def para_spell_corr(dicowsc, pdser):
# Parallelisation
nb_cpu = mp.cpu_count()
p = mp.Pool(processes=nb_cpu)
split_serie = np.array_split(pdser, nb_cpu)
splserdico = [(split_serie[i], dicowsc) for i in range(nb_cpu)]
pool_results = p.map(map_spell_corr, splserdico)
p.close()
p.join()
# merging parts processed by different processes
parts = pd.concat(pool_results, axis=0)
return parts
def parallel_serie_stem(pdser):
# Parallelisation
nb_cpu = mp.cpu_count()
p = mp.Pool(processes=nb_cpu)
split_serie = np.array_split(pdser, nb_cpu)
pool_results = p.map(map_stem, split_serie)
p.close()
p.join()
# merging parts processed by different processes
parts = pd.concat(pool_results, axis=0)
return parts
def para_spell_corr(dicowsc, pdser):
# Parallelisation
nb_cpu = mp.cpu_count()
p = mp.Pool(processes=nb_cpu)
split_serie = np.array_split(pdser, nb_cpu)
splserdico = [(split_serie[i], dicowsc) for i in range(nb_cpu)]
pool_results = p.map(map_spell_corr, splserdico)
p.close()
p.join()
# merging parts processed by different processes
parts = pd.concat(pool_results, axis=0)
return parts
def parallel_serie_stem(pdser):
# Parallelisation
nb_cpu = mp.cpu_count()
p = mp.Pool(processes=nb_cpu)
split_serie = np.array_split(pdser, nb_cpu)
pool_results = p.map(map_stem, split_serie)
p.close()
p.join()
# merging parts processed by different processes
parts = pd.concat(pool_results, axis=0)
return parts
def para_split(lwordref, pdser):
dwordcost = dict((str(k), log((i+1)*log(len(lwordref)))) for i, k in enumerate(lwordref))
# Parallelisation
nb_cpu = mp.cpu_count()
p = mp.Pool(processes=nb_cpu)
split_serie = np.array_split(pdser, nb_cpu)
splserdico = [(split_serie[i], dwordcost) for i in range(nb_cpu)]
pool_results = p.map(map_split, splserdico)
p.close()
p.join()
# merging parts processed by different processes
parts = pd.concat(pool_results, axis=0)
return parts
def para_split(lwordref, pdser):
dwordcost = dict((str(k), log((i + 1) * log(len(lwordref))))
for i, k in enumerate(lwordref))
# Parallelisation
nb_cpu = mp.cpu_count()
p = mp.Pool(processes=nb_cpu)
split_serie = np.array_split(pdser, nb_cpu)
splserdico = [(split_serie[i], dwordcost) for i in range(nb_cpu)]
pool_results = p.map(map_split, splserdico)
p.close()
p.join()
# merging parts processed by different processes
parts = pd.concat(pool_results, axis=0)
return parts