def load_classifier(auto_parse=False, fname=None):
if auto_parse:
ac = load_imported_data_for_antecedent(fname=fname)
else:
ac = AntecedentClassifier(0, 14, 15, 19, 20, 24)
ac.load_imported_data(fname=(AUTO_PARSE_NPY_DATA if auto_parse else GOLD_PARSE_FULL_NPY_DATA))
return ac
def load_classifier(auto_parse=False, fname=None):
if auto_parse:
ac = load_imported_data_for_antecedent(fname=fname)
else:
ac = AntecedentClassifier(0, 14, 15, 19, 20, 24)
ac.load_imported_data(fname=(
AUTO_PARSE_NPY_DATA if auto_parse else GOLD_PARSE_FULL_NPY_DATA))
return ac
def load_imported_data_for_antecedent(fname=AUTO_PARSE_NPY_DATA):
ac = AntecedentClassifier(0, 14, 15, 19, 20, 24)
print 'Loading NPY data from this file:',fname
data = np.load(fname)
ac.sentences = data[0]
ac.train_triggers = data[1]
ac.val_triggers = data[2]
ac.test_triggers = data[3]
for i,sentwords in enumerate(data[4]):
ac.sentences[i].words = sentwords
return ac
def load_imported_data_for_antecedent(fname=AUTO_PARSE_NPY_DATA):
ac = AntecedentClassifier(0, 14, 15, 19, 20, 24)
print 'Loading NPY data from this file:', fname
data = np.load(fname)
ac.sentences = data[0]
ac.train_triggers = data[1]
ac.val_triggers = data[2]
ac.test_triggers = data[3]
for i, sentwords in enumerate(data[4]):
ac.sentences[i].words = sentwords
return ac
c, lr, k = float(splitt[1][1:]), float(splitt[2][2:]), float(
splitt[3][1:])
combos.add((c, lr, k))
return combos
if __name__ == '__main__':
grid = build_grid([[0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1.0],
[0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1.0],
[int(argv[1])]])
completed = completed_combos()
print 'How much we need versus how much we did: %d, %d' % (len(grid),
len(completed))
a = AntecedentClassifier(0, 14, 15, 19, 20, 24)
a.initialize(['VP', wc.is_adjective, wc.is_verb],
seed=9001,
save=False,
load=True,
update=False)
for combo in grid:
if combo not in completed:
print "Current Params: ", combo
a.C = combo[0]
a.learn_rate = lambda x: combo[1]
name = 'NEWFEATURES_c%s_lr%s_k%s_' % (combo[0], combo[1], combo[2])
a.fit(epochs=100, k=combo[2])
a.make_graphs(name)
return ac
if __name__ == '__main__':
mrg = 'mrg' in argv
save_file = GOLD_PARSE_FULL_NPY_DATA if mrg else AUTO_PARSE_ALL_ANTS_NPY
results_save = 'final_results_ALL_TYPES_ALL_ANTS_WITH_LIU_c%s_lr%s.txt' % (
str(C), str(LR))
if 'gen2' in argv:
AUTO_PARSE_ALL_ANTS_NPY = AUTO_PARSE_ALL_ANTS_NPY[:-4] + '_antgen2.npy'
results_save = results_save[:-4] + '_antgen2.txt'
if 'build' in argv:
ac = AntecedentClassifier(0, 14, 15, 19, 20, 24)
ac.import_data(get_mrg=mrg)
# save_imported_data_for_antecedent(ac, fname=save_file)
# exit(0)
ac = load_imported_data_for_antecedent(fname=save_file)
ac.generate_possible_ants(
['VP', wc.is_predicative, wc.is_adjective, wc.is_verb],
filter=True)
ac.debug_ant_selection()
# save_imported_data_for_antecedent(ac, fname=save_file)
# exit(0)
ac.build_feature_vectors()
ac.normalize()
save_imported_data_for_antecedent(ac, fname=save_file)
for i,sentwords in enumerate(data[4]):
ac.sentences[i].words = sentwords
return ac
if __name__ == '__main__':
mrg = 'mrg' in argv
save_file = GOLD_PARSE_FULL_NPY_DATA if mrg else AUTO_PARSE_ALL_ANTS_NPY
results_save = 'final_results_ALL_TYPES_ALL_ANTS_WITH_LIU_c%s_lr%s.txt' %(str(C), str(LR))
if 'gen2' in argv:
AUTO_PARSE_ALL_ANTS_NPY = AUTO_PARSE_ALL_ANTS_NPY[:-4]+'_antgen2.npy'
results_save = results_save[:-4]+'_antgen2.txt'
if 'build' in argv:
ac = AntecedentClassifier(0,14,15,19,20,24)
ac.import_data(get_mrg=mrg)
# save_imported_data_for_antecedent(ac, fname=save_file)
# exit(0)
ac = load_imported_data_for_antecedent(fname=save_file)
ac.generate_possible_ants(['VP', wc.is_predicative, wc.is_adjective, wc.is_verb], filter=True)
ac.debug_ant_selection()
# save_imported_data_for_antecedent(ac, fname=save_file)
# exit(0)
ac.build_feature_vectors()
ac.normalize()
save_imported_data_for_antecedent(ac, fname=save_file)
if 'types' in argv:
splitt = fname.split('_')
c, lr, k = float(splitt[1][1:]), float(splitt[2][2:]), float(splitt[3][1:])
combos.add((c,lr,k))
return combos
if __name__ == '__main__':
grid = build_grid(
[[0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1.0],
[0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1.0],
[int(argv[1])]]
)
completed = completed_combos()
print 'How much we need versus how much we did: %d, %d'%(len(grid),len(completed))
a = AntecedentClassifier(0,14, 15,19, 20,24)
a.initialize(['VP', wc.is_adjective, wc.is_verb], seed=9001, save=False, load=True, update=False)
for combo in grid:
if combo not in completed:
print "Current Params: ",combo
a.C = combo[0]
a.learn_rate = lambda x: combo[1]
name = 'NEWFEATURES_c%s_lr%s_k%s_'%(combo[0], combo[1], combo[2])
a.fit(epochs=100, k=combo[2])
a.make_graphs(name)
a.log_results(name)
np.save('saved_weights/'+name, np.array(a.W_avg))
a.reset()
