def select_by(population, infile, outfile, nval, val):
print(infile)
rows = qlibs.get_rows(infile)
header = 1000
text = ""
posgs = -1
for i in range(len(rows)):
cols = rows[i].split(";")
if len(cols) > 1:
if header == 1000:
text = rows[i] + ("\n")
header = i
hcols = rows[i].split(";")
posgs = qlibs.find(nval, hcols)
if posgs == -1:
posgs = qlibs.find(nval.replace('"', ''), hcols)
if posgs == -1:
qlibs.trace("selectBy", infile, population)
return
if i > header:
if cols[posgs] == val: text = text + rows[i] + "\n"
fout = open(outfile, "w")
fout.write(text)
fout.close()
return
def get_genes(population, datafile, xname, yname):
rows = qlibs.get_rows(datafile)
header = False
x = []
y = []
xcol = -1
ycol = -1
prev = ""
id = 0
for row in rows:
cols = row.split(";")
if len(cols) > 1:
if header == False:
xcol = qlibs.find(xname, cols)
if xcol >= 0: header = True
ycol = qlibs.find(yname, cols)
if ycol >= 0: header = True
else:
if cols[xcol] != prev:
id = id + 1
prev = cols[xcol]
x.append(id)
if cols[ycol].replace(",","").replace("-","").isdecimal() == True: y.append(float(cols[ycol].replace(",",".")))
else:
y.append(0)
qlibs.trace("graph_fields" + yname, datafile + "\n" + str(cols), population)
return [x, y]
def select_score(population, infile, outfile, nval, rel, threshold):
print(infile)
rows = qlibs.get_rows(infile)
header = 1000
text = ""
posgs = -1
for i in range(len(rows)):
cols = rows[i].split(";")
if len(cols) > 1:
if header == 1000:
text = rows[i] + ("\n")
header = i
hcols = rows[i].split(";")
posgs = qlibs.find(nval, hcols)
if posgs == -1:
posgs = qlibs.find(nval.replace('"', ''), hcols)
if posgs == -1:
qlibs.trace("selectS", infile, population)
return
if i > header:
if rel == "greater_than":
if int(cols[posgs]) >= threshold:
text = text + rows[i] + "\n"
if rel == "less_than":
if int(cols[posgs]) <= threshold:
text = text + rows[i] + "\n"
if rel == "equal_to":
if int(cols[posgs]) == threshold:
text = text + rows[i] + "\n"
fout = open(outfile, "w")
fout.write(text)
fout.close()
return
def get_scores(population, datafile, nscore):
rows = qlibs.get_rows(datafile)
header = False
result = []
ncol = -1
for row in rows:
cols = row.split(";")
if len(cols) > 1:
if header == False:
ncol = qlibs.find(nscore, cols)
if ncol >= 0: header = True
else:
ncol = qlibs.find(nscore.replace('"',''), cols)
if ncol >= 0: header = True
else:
if cols[ncol].isnumeric() == True: result.append(int(cols[ncol]))
else: qlibs.trace("graph_freq", datafile + "\n" + str(cols), population)
return result
def getlost_fromerrors(infile, population, set):
datadir = qlibs.get_datadir()
outdir = datadir + "Lost/" + set + "/"
outfile = outdir + "/declost_" + set + ".csv"
qlibs.create_path(outdir)
rows = qlibs.get_rows(infile)
text = ""
for row in rows:
cols = row.split("\t")
if len(cols) > 1:
codebuf = cols[1]
gene = cols[0]
buf = codebuf.split(".")
if int(buf[1]) > 1:
code = buf[0] + "." + str(int(buf[1]) - 1)
text += code + ";" + gene + ";\n"
ft = open(outfile, "a")
ft.write(text)
ft.close()
return
def getlost(infile, population, set):
datadir = qlibs.get_datadir()
outdir = datadir + "Lost/" + set + "/"
outfile = outdir + "/lost_" + set + ".csv"
qlibs.create_path(outdir)
rows = qlibs.get_rows(infile)
text = ""
for row in rows:
cols = row.split(";")
if len(cols) > 1:
code = cols[0]
gene = cols[1]
found = False
indir = qlibs.get_datadir() + population + "/" + set + "/Text/"
for region in os.listdir(indir):
if os.path.isdir(indir + region):
datadir = indir + region + "/" + gene + "__" + code
if os.path.isdir(datadir):
found = True
if found == False: text += code + ";" + gene + ";\n"
ft = open(outfile, "w")
ft.write(text)
ft.close()
return