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 start_file(population, algo):
logdir = qlibs.get_logdir() + population + "/"
startf = get_filename(population, algo, 0)
files = []
for name in os.listdir(logdir):
if os.path.isfile(os.path.join(logdir, name)):
if name.find(algo.lower() + "_error") >= 0:
if name.find(".log") >= 0:
files.append(name)
list = []
for file in files:
infile = logdir + file
f = open(infile, "r")
buf = f.read()
f.close()
lines = buf.split("\n")
for line in lines:
if line.find("C:/") >= 0 or line.find("./") >= 0:
if line.find(".txt") >= 0:
if qlibs.find(line, list) < 0:
list.append(line)
f = open(startf, "w")
for line in list:
f.write(line + "\n")
f.close()
return
def txt_equals_csv(population, algo, reverse, count):
splitted = ""
for i in range(0, count):
splitted = splitted + "Splitted"
indir = qlibs.get_datadir() + population
sets = os.listdir(indir)
text = ""
for set in sets:
csvfiles = []
txtfiles = []
if os.path.isdir(indir + "/" + set):
for dir in os.listdir(indir + "/" + set):
if dir.find(algo + reverse + splitted) >= 0:
if os.path.isdir(indir + "/" + set + "/" + dir + "/"):
for file in os.listdir(indir + "/" + set + "/" + dir +
"/"):
if file.find(".csv") > 0: csvfiles.append(file)
if dir.find("Text" + reverse + algo + splitted) >= 0:
if os.path.isdir(indir + "/" + set + "/" + dir + "/"):
for file in os.listdir(indir + "/" + set + "/" + dir +
"/"):
if file.find(".txt") > 0: txtfiles.append(file)
for file in txtfiles:
if qlibs.find(file.replace(".txt", ".csv"), csvfiles) < 0:
text = text + qlibs.get_datadir(
) + population + "/" + set + "/Text" + reverse + algo + splitted + "/" + file + "\n"
if text == "": result = True
else:
outfile = get_filename(population, algo, count)
fout = open(outfile, "w")
fout.write(text)
fout.close()
result = False
return result
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 get_seq(population, argv):
result = []
basedir = qlibs.get_datadir() + population + "/"
countfile = qlibs.get_datadir() + "Countfile.log"
indata = params(argv)
finput = indata[0]
search = indata[1]
col3rd = indata[3]
if col3rd == False:
basename = os.path.basename(indata[0])
result.append(basename[:len(basename) - 4])
datadir = basedir + basename[:len(basename) - 4]
datadir = create_dir(datadir, indata)
fin = open(finput, "r")
buf = fin.read()
fin.close()
rows = buf.split("\n")
try:
fc = open(countfile, "r")
buf = fc.read()
fc.close()
cols = buf.split("\t")
count = int(cols[0])
day = time.strptime(cols[3], "%Y-%m-%d")
today = time.strptime(str(datetime.date.today()), "%Y-%m-%d")
print(day, today)
if today > day:
count = 0
elif count >= 5000:
tk.messagebox.showinfo("Quad", "Daily hits limit reached!")
return result
if cols[2] == finput:
i = int(cols[1])
if i >= len(rows):
res = tk.messagebox.askyesno(
"Quad",
"WARNING:\n\n File already processed \n\n Do you want to force Execution?"
)
if res == True:
i = 0
else:
i = 0
except:
count = 0
i = 0
while i < len(rows):
cols = rows[i].split(";")
if len(cols) > 1:
code = cols[0]
gene = cols[1]
if col3rd == True:
if qlibs.find(cols[2], result) < 0: result.append(cols[2])
datadir = basedir + cols[2]
datadir = create_dir(datadir, indata)
count = count + 1
print(count, gene, code)
text = get_fasta(gene, code, search)
if text == "":
text = get_fasta_gene(gene, code, search)
if text == "":
get_fasta_alt(gene, code, search)
if text == "":
text = get_fasta_gene_alt(gene, code, search)
if text == "":
qlibs.trace("fasta", gene + "\t" + code,
population)
else:
fout = open(
datadir + gene + "__" + code + ".fasta", "w")
fout.write(text)
fout.close()
else:
fout = open(datadir + gene + "__" + code + ".fasta",
"w")
fout.write(text)
fout.close()
else:
fout = open(datadir + gene + "__" + code + ".fasta", "w")
fout.write(text)
fout.close()
else:
fout = open(datadir + gene + "__" + code + ".fasta", "w")
fout.write(text)
fout.close()
if count % 5000 == 0:
tk.messagebox.showinfo("Quad", "Daily hits limit reached!")
break
time.sleep(5)
i = i + 1
fc = open(countfile, "w")
fc.write(
str(count) + "\t" + str(i) + "\t" + finput + "\t" +
str(datetime.date.today()))
fc.close()
return result
def intersect(population, algo):
lists = []
sets = []
dists = []
indir = qlibs.get_datadir() + population + "/"
outfile = indir + "intersect_genes_" + population + str(
datetime.date.today()).replace("-", "") + ".csv"
for set in os.listdir(indir):
if os.path.isdir(indir + set):
files = [
f for f in os.listdir(indir + set)
if os.path.isfile(indir + set + "/" + f)
]
lastfile = ""
for file in files:
try:
if file.index("dist_" + algo) == 0 and file.index(
".csv") == len(file) - 4:
if file > lastfile: lastfile = file
except:
pass
if lastfile == "": qlibs.trace("intersect", set, pop=population)
else:
lists.append(qlibs.get_uniques(indir + set + "/" + lastfile))
sets.append(set)
f = open(indir + set + "/" + lastfile, "r")
buf = f.read()
f.close()
dists.append(buf)
elems = []
setreps = []
setidxs = []
for i in range(len(sets) - 1):
j = i + 1
while j < len(lists):
for elem in lists[i]:
if qlibs.find(elem, lists[j]) >= 0:
k = qlibs.find(elem, elems)
if k >= 0:
if qlibs.find(sets[j], setreps[k]) < 0:
setreps[k].append(sets[j])
setidxs[k].append(j)
else:
elems.append(elem)
list = [sets[i], sets[j]]
setreps.append(list)
list = [i, j]
setidxs.append(list)
j = j + 1
text = ""
print(sets)
print(setreps)
print(setidxs)
for i in range(len(elems)):
text = text + elems[i] + ";"
for set in setreps[i]:
text = text + set + ";"
text = text + "\n"
if text == "": text = "No intersection found"
fout = open(outfile, "w")
fout.write(text)
fout.close()
text = ""
for i in range(len(elems)):
j = setidxs[i][0]
buf = dists[j]
print(j)
print(elems[i])
rows = buf.split("\n")
for row in rows:
if row.find(elems[i]) >= 0:
text = text + row
for set in setreps[i]:
text = text + set + ";"
text = text + "\n"
outfile = indir + "intersect_dists_" + algo + "_" + population + str(
datetime.date.today()).replace("-", "") + ".csv"
fout = open(outfile, "w")
fout.write(text)
fout.close()
return
def union(indir, set, dir, infile, population, algo, reverse):
fgr = split_dir(infile)
name = fgr[0]
csvudir = indir + set + "/"
if not os.path.exists(csvudir):
os.mkdir(csvudir)
csvudir = indir + set + "/" + algo + reverse + "/"
if not os.path.exists(csvudir):
os.mkdir(csvudir)
csvudir = indir + set + "/" + algo + reverse + "/" + fgr[2] + "/"
if not os.path.exists(csvudir):
os.mkdir(csvudir)
csvudir = indir + set + "/" + algo + reverse + "/" + fgr[2] + "/" + fgr[
1] + "/"
if not os.path.exists(csvudir):
os.mkdir(csvudir)
if name.find(".csv") < 0: csvufile = csvudir + name + ".csv"
ucsvdir = indir + "/" + set + "/"
if not os.path.exists(ucsvdir):
os.mkdir(ucsvdir)
ucsvdir = indir + "/" + set + "/" + algo + reverse + "Union/"
if not os.path.exists(ucsvdir):
os.mkdir(ucsvdir)
ucsvdir = indir + "/" + set + "/" + algo + reverse + "Union/" + fgr[2] + "/"
if not os.path.exists(ucsvdir):
os.mkdir(ucsvdir)
ucsvdir = indir + "/" + set + "/" + algo + reverse + "Union/" + fgr[
2] + "/" + fgr[1] + "/"
if not os.path.exists(ucsvdir):
os.mkdir(ucsvdir)
if name.find(".csv") < 0: ucsvfile = ucsvdir + name + ".csv"
split_files = []
split_texts = []
split_dirs = []
if not os.path.exists(csvufile):
if os.path.sdir(indir + "/" + set + "/"):
for bufdir in os.listdir(indir + "/" + set + "/"):
if bufdir.find(algo + reverse + "Splitted") >= 0:
if os.path.sdir(indir + "/" + set + "/" + bufdir):
for file in os.listdir(indir + "/" + set + "/" +
bufdir):
if file.find(name) >= 0 and file.find(".csv") >= 0:
split_files.append(file)
split_dirs.append(indir + "/" + set + "/" +
bufdir + "/")
if bufdir.find("Text" + reverse + algo + "Splitted") >= 0:
if os.path.sdir(indir + "/" + set + "/" + bufdir):
for file in os.listdir(indir + "/" + set + "/" +
bufdir):
if file.find(name) >= 0 and file.find(".txt"):
split_texts.append(file)
founds = True
for i in range(len(split_files)):
file = split_files[i].replace(".csv", ".txt")
if qlibs.find(file, split_texts) < 0:
founds = False
qlibs.trace("union", split_dirs[i] + file, population)
if founds == True:
textdir = indir + "/" + set + "/Text" + reverse + "/" + fgr[
2] + "/" + fgr[1] + "/"
if name.find(".txt") < 0: textfile = textdir + name + ".txt"
fin = open(textfile, "r")
text = fin.read()
fin.close()
csv = ""
header = False
print(split_files)
for i in range(len(split_files)):
textsplit = split_files[i].replace(".csv", ".txt")
fin = open(split_dirs[i].replace(algo, "Text") + textsplit,
"r")
buf = fin.read()
fin.close()
offset = text.find(buf)
print(split_files[i], offset)
fin = open(split_dirs[i] + split_files[i], "r")
buf = fin.read()
fin.close()
rows = buf.split("\n")
if header == False:
csv = csv + rows[0] + "\n"
header = True
for j in range(1, len(rows)):
cols = rows[j].split(";")
if len(cols) > 1:
cols[0] = str(int(cols[0]) + offset)
for col in cols:
csv = csv + col + ";"
csv = csv + "\n"
print(ucsvfile)
print(csv)
fout = open(ucsvfile, "w")
fout.write(csv)
fout.close()
data = qlibs.get_uniquerows(ucsvfile, population)
fout = open(csvufile, "w")
fout.write(data)
fout.close()
return
