def apply_GenMod(L_train):
"""
Applies generative model on label matrix
:param L_train: Label matrix
:return: None
"""
gen_model = GenerativeModel()
# gen_model.train(L_train, epochs=100, decay=0.95, step_size=0.1 / L_train.shape[0], reg_param=1e-6)
gen_model.train(L_train, cardinality=3)
# print(gen_model.weights.lf_accuracy)
train_marginals = gen_model.marginals(L_train)
report.append('\n#Gen Model Stats\n')
report.append(gen_model.learned_lf_stats().to_csv(sep=' ', index=False, header=True))
save_marginals(session, L_train, train_marginals)
def score_gen_model(predicate_resume,
session,
gen_model_name=None,
parallelism=16):
if gen_model_name is None:
model_name = "G" + predicate_resume["predicate_name"] + "Latest"
logging.info("Stats logging")
key_group = predicate_resume["label_group"]
train_cids_query = get_train_cids_with_span(predicate_resume, session)
L_train = load_ltrain(predicate_resume, session)
gen_model = GenerativeModel()
gen_model.load(model_name)
gen_model.train(L_train,
epochs=100,
decay=0.95,
step_size=0.1 / L_train.shape[0],
reg_param=1e-6)
logging.info(gen_model.weights.lf_accuracy)
print(gen_model.weights.lf_accuracy)
train_marginals = gen_model.marginals(L_train)
fig = plt.figure()
#hist=plt.hist(train_marginals, bins=20)
#plt.savefig("plt"+strftime("%d-%m-%Y_%H_%M_%S", gmtime())+".png", dpi=fig.dpi)
gen_model.learned_lf_stats()
def score_lfs(predicate_resume,
L_gold_test,
session,
date_time,
parallelism=8):
dump_file_path = "./results/" + "lfs_1_" + predicate_resume[
"predicate_name"] + date_time + ".csv"
key_group = predicate_resume["label_group"]
LFs = get_labelling_functions(predicate_resume)
labeler = LabelAnnotator(lfs=LFs)
test_cids_query = get_test_cids_with_span(predicate_resume, session)
L_test = labeler.apply(parallelism=parallelism,
cids_query=test_cids_query,
key_group=key_group,
clear=True,
replace_key_set=False)
data_frame = L_test.lf_stats(session)
print(data_frame)
logging.info(data_frame)
data_frame.to_csv(dump_file_path)
gen_model = GenerativeModel()
gen_model.train(L_test,
epochs=100,
decay=0.95,
step_size=0.1 / L_test.shape[0],
reg_param=1e-6)
p, r, f1 = gen_model.score(L_test, L_gold_test)
print("Prec: {0:.3f}, Recall: {1:.3f}, F1 Score: {2:.3f}".format(p, r, f1))
logging.info("Prec: {0:.3f}, Recall: {1:.3f}, F1 Score: {2:.3f}".format(
p, r, f1))
dump_file_path1 = "./results/" + "test_gen_1_" + predicate_resume[
"predicate_name"] + date_time + ".csv"
with open(dump_file_path1, 'w+b') as f:
writer = csv.writer(f, delimiter=',', quoting=csv.QUOTE_MINIMAL)
writer.writerow(["Precision", "Recall", "F1"])
writer.writerow(
["{0:.3f}".format(p), "{0:.3f}".format(r), "{0:.3f}".format(f1)])
test_marginals = gen_model.marginals(L_test)
dump_file_path2 = "./results/" + "plt_1_" + predicate_resume[
"predicate_name"] + date_time + ".csv"
#plt.hist(test_marginals, bins=20)
#plt.savefig(dump_file_path2)
#plt.show()
dump_file_path3 = "./results/" + "gen_2_" + predicate_resume[
"predicate_name"] + date_time + ".csv"
data_frame3 = gen_model.learned_lf_stats()
data_frame3.to_csv(dump_file_path3)
dump_file_path4 = "./results/" + "gen_3_" + predicate_resume[
"predicate_name"] + date_time + ".csv"
tp, fp, tn, fn = gen_model.error_analysis(session, L_test, L_gold_test)
with open(dump_file_path4, 'w+b') as f:
writer = csv.writer(f, delimiter=',', quoting=csv.QUOTE_MINIMAL)
writer.writerow(["TP", "FP", "TN", "FN"])
writer.writerow(
[str(len(tp)),
str(len(fp)),
str(len(tn)),
str(len(fn))])
dump_file_path5 = "./results/" + "gen_4_" + predicate_resume[
"predicate_name"] + date_time + ".csv"
data_frame4 = L_test.lf_stats(session, L_gold_test,
gen_model.learned_lf_stats()['Accuracy'])
data_frame4.to_csv(dump_file_path5)
print(L_train.lf_stats(session))
# generative model, training_marginals are probabilistic training labels
gen_model = GenerativeModel()
gen_model.train(L_train, epochs=100, decay=0.95, step_size=0.1 / L_train.shape[0], reg_param=1e-6)
print(gen_model.weights.lf_accuracy)
train_marginals = gen_model.marginals(L_train)
plt.hist(train_marginals, bins=20)
plt.show()
print(gen_model.learned_lf_stats())
#L_dev = labeler.apply_existing()
##### writing down labels
matchpath='/Users/marcel/Documents/RECHERCHE/STUDENTS/Willeme/sqlshare-cuts-snorkel-tmp.csv'
#matchpath='/Users/marcel/Documents/RECHERCHE/STUDENTS/Willeme/check_match.csv'
with open(matchpath, mode='w') as match_file:
match_writer = csv.writer(match_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
match_writer.writerow(['idSession','idQuery','cut'])
i=0
for c in session.query(pairs):
#print('i=',i)
# In[ ]:
from snorkel.learning import GenerativeModel
gen_model = GenerativeModel()
get_ipython().magic(
u'time gen_model.train(L_train, epochs=10, decay=0.95, step_size=0.1 / L_train.shape[0], reg_param=1e-6, threads=50, verbose=True)'
)
# In[ ]:
get_ipython().magic(u'time train_marginals = gen_model.marginals(L_train)')
# In[ ]:
gen_model.learned_lf_stats()
# In[ ]:
plt.hist(train_marginals, bins=20)
plt.title("Training Marginals for Gibbs Sampler")
plt.show()
# # Save Training Marginals
# Save the training marginals for [Notebook 4](4.data-disc-model).
# In[ ]:
get_ipython().magic(u'time save_marginals(session, L_train, train_marginals)')
for L in [L_train_BC, L_train_BD, L_train_BD, L_train_BD]:
ds = DependencySelector()
deps = ds.select(L, threshold=0.1)
len(deps)
Ldeps.append(deps)
gen_model = GenerativeModel(lf_propensity=True)
gen_model.train(L_train,
deps=deps,
decay=0.95,
step_size=0.1 / L_train.shape[0],
reg_param=0.0)
train_marginals = gen_model.marginals(L_train)
plt.hist(train_marginals, bins=20)
plt.show()
gen_model.learned_lf_stats()
save_marginals(session, L_train, train_marginals)
load_external_labels(session,
BiomarkerCondition,
'Biomarker',
'Condition',
'articles/disease_gold_labels.tsv',
dev_cands,
annotator_name='gold')
L_gold_dev = load_gold_labels(session, annotator_name='gold', split=1)
L_gold_dev
L_dev = labeler.apply_existing(split=1)
_ = gen_model.score(session, L_dev, L_gold_dev)
L_dev.lf_stats(session, L_gold_dev, gen_model.learned_lf_stats()['Accuracy'])