def test_bio_f_score():
# Check against putputs from the "conlleval" Perl script from CoNLL 2002.
examples = [("OBIO", "OBIO", 1.), ("BII", "OBI", 0.), ("BB", "BI", 0.),
("BBII", "BBBB", 1 / 3.), ("BOOBIB", "BOBOOB", 2 / 3.),
("B-PER I-PER O B-PER I-PER O O B-LOC O".split(),
"B-LOC I-LOC O B-PER I-PER O O B-LOC I-LOC".split(), 1 / 3.)]
for y_true, y_pred, score in examples:
y_true = list(y_true)
y_pred = list(y_pred)
assert_equal(score, bio_f_score(y_true, y_pred))
def test_bio_f_score():
# Outputs from with the "conlleval" Perl script from CoNLL 2002.
examples = [
("OBIO", "OBIO", 1.),
("BII", "OBI", 0.),
("BB", "BI", 0.),
("BBII", "BBBB", 1 / 3.),
("BOOBIB", "BOBOOB", 2 / 3.),
]
for y_true, y_pred, score in examples:
y_true = list(y_true)
y_pred = list(y_pred)
assert_equal(score, bio_f_score(y_true, y_pred))
def test_bio_f_score():
# Check against putputs from the "conlleval" Perl script from CoNLL 2002.
examples = [
("OBIO", "OBIO", 1.),
("BII", "OBI", 0.),
("BB", "BI", 0.),
("BBII", "BBBB", 1 / 3.),
("BOOBIB", "BOBOOB", 2 / 3.),
("B-PER I-PER O B-PER I-PER O O B-LOC O".split(),
"B-LOC I-LOC O B-PER I-PER O O B-LOC I-LOC".split(),
1 / 3.)
]
for y_true, y_pred, score in examples:
y_true = list(y_true)
y_pred = list(y_pred)
assert_equal(score, bio_f_score(y_true, y_pred))
def train_model():
print "Loading training data..."
X_train, y_train, lengths_train = load_conll(os.path.join( current_dir, "./../data/train.conll"), features)
clf = StructuredPerceptron(verbose=True,max_iter = 10)
describe(X_train, lengths_train)
print "Loading test data..."
X_test, y_test, lengths_test = load_conll(os.path.join( current_dir, "./../data/test.conll"), features)
describe(X_test, lengths_test)
print("Training %s" % clf)
clf.fit(X_train, y_train, lengths_train)
y_pred = clf.predict(X_test, lengths_test)
print("Accuracy: %.3f" % (100 * accuracy_score(y_test, y_pred)))
print("CoNLL F1: %.3f" % (100 * bio_f_score(y_test, y_pred)))
return clf
def analyze_results(y_true,y_pred):
print len(y_true), len(y_pred)
#for v in ['B-Iden','B-Ind']:
print("Accuracy: %.3f" % (100 * accuracy_score(y_true, y_pred)))
print("CoNLL F1: %.3f" % (100 * bio_f_score(y_true, y_pred)))
got_id = 0
tot_true_id = 0
tot_false_id = 0
for i, lab in enumerate(y_true):
if lab != 'O':
tot_true_id +=1
if y_pred[i] != 'O':
tot_false_id += 1
if lab != 'O' and y_pred[i] != 'O':
got_id +=1
if tot_true_id > 0 and tot_false_id > 0:
print got_id/float(tot_true_id), got_id/float(tot_false_id)
def train_model():
print "Loading training data..."
X_train, y_train, lengths_train = load_conll(
os.path.join(current_dir, "./../data/train.conll"), features)
clf = StructuredPerceptron(verbose=True, max_iter=10)
describe(X_train, lengths_train)
print "Loading test data..."
X_test, y_test, lengths_test = load_conll(
os.path.join(current_dir, "./../data/test.conll"), features)
describe(X_test, lengths_test)
print("Training %s" % clf)
clf.fit(X_train, y_train, lengths_train)
y_pred = clf.predict(X_test, lengths_test)
print("Accuracy: %.3f" % (100 * accuracy_score(y_test, y_pred)))
print("CoNLL F1: %.3f" % (100 * bio_f_score(y_test, y_pred)))
return clf
test_files = [f for i, f in enumerate(files) if i % 5 == 0]
test = load_conll(fileinput.input(test_files), features)
X_test, _, lengths_test = test
describe(X_test, lengths_test)
return train, test
if __name__ == "__main__":
print(__doc__)
#print("Loading training data...", end=" ")
#X_train, y_train, lengths_train = load_conll(sys.argv[1], features)
#describe(X_train, lengths_train)
train, test = load_data()
X_train, y_train, lengths_train = train
X_test, y_test, lengths_test = test
#print("Loading test data...", end=" ")
#X_test, y_test, lengths_test = load_conll(sys.argv[2], features)
#describe(X_test, lengths_test)
clf = StructuredPerceptron(verbose=True, max_iter=10)
print("Training %s" % clf)
clf.fit(X_train, y_train, lengths_train)
y_pred = clf.predict(X_test, lengths_test)
print("Accuracy: %.3f" % (100 * accuracy_score(y_test, y_pred)))
print("CoNLL F1: %.3f" % (100 * bio_f_score(y_test, y_pred)))
yield "folUpper"
if re.search(r"\d", nnp.lower()):
yield "folNumber"
yield "folword=" + nnp.lower()
if p.isupper() and len(p) == 3:
yield "Uppercase"
if re.search(r"\d", p.lower()):
yield "Number"
if len(p) > 8: # check if current word is unusually long
yield "Long"
if __name__ == '__main__':
train_path = "../Data/bio-ner/train"
dev_path = "../Data/bio-ner/dev"
# create_file(train_path, "train")
# create_file(dev_path, "dev")
X_train, y_train, l_train = load_conll("train", features)
X_test, y_test, l_test = load_conll("dev", features)
per = StructuredPerceptron(lr_exponent=0.15, max_iter=300, verbose=1)
per.fit(X_train, y_train, l_train)
y_p = per.predict(X_test, l_test)
# for x in zip(y_p, y_test):
# print(x)
print(bio_f_score(y_test, y_p))
test_files = [f for i, f in enumerate(files) if i % 5 == 0]
test = load_conll(fileinput.input(test_files), features)
X_test, _, lengths_test = test
describe(X_test, lengths_test)
return train, test
if __name__ == "__main__":
print(__doc__)
#print("Loading training data...", end=" ")
#X_train, y_train, lengths_train = load_conll(sys.argv[1], features)
#describe(X_train, lengths_train)
train, test = load_data()
X_train, y_train, lengths_train = train
X_test, y_test, lengths_test = test
#print("Loading test data...", end=" ")
#X_test, y_test, lengths_test = load_conll(sys.argv[2], features)
#describe(X_test, lengths_test)
clf = StructuredPerceptron(verbose=True, max_iter=10)
print("Training %s" % clf)
clf.fit(X_train, y_train, lengths_train)
y_pred = clf.predict(X_test, lengths_test)
print("Accuracy: %.3f" % (100 * accuracy_score(y_test, y_pred)))
print("CoNLL F1: %.3f" % (100 * bio_f_score(y_test, y_pred)))
def get_bio_f1(y_true, y_pred, label_mapping=None):
str_true, str_pred = int_to_str(y_true, y_pred, label_mapping)
fscore = bio_f_score(str_true, str_pred)
return fscore
def bio_f1_crf(y_true, y_pred):
y_true = flatten_y(y_true)
y_pred = flatten_y(y_pred)
return bio_f_score(y_true, y_pred)
if s.isalpha():
predict_seq.append(s)
file.close()
file = open("predict_seq.txt", "w")
for ch in predict_seq:
c = ch.join(' ')
file.write(c)
file.write('\n')
file.close()
X_test, y_test, lengths_test = load_conll("predict_seq.txt", features)
y_pred = clf.predict(X_test, lengths_test)
print(bio_f_score(y_test, y_pred))
print(lengths_test)
print(X_test)
print(y_test)
file = open(output_list_name[count], "w")
for i in y_pred:
file.write(i)
#file.write(np.array2string(i, precision=2, separator=','))
file.close()
count += 1
predict_seq.clear()
kf = KFold(p.L.shape[0], n_folds=2)
for train_ids, test_ids in kf:
L_train = p.L[train_ids]
L_test = p.L[test_ids]
X_train = np.zeros((0, p.X.shape[1]))
y_train = np.zeros((0,))
X_test = np.zeros((0, p.X.shape[1]))
y_test = np.zeros((0,))
for i, l in enumerate(L_train):
start = sum(L_train[:i])
end = sum(L_train[:i+1])
X_train = np.vstack([X_train, p.X[start:end]])
y_train = np.append(y_train, p.Y[start:end])
for i, l in enumerate(L_test):
start = sum(L_test[:i])
end = sum(L_test[:i+1])
X_test = np.vstack([X_test, p.X[start:end]])
y_test = np.append(y_test, p.Y[start:end])
clf = StructuredPerceptron()
clf.fit(X_train, y_train, L_train)
y_pred = clf.predict(X_test, L_test)
print("The Bio Score for Kfold = %s" % bio_f_score(y_test, y_pred))
