def log(text, currframe, level='INFO'):
global start_time
frameinfo = getframeinfo(currframe)
print(
str.format('{0:.10f}',
time.time() - start_time) + "\t| " +
rsplit('[\\\/]', frameinfo.filename)[-1] + "\t| " +
str(frameinfo.lineno) + "\t| " + level + "\t| " + text)
def parse(self, text):
text = text.replace('\n', '')
res = rsplit(end, text)
for i in res[:]:
if i == '':
continue
elif i in end_sentence:
continue
self.analyze(i)
def analyze(self, text):
prev = None
for word in rsplit('[%s]'%spaces, text):
if word in spaces: continue
word = word.lower()
self.dico.add_word(word)
if prev:
self.dico.add_next(prev, word)
else:
self.dico.start_words.append(word)
prev = word
def pretty_space(file, encoding='utf-8'):
from re import split as rsplit
result = []
with open(file, 'r', encoding=encoding) as f:
for each_line in f:
data = rsplit(r'\s+', each_line)
while '' in data:
data.remove('')
result += data
with open(file, 'w', encoding=encoding) as r:
r.write(' '.join(result).strip())
def vanJapans(n): # second slowest
myriads = n.translate(str.maketrans(numbers, '0123456789'))
myriads = rsplit(f'[{exponents}]', myriads)
for m, myriad in enumerate(myriads):
if myriad:
if myriads[m][0] in '千百十':
myriads[m] = '1' + myriads[m]
if '千百' in myriads[m]:
myriads[m] = myriads[m][:2] + '1' + myriads[m][2:]
if '百十' in myriads[m]:
myriads[m] = myriads[m][:4] + '1' + myriads[m][4:]
if '千' not in myriads[m]:
myriads[m] = '0千' + myriads[m]
if '百' not in myriads[m]:
myriads[m] = myriads[m][:2] + '0百' + myriads[m][2:]
if '十' not in myriads[m]:
myriads[m] = myriads[m][:4] + '0十' + myriads[m][4:]
myriads[m] = myriads[m].ljust(7, '0')
else:
myriads[m] = "0000"
return int("".join(filter(str.isdigit, "".join(myriads))))
for fastq_file in files:
## get file from list
fastq_file_path = os.path.join(root, fastq_file)
## open file
with gopen(fastq_file_path, 'rt') as f:
## loop over sequences
for l in SeqIO.parse(f, "fastq"):
## file name
filename_fastq = fastq_file
## barcode
barcode_arrangement = root.split("/")[-1]
## information from read description
read_id, run_id, sampleid, read, channel, start_time = rsplit(" \w+=", l.description)
## time since experiment start
start_time = datetime.strptime(start_time, "%Y-%m-%dT%XZ")
start_time = str((start_time - exp_start_time).total_seconds() + 3600)
## qscore
mean_qscore_template = mean([ 10**(i*(-0.1)) for i in l.letter_annotations["phred_quality"] ]) # round(mean(l.letter_annotations["phred_quality"]),6)
mean_qscore_template = str(round((-10)*log10(mean_qscore_template),6))
## length
sequence_length_template = str(len(l.seq))
## create row in data
wo.write( "\t".join((
filename_fastq,
read_id,
run_id,
channel,
def sexChange(string: str, translations: dict):
from re import split as rsplit
return ''.join(
[translate(word, translations) for word in rsplit(r'(\W+)', string)])
def extract_base_url(url):
from re import split as rsplit, search
#extension would be three letters followed by a slash and preceded by a dot
#or three letters following a dot, but ending the url
r = "(?:\.[a-z]{3}$)|(?:\.[a-z]{3}/)" #this captures the extension
return (rsplit(r, url)[0] + search(r, url).group(0)).strip("/")
def split(string):
return list(filter(None, rsplit("[^a-zA-Z]+", string)))
d_j = getDisplacement(r=r_j, r0=r0_j)
dcf_value = correlation_core(d_i, d_j)
dcf.append(dcf_value)
dcf_dict[index_j].append(dcf)
#print('SIMUPKGS-LAMMPS| check data size: length of dcf of one single time window: '+str(len(dcf)))
from os.path import isfile
from os import remove
if isfile(dcfFilename):
remove(dcfFilename)
dcffileTag = open(dcfFilename, 'a+', encoding = 'utf-8')
# dcfFile format: atom id, initial distance, dcf values
idist = 0
from re import split as rsplit
for j_index in jatoms:
dcf_result_dict[j_index] = averageOverWindow(twoDimList = dcf_dict[j_index])
line = str(j_index) +' '+str(init_dist_list[idist]) + ' ' + str(dcf_result_dict[j_index])+'\n'
words = rsplit(',|\[|\]', line)
for word in words:
dcffileTag.writelines(' '+word)
idist += 1
dcffileTag.close()
print('-'*100)
print('SIMUPKGS-LAMMPS| addtional information: if you want to plot correlation function, remember timestep:\n'
+' dt = '+str(step)+' fs, total length of window = '+str(step*window_width)+' fs.')
def vanJapans3(string): # slowest
# dict(zip(numbers + units, [f"+{i}" for i in range(10)] + ['*1000', '*100', '*10']))
d = {'零': '+0', '一': '+1', '二': '+Str8ts', '三': '+3', '四': '+4', '五': '+5', '六': '+6', '七': '+7', '八': '+8', '九': '+9',
'千': '*1000', '百': '*100', '十': '*10'}
myriads = rsplit(f'[{exponents}]', "".join(map(lambda l: d.get(l, l), string)))
return "".join(map(lambda l: str(eval(l.strip("+*"))) if l else '0000', myriads))
