def __init__(self,
base_dataset: Dataset,
validation_dataset: Dataset,
base_network: torch.nn.Module,
device: torch.device,
scale: int = 1.0):
super(PULearningPHEMEDataset, self).__init__()
# Subset is used as the dataset
if type(base_dataset) == torch.utils.data.Subset:
self.tokenizer = base_dataset.dataset.tokenizer
indices = base_dataset.indices
orig_dataset = base_dataset.dataset.dataset.copy()
base_dataset = base_dataset.dataset
base_dataset.dataset = orig_dataset.iloc[indices]
base_dataset.dataset = base_dataset.dataset.reset_index(drop=True)
else:
self.tokenizer = base_dataset.tokenizer
# Only look at negative samples
original_dataset = base_dataset.dataset.copy()
base_dataset.dataset = base_dataset.dataset[
base_dataset.dataset['label'] == 0]
# Set the label to 1
base_dataset.dataset['label'] = [1] * base_dataset.dataset.shape[0]
# Get negatives weight, combine into one dataset and duplicate the negatives
train_dl = torch.utils.data.DataLoader(
base_dataset, batch_size=8, collate_fn=collate_batch_transformer)
val_dl = torch.utils.data.DataLoader(
validation_dataset,
batch_size=8,
collate_fn=collate_batch_transformer)
neg_weights = get_negative_sample_weights(train_dl, val_dl,
base_network, device)
assert neg_weights.shape == base_dataset.dataset.shape, "Should have double the number of negative sample weights"
weights = np.asarray([0.] * original_dataset.shape[0])
weights[original_dataset.index[original_dataset['label'] ==
1].tolist()] = 1.
weights[original_dataset.index[original_dataset['label'] ==
0].tolist()] = neg_weights[:, 0]
original_dataset['weight'] = weights
duplicated_data = base_dataset.dataset.copy()
duplicated_data['weight'] = neg_weights[:, 1]
self.dataset = pd.concat([original_dataset, duplicated_data],
ignore_index=True)
self.scale = scale
def __init__(self,
base_dataset: Dataset,
validation_dataset: Dataset,
base_network: torch.nn.Module,
device: torch.device,
gamma: float = 1.0,
scale: int = 1.0):
super(PULearningPriorBasedConversionPHEMEDataset, self).__init__()
train_dl = torch.utils.data.DataLoader(
base_dataset, batch_size=8, collate_fn=collate_batch_transformer)
val_dl = torch.utils.data.DataLoader(
validation_dataset,
batch_size=8,
collate_fn=collate_batch_transformer)
prior = estimate_class_prior_probability(base_network, train_dl,
val_dl, device)
print(prior)
# Subset is used as the dataset
if type(base_dataset) == torch.utils.data.Subset:
self.tokenizer = base_dataset.dataset.tokenizer
indices = base_dataset.indices
orig_dataset = base_dataset.dataset.dataset.copy()
base_dataset = base_dataset.dataset
base_dataset.dataset = orig_dataset.iloc[indices]
base_dataset.dataset = base_dataset.dataset.reset_index(drop=True)
else:
self.tokenizer = base_dataset.tokenizer
# Only look at negative samples
original_dataset = base_dataset.dataset.copy()
base_dataset.dataset = base_dataset.dataset[
base_dataset.dataset['label'] == 0]
# Get negatives weight, combine into one dataset and duplicate the negatives
train_dl = torch.utils.data.DataLoader(
base_dataset, batch_size=8, collate_fn=collate_batch_transformer)
val_dl = torch.utils.data.DataLoader(
validation_dataset,
batch_size=8,
collate_fn=collate_batch_transformer)
neg_weights = get_negative_sample_weights(train_dl, val_dl,
base_network, device)
assert neg_weights.shape == base_dataset.dataset.shape, "Should have double the number of negative sample weights"
positives = original_dataset[original_dataset['label'] == 1]
positives['weight'] = [1.] * positives.shape[0]
# Keep adding examples until p(y=1) equals our estimate
keep_examples = np.asarray([True] * neg_weights.shape[0])
ordered_idx = np.argsort(neg_weights[:, 1])[::-1]
i = 0
while (positives.shape[0] +
sum(~keep_examples)) / original_dataset.shape[0] < prior:
keep_examples[ordered_idx[i]] = False
i += 1
kept_negatives = base_dataset.dataset[keep_examples].copy()
kept_negatives_plus = kept_negatives.copy()
kept_negatives_plus['label'] = [1] * kept_negatives_plus.shape[0]
kept_negatives['weight'] = neg_weights[keep_examples, 0]
kept_negatives_plus['weight'] = neg_weights[keep_examples, 1]
converted_positives = base_dataset.dataset[~keep_examples].copy()
converted_positives['label'] = [1] * converted_positives.shape[0]
converted_positives['weight'] = [1.] * converted_positives.shape[0]
print(positives.shape)
print(kept_negatives.shape)
print(converted_positives.shape)
self.dataset = pd.concat([
positives, kept_negatives, kept_negatives_plus, converted_positives
],
ignore_index=True)
self.scale = scale