def correct_count(result_dict):
correct = 0
no_error_correct = 0
no_error_sentences = 0
correct_spot = 0
found = 0
missed_spans = 0
total_spans = 0
counted_as_no_err = 0
fce_data = fd.extract_data('fce_train.gold.max.rasp.old_cat.m2')
for key in result_dict.keys():
if -2 in result_dict[key]:
counted_as_no_err += 1
for sentence in fce_data:
spans_selected = []
if key == sentence[0][1:]:
found += 1
if len(sentence[1]) < 1:
no_error_sentences += 1
for start in result_dict[key]:
if start == -2 and len(sentence[1]) == 0:
correct += 1
no_error_correct += 1
else:
for i, span in enumerate(sentence[1]):
if int(start) >= span[0] and int(start) < span[1]:
correct_spot += 1
correct += 1
spans_selected.append(i)
missed_spans += len(sentence[1]) - len(
list(set(spans_selected)))
total_spans += len(sentence[1])
print('No error match: ', no_error_correct)
print('No error sentences: ', no_error_sentences)
print('Has no error answer: ', counted_as_no_err)
print('Error match: ', correct_spot)
print('Error missed: ', missed_spans)
print('Found sentences: ', found)
print('Total spans: ', total_spans)
return correct
rows=(len(error_sentences) + 1),
cols=1)
worksheet.update_acell('A1', 'Sentence')
counterOffset = 2
for sentence in _error_sentences:
worksheet.update_acell('A' + str(counterOffset), sentence[0])
counterOffset = counterOffset + 1
json_key = 'gspread-test.json'
scope = ['https://spreadsheets.google.com/feeds']
credentials = ServiceAccountCredentials.from_json_keyfile_name(json_key, scope)
gc = gspread.authorize(credentials)
spreadsheet = gc.open("FCE_ERR")
error_sentences = fd.extract_data('fce_train.gold.max.rasp.old_cat.m2')
threads = []
batch_size = 5000
batch_count = len(error_sentences) // batch_size
for i in range(batch_count):
t = threading.Thread(target=create_worksheet_sentence_batch,
args=(spreadsheet, "fce_errors" + str(i),
error_sentences[i * batch_size:(i + 1) *
batch_size]))
threads.append(t)
t.start()
import tensorflow as tf
import sklearn as sk
import sklearn.metrics as skm
import numpy as np
import math
import fce_api as fd
import re
import matplotlib.pyplot as plt
# variables
# data
data = fd.extract_data('fce_train.gold.max.rasp.old_cat.m2')
window_size = 3
labels = []
PAD = 0
display_step = 1
# classes
has_error = 1
no_error = 0
# learning variables
learning_rate = 0.01
epochs = 50
# generating the word windows, including the spaces.
def feed_windows_with_spaces(_data, _window_size):
windows = []
# general variables
window_size = 5
# classes
has_error = 1
no_error = 0
# # training data
# training_data = fd.extract_data_from_tsv('fce-public.train.original.tsv')
#
# # dev data
# dev_data = fd.extract_data_from_tsv('fce-public.dev.original.tsv')
# amt golden data
amt_golden = fd.extract_data(
'amt_data_sets/fce_amt.experiment_two.max.rasp.m2')
# amt non-expert data
amt_non_expert = fd.extract_data(
'amt_data_sets/fce_amt.experiment_two.max.rasp.m2')
# omitting the spaces
e_feed_windows = feed_windows_only_tokens(amt_golden, window_size)
ne_feed_windows = feed_windows_only_tokens(amt_non_expert, window_size)
labels = []
PAD = 0.0
OOV = 1.0
display_step = 1