def eval_hc_train(hc, labels, print_err = False):
"""
evaluate in the train set
:param hc:
:param labels:
:return:
"""
n = len(hc.res)
tp = 0
fp = 0
fn = 0
for i in range(n):
if len(hc.data.sentences[i]) > 0:
(x, y, z) = eval_ner(util.get_lab(
hc.data.sentences[i]), hc.res[i], labels)
tp += x
fp += y
fn += z
try:
pre = tp * 1.0 / (tp + fp)
rec = tp * 1.0 / (tp + fn)
f = 2.0 * pre * rec / (pre + rec)
print pre, rec, f
except ZeroDivisionError:
print "DIV BY 0 ", tp, fp, fn
def eval_hc_test(hc, features, labels, print_err=False, decoder='hc'):
"""
evaluate in the train set
:param hc:
:param labels:
:return:
"""
tp = 0
fp = 0
fn = 0
dirname = "testa"
input = []
for file in os.listdir(dirname):
# print file
if file.endswith(".txt"):
f = open(os.path.join(dirname, file))
l = list(f)
input.extend(l)
f.close()
# return input
sentences = util.extract(input, features, labels, keep_word = True)
# return sentences
for sen in sentences:
if True:
# if not has_oov(sen):
#predicted = hc.decode(util.get_obs(sen))
predicted = get_tag(hc, sen, features, decoder)
(x, y, z) = eval_ner(util.get_lab(sen), predicted, labels)
tp += x
fp += y
fn += z
if print_err:
if y + z > 0:
print "sen: ", util.get_words(sen, features) + " OOV = " + str(has_oov(sen))
print "true labels: ", util.get_lab_name(util.get_lab(sen), labels)
print "predicted: ", util.get_lab_name(predicted, labels)
try:
pre = tp * 1.0 / (tp + fp)
rec = tp * 1.0 / (tp + fn)
f = 2.0 * pre * rec / (pre + rec)
print pre, rec, f
except ZeroDivisionError:
print "DIV BY 0 ", tp, fp, fn
def run_test(test, h):
cnt = 0
correct = 0
for s in test:
x = util.get_obs(s)
g = util.get_lab(s)
p = h.decode(x)
for i, j in zip(g, p):
cnt += 1
if i == j:
correct += 1
print correct * 1.0 / cnt