def funcIDNormPCL(target, source, env, iMaxLines=100000):
strT, astrSs = sfle.ts(target, source)
strS = astrSs[1] if (
len(sfle.readcomment(astrSs[1])) > c_iSkip) else astrSs[0]
iLC = sfle.lc(strS)
return (sfle.ex("Normalizer -t pcl -T medmult < " + strS, strT) if
(iLC < iMaxLines) else sfle.ex("head -n 3 < " + strS, strT))
def funcMergeMap(target, source, env):
strT, astrSs = sfle.ts(target, source)
fileTaxa, fileMerge, fileIDRaw = astrSs[:3]
astrTaxa = sfle.readcomment(fileTaxa)
strMap = arepa.get_mappingfile(astrTaxa[0]) if astrTaxa else ""
return (sfle.ex([fileMerge, fileIDRaw, strMap, strT])
if strMap else sfle.ex(["cp", fileIDRaw, strT]))
def funcRawProcess(target, source, env):
strT, astrSs = sfle.ts(target, source)
strIn, strRData, strExpMetadata, strCondMetadata = astrSs[:4]
iRet = sfle.ex((sfle.cat(strIn), "| R --no-save", "--args", strRData, strT,
c_strPPfun, strExpMetadata, strCondMetadata))
if iRet:
iRet = sfle.ex((sfle.cat(strIn), " | R --no-save --args", c_strFilePCL,
strT, c_strPPfun, strExpMetadata, strCondMetadata))
return iRet
def getGPL(target, source, env):
astrTs, astrSs = ([f.get_abspath() for f in a] for a in (target, source))
strAnnot, strPlatform = astrTs[:2]
strRMeta = astrSs[0]
pid = [row for row in csv.DictReader(open(strRMeta))][0]["platform_id"]
strGPLID = c_strID.split("-")[1] if len(c_strID.split("-")) == 2 else pid
listGPL = [
v.replace(".annot.gz", "") for v in sfle.readcomment(c_fileAnnot)
]
if strGPLID in listGPL:
#Annotation file exist, download
sfle.ex([
"wget",
sfle.d(c_strURLGPL, strGPLID + ".annot.gz"), "-O", strAnnot
])
else:
#Annotation file does not exist, skip download
sfle.ex(["touch", strAnnot])
#Make platform file containing gpl identifier
with open(strPlatform, "w") as outputf:
outputf.write(strGPLID)
def _compileR( target, source, env ): strT, astrSs = sfle.ts( target, source ) sfle.ex( ["chmod", "755", strDirectory] ) sfle.ex( ["R", "CMD", "build", strDirectory] ) with open( strT, "w" ) as outputf: outputf.write( "R package compiled OK")
# Iteratively download temporary xml files
#===========================================================================
def discrete_list(num, increment):
iTries = (num / increment) + 1
return [str(1 + (a * increment)) for a in range(iTries)]
count_list = discrete_list(int(id_count), c_iIncrement)
astrOutput = [
sfle.d(sfle.c_strDirTmp, geo_id + str(i) + c_strSufXML)
for i in range(1,
len(count_list) + 1)
]
query_list = list(
zip(astrOutput, count_list, [query_key] * len(count_list),
[web_env] * len(count_list)))
# Download
for astr in query_list:
strT, strCount, strQuery, strWeb = astr
sfle.ex([
"curl", "-g", "-f", "-z", '"' + strT + '"',
'"' + c_strURLSum % (strCount, strQuery, strWeb) + '"', ">", strT
])
#Save
with open(sfle.d(sfle.c_strDirTmp, geo_id + c_strSufXML), "w") as idXML:
idXML.write("\n".join([open(f).read() for f in zip(*query_list)[0]]))
def funcRawMap(target, source, env):
astrTs, astrSs = ([f.get_abspath() for f in a] for a in (target, source))
strOutputRData = astrTs[0]
strIn, astrCel = astrSs[0], astrSs[1:]
return sfle.ex([sfle.cat(strIn), " | R --no-save --args", strOutputRData] +
astrCel)
def funcIDQUANT(target, source, env):
strT, astrSs = sfle.ts(target, source)
strS = astrSs[0]
iLC = sfle.lc(strS)
return (sfle.ex("echo '-1.5\t-0.5\t0.5\t1.5\t2.5\t3.5\t4.5' >" + strT))
def funcIDDAB(target, source, env):
strT, astrSs = sfle.ts(target, source)
strS = astrSs[0]
iLC = sfle.lc(strS)
return (sfle.ex((sfle.cat(strS), " | Distancer -o", strT)) if
(iLC > 3) else sfle.ex("echo", strT))
def funcIDKNNPCL(target, source, env, iMaxLines=40000):
strT, astrSs = sfle.ts(target, source)
strS = astrSs[0]
iLC = sfle.lc(strS)
return (sfle.ex("KNNImputer < " + strS, strT) if
(iLC < iMaxLines) else sfle.ex("head -n 3 < " + strS, strT))
def _funcDAB(target, source, env):
strT, astrSs = sfle.ts(target, source)
strOut, strMap = astrSs[:2]
return sfle.ex(("Dat2Dab", "-o", strT, "-i",
(strOut if sfle.isempty(strMap) else strMap)))
