def preProcessLandscapeV2(pathMean,
pathTraces,
expName,
drive,
prePath='./',
nodesAggLst=[[0]],
analysisOI='HLT',
fNameFmt='{}/{}-{}_',
MF=(True, True),
cmpr='bz2',
nodeDigits=4,
SUM=True,
AGG=True,
SPA=True,
REP=True,
SRP=True,
sexFilenameID={
"male": ["M_"],
"female": ["FS_", "FE_", "FI_"]
}):
dirsTraces = monet.listDirectoriesWithPathWithinAPath(pathTraces)
files = readExperimentFilenamesV2(pathMean)
filesList = [monet.filterFilesByIndex(files, ix) for ix in nodesAggLst]
landReps = None
if REP or SRP:
landReps = monet.loadAndAggregateLandscapeDataRepetitions(
dirsTraces, drive, MF[0], MF[1])
for (nodeAggIx, pop) in enumerate(filesList):
fName = fNameFmt + str(nodeAggIx).zfill(nodeDigits)
preProcessSubLandscapeV2(pop,
landReps,
fName,
drive,
nodesAggLst,
nodeAggIx,
MF=MF,
cmpr=cmpr,
SUM=SUM,
AGG=AGG,
SPA=SPA,
REP=REP,
SRP=SRP)
return None
aux.printProggress(i, xpNumb, sig)
expSet = sig[i]
(name, aPath, gPath) = expSet
(aFiles, gFiles) = fun.readDataPaths(aPath, gPath)
# Heatmap Analysis --------------------------------------------------------
print(aux.CBLU + '- Loading gene-landscape... ' + aux.PADC,
end='\r')
landscapeData = monet.loadLandscapeData(aFiles, male=MALE, female=FEMALE)
aggregatedNodesData = monet.aggregateGenotypesInLandscape(
landscapeData, GDICT)
geneSpatiotemporals = monet.getGenotypeArraysFromLandscape(
aggregatedNodesData)
# Filtering ---------------------------------------------------------------
# Analysis
print(aux.CBLU + '- Loading mean... ' + aux.PADC, end='\r')
(ykFaPath, tpFaPath) = (monet.filterFilesByIndex(aFiles, sectorsIx[1],
MALE, FEMALE),
monet.filterFilesByIndex(aFiles, sectorsIx[0],
MALE, FEMALE))
(ykAggData,
tpAggData) = (fun.loadSummedMeanResponse(ykFaPath, GDICT, True, True),
fun.loadSummedMeanResponse(tpFaPath, GDICT, True, True))
# Garbage
print(aux.CBLU + '- Loading traces... ' + aux.PADC, end='\r')
landscapeReps = monet.loadAndAggregateLandscapeDataRepetitions(gFiles,
GDICT,
male=True,
female=True)
(ykLand,
tpLand) = (monet.filterAggregateGarbageByIndex(landscapeReps,
sectorsIx[1]),
monet.filterAggregateGarbageByIndex(landscapeReps,
# (USR, DRV, AOI) = (sys.argv[1], sys.argv[2], sys.argv[3])
(USR, DRV, AOI) = ('dsk', 'LDR', 'HLT')
(OVW, MF, JOB) = (True, (False, True), 1)
(SUM, AGG, SPA, REP, SRP) = (True, False, False, True, False)
(PT_ROT, PT_IMG, PT_DTA, PT_PRE, PT_OUT, PT_MTR) = aux.selectPath(USR)
(drive, land) = (drv.driveSelector(DRV), lnd.landSelector('PAN'))
gene = drive.get(AOI).get('gDict')
###############################################################################
# Load folders
###############################################################################
(expDirsMean, expDirsTrac) = aux.getExpPaths(PT_ROT)
exIx = 0
(pathMean, pathTraces) = (expDirsMean[exIx], expDirsTrac[exIx])
# frame.preProcessLandscapeV2(
# pathMean, pathTraces, 'test', drive, prePath='./',
# nodesAggLst=[[0]], analysisOI='HLT', fNameFmt='{}/{}-{}_',
# MF=(True, True), cmpr='bz2', nodeDigits=4,
# SUM=True, AGG=True, SPA=True, REP=True, SRP=True,
# sexFilenameID={'male': ['M_'], 'female': ['FS_', 'FE_', 'FI_']}
# )
nodesAggLst = [[0]]
sexID = {'male': ['M_'], 'female': ["FS_", "FE_", "FI_"]}
files = frame.readExperimentFilenamesV2(pathMean, sexFilenameID=sexID)
files
dirsTraces = monet.listDirectoriesWithPathWithinAPath(pathTraces)
filesList = [monet.filterFilesByIndex(files, ix) for ix in nodesAggLst]
filesList
def preProcessLandscape(pathMean,
pathTraces,
expName,
drive,
prePath='./',
nodesAggLst=[[0]],
analysisOI='HLT',
fNameFmt='{}/{}-{}_',
MF=(True, True),
cmpr='bz2',
nodeDigits=4,
SUM=True,
AGG=True,
SPA=True,
REP=True,
SRP=True):
"""
Preprocesses a subset of the landscape
Args:
pathMean (str): Files list element aggregated by landscape subset
pathTraces (str): Landscape repetitions
(spatial from monet.loadAndAggregateLandscapeDataRepetitions)
expName (str): Filename (including path)
drive (dict): Gene-drive dictionary
prePath (str): Preprocess path for export
nodesAggLst (int): Current list to process (from the nodeAggLst)
analysisOI (str): ID for type of analysis (HLT or ECO for now)
fNameFmt (str): Format string for the experiments (prePath+expName+AOI)
MF (bool tuple): Male and Female boolean selectors
nodeDigits
cmpr (str): Compression algorithm to be used by compress-python
SUM (bool): Population summed and gene-aggregated into one node
AGG (bool): Population gene-aggregated in their own nodes
SPA (bool): Genetic landscape (gene-aggregated)
REP (bool): Garbage gene-aggregated data
SRP (bool): Summed into one garbage gene-aggregated data
Returns:
None
"""
dirsTraces = monet.listDirectoriesWithPathWithinAPath(pathTraces)
files = monet.readExperimentFilenames(pathMean)
filesList = [monet.filterFilesByIndex(files, ix) for ix in nodesAggLst]
landReps = None
if REP:
landReps = monet.loadAndAggregateLandscapeDataRepetitions(
dirsTraces, drive, MF[0], MF[1])
for (nodeAggIx, pop) in enumerate(filesList):
fName = fNameFmt + str(nodeAggIx).zfill(nodeDigits)
preProcessSubLandscape(pop,
landReps,
fName,
drive,
nodesAggLst,
nodeAggIx,
MF=MF,
cmpr=cmpr,
SUM=SUM,
AGG=AGG,
SPA=SPA,
REP=REP,
SRP=SRP)
return None
