def update_papers(conn, lock, status=1):
"""Update papers from all ReDIF documents."""
c = conn.cursor()
c.execute('SELECT code FROM jel WHERE parent IS NOT NULL')
alljel = [r[0] for r in c.fetchall()]
c.execute('SELECT url FROM listings WHERE status = ?', (status, ))
urls = [r[0] for r in c.fetchall()]
urls = random.sample(urls, k=len(urls)) # to redistribute load
c.close()
def worker(u):
return update_papers_1(conn, lock, u, alljel)
size = settings.batch_size
no_batches = math.ceil(len(urls) / size)
status = 0
for i in range(no_batches):
print('Downloading batch {}/{}...'.format(i + 1, no_batches))
batch = urls[i * size:(i + 1) * size]
bs = sum(parallel(worker, batch, threads=settings.no_threads_www))
status += bs
conn.commit()
print(f'{bs} out of {len(batch)} records updated successfully')
print(f'All batches: {status} out of {len(urls)} records'
' updated successfully')
def conformation(filename, procs=0):
scr = "_tmp_ensemble_/"
molecules = cheminfo.read_sdffile(filename)
if procs == 0:
for im, molecule in enumerate(molecules):
get_conformations((im, molecule), scr=scr)
else:
def workpackages():
for im, molecule in enumerate(molecules):
yield im, molecule
lines = workpackages()
results = misc.parallel(lines,
get_conformations, [], {"scr": scr},
procs=procs)
for result in results:
pass
# misc.parallel(lines)#, get_conformations, [], {"scr":scr}, procs=procs)
return
def update_series(conn, lock, status=1):
"""Update all archive and series files in the database."""
c = conn.cursor()
c.execute('SELECT file, type FROM repec WHERE status = ?', (status, ))
files = c.fetchall()
c.close()
print('Updating archive and series files...')
def worker(el):
return update_series_1(conn, lock, *el)
status = parallel(worker, files, threads=settings.no_threads_repec)
print(f'{sum(status)} out of {len(files)} records updated successfully')
def update_listings(conn, lock, status=1):
"""Update remote listings for all series."""
c = conn.cursor()
c.execute('SELECT url FROM remotes WHERE status = ?', (status, ))
urls = [r[0] for r in c.fetchall()]
urls = random.sample(urls, k=len(urls)) # to redistribute load
c.close()
print('Updating remote listings...')
def worker(u):
return update_listings_1(conn, lock, u)
status = parallel(worker, urls, settings.no_threads_www)
print(f'{sum(status)} out of {len(urls)} records updated successfully')
def main(datafile, procs=0, scr="_tmp_"):
db = misc.load_obj(datafile)
keys = db.keys()
print("total keys:", len(keys))
xaxis = []
yaxis = []
if procs == 0:
def get_results():
for i, key in enumerate(keys):
smi = key
kelvin = db[key]
result = prepare_sdf_and_csv(smi, kelvin)
if result is None: continue
yield result
results = get_results()
else:
def workpackages():
for i, key in enumerate(keys):
# if i > 5000: break
smi = key
kelvin = db[key]
yield smi, kelvin
lines = workpackages()
results = misc.parallel(lines,
prepare_sdf_and_csv_procs, [], {},
procs=procs)
print("streaming results")
# Write results
fullsdf = ""
fsdf = gzip.open("data/sdf/structures.sdf.gz", 'w')
fprop = open("data/sdf/properties.csv", 'w')
for i, result in enumerate(results):
if result is None: continue
molobj, values = result
sdfstr = cheminfo.molobj_to_sdfstr(molobj)
fsdf.write(sdfstr.encode())
valuesstr = " ".join(values)
# propstr = "{:} {:}\n".format(mean, standard_deviation)
propstr = f"{i} " + valuestr
fprop.write(propstr)
fsdf.close()
fprop.close()
return
