correct = 0
for sentence in predicted:
for row in sentence:
word_cnt += 1
if row['chunk'] == row['pchunk']:
correct += 1
return correct / word_cnt
if __name__ == '__main__':
column_names = ['form', 'pos', 'chunk']
train_file = '../../../corpus/conll2000/train.txt'
test_file = '../../../corpus/conll2000/test.txt'
train_corpus = conll_reader.read_sentences(train_file)
train_corpus = conll_reader.split_rows(train_corpus, column_names)
test_corpus = conll_reader.read_sentences(test_file)
test_corpus = conll_reader.split_rows(test_corpus, column_names)
model = train(train_corpus)
predicted = predict(model, test_corpus)
accuracy = eval(predicted)
print("Accuracy", accuracy)
f_out = open('out', 'w', newline='\n')
# We write the word (form), part of speech (pos),
# gold-standard chunk (chunk), and predicted chunk (pchunk)
for sentence in predicted:
for row in sentence:
f_out.write(row['form'] + ' ' + row['pos'] + ' ' + row['chunk'] +
' ' + row['pchunk'] + '\n')
correct = 0
for sentence in predicted:
for row in sentence:
word_cnt += 1
if row['chunk'] == row['pchunk']:
correct += 1
return correct / word_cnt
if __name__ == '__main__':
column_names = ['form', 'pos', 'chunk']
train_file = '../../corpus/conll2000/train.txt'
test_file = '../../corpus/conll2000/test.txt'
train_corpus = conll_reader.read_sentences(train_file)
train_corpus = conll_reader.split_rows(train_corpus, column_names)
test_corpus = conll_reader.read_sentences(test_file)
test_corpus = conll_reader.split_rows(test_corpus, column_names)
model = train(train_corpus)
predicted = predict(model, test_corpus)
accuracy = eval(predicted)
print("Accuracy", accuracy)
f_out = open('out', 'w')
# We write the word (form), part of speech (pos),
# gold-standard chunk (chunk), and predicted chunk (pchunk)
for sentence in predicted:
for row in sentence:
f_out.write(row['form'] + ' ' + row['pos'] + ' ' +
row['chunk'] + ' ' + row['pchunk'] + '\n')