def run_wb_sim(language, viol, mgain, nconstraints, mb, gam, parameters,
reducemem):
'''
this learning simulation is described in Gouskova and Gallagher (NLLT). The learner starts with a baseline
grammar; if this grammar contains placeholder trigrams, it creates projections for each distinct trigram and runs a final simulation with those projections available.
'''
basepath = os.getcwd().split('code')[0]
simfunc.cleanUpWorkdir(basepath)
if parameters:
params.move_params(
os.path.join(basepath, 'data', language, 'params.txt'))
viol, mgain, nconstraints, gamma = params.read_params()
else:
params.makeParams(consize=nconstraints,
violable=viol,
mingain=mgain,
gamma=gam,
predefault=False)
simfunc.makeSimFiles(language)
#baseline simulation
simfunc.runBaselineSim(basepath, reducemem=reducemem)
#analyze resulting grammar.txt file, make projections for each wb-mentioning constraint
simfunc.makeProjection(basepath, 'wb', mb)
if len(os.listdir('projections')) == 0:
print(
'\nNo projections were found because there were no placeholder constraints in the baseline grammar.'
)
else:
simfunc.runCustomSim(reducemem=reducemem, simtype='wb')
vio = viol[0:2]
wrapstring = os.path.join('sims', language.replace(
os.sep, "_")) + "_" + '_'.join(
['wb', vio, 'gain' + str(mgain), 'con' + str(nconstraints)])
return simfunc.wrapSims(wrapstring, ret=True)
def run_handmade_projection_sim(language, viol, mgain, nconstraints, gam,
parameters, feature, reducemem):
'''
this either creates a projection file based on the value of "feature" (e.g., "-son") or runs a simulation with a custom projection file. To do the latter, supply a full path to the projection file as the last argument.
'''
basepath = os.getcwd().split('code')[0]
lgfullpath = os.path.join(basepath, 'data', language)
simfunc.cleanUpWorkdir(basepath)
simfunc.makeSimFiles(language)
if parameters:
params.move_params(lgfullpath, 'params.txt')
viol, mgain, nconstraints, gam = params.read_params()
else:
params.makeParams(consize=nconstraints,
violable=viol,
mingain=mgain,
gamma=gam)
simfunc.handmakeProjection(basepath, feature)
simfunc.runCustomSim(feature, reducemem=reducemem)
if 'output_baseline' in os.listdir(basepath):
shutil.rmtree(basepath + 'output_baseline')
simfunc.wrapSims(os.path.join(
'sims', '_'.join(language.replace(os.sep, "_"), 'custom')),
cust=True)
def run_mbsublex_sim(language, viol, mgain, nconstraints, mb, gam, parameters,
reducemem):
'''
this simulation needs a corpus with morpheme boundaries.
it starts by running a baseline simulation on the corpus.
then, if it finds constraints in the resulting grammar that mention [-mb] (see mbsublex module), it splits the learning data into individual morphemes, one morph per line
it then uses that as a new baseline data set. if it locates any placeholder trigrams in that subset, it makes a projection from them
and then it runs a projection simulation on the morpheme sublexicon, and on the whole corpus.
'''
basepath = os.getcwd().split('code')[0]
maxentdir = os.path.join(basepath, 'maxent2', 'temp')
dircontent = os.listdir(maxentdir)
vio = viol[0:2]
wrapstring = os.path.join('sims', language.replace(
os.sep, "_")) + "_" + '_'.join([
'wb', 'mbsublex', vio, 'gain' + str(mgain),
'con' + str(nconstraints)
])
if not 'output_baseline' in dircontent:
simfunc.cleanUpWorkdir(basepath)
if parameters:
params.move_params(
os.path.join(basepath, 'data', language, 'params.txt'))
viol, mgain, nconstraints, gamma = params.read_params()
else:
params.makeParams(consize=nconstraints,
violable=viol,
mingain=mgain,
gamma=gam,
predefault=False)
simfunc.makeSimFiles(language)
print('running the baseline simulation using original training corpus')
simfunc.runBaselineSim(
basepath, reducemem=reducemem, rt_output_baseline=False
) #copies grammar, proj, tableau, maxentouptut in maxent2/temp/output_baseline
mbsublex.move_sublex_files(kind='output_baseline')
if not 'output_mbsublex_baseline' in dircontent:
print("Baseline simulation found at " +
os.path.join(maxentdir, 'output_baseline'))
#analyze resulting grammar.txt file for [-mb] constraints, and make projections
found_mb = mbsublex.search_grammar_for_mb()
if found_mb:
print('Making a sublexicon with one morph per line')
mbsublex.make_freewd_sublexicon(
) #renames curr corpus 'orig_corpus.txt', creates new corpus that consists of just morphologically simple words and is called 'corpus.txt'
print(
'Running a new baseline simulation using a sublexicon as training data'
)
if parameters:
params.scale_params(inpath=os.path.join(
basepath, 'data', language, 'params.txt'),
multiply_by=0.01,
keepconsize=True)
else:
params.scale_params(viol, gain, consize, gamma, 0.01,
True) #last one is keepconsize
simfunc.runBaselineSim(basepath,
reducemem=reducemem,
rt_output_baseline=False)
mbsublex.move_sublex_files(kind="output_mbsublex_baseline")
else:
print('Did not find any *X-mb-Y trigrams. Quitting now.')
return mbsublex.wrapSims(wrapstring, basepath, ret=True)
if not 'output_mbsublex' in dircontent:
print("Sublexicon baseline simulation found at " +
os.path.join(maxentdir, 'output_mbsublex'))
mbsublex.makeProjection(basepath, 'wb', mb=True)
print(
'projections found--running a projection simulation on morph sublexicon'
)
simfunc.runCustomSim(reducemem=reducemem, simtype='wb')
mbsublex.move_sublex_files(kind='output_mbsublex')
if not 'output_final' in dircontent:
mbsublex.rename_corpus_back()
print(
'now running a projection simulation on the original training corpus'
)
if parameters:
params.scale_params(inpath=os.path.join(basepath, 'data', language,
'params.txt'),
multiply_by=1,
keepconsize=True)
else:
params.scale_params(viol, gain, consize, gamma, 10, True)
simfunc.runCustomSim(reducemem=reducemem, simtype='wb')
mbsublex.move_sublex_files(kind='output_final')
print('done!')
try:
return mbsublex.wrapSims(wrapstring, basepath=maxentdir, ret=True)
except:
print("The simulation failed for some reason. Check the contents of " +
maxentdir + " to help with debugging.")