(snp0cpp,snp1cpp,pvaluecpp,pvaluepy,diff)
break
assert found
def compare_files(self, frame, ref_base):
reffile = TestFeatureSelection.reference_file("single_snp/" +
ref_base + ".txt")
#sid_list,pvalue_list = frame['SNP'].as_matrix(),frame['Pvalue'].as_matrix()
#sid_to_pvalue = {}
#for index, sid in enumerate(sid_list):
# sid_to_pvalue[sid] = pvalue_list[index]
reference = pd.read_csv(reffile,
delimiter='\s',
comment=None,
engine='python')
assert len(frame) == len(
reference), "# of pairs differs from file '{0}'".format(reffile)
frame.set_index('SNP', inplace=True)
reference.set_index('SNP', inplace=True)
diff = (frame.PValue - reference.PValue)
bad = diff[np.abs(diff) > 1e-5]
if len(bad) > 0:
raise Exception(
"snps differ too much from file '{0}' at these snps {1}".
format(reffile, bad))
def test_match_cpp(self):
'''
match
FaSTLMM.207\Data\DemoData>..\.cd.\bin\windows\cpp_mkl\fastlmmc -bfile snps -extract topsnps.txt -bfileSim snps -extractSim ASout.snps.txt -pheno pheno.txt -covar covariate.txt -out topsnps.singlesnp.txt -logDelta 0 -verbose 100
'''
logging.info("TestSingleSnp test_match_cpp")
snps = Bed(
os.path.join(self.pythonpath, "tests/datasets/selecttest/snps"))
pheno = os.path.join(self.pythonpath,
"tests/datasets/selecttest/pheno.txt")
covar = os.path.join(self.pythonpath,
"tests/datasets/selecttest/covariate.txt")
sim_sid = [
"snp26250_m0_.19m1_.19", "snp82500_m0_.28m1_.28",
"snp63751_m0_.23m1_.23", "snp48753_m0_.4m1_.4",
"snp45001_m0_.26m1_.26", "snp52500_m0_.05m1_.05",
"snp75002_m0_.39m1_.39", "snp41253_m0_.07m1_.07",
"snp11253_m0_.2m1_.2", "snp86250_m0_.33m1_.33",
"snp3753_m0_.23m1_.23", "snp75003_m0_.32m1_.32",
"snp30002_m0_.25m1_.25", "snp26252_m0_.19m1_.19",
"snp67501_m0_.15m1_.15", "snp63750_m0_.28m1_.28",
"snp30001_m0_.28m1_.28", "snp52502_m0_.35m1_.35",
"snp33752_m0_.31m1_.31", "snp37503_m0_.37m1_.37",
"snp15002_m0_.11m1_.11", "snp3751_m0_.34m1_.34",
"snp7502_m0_.18m1_.18", "snp52503_m0_.3m1_.3",
"snp30000_m0_.39m1_.39", "isnp4457_m0_.11m1_.11",
"isnp23145_m0_.2m1_.2", "snp60001_m0_.39m1_.39",
"snp33753_m0_.16m1_.16", "isnp60813_m0_.2m1_.2",
"snp82502_m0_.34m1_.34", "snp11252_m0_.13m1_.13"
]
sim_idx = snps.sid_to_index(sim_sid)
test_sid = [
"snp26250_m0_.19m1_.19", "snp63751_m0_.23m1_.23",
"snp82500_m0_.28m1_.28", "snp48753_m0_.4m1_.4",
"snp45001_m0_.26m1_.26", "snp52500_m0_.05m1_.05",
"snp75002_m0_.39m1_.39", "snp41253_m0_.07m1_.07",
"snp86250_m0_.33m1_.33", "snp15002_m0_.11m1_.11",
"snp33752_m0_.31m1_.31", "snp26252_m0_.19m1_.19",
"snp30001_m0_.28m1_.28", "snp11253_m0_.2m1_.2",
"snp67501_m0_.15m1_.15", "snp3753_m0_.23m1_.23",
"snp52502_m0_.35m1_.35", "snp30000_m0_.39m1_.39",
"snp30002_m0_.25m1_.25"
]
test_idx = snps.sid_to_index(test_sid)
for G0, G1 in [(snps[:, sim_idx], KernelIdentity(snps.iid)),
(KernelIdentity(snps.iid), snps[:, sim_idx])]:
frame_h2 = single_snp(test_snps=snps[:, test_idx],
pheno=pheno,
G0=G0,
G1=G1,
covar=covar,
h2=.5,
leave_out_one_chrom=False)
frame_log_delta = single_snp(test_snps=snps[:, test_idx],
pheno=pheno,
G0=G0,
G1=G1,
covar=covar,
log_delta=0,
leave_out_one_chrom=False)
for frame in [frame_h2, frame_log_delta]:
referenceOutfile = TestFeatureSelection.reference_file(
"single_snp/topsnps.single.txt")
reference = pd.read_table(
referenceOutfile, sep="\t"
) # We've manually remove all comments and blank lines from this file
assert len(frame) == len(reference)
for _, row in reference.iterrows():
sid = row.SNP
pvalue = frame[frame['SNP'] == sid].iloc[0].PValue
reldiff = abs(row.Pvalue - pvalue) / row.Pvalue
assert reldiff < .035, "'{0}' pvalue_list differ too much {4} -- {2} vs {3}".format(
sid, None, row.Pvalue, pvalue, reldiff)
