def getTheGenes(theStartDate, templateList, dirr=os.getcwd()):
"""Walking the dir using Python 3.5. Variable theStartDate has to be
a datetime.date() data type."""
vv = ppma.lookForVARinList(templateList)
datOut = []
# dataOrdering = ['VAR', 'VARX', 'meanAllel', 'stdAllel', 'slope']
for dirName, subdirList, fileList in os.walk(dirr):
for file in fileList:
filepath = os.path.join(dirName, file)
if(filepath == os.path.join(dirName, 'InputParameters.json') and
ppma.loadTheDateFromParamFile(filepath) >= theStartDate):
paramzList = ppma.loadParamSettings(filepath)
# with open(filepath) as f:
# prms = json.load(f)
if ppma.compareParams(templateList, paramzList):
print("Data from:", dirName, end=" ")
popFiles = os.path.join(dirName, "HostGenomesFile.*.csv")
for fil in glob.glob(popFiles):
if not re.search('HostGenomesFile.0.csv', fil):
hostPopFile = fil
Gene_list = loadHostPopulation(hostPopFile)
geneStats = analiseGeneContent(Gene_list)
var = float(paramzList[vv['VAR']])
varx = float(paramzList[vv['VARX']])
geneStats['spp'] = varx
geneStats['patho_mut'] = var
datOut.append((geneStats))
print("- done!")
return datOut
def main():
"""Main function - the script's main body."""
if len(sys.argv) <= 3:
print("Two arguments are needed:")
print(" 1. Give the path to template file.")
print(" 2. Give the name of the output file.")
print(" 3. Give the name of HostGenomesFile.XXXX.csv file")
sys.exit()
headerr = 'VAR VARX MRCA_time maxMutNumb numOfGenes sourceDir'
outputFile = str(sys.argv[2])
try:
template = ppma.loadParamSettings(sys.argv[1])
except Exception:
print("Cannot load the template file. Exiting.")
sys.exit()
try:
theData = serchTheDirs(sys.argv[3], template)
except Exception:
print("Failed to process the data. Some serious issues arose.")
sys.exit()
if len(theData):
FMT = '%.4e %.4e %.4e %.4e %.4e %s'
open(outputFile, 'w').close()
np.savetxt(outputFile, theData, fmt=FMT, header=headerr,
comments='#')
for itm in theData:
for ii in range(len(itm) - 1):
print(itm[ii], "\t", end=" ")
print()
print("Check the output file:", str(os.getcwd()) + "/" + outputFile +
" for details.")
else:
print("No data files matching the criterions were found.",
"Specify your template file.")
sys.exit()
def main():
"""Main function - the script's main body."""
if len(sys.argv) <= 3:
print("Two arguments are needed:")
print(" 1. Give a starting date. It has to be in yyyy-mm-dd format.")
print(" 2. Give the path to template file.")
print(" 3. Give the name of the output file.")
sys.exit()
startDate = None
headerr = 'VAR VARX slope intercept R2 p_value sr_err patho_number '\
+ 'sourceDir'
try:
startDate = ppma.readDate(sys.argv[1])
outputFile = str(sys.argv[3])
except ValueError:
print("Cannot convert argument #1 to a date format.")
sys.exit()
if startDate:
try:
template = ppma.loadParamSettings(sys.argv[2])
# x_Label = ppma.getVarxLabel(sys.argv[2])
except Exception:
print("Cannot load the template file. Exiting.")
sys.exit()
try:
print("Computing data...")
theData = getTheData(startDate, template)
except Exception:
print("Failed to process the data. Some serious issues arose.")
sys.exit()
if len(theData):
FMT = '%.4e %.4e %.4e %.4e %.4e %.4e %.4e %.4e %s'
open(outputFile, 'w').close()
np.savetxt(outputFile,
theData,
fmt=FMT,
header=headerr,
comments='#')
for itm in theData:
for ii in range(len(itm) - 1):
print(itm[ii], "\t", end=" ")
print()
print("Check the output file:",
str(os.getcwd()) + "/" + outputFile + " for details.")
else:
print("No data files matching the criterions were found.",
"Specify your template file.")
sys.exit()
else:
print("Wrong date format.")
sys.exit()
def main():
""" """
"""Main function - the script's main body."""
if len(sys.argv) <= 3:
print("Two arguments are needed:")
print(" 1. Give a starting date. It has to be in yyyy-mm-dd format.")
print(" 2. Give the path to template file.")
print(" 3. Give the output figure name's prefix (e.g. the number",
"of individual number of MHC variants.")
sys.exit()
startDate = None
try:
startDate = ppma.readDate(sys.argv[1])
ymaxx = 75
frame = 250
except ValueError:
print("Cannot convert argument #1 to a date format.")
sys.exit()
if startDate:
try:
template = ppma.loadParamSettings(sys.argv[2])
if template is None:
print(
"Failed to load the template file. Exiting.",
"Check if the path is correct - you may wish to provide",
"an absolute path.")
sys.exit()
figLabel = ppma.getVarxLabel(sys.argv[2])
except Exception:
print("Cannot load the template file. Exiting.")
sys.exit()
if True:
# third argument is very important
theData = getTheData(startDate, template)
# print(theData)
# except Exception:
else:
print("Failed to process the data. Some serious issues arose.")
sys.exit()
if len(theData):
aggrOutCI = aggrDataByRunsCI(theData)
plotAggrOut(aggrOutCI, frame, ymaxx, figLabel)
else:
print("No data files matching the criterions were found.",
"Specify your template file.")
sys.exit()
else:
print("Wrong date format.")
sys.exit()
def main():
"""Main function - the script's main body."""
if len(sys.argv) <= 3:
print("Two arguments are needed:")
print(" 1. Give a starting date. It has to be in yyyy-mm-dd format.")
print(" 2. Give the path to template file.")
print(" 3. The last N generations to analyse. Type 0 if you wand to",
"analyse everything.")
print(" 4. Give the plot file suffix.")
sys.exit()
startDate = None
try:
startDate = ppma.readDate(sys.argv[1])
except ValueError:
print("Cannot convert argument #1 to a date format.")
sys.exit()
try:
cc = int(sys.argv[3])
except ValueError:
print("Cannot convert argument #3 to integer.")
sys.exit()
if startDate:
try:
template = ppma.loadParamSettings(sys.argv[2])
print("The template:", template)
except Exception:
print("Cannot load the template file. Exiting.")
sys.exit()
try:
wdir = os.getcwd()
print("Working directory:", wdir)
theData = getTheData(startDate, template, wdir, cc)
except Exception:
print(
"Failed to process the data. Some serious issues arose.",
"Check if the cut-off host generation for calculating stats",
"is smaller than the total number of host generations.")
sys.exit()
if len(theData):
np.save("sexSelectStrgt" + sys.argv[4], theData)
out = avgDatOut(theData)
justPlotDeviantFromMeanFather(out[:, 0], out[:, 1], out[:, 2], ".",
sys.argv[4])
else:
print("No data files matching the criterions were found.",
"Specify your template file.")
sys.exit()
else:
print("Wrong date format.")
sys.exit()
def getTheData(theStartDate, templateList, dirr=os.getcwd()):
"""Walking the dir using Python 3.6. Variable theStartDate has to be
a datetime.date() data type."""
vv = ppma.lookForVARinList(templateList)
datOut = []
dataOrdering = ['VAR', 'VARX', 'slope', 'intercept']
for dirName, subdirList, fileList in os.walk(dirr):
for file in fileList:
filepath = os.path.join(dirName, file)
if (filepath == os.path.join(dirName, 'InputParameters.json') and
ppma.loadTheDateFromParamFile(filepath) >= theStartDate):
paramzList = ppma.loadParamSettings(filepath)
if ppma.compareParams(templateList, paramzList):
with open(filepath) as f:
prms = json.load(f)
path_spp = float(prms['number_of_pathogen_species'])
lg = prms['number_of_host_generations']
genomeFileName = "HostGenomesFile." + str(lg) + ".csv"
genomeFileName = os.path.join(dirName, genomeFileName)
# print(genomeFileName)
var = float(paramzList[vv['VAR']])
varx = float(paramzList[vv['VARX']])
try:
print(dirName, end=' : ')
pathos = loadPathoExposed(genomeFileName)
hosts = loadHostPopulation(genomeFileName)
if hosts is None or pathos is None:
print("Failed to read data")
continue
else:
print("Done")
except Exception:
print("ERROR in getTheData(): cant's load the host",
"population data")
continue
uniqNumb, pathoNumb = calculateTheNumbers(hosts, pathos)
uniqNumb = np.hstack((uniqNumb, 0))
pathoNumb = np.hstack((pathoNumb, 0))
# slope, intercept, r_val, p_val, std_err
data = linregress(uniqNumb, pathoNumb)
plotMHCvsPathoPresent(uniqNumb, pathoNumb, data[0],
data[1], dirName)
datOut.append((var, varx, data[0], data[1], data[2]**2,
data[3], data[4], path_spp, dirName))
datOut = np.array(datOut, dtype=outType)
return np.sort(datOut, order=dataOrdering)
def getTheData(theStartDate, templateList, dirr=os.getcwd()):
""" """
datOut = []
vv = ppma.lookForVARinList(templateList)
for dirName, subdirList, fileList in os.walk(dirr):
for file in fileList:
filepath = os.path.join(dirName, file)
if (filepath == os.path.join(dirName, 'InputParameters.json') and
ppma.loadTheDateFromParamFile(filepath) >= theStartDate):
paramzList = ppma.loadParamSettings(filepath)
if ppma.compareParams(templateList, paramzList):
var = float(paramzList[vv['VAR']])
varx = float(paramzList[vv['VARX']])
awkMeanINV(dirName)
meanINV = loadMeanInvdMhcNumb(dirName)
datOut.append((var, varx, meanINV))
print("Done dir:", dirName)
return datOut
def main():
"""Main function - the script's main body."""
if len(sys.argv) <= 2:
print("Two arguments are needed:")
print(" 1. Give a starting date. It has to be in yyyy-mm-dd format.")
print(" 2. Give the path to template file.")
sys.exit()
startDate = None
try:
startDate = ppma.readDate(sys.argv[1])
except ValueError:
print("Cannot convert argument #1 to a date format.")
sys.exit()
if startDate:
try:
template = ppma.loadParamSettings(sys.argv[2])
if template is None:
print("Failed to load the template file. Exiting.",
"Check if the path is correct - you may wish to provide",
"an absolute path.")
sys.exit()
except Exception:
print("Cannot load the template file. Exiting.")
sys.exit()
try:
datOut = getTheGenes(startDate, template, os.getcwd())
result = pd.concat(datOut, ignore_index=True)
plotFraction(result)
plotHetero(result)
plotTotNumb(result)
plotChrVsUnq(result, 'corr', 'chr_2', 'unq_2')
plotChrVsUnq(result, 'slope', 'chr_2', 'unq_2')
plotChrVsUnq(result, 'corr', 'chr_1', 'unq_1')
plotChrVsUnq(result, 'slope', 'chr_1', 'unq_1')
plotChromoProp(result)
except Exception:
print("Failed to process the data. Some serious issues arose.",
"Check if the cut-off host generation for calculating stats",
"is smaller than the total number of host generations.")
sys.exit()
def getTheData(theStartDate, templateList, dirr=os.getcwd(), genLast=0):
"""Walking the dir using Python 3.5. Variable theStartDate has to be
a datetime.date() data type. Each item in the `datOut` structure is the
result of computing one simulation."""
datOut = []
for dirName, subdirList, fileList in os.walk(dirr):
for file in fileList:
filepath = os.path.join(dirName, file)
if (filepath == os.path.join(dirName, 'InputParameters.json') and
ppma.loadTheDateFromParamFile(filepath) >= theStartDate):
paramzList = ppma.loadParamSettings(filepath)
if ppma.compareParams(templateList, paramzList):
print("Processing dir:", dirName, end=" ")
moPth = os.path.join(dirName, 'NumberOfMhcInMother.csv')
faPth = os.path.join(dirName, 'NumberOfMhcInFather.csv')
mPth = os.path.join(dirName, 'NumberOfMhcBeforeMating.csv')
mothr, fathr, bmate = loadTheParents(
genLast, moPth, faPth, mPth)
moth, fath, bmate = trimData(mothr, fathr, bmate, 2, 100)
mmMt = avrgMateMHCnumb(bmate)
rMom, rDad, rMmMt = reshapeMatherFather(moth, fath, mmMt)
ww, Fatrs, meanM = pickMotherSizeGroups(rMom, rDad, rMmMt)
bSize = np.zeros(len(Fatrs))
for i, itm in enumerate(Fatrs):
bSize[i] = len(itm)
deltas = []
for i, it in enumerate(ww):
deltas.append(np.nanmean(Fatrs[i] - meanM[i]))
justPlotDeviantFromMeanFather(ww, deltas, bSize, dirName)
try:
xx = np.transpose(
np.vstack((ww, np.array(deltas), bSize)))
except Exception:
print(" - failed to stack the data! Check if the",
"input file sizes (e.g. line numbers) are OK.")
continue
datOut.append(xx)
print(" - done.")
return datOut
def serchTheDirs(FILE, template, dirr=os.getcwd()):
"""Walk the directory tree in search of model runs and process each
simulation individually. Produces some meta-statistics regarding the
results geathered in Numpy structured array."""
# vv = ppma.lookForVAR(template)
vv = ppma.lookForVARinList(template)
datOut = []
dataOrdering = ['VAR', 'VARX', 'MRCA_time', 'maxMutNumb', 'numOfGenes']
for dirName, subdirList, fileList in os.walk(dirr):
for file in fileList:
filepath = os.path.join(dirName, file)
if filepath == os.path.join(dirName, FILE):
try:
paramList = ppma.loadParamSettings(os.path.join(dirName,
"InputParameters.json"))
except Exception:
print("Cannot load the parameters. in dir", dirName)
continue
if ppma.compareParams(template, paramList):
try:
DATA = processDataOneFile(filepath)
except Exception:
print("Cannot load the data. in dir", dirName)
continue
plotTheTimes(DATA[0], DATA[1], DATA[2], DATA[3], DATA[4],
dirName)
var = float(paramList[vv['VAR']])
varx = float(paramList[vv['VARX']])
datOut.append((var, varx, DATA[6], DATA[0].shape[1],
DATA[0].shape[0], dirName))
if len(datOut) > 0:
datOut = np.array(datOut, dtype=outType)
return np.sort(datOut, order=dataOrdering)
else:
print("ERROR in serchTheDirs(): output array is empty")
return None