def deanonymize_dataset(
rg_path: str,
standardized_dataset: Dataset,
processed_dataset_path: str = None,
n_samples: int = None,
):
"""Take an anonymized dataset and add back the original dataset columns."""
assert processed_dataset_path is not None, \
"Please specify a path to save the dataset."
# Load the dataset
dataset = Dataset.load_from_disk(rg_path)
if n_samples:
dataset.set_visible_rows(list(range(n_samples)))
standardized_dataset.set_visible_rows(list(range(n_samples)))
text_columns = []
# Add columns from the standardized dataset
dataset.add_column('document', standardized_dataset['document'])
text_columns.append('document')
if 'summary:reference' in standardized_dataset.column_names:
dataset.add_column('summary:reference',
standardized_dataset['summary:reference'])
text_columns.append('summary:reference')
# Preprocessing all the text columns
dataset = dataset.update(
lambda x: {
f'preprocessed_{k}': x[k] if args.no_clean else clean_text(x[k])
for k in text_columns
})
# Run the Spacy pipeline on all preprocessed text columns
try:
nlp = load('en_core_web_lg')
except OSError:
nlp = load('en_core_web_sm')
nlp.add_pipe('sentencizer', before="parser")
spacy = Spacy(nlp=nlp)
dataset = spacy(
dataset,
[f'preprocessed_{col}' for col in text_columns],
batch_size=100,
)
# Directly save to disk
dataset.save_to_disk(processed_dataset_path)
return dataset
def run_workflow(
jsonl_path: str = None,
dataset: Dataset = None,
doc_column: str = None,
reference_column: str = None,
summary_columns: List[str] = None,
bert_aligner_threshold: float = 0.5,
bert_aligner_top_k: int = 3,
embedding_aligner_threshold: float = 0.5,
embedding_aligner_top_k: int = 3,
processed_dataset_path: str = None,
n_samples: int = None,
anonymize: bool = False,
):
assert (jsonl_path is None) != (dataset is None), \
"One of `jsonl_path` and `dataset` must be specified."
assert processed_dataset_path is not None, \
"Please specify a path to save the dataset."
# Load the dataset
if jsonl_path is not None:
dataset = Dataset.from_jsonl(jsonl_path)
if doc_column is None:
# Assume `doc_column` is called "document"
doc_column = 'document'
assert doc_column in dataset.column_names, \
f"`doc_column={doc_column}` is not a column in dataset."
print("Assuming `doc_column` is called 'document'.")
if reference_column is None:
# Assume `reference_column` is called "summary:reference"
reference_column = 'summary:reference'
print("Assuming `reference_column` is called 'summary:reference'.")
if reference_column not in dataset.column_names:
print("No reference summary loaded")
reference_column = None
if summary_columns is None or len(summary_columns) == 0:
# Assume `summary_columns` are prefixed by "summary:"
summary_columns = []
for col in dataset.column_names:
if col.startswith("summary:") and col != "summary:reference":
summary_columns.append(col)
print(
f"Reading summary columns from dataset. Found {summary_columns}.")
if len(summary_columns) == 0 and reference_column is None:
raise ValueError("At least one summary is required")
# Set visible rows to restrict to the first `n_samples`
if n_samples:
dataset.set_visible_rows(list(range(n_samples)))
# Combine the text columns into one list
text_columns = [doc_column] + ([reference_column] if reference_column else
[]) + summary_columns
# Preprocessing all the text columns
dataset = dataset.update(
lambda x: {
f'preprocessed_{k}': x[k] if args.no_clean else clean_text(x[k])
for k in text_columns
})
# Run the Spacy pipeline on all preprocessed text columns
try:
nlp = load('en_core_web_lg')
except OSError:
nlp = None
if nlp is None:
raise OSError(
'Missing spaCy model "en_core_web_lg". Please run "python -m spacy download en_core_web_lg"'
)
nlp.add_pipe('sentencizer', before="parser")
spacy = Spacy(nlp=nlp)
dataset = spacy(
dataset,
[f'preprocessed_{col}' for col in text_columns],
batch_size=100,
)
# Run the 3 align pipelines
bert_aligner = BertscoreAlignerCap(
threshold=bert_aligner_threshold,
top_k=bert_aligner_top_k,
spacy=spacy,
)
embedding_aligner = StaticEmbeddingAlignerCap(
threshold=embedding_aligner_threshold,
top_k=embedding_aligner_top_k,
spacy=spacy,
)
ngram_aligner = NGramAlignerCap(spacy=spacy, )
dataset = _run_aligners(
dataset=dataset,
aligners=[bert_aligner, embedding_aligner, ngram_aligner],
doc_column=f'preprocessed_{doc_column}',
reference_column=f'preprocessed_{reference_column}'
if reference_column else None,
summary_columns=[f'preprocessed_{col}' for col in summary_columns],
)
# Save the dataset
if anonymize:
# Remove certain columns to anonymize and save to disk
for col in [doc_column, reference_column]:
if col is not None:
dataset.remove_column(col)
dataset.remove_column(f'preprocessed_{col}')
dataset.remove_column(
str(spacy.identifier(columns=[f'preprocessed_{col}'])))
del dataset.interactions[CACHEDOPS].history[(
spacy.identifier, f'preprocessed_{col}')]
dataset.save_to_disk(f'{processed_dataset_path}.anonymized')
else:
# Directly save to disk
dataset.save_to_disk(processed_dataset_path)
return dataset