def arrow_to_char_span(extension_array: pa.ExtensionArray) -> CharSpanArray:
"""
Convert a pyarrow.ExtensionArray with type ArrowCharSpanType to
a CharSpanArray.
:param extension_array: pyarrow.ExtensionArray with type ArrowCharSpanType
:return: CharSpanArray
"""
if isinstance(extension_array, pa.ChunkedArray):
if extension_array.num_chunks > 1:
raise ValueError(
"Only pyarrow.Array with a single chunk is supported")
extension_array = extension_array.chunk(0)
assert pa.types.is_struct(extension_array.storage.type)
# Get target text from the begins field metadata and decode string
metadata = extension_array.storage.type[
ArrowCharSpanType.BEGINS_NAME].metadata
target_text = metadata[ArrowCharSpanType.TARGET_TEXT_KEY]
if isinstance(target_text, bytes):
target_text = target_text.decode()
# Get the begins/ends pyarrow arrays
begins_array = extension_array.storage.field(ArrowCharSpanType.BEGINS_NAME)
ends_array = extension_array.storage.field(ArrowCharSpanType.ENDS_NAME)
# Zero-copy convert arrays to numpy
begins = begins_array.to_numpy()
ends = ends_array.to_numpy()
return CharSpanArray(target_text, begins, ends)
def arrow_to_token_span(extension_array: pa.ExtensionArray) -> TokenSpanArray:
"""
Convert a pyarrow.ExtensionArray with type ArrowTokenSpanType to
a TokenSpanArray.
:param extension_array: pyarrow.ExtensionArray with type ArrowTokenSpanType
:return: TokenSpanArray
"""
if isinstance(extension_array, pa.ChunkedArray):
if extension_array.num_chunks > 1:
raise ValueError("Only pyarrow.Array with a single chunk is supported")
extension_array = extension_array.chunk(0)
assert pa.types.is_struct(extension_array.storage.type)
# Get target text from the begins field metadata and decode string
metadata = extension_array.storage.type[ArrowTokenSpanType.BEGINS_NAME].metadata
target_text = metadata[ArrowCharSpanType.TARGET_TEXT_KEY]
if isinstance(target_text, bytes):
target_text = target_text.decode()
# Get the begins/ends pyarrow arrays
token_begins_array = extension_array.storage.field(ArrowTokenSpanType.BEGINS_NAME)
token_ends_array = extension_array.storage.field(ArrowTokenSpanType.ENDS_NAME)
# Check if CharSpans have been split
num_char_span_splits = extension_array.type.num_char_span_splits
if num_char_span_splits > 0:
char_begins_splits = []
char_ends_splits = []
for i in range(num_char_span_splits):
char_begins_splits.append(
extension_array.storage.field(ArrowCharSpanType.BEGINS_NAME + "_{}".format(i)))
char_ends_splits.append(
extension_array.storage.field(ArrowCharSpanType.ENDS_NAME + "_{}".format(i)))
char_begins_array = pa.concat_arrays(char_begins_splits)
char_ends_array = pa.concat_arrays(char_ends_splits)
else:
char_begins_array = extension_array.storage.field(ArrowCharSpanType.BEGINS_NAME)
char_ends_array = extension_array.storage.field(ArrowCharSpanType.ENDS_NAME)
# Remove any trailing padding
if char_begins_array.null_count > 0:
char_begins_array = char_begins_array[:-char_begins_array.null_count]
char_ends_array = char_ends_array[:-char_ends_array.null_count]
# Zero-copy convert arrays to numpy
token_begins = token_begins_array.to_numpy()
token_ends = token_ends_array.to_numpy()
char_begins = char_begins_array.to_numpy()
char_ends = char_ends_array.to_numpy()
# Create the CharSpanArray, then the TokenSpanArray
char_span = CharSpanArray(target_text, char_begins, char_ends)
return TokenSpanArray(char_span, token_begins, token_ends)
def make_tokens(target_text: str, tokenizer) -> pd.Series:
"""
:param target_text: Text to tokenize
:param tokenizer: Preconfigured `spacy.tokenizer.Tokenizer` object
:return: The tokens (and underlying text) as a Pandas Series wrapped around
a `CharSpanArray` value.
"""
spacy_doc = tokenizer(target_text)
tok_begins = np.array([t.idx for t in spacy_doc])
tok_ends = np.array([t.idx + len(t) for t in spacy_doc])
return pd.Series(CharSpanArray(target_text, tok_begins, tok_ends))
def _doc_to_df(doc: List[Dict[str, List[str]]],
space_before_punct: bool) -> pd.DataFrame:
"""
Convert the "Python objects" representation of a document from a
CoNLL-2003 file into a `pd.DataFrame` of token metadata.
:param doc: Tree of Python objects that represents the document,
List with one dictionary per sentence.
:param space_before_punct: If `True`, add whitespace before
punctuation characters when reconstructing the text of the document.
:return: DataFrame with four columns:
* `char_span`: Span of each token, with character offsets.
Backed by the concatenation of the tokens in the document into
a single string with one sentence per line.
* `token_span`: Span of each token, with token offsets.
Backed by the contents of the `char_span` column.
* `ent_iob`: IOB2-format tags of tokens, exactly as they appeared
in the original file, with no corrections applied.
* `ent_type`: Entity type names for tokens tagged "I" or "B" in
the `ent_iob` column; `None` everywhere else.
"""
begins_list = [] # Type: List[np.ndarray]
ends_list = [] # Type: List[np.ndarray]
sentences_list = [] # Type: List[np.ndarray]
iobs_list = [] # Type: List[np.ndarray]
entities_list = [] # Type: List[np.ndarray]
sentence_begins_list = [] # Type: List[np.ndarray]
sentence_ends_list = [] # Type: List[np.ndarray]
char_position = 0
token_position = 0
for sentence in doc:
tokens = sentence["token"]
# Don't put spaces before punctuation in the reconstituted string.
no_space_mask = (
np.zeros(len(tokens), dtype=np.bool) if space_before_punct
else _PUNCT_MATCH_FN(tokens))
no_space_mask[0] = True # No space before first token
prefixes = np.where(no_space_mask, "", " ")
string_parts = np.ravel((prefixes, tokens), order='F')
sentence_text = "".join(string_parts)
sentences_list.append(sentence_text)
lengths = np.array([len(t) for t in tokens])
prefix_lengths = np.array([len(p) for p in prefixes])
# Begin and end offsets, accounting for which tokens have spaces
# before them.
e = np.cumsum(lengths + prefix_lengths)
b = e - lengths
iobs = np.array(sentence["iob"])
entities = np.array(sentence["entity"])
sentence_begin_token = token_position
sentence_end_token = token_position + len(e)
sentence_begins = np.repeat(sentence_begin_token, len(e))
sentence_ends = np.repeat(sentence_end_token, len(e))
begins_list.append(b + char_position)
ends_list.append(e + char_position)
iobs_list.append(iobs)
entities_list.append(entities)
sentence_begins_list.append(sentence_begins)
sentence_ends_list.append(sentence_ends)
char_position += e[-1] + 1 # "+ 1" to account for newline
token_position += len(e)
begins = np.concatenate(begins_list)
ends = np.concatenate(ends_list)
doc_text = "\n".join(sentences_list)
char_spans = CharSpanArray(doc_text, begins, ends)
token_begins = np.arange(len(begins))
token_spans = TokenSpanArray(char_spans, token_begins, token_begins + 1)
sentence_spans = TokenSpanArray(char_spans,
np.concatenate(sentence_begins_list),
np.concatenate(sentence_ends_list))
return pd.DataFrame(
{"char_span": char_spans,
"token_span": token_spans,
"ent_iob": np.concatenate(iobs_list),
"ent_type": np.concatenate(entities_list),
"sentence": sentence_spans})
def _doc_to_df(doc: List[_SentenceData], column_names: List[str],
iob_columns: List[bool],
space_before_punct: bool) -> pd.DataFrame:
"""
Convert the "Python objects" representation of a document from a
CoNLL-2003 file into a `pd.DataFrame` of token metadata.
:param doc: List of Python objects that represents the document.
:param column_names: Names for the metadata columns that come after the
token text. These names will be used to generate the names of the dataframe
that this function returns.
:param iob_columns: Mask indicating which of the metadata columns after the
token text should be treated as being in IOB format. If a column is in IOB format,
the returned dataframe will contain *two* columns, holding IOB2 tags and
entity type tags, respectively. For example, an input column "ent" will turn into
output columns "ent_iob" and "ent_type".
:param space_before_punct: If `True`, add whitespace before
punctuation characters (and after left parentheses)
when reconstructing the text of the document.
:return: DataFrame with four columns:
* `char_span`: Span of each token, with character offsets.
Backed by the concatenation of the tokens in the document into
a single string with one sentence per line.
* `token_span`: Span of each token, with token offsets.
Backed by the contents of the `char_span` column.
* `ent_iob`: IOB2-format tags of tokens, exactly as they appeared
in the original file, with no corrections applied.
* `ent_type`: Entity type names for tokens tagged "I" or "B" in
the `ent_iob` column; `None` everywhere else.
"""
# Character offsets of tokens in the reconstructed document
begins_list = [] # Type: List[np.ndarray]
ends_list = [] # Type: List[np.ndarray]
# Reconstructed text of each sentence
sentences_list = [] # Type: List[np.ndarray]
# Token offsets of sentences containing each token in the document.
sentence_begins_list = [] # Type: List[np.ndarray]
sentence_ends_list = [] # Type: List[np.ndarray]
# Token metadata column values. Key is column name, value is metadata for
# each token.
meta_lists = _make_empty_meta_values(column_names, iob_columns)
char_position = 0
token_position = 0
for sentence_num in range(len(doc)):
sentence = doc[sentence_num]
tokens = sentence.tokens
# Don't put spaces before punctuation in the reconstituted string.
no_space_before_mask = (np.zeros(len(tokens), dtype=np.bool)
if space_before_punct else
_SPACE_BEFORE_MATCH_FN(tokens))
no_space_after_mask = (np.zeros(len(tokens), dtype=np.bool)
if space_before_punct else
_SPACE_AFTER_MATCH_FN(tokens))
no_space_before_mask[0] = True # No space before first token
no_space_after_mask[-1] = True # No space after last token
shifted_no_space_after_mask = np.roll(no_space_after_mask, 1)
prefixes = np.where(
np.logical_or(no_space_before_mask, shifted_no_space_after_mask),
"", " ")
string_parts = np.ravel((prefixes, tokens), order="F")
sentence_text = "".join(string_parts)
sentences_list.append(sentence_text)
lengths = np.array([len(t) for t in tokens])
prefix_lengths = np.array([len(p) for p in prefixes])
# Begin and end offsets, accounting for which tokens have spaces
# before them.
e = np.cumsum(lengths + prefix_lengths)
b = e - lengths
begins_list.append(b + char_position)
ends_list.append(e + char_position)
sentence_begin_token = token_position
sentence_end_token = token_position + len(e)
sentence_begins = np.repeat(sentence_begin_token, len(e))
sentence_ends = np.repeat(sentence_end_token, len(e))
sentence_begins_list.append(sentence_begins)
sentence_ends_list.append(sentence_ends)
for k in sentence.token_metadata.keys():
meta_lists[k].extend(sentence.token_metadata[k])
char_position += e[-1] + 1 # "+ 1" to account for newline
token_position += len(e)
begins = np.concatenate(begins_list)
ends = np.concatenate(ends_list)
doc_text = "\n".join(sentences_list)
char_spans = CharSpanArray(doc_text, begins, ends)
token_begins = np.arange(len(begins))
token_spans = TokenSpanArray(char_spans, token_begins, token_begins + 1)
sentence_spans = TokenSpanArray(char_spans,
np.concatenate(sentence_begins_list),
np.concatenate(sentence_ends_list))
ret = pd.DataFrame({"char_span": char_spans, "token_span": token_spans})
for k, v in meta_lists.items():
ret[k] = v
ret["sentence"] = sentence_spans
return ret
def make_tokens_and_features(
target_text: str,
language_model,
add_left_and_right=False,
) -> pd.DataFrame:
"""
:param target_text: Text to analyze
:param language_model: Preconfigured spaCy language model (`spacy.language.Language`)
object
:param add_left_and_right: If `True`, add columns "left" and "right"
containing references to previous and next tokens.
:return: A tuple of two dataframes:
1. The tokens of the text plus additional linguistic features that the
language model generates, represented as a `pd.DataFrame`.
2. A table of named entities identified by the language model's named entity
tagger, represented as a `pd.DataFrame`.
"""
spacy_doc = language_model(target_text)
# TODO: Performance tuning of the translation code that follows
# Represent the character spans of the tokens
tok_begins = np.array([t.idx for t in spacy_doc])
tok_ends = np.array([t.idx + len(t) for t in spacy_doc])
tokens_array = CharSpanArray(target_text, tok_begins, tok_ends)
tokens_series = pd.Series(tokens_array)
# Also build single-token token-based spans to make it easier to build
# larger token-based spans.
token_spans = TokenSpanArray.from_char_offsets(tokens_series.values)
# spaCy identifies tokens by semi-arbitrary integer "indexes" (in practice,
# the offset of the first character in the token). Translate from these
# to a dense range of integer IDs that will correspond to the index of our
# returned DataFrame.
idx_to_id = {spacy_doc[i].idx: i for i in range(len(spacy_doc))}
# Define the IOB categorical type with "O" == 0, "B"==1, "I"==2
iob2_dtype = pd.CategoricalDtype(["O", "B", "I"], ordered=False)
df_cols = {
"id":
range(len(tok_begins)),
"char_span":
tokens_series,
"token_span":
token_spans,
"lemma": [t.lemma_ for t in spacy_doc],
"pos":
pd.Categorical([str(t.pos_) for t in spacy_doc]),
"tag":
pd.Categorical([str(t.tag_) for t in spacy_doc]),
"dep":
pd.Categorical([str(t.dep_) for t in spacy_doc]),
"head":
np.array([idx_to_id[t.head.idx] for t in spacy_doc]),
"shape":
pd.Categorical([t.shape_ for t in spacy_doc]),
"ent_iob":
pd.Categorical([str(t.ent_iob_) for t in spacy_doc], dtype=iob2_dtype),
"ent_type":
pd.Categorical([str(t.ent_type_) for t in spacy_doc]),
"is_alpha":
np.array([t.is_alpha for t in spacy_doc]),
"is_stop":
np.array([t.is_stop for t in spacy_doc]),
"sentence":
_make_sentences_series(spacy_doc, tokens_array),
}
if add_left_and_right:
# Use nullable int type because these columns contain nulls
df_cols["left"] = pd.array([None] + list(range(len(tok_begins) - 1)),
dtype=pd.Int32Dtype())
df_cols["right"] = pd.array(list(range(1, len(tok_begins))) + [None],
dtype=pd.Int32Dtype())
return pd.DataFrame(df_cols)
def make_bert_tokens(target_text: str, tokenizer) -> pd.DataFrame:
"""
Tokenize the indicated text for BERT embeddings and return a DataFrame
with one row per token.
:param: target_text: string to tokenize
:param: tokenizer: A tokenizer that is a subclass of huggingface transformers
PreTrainingTokenizerFast which supports `encode_plus` with
return_offsets_mapping=True.
:returns: A `pd.DataFrame` with the following columns:
* "id": unique integer ID for each token
* "char_span": span of the token with character offsets
* "token_span": span of the token with token offsets
* "input_id": integer ID suitable for input to a BERT embedding model
* "token_type_id": list of token type ids to be fed to a model
* "attention_mask": list of indices specifying which tokens should be
attended to by the model
* "special_tokens_mask": `True` if the token is a zero-length special token
such as "start of document"
"""
from transformers.tokenization_utils import PreTrainedTokenizerFast
if not isinstance(tokenizer, PreTrainedTokenizerFast):
raise TypeError("Tokenizer must be an instance of "
"transformers.PreTrainedTokenizerFast that supports "
"encode_plus with return_offsets_mapping=True.")
tokenized_result = tokenizer.encode_plus(target_text,
return_special_tokens_mask=True,
return_offsets_mapping=True)
# Get offset mapping from tokenizer
offsets = tokenized_result["offset_mapping"]
# Init any special tokens at beginning
i = 0
while offsets[i] is None:
offsets[i] = (0, 0)
i += 1
# Make a DataFrame to unzip (begin, end) offsets
offset_df = pd.DataFrame(offsets, columns=["begin", "end"])
# Convert special tokens mask to boolean
special_tokens_mask = pd.Series(
tokenized_result["special_tokens_mask"]).astype("bool")
# Fill remaining special tokens to zero-length spans
ends = offset_df["end"].fillna(method="ffill").astype("int32")
begins = offset_df["begin"].mask(special_tokens_mask,
other=ends).astype("int32")
# Create char and token span arrays
char_spans = CharSpanArray(target_text, begins, ends)
token_spans = TokenSpanArray(char_spans, np.arange(len(char_spans)),
np.arange(1,
len(char_spans) + 1))
token_features = pd.DataFrame({
"id":
special_tokens_mask.index,
# Use values instead of series because different indexes
"char_span":
pd.Series(char_spans).values,
"token_span":
pd.Series(token_spans).values,
"input_id":
tokenized_result["input_ids"],
"token_type_id":
tokenized_result["token_type_ids"],
"attention_mask":
tokenized_result["attention_mask"],
"special_tokens_mask":
special_tokens_mask,
})
return token_features