def test_old_sel_plus_pc(self): #!!! rather a big test case
logging.info("TestSingleSnpSelect old_sel_plus_pc")
from pysnptools.snpreader import Bed
from fastlmm.util import compute_auto_pcs
# define file names
bed_fn = self.pythonpath + "/tests/datasets/synth/all"
cov_fn = "pcs_cov.txt"
# run PCgeno
#TODO: rename to auto_pcs
result = compute_auto_pcs(bed_fn, output_file_name=cov_fn)
logging.info("selected number of PCs: {0}".format(result["vals"].shape[1]))
# import algorithms
from fastlmm.util.run_fastlmmc import runFASTLMM, runLMMSELECT
# set some file paths for fastlmmc
phen_fn = self.pythonpath + "/tests/datasets/synth/pheno_10_causals.txt"
out_dir = self.tempout_dir
fastlmm_path = self.pythonpath + "/external/fastlmmc"
# consists of two fastlmmc calls, one that does feature selection and one that runs GWAS
for suffix,logdelta in [("h2IsHalf",0),("h2Search",None)]:
result_file_name = "sel_plus_pc_old_{0}".format("h2IsHalf" if logdelta is 0 else "h2Search")
runLMMSELECT(bed_fn, phen_fn, out_dir, result_file_name, bfileSim=bed_fn, covar=cov_fn, fastlmm_path=fastlmm_path,autoSelectCriterionMSE=False,excludeByGeneticDistance=1000,optLogdelta=logdelta)
# compare sel_plus_pc_old_h2*.LMMSELECT.out.txt
short = result_file_name+".LMMSELECT.out"
results=pd.read_csv(self.tempout_dir+"/"+short+".txt",delimiter='\s',comment=None,engine='python')
results['PValue']=results.Pvalue #add a new column with different capitalization
self.compare_files(results,short)
def test_old_sel_plus_pc(self): #!!! rather a big test case
logging.info("TestSingleSnpSelect old_sel_plus_pc")
from pysnptools.snpreader import Bed
from fastlmm.util import compute_auto_pcs
# define file names
bed_fn = self.pythonpath + "/tests/datasets/synth/all"
cov_fn = "pcs_cov.txt"
# run PCgeno
#TODO: rename to auto_pcs
result = compute_auto_pcs(bed_fn, output_file_name=cov_fn)
logging.info("selected number of PCs: {0}".format(result["vals"].shape[1]))
# import algorithms
from fastlmm.util.run_fastlmmc import runFASTLMM, runLMMSELECT
# set some file paths for fastlmmc
phen_fn = self.pythonpath + "/tests/datasets/synth/pheno_10_causals.txt"
out_dir = self.tempout_dir
fastlmm_path = self.pythonpath + "/external/fastlmmc"
# consists of two fastlmmc calls, one that does feature selection and one that runs GWAS
for suffix,logdelta in [("h2IsHalf",0),("h2Search",None)]:
result_file_name = "sel_plus_pc_old_{0}".format("h2IsHalf" if logdelta is 0 else "h2Search")
runLMMSELECT(bed_fn, phen_fn, out_dir, result_file_name, bfileSim=bed_fn, covar=cov_fn, fastlmm_path=fastlmm_path,autoSelectCriterionMSE=False,excludeByGeneticDistance=1000,optLogdelta=logdelta)
# compare sel_plus_pc_old_h2*.LMMSELECT.out.txt
short = result_file_name+".LMMSELECT.out"
results=pd.read_csv(self.tempout_dir+"/"+short+".txt",delimiter='\s',comment=None,engine='python')
results['PValue']=results.Pvalue #add a new column with different capitalization
self.compare_files(results,short)
def _sel_plus_pc(self, h2, force_low_rank, force_full_rank, count_A1=None):
do_plot = False
use_cache = False
# define file names
bed_fn = self.pythonpath + "/tests/datasets/synth/all.bed"
phen_fn = self.pythonpath + "/tests/datasets/synth/pheno_10_causals.txt"
pcs_fn = os.path.join(self.tempout_dir, "sel_plus_pc.pcs.txt")
if not (use_cache and os.path.exists(pcs_fn)):
from fastlmm.util import compute_auto_pcs
covar = compute_auto_pcs(bed_fn, count_A1=count_A1)
logging.info("selected number of PCs: {0}".format(
covar["vals"].shape[1]))
Pheno.write(
pcs_fn,
SnpData(iid=covar['iid'],
sid=covar['header'],
val=covar['vals']))
else:
logging.info("Using top pcs's cache")
covar = Pheno(pcs_fn)
mf_name = "lmp" #"lmpl" "local", "coreP", "nodeP", "socketP", "nodeE", "lmp"
runner = mf_to_runner_function(mf_name)(20)
logging.info(
"Working on h2={0},force_low_rank={1},force_full_rank={2}".format(
h2, force_low_rank, force_full_rank))
result_file_name = "sel_plus_pc_{0}".format("h2IsHalf" if h2 ==
.5 else "h2Search")
output_file_name = os.path.join(self.tempout_dir,
result_file_name) + ".txt"
results = single_snp_select(test_snps=bed_fn,
G=bed_fn,
pheno=phen_fn,
k_list=[
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 20,
30, 40, 50, 60, 70, 80, 90, 100, 125,
160, 200, 250, 320, 400, 500, 630, 800,
1000
],
h2=h2,
n_folds=self.pythonpath +
"/tests/datasets/synth/DebugEmitFolds.txt",
covar=covar,
output_file_name=output_file_name,
force_low_rank=force_low_rank,
force_full_rank=force_full_rank,
GB_goal=2,
count_A1=False
#runner = runner
)
logging.info(results.head())
self.compare_files(results, result_file_name)
def _sel_plus_pc(self,h2,force_low_rank,force_full_rank,count_A1=None):
do_plot = False
use_cache = False
# define file names
bed_fn = self.pythonpath + "/tests/datasets/synth/all.bed"
phen_fn = self.pythonpath + "/tests/datasets/synth/pheno_10_causals.txt"
pcs_fn = os.path.join(self.tempout_dir,"sel_plus_pc.pcs.txt")
if not (use_cache and os.path.exists(pcs_fn)):
from fastlmm.util import compute_auto_pcs
covar = compute_auto_pcs(bed_fn,count_A1=count_A1)
logging.info("selected number of PCs: {0}".format(covar["vals"].shape[1]))
Pheno.write(pcs_fn,SnpData(iid=covar['iid'],sid=covar['header'],val=covar['vals']))
else:
logging.info("Using top pcs's cache")
covar=Pheno(pcs_fn)
mf_name = "lmp" #"lmpl" "local", "coreP", "nodeP", "socketP", "nodeE", "lmp"
runner = mf_to_runner_function(mf_name)(20)
logging.info("Working on h2={0},force_low_rank={1},force_full_rank={2}".format(h2,force_low_rank,force_full_rank))
result_file_name = "sel_plus_pc_{0}".format("h2IsHalf" if h2 == .5 else "h2Search")
output_file_name = os.path.join(self.tempout_dir,result_file_name)+".txt"
results = single_snp_select(test_snps=bed_fn, G=bed_fn, pheno=phen_fn,
k_list = [0,1,2,3,4,5,6,7,8,9,10,20,30,40,50,60,70,80,90,100,125,160,200,250,320,400,500,630,800,1000],
h2=h2,
n_folds = self.pythonpath + "/tests/datasets/synth/DebugEmitFolds.txt",
covar=covar,
output_file_name=output_file_name,
force_low_rank=force_low_rank,force_full_rank=force_full_rank,
GB_goal=2,
count_A1=False
#runner = runner
)
logging.info(results.head())
self.compare_files(results,result_file_name)
f.write(' '.join([str(pc) for pc in X_fit[iid_index, :]]))
f.write('\n')
result = {'iid':sp.array(snpreader.iid),'vals':X_fit}
return result
def _snp_fixup(snp_input):
if isinstance(snp_input, str):
return Bed(snp_input)
else:
return snp_input
if __name__ == "__main__":
import doctest
doctest.testmod()
import logging
from pysnptools.snpreader import Bed
from fastlmm.util import compute_auto_pcs
logging.basicConfig(level=logging.INFO)
#file_name = "../../tests/datasets/mouse/alldata"
file_name = "../feature_selection/examples/toydata"
#file_name = r"c:\deldir\N4000S50000c500h0.50s0.00p0.50F0.0050FH0.2000v0.30_3"
result = compute_auto_pcs(file_name)
#print result
print "done"