args=config,
use_cuda=torch.cuda.is_available())
train_df, eval_df = train_test_split(full,
test_size=0.1,
random_state=SEED * i)
model.train_model(train_df,
eval_df=eval_df,
precision=precision,
recall=recall,
f1=f1)
model = ClassificationModel(MODEL_TYPE,
config["best_model_dir"],
args=config,
use_cuda=torch.cuda.is_available())
predictions, raw_outputs = model.predict(dev_sentences)
dev_preds[:, i] = predictions
print("Completed Fold {}".format(i))
# select majority class of each instance (row)
dev_predictions = []
for row in dev_preds:
row = row.tolist()
dev_predictions.append(int(max(set(row), key=row.count)))
dev["predictions"] = dev_predictions
print("Precision: ",
precision(dev['labels'].tolist(), dev['predictions'].tolist()))
print("Recall: ", recall(dev['labels'].tolist(), dev['predictions'].tolist()))
num_labels=1,
use_cuda=torch.cuda.is_available())
train_df, eval_df = train_test_split(train,
test_size=0.2,
random_state=SEED * i)
model.train_model(train_df, eval_df=eval_df, mae=mean_absolute_error)
model = ClassificationModel(MODEL_TYPE,
config["best_model_dir"],
args=config,
num_labels=1,
use_cuda=torch.cuda.is_available())
for dev_sentences, test_sentences, dev_preds, test_preds in zip(
dev_sentences_list, test_sentences_list, dev_preds_list,
test_preds_list):
dev_predictions, dev_raw_outputs = model.predict(dev_sentences)
test_predictions, test_raw_outputs = model.predict(test_sentences)
dev_preds[:, i] = dev_predictions
test_preds[:, i] = test_predictions
for dev, dev_preds, test, test_preds in zip(dev_list, dev_preds_list,
test_list, test_preds_list):
dev['predictions'] = dev_preds.mean(axis=1)
test['predictions'] = test_preds.mean(axis=1)
for dev, test, language in zip(dev_list, test_list, [*languages]):
dev["run_id"] = MODEL_NAME
test["run_id"] = MODEL_NAME
dev = dev[['topic_id', 'tweet_id', "predictions", "run_id"]]
test = test[['topic_id', 'tweet_id', "predictions", "run_id"]]
use_cuda=torch.cuda.is_available())
train_df, eval_df = train_test_split(train,
test_size=0.1,
random_state=SEED * i)
model.train_model(train_df,
eval_df=eval_df,
precision=precision,
recall=recall,
f1=f1)
model = ClassificationModel(MODEL_TYPE,
config["best_model_dir"],
args=config,
use_cuda=torch.cuda.is_available())
# predict Arabic dev
ara_test_final_predictions, raw_outputs = model.predict(
dev_sentences_list[0])
ara_dev_preds[:, i] = ara_test_final_predictions
# predict Bulgarian dev
bul_test_final_predictions, raw_outputs = model.predict(
dev_sentences_list[1])
bul_dev_preds[:, i] = bul_test_final_predictions
# predict English dev
eng_test_final_predictions, raw_outputs = model.predict(
dev_sentences_list[2])
eng_dev_preds[:, i] = eng_test_final_predictions
# predict Arabic test
ara_test_predictions, raw_outputs = model.predict(test_sentences_list[0])
ara_test_preds[:, i] = ara_test_predictions