def replace_line(path: str, match: Callable[[str], bool], replacement: str):
for line in fileinput(path, inplace=True):
if match(line):
end = ''
if line.endswith('\r\n'):
end = '\r\n'
elif line.endswith('\n'):
end = '\n'
if replacement.endswith(end):
end = ''
print(replacement, end=end)
else:
print(line, end='')
def main():
from argparse import ArgumentParser
from fileinput import input as fileinput
arg_parser = ArgumentParser()
arg_parser.add_argument(
"-e",
dest="expression",
help="starting expression; if omitted, first defined term is used")
arg_parser.add_argument("-g", dest="grammar", help="EBNF grammar file")
arg_parser.add_argument("-v",
dest="verbose",
default=False,
action="store_true",
help="show what the parser is doing")
arg_parser.add_argument("file",
default="-",
nargs="?",
help="text file to be parsed")
args = arg_parser.parse_args()
if args.grammar:
grammar = ""
with open(args.grammar, "r") as fd:
grammar = fd.read()
parser = create_parser(grammar)
if parser is None:
print("error: grammar file cannot be parsed")
exit(1)
if args.expression:
if args.expression not in parser.custom_defs:
print("error: specified expression not defined")
exit(1)
term = args.expression
else:
term = PEGParser(EBNF_DEFS).parse(
grammar,
"Syntax").first_descendant("Definition/Identifier").match
else:
parser = PEGParser(EBNF_DEFS)
term = "Syntax"
parser.debug = args.verbose
contents = "".join(fileinput(files=args.file))
ast, chars_parsed = parser.partial_parse(contents, term)
length = len(contents)
if not ast or chars_parsed != length:
print("failed: only parsed {} of {} characters\n".format(
chars_parsed, length))
exit(1)
else:
ast.pretty_print()
def prepare_mcpb_input(structures, software_version='g09', cut_off=2.8):
"""
Get all the substructure files and prepare the MCPB.py input
"""
template = dedent("""
original_pdb master.pdb
group_name {name}
cut_off {cut_off}
ion_ids {metal_id}
ion_mol2files {metal_mol2}
naa_mol2files {residues_mol2}
frcmod_files {residues_frcmod}
large_opt 1
software_version {software_version}
""")
# First collect all files in the same master PDB
pdbfiles = [
s['pdb'] for s in structures['metals'] + structures['residues']
]
if 'pdb' in structures['protein']:
pdbfiles.append(structures['protein']['pdb'])
with open('master.unfixed.pdb', 'w') as f:
for line in fileinput(pdbfiles):
f.write(line)
# Fix residue numbering issues
pdb4amber.run(arg_pdbin='master.unfixed.pdb', arg_pdbout='master.pdb')
name = os.path.basename(os.getcwd())
with open('mcbp.in', 'w') as f:
f.write(
template.format(
name=name,
metal_id=' '.join(
map(str, range(1,
len(structures['metals']) + 1))),
metal_mol2=' '.join([s['mol2'] for s in structures['metals']]),
residues_mol2=' '.join(
[r['mol2'] for r in structures['residues']]),
residues_frcmod=' '.join(
[r['frcmod'] for r in structures['residues']]),
cut_off=cut_off,
software_version=software_version,
))
return 'mcbp.in'
def handle(self, *args, **options):
count = 0
UserModel = get_user_model()
for line in fileinput(args, openhook=hook_encoded("utf-8")):
try:
username, password = line.rstrip("\r\n").split(":", 1)
except ValueError:
raise CommandError(
"Invalid input provided. "
"Format is 'username:password', one per line.")
try:
user = UserModel._default_manager.get(
**{UserModel.USERNAME_FIELD: username})
except UserModel.DoesNotExist:
raise CommandError("User '%s' does not exist." % username)
user.set_password(password)
user.save()
count += 1
return "%d password(s) successfully changed." % count
def main():
from argparse import ArgumentParser
from fileinput import input as fileinput
arg_parser = ArgumentParser()
arg_parser.add_argument('-e', dest='expression', help='starting expression; if omitted, first defined term is used')
arg_parser.add_argument('-g', dest='grammar', default=EBNF_GRAMMAR, help='EBNF grammar file')
arg_parser.add_argument('-v', dest='verbose', default=False, action='store_true', help='show what the parser is doing')
arg_parser.add_argument('file', default='-', nargs='?', help='text file to be parsed')
args = arg_parser.parse_args()
grammar = ''
with open(args.grammar, 'r') as fd:
grammar = fd.read()
parser = create_parser(grammar)
if args.expression:
term = args.expression
else:
term = PEGParser(EBNF_DEFS).parse(grammar, 'Syntax').first_descendant('Definition/Identifier').match
parser.debug = args.verbose
contents = ''.join(fileinput(files=args.file))
parser.parse(contents, term).pretty_print()
def main():
with fileinput() as fs:
data = list(
set(r[4].replace('AND ', '').replace('OF ', '')
for r in reader(fs)))
vec = CountVectorizer(tokenizer=word_tokenize).fit_transform(data)
svd = TruncatedSVD().fit_transform(vec)
fig, axes = plt.subplots(2, 3)
fig.subplots_adjust(wspace=1)
for i, ax in enumerate(np.array(axes).flatten()):
clustering = SpectralClustering(n_clusters=N_CLUSTERS -
i).fit_predict(svd)
labeled = np.append(svd, clustering.reshape(len(data), 1), axis=1)
clusters = defaultdict(set)
for c, r in zip(clustering, data):
clusters[c].add(r)
pprint(clusters)
for c, titles in clusters.items():
# others = set(data) - titles
wc = wordcount(titles)
t = labeled[labeled[:, 2] == c]
ax.scatter(t[:, 0],
t[:, 1],
c=COLORS[c],
label=', '.join(w for w, _ in wc.most_common(3)))
ax.set_title(f'{N_CLUSTERS - i} Clusters')
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# ax.legend(loc='lower center', bbox_to_anchor=(0.0, -0.3))
# plt.title('Clustering of %d Job Titles' % len(data))
# plt.show()
plt.savefig('clustering.png')
def main():
from argparse import ArgumentParser
from fileinput import input as fileinput
arg_parser = ArgumentParser()
arg_parser.add_argument("-e", dest="expression", help="starting expression; if omitted, first defined term is used")
arg_parser.add_argument("-g", dest="grammar", help="EBNF grammar file")
arg_parser.add_argument("-v", dest="verbose", default=False, action="store_true", help="show what the parser is doing")
arg_parser.add_argument("file", default="-", nargs="?", help="text file to be parsed")
args = arg_parser.parse_args()
if args.grammar:
grammar = ""
with open(args.grammar, "r") as fd:
grammar = fd.read()
parser = create_parser(grammar)
if parser is None:
print("error: grammar file cannot be parsed")
exit(1)
if args.expression:
if args.expression not in parser.custom_defs:
print("error: specified expression not defined")
exit(1)
term = args.expression
else:
term = PEGParser(EBNF_DEFS).parse(grammar, "Syntax").first_descendant("Definition/Identifier").match
else:
parser = PEGParser(EBNF_DEFS)
term = "Syntax"
parser.debug = args.verbose
contents = "".join(fileinput(files=args.file))
ast, chars_parsed = parser.partial_parse(contents, term)
length = len(contents)
if not ast or chars_parsed != length:
print("failed: only parsed {} of {} characters\n".format(chars_parsed, length))
exit(1)
else:
ast.pretty_print()
def main():
l = []
for line in fileinput():
l += line.strip(),
print(mergeex(l))
# Bozo may be set to 1 if the feed has an error (but is still parsable). Since I don't own these feeds, there's no need to report this.
if d['bozo'] == 1:
if (isinstance(d['bozo_exception'], URLError) # Network error
or isinstance(d['bozo_exception'],
SAXException)): # XML Parsing error
print(f'URLError while parsing feed: {feed_url}')
print_exception(None, d['bozo_exception'], None, chain=False)
return [
] # These two errors are indicative of a critical parse failure, so there's no value in continuing.
if d['status'] == 304: # etag / modified indicates no new data
return []
if d['status'] == 301:
print(f'Feed {feed_url} has permanently moved to {d.href}')
for line in fileinput('feed_list.txt', inplace=True):
print(line.replace(feed_url, d.href), end='')
cache[d.href] = cache[feed_url]
del cache[feed_url]
feed_url = d.href
if d['status'] == 410:
print(f'Feed {feed_url} has been permanently deleted')
for line in fileinput('feed_list.txt', inplace=True):
if feed_url not in line:
print(line, end='')
continue
print('# (Permanently deleted)')
print('# ' + line, end='')
return []
/ (judgements['true positive']
+ judgements['false positive']
+ judgements['false negative']
)
)
accuracy = ((judgements['true positive']
+ judgements['true negative'])
/ sum(judgements.values())
)
quasi_f = 2*((precision*recall)/(precision+recall))
coverage = ((judgements['true positive'] + judgements['incorrectly split'])
/(judgements['true positive'] + judgements['incorrectly split'] + judgements['false negative']))
return precision, recall, accuracy, quasi_f, coverage, error_analysis
if __name__ == '__main__':
if version_info < (3, 5):
print("Error: Python >=3.5 required.", file=sys.stderr)
exit(1)
args = docopt.docopt(__doc__)
spl = Splitter(language=args['--lang'], verbose=args['--verbose'], args=args)
if args['--evaluate']:
# Fix rounding to make 2.345 mean 2.35
L = lambda x: int(round(x+0.001, 2)*100)
p, r, a, f, c, E = spl.evaluate(args['<file>'][0])
print(".{} .{} .{} .{} .{}".format(*map(L, (p, r, a, f, c))), E)
else:
for line in fileinput(args['<file>']):
if not line.strip():
break
print(line.strip(), spl.split(line.strip(), output="eval"), sep="\t")
def main():
l = ()
for line in fileinput():
l += line.strip(),
print mergeex(l)
from fileinput import fileinput
from derivation.first import first_set
from derivation.follow import follow_set
from derivation.select import select_set
from derivation.anaslysis import analysis_table
fistTable = {}
followTable = {}
formulas = fileinput("in.txt")
for c in formulas.non_terminator():
a = first_set(c, formulas, fistTable)
for c in formulas.non_terminator():
a = follow_set(c, formulas, followTable, fistTable)
selectTable = select_set(formulas, followTable, fistTable)
terminators = formulas.terminators()
analysisTable = analysis_table(terminators, selectTable)
def analysis(s, analysisTable):
# todo 使用状态机的状态迁移简化过程
print("步骤\t分析栈\t剩余输入串\t所用产生式")
stack = ['#', 'E']
step = 0
while True:
if stack[-1] == s[0]:
print(step + 1, end="\t")