def transform(input_path, output_path):
dataset = csv_handler.csv_readlines(input_path)
dataset = dataset[1:]
dataset = transformer.map_func(
range(len(dataset)), lambda i: (i, dataset[i][0], 1
if dataset[i][1] == "True" else 0))
csv_handler.csv_writelines(output_path, dataset)
def bert_estimate(input_path, text_col, output_path, model_dir, gpu,
with_header):
# assign GPU
os.environ['CUDA_VISIBLE_DEVICES'] = gpu
# load model
if model_dir == '':
model_dir = os.path.join(os.environ['FACTMINE_HOME'],
'cache/company_model')
print("Loading model from %s ...\n" % (model_dir))
model = BertModel(model_dir)
print("Calculating negative score, positive score, and argmax class...\n")
dataset = csv_handler.csv_readlines(input_path)
header = None
if with_header == True:
header = dataset[0]
dataset = dataset[1:]
text_col = text_col - 1
texts = transform.map_func(dataset, lambda row: row[text_col])
preds = model.predict(texts)
assert (len(dataset) == len(preds))
# apply sigmoid
preds = transform.map_func(
preds, lambda quad:
[util.sigmoid(quad[0]),
util.sigmoid(quad[1]), quad[2], quad[3]])
for i in range(len(dataset)):
dataset[i].append(preds[i][0])
dataset[i].append(preds[i][1])
dataset[i].append(preds[i][2])
if with_header == True:
header.append('score_0')
header.append('score_1')
header.append('arg_class')
dataset = [header] + dataset
csv_handler.csv_writelines(output_path, dataset)
if output_path != "":
print("Finished, Results are ready at %s " % (output_path))
def extract(data, typename):
dataset = csv_handler.csv_readlines("./dataset/" + data + "set.csv")
dataset = transformer.indexleft_func(dataset)
dataset = transformer.map_func(dataset, lambda row:
(row[0], row[1][1], row[1][2]))
output_path = "./" + data + ".csv"
def e_func(triplet):
label = 0
if triplet[2] == typename:
label = 1
return (triplet[0], triplet[1], label)
final = transformer.map_func(dataset, lambda triplet: e_func(triplet))
csv_handler.csv_writelines(output_path, final)
def max_balancer(input_csv_path, output_csv_path='./output.csv'):
dataset = csv_handler.csv_readlines(input_csv_path)
pos_dataset = transform.filter_func(dataset, lambda row: row[2] == '1')
neg_dataset = transform.filter_func(dataset, lambda row: row[2] == '0')
assert (len(pos_dataset) <= len(neg_dataset))
sampler = Sampler()
neg_dataset = sampler.sample_rows(neg_dataset, len(pos_dataset))
pos_ids = transform.map_func(pos_dataset, lambda row: row[0])
neg_ids = transform.map_func(neg_dataset, lambda row: row[0])
select_id_set = set(pos_ids + neg_ids)
final = transform.filter_func(dataset, lambda row: row[0] in select_id_set)
csv_handler.csv_writelines(output_csv_path, final)
def extract(data, typename):
dataset = csv_handler.csv_readlines("./dataset/" + data + "_raw.csv")
output_path = "./" + data + ".csv"
def func_1(triplet):
label = 0
if triplet[2] == typename:
label = 1
return (triplet[0], triplet[1], label)
e_func = func_1
def func_2(triplet):
label = 1
if triplet[2] == typename:
label = 0
return (triplet[0], triplet[1], label)
if typename == 'NoArgument':
e_func = func_2
final = transformer.map_func(dataset, lambda triplet: e_func(triplet))
csv_handler.csv_writelines(output_path, final)
def evaluate(input_path, col_true, col_pred, metric, output_path, with_header):
'''evaluate the quality of predictions with a metric (f1 by default), and output the metric scores'''
result = []
dataset = csv_handler.csv_readlines(input_path)
if with_header == True:
dataset = dataset[1:]
col_true = int(col_true) - 1
col_pred = int(col_pred) - 1
y_true = transform.map_func(dataset, lambda row : int(row[col_true]))
y_pred = transform.map_func(dataset, lambda row : int(row[col_pred]))
def check_validity(class_array):
for cls in class_array:
assert(cls == 0 or cls == 1)
check_validity(y_true)
check_validity(y_pred)
support_set = {'f1', 'accuracy', 'cohen', 'quad'}
if metric not in support_set:
sys.exit('please specify a valid metric in terms of f1, accuracy, cohen, or quad (i.e. precision_recall_fscore_support)')
elif metric == 'f1':
result.append(['f1'])
result.append([f1_score(y_true, y_pred)])
elif metric == 'accuracy':
result.append(['accuracy'])
result.append([accuracy_score(y_true, y_pred)])
elif metric == 'cohen':
result.append([cohen_kappa_score(y_true, y_pred)])
elif metric == 'quad':
(precision, recall, fscore, support) = precision_recall_fscore_support(y_true, y_pred)
result.append(['class', 'precision', 'recall', 'fscore', 'support'])
result.append([0, precision[0], recall[0], fscore[0], support[0]])
result.append([1, precision[1], recall[1], fscore[1], support[1]])
csv_handler.csv_writelines(output_path, result)
def write_preds(ori_preds, labels, dev_path , output_path = "./tmp.csv"):
eval_examples = csv_handler.csv_readlines(dev_path)
assert(len(ori_preds) == len(labels))
assert(len(ori_preds) == len(eval_examples))
# append header
header = ['id', 'sent', 'label']
for i in range(len(ori_preds[0])):
header.append('p' + str(i))
header.append('pred')
final = []
final.append(header)
# append data
for i in range(len(labels)):
row = []
sent_id = eval_examples[i][0]
sent = eval_examples[i][1]
sent_label = int(eval_examples[i][2])
assert(sent_label == labels[i])
row.append(sent_id)
row.append(sent)
row.append(sent_label)
for j in range(len(ori_preds[i])):
row.append(ori_preds[i][j])
pred_label = np.argmax(ori_preds[i])
row.append(pred_label)
final.append(row)
csv_handler.csv_writelines(output_path, final)
examples = []
for (i, txt) in enumerate(batch):
guid = "%s" % (i)
text_a = txt
label = self.dummy_label
examples.append(
InputExample(guid=guid, text_a=text_a, text_b=None, label=label))
return examples
if __name__ == "__main__":
data_path = sys.argv[1]
model_dir = sys.argv[2]
output_path = sys.argv[3]
# load test dataset
raw_dataset = csv_handler.csv_readlines(data_path)
ids = transform.map_func(raw_dataset, lambda row : row[0])
texts = transform.map_func(raw_dataset, lambda row : row[1])
# load model
model = BertModel(model_dir)
pred = model.predict(texts, 100)
assert(len(ids) == len(pred))
output = transform.map_func(range(len(ids)), lambda idx : [ids[idx]] + pred[idx])
csv_handler.csv_writelines(output_path, output)
return (rid, sent, label, split)
records = transformer.map_func(range(len(records)),
lambda i: row_functor(i, records))
print(len(records))
dataset = dataset + records[1:]
print(len(dataset))
print(dataset[0])
def select(split, dataset):
final = transformer.filter_func(dataset, lambda row: row[3] == split)
final = transformer.map_func(final, lambda row: (row[0], row[1], row[2]))
return final
train_set = select("train", dataset)
print(len(train_set))
dev_set = select("test", dataset)
print(len(dev_set))
val_set = select("val", dataset)
print(len(val_set))
csv_handler.csv_writelines(data_root + "/train_raw.csv", train_set)
csv_handler.csv_writelines(data_root + "/dev_raw.csv", dev_set)
csv_handler.csv_writelines(data_root + "/val_raw.csv", val_set)
#('clf', LogisticRegression(class_weight='balanced', random_state=seed, solver='liblinear')),
('clf', LogisticRegression(random_state=seed, solver='liblinear')),
])
text_clf.fit(X_train, y_train)
train_finish_time = time.time()
train_duration = train_finish_time - start_time
print("train time is " + str(train_finish_time - start_time))
print("predicting...")
predicted = text_clf.predict(X_dev)
predicted_proba = text_clf.predict_proba(X_dev)
assert (len(predicted_proba) == len(X_dev))
assert (len(X_dev) == len(y_dev))
print("logging...")
csv_handler.append_row(output_path,
['score_0', 'score_1', 'predict', 'text', 'ground'])
result = []
for i in range(len(predicted_proba)):
score_0 = predicted_proba[i][0]
score_1 = predicted_proba[i][1]
predict = predicted[i]
text = X_dev[i]
ground = y_dev[i]
result.append([score_0, score_1, predict, text, ground])
csv_handler.csv_writelines(output_path, result)
train_test_ids.sort()
assert (anno_ids == train_test_ids)
id_to_file = transformer.map_func(files, lambda file: (get_id(file), file))
id_to_file = dict(id_to_file)
def extractor(anno_dir, id_to_file, paper_id):
file_path = anno_dir + id_to_file[paper_id]
label_sent_dataset = csv_handler.csv_readlines(file_path, delimit='\t')
indexed_result = transformer.indexleft_func(label_sent_dataset)
final = transformer.map_func(
indexed_result, lambda p:
(paper_id + "_" + str(p[0]), p[1][1], p[1][0]))
return final
tmp = extractor(anno_dir, id_to_file, 'r18RxrXlG')
transformer.print_rows(tmp, 3)
train_dataset = transformer.flatmap_func(
train_id_dataset,
lambda paper_id: extractor(anno_dir, id_to_file, paper_id))
csv_handler.csv_writelines(train_output_path, train_dataset)
test_dataset = transformer.flatmap_func(
test_id_dataset,
lambda paper_id: extractor(anno_dir, id_to_file, paper_id))
csv_handler.csv_writelines(test_output_path, test_dataset)
import transform as transform
import csv_handler as csv_handler
if __name__ == "__main__":
result = []
first_file = sys.argv[1]
first_idx = sys.argv[2].split(',')
first_idx = transform.map_func(first_idx, lambda idx: int(idx))
second_file = sys.argv[3]
second_idx = sys.argv[4].split(',')
second_idx = transform.map_func(second_idx, lambda idx: int(idx))
output_csv_file = sys.argv[5]
first_dataset = csv_handler.csv_readlines(first_file)
result = transform.map_func(first_dataset,
lambda row: [row[idx] for idx in first_idx])
second_dataset = csv_handler.csv_readlines(second_file)
second_result = transform.map_func(
second_dataset, lambda row: [row[idx] for idx in second_idx])
assert (len(first_dataset) == len(second_dataset))
final = transform.map_func(zip(result, second_result),
lambda p: p[0] + p[1])
csv_handler.csv_writelines(output_csv_file, final)
# get idx for review_id, text, and funny_count
def get_triplet_idx(header):
idx_id = header.index('review_id')
idx_text = header.index('text')
idx_count = header.index('funny')
return (idx_id, idx_text, idx_count)
def selector(row, idx_id, idx_text, idx_count):
r_id = row[idx_id]
text = row[idx_text]
funny_count = int(row[idx_count])
is_funny = None
if (funny_count >= 5):
is_funny = 1
elif (funny_count == 0):
is_funny = 0
return (r_id, text, is_funny)
(idx_id, idx_text, idx_count) = get_triplet_idx(dataset[0])
selected_datasets = transformer.map_func(
dataset[1:], lambda line: selector(line, idx_id, idx_text, idx_count))
final_datasets = transformer.filter_func(selected_datasets,
lambda row: row[2] != None)
csv_handler.csv_writelines(review_output_path, final_datasets)
elif num_true == 1:
assert (num_false == 0)
line = line.replace('"has_spoiler": true,', '"has_spoiler": "true",')
else:
assert (False)
line = json.loads(line)
return line
json_dataset = transformer.map_func(dataset, lambda line: format_func(line))
id_sents = transformer.map_func(
json_dataset, lambda jsn: (jsn['review_id'], jsn['review_sentences']))
def flat_sents_func(review_id, sents):
result = []
for i in range(len(sents)):
sent_id = review_id + "###" + str(i)
sent_text = sents[i][1]
sent_label = sents[i][0]
result.append((sent_id, sent_text, sent_label))
return result
final_sents = transformer.flatmap_func(id_sents,
lambda p: flat_sents_func(p[0], p[1]))
csv_handler.csv_writelines(output_path, final_sents)
