You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/11/12 07:46:35 UTC
[GitHub] nswamy closed pull request #13149: Fix Sphinx python docstring
error: text contrib module (#12949)
nswamy closed pull request #13149: Fix Sphinx python docstring error: text contrib module (#12949)
URL: https://github.com/apache/incubator-mxnet/pull/13149
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/python/mxnet/contrib/text/embedding.py b/python/mxnet/contrib/text/embedding.py
index 277f7822292..e2a05c841af 100644
--- a/python/mxnet/contrib/text/embedding.py
+++ b/python/mxnet/contrib/text/embedding.py
@@ -161,7 +161,7 @@ class _TokenEmbedding(vocab.Vocabulary):
pre-trained token embedding file, are taken as the indexed tokens of the embedding.
- Properties
+ Attributes
----------
token_to_idx : dict mapping str to int
A dict mapping each token to its index integer.
@@ -506,25 +506,6 @@ class GloVe(_TokenEmbedding):
embedding vectors, such as loaded from a pre-trained token embedding file. If None, all the
tokens from the loaded embedding vectors, such as loaded from a pre-trained token embedding
file, will be indexed.
-
-
- Properties
- ----------
- token_to_idx : dict mapping str to int
- A dict mapping each token to its index integer.
- idx_to_token : list of strs
- A list of indexed tokens where the list indices and the token indices are aligned.
- unknown_token : hashable object
- The representation for any unknown token. In other words, any unknown token will be indexed
- as the same representation.
- reserved_tokens : list of strs or None
- A list of reserved tokens that will always be indexed.
- vec_len : int
- The length of the embedding vector for each token.
- idx_to_vec : mxnet.ndarray.NDArray
- For all the indexed tokens in this embedding, this NDArray maps each token's index to an
- embedding vector. The largest valid index maps to the initialized embedding vector for every
- reserved token, such as an unknown_token token and a padding token.
"""
# Map a pre-trained token embedding archive file and its SHA-1 hash.
@@ -610,25 +591,6 @@ class FastText(_TokenEmbedding):
embedding vectors, such as loaded from a pre-trained token embedding file. If None, all the
tokens from the loaded embedding vectors, such as loaded from a pre-trained token embedding
file, will be indexed.
-
-
- Properties
- ----------
- token_to_idx : dict mapping str to int
- A dict mapping each token to its index integer.
- idx_to_token : list of strs
- A list of indexed tokens where the list indices and the token indices are aligned.
- unknown_token : hashable object
- The representation for any unknown token. In other words, any unknown token will be indexed
- as the same representation.
- reserved_tokens : list of strs or None
- A list of reserved tokens that will always be indexed.
- vec_len : int
- The length of the embedding vector for each token.
- idx_to_vec : mxnet.ndarray.NDArray
- For all the indexed tokens in this embedding, this NDArray maps each token's index to an
- embedding vector. The largest valid index maps to the initialized embedding vector for every
- reserved token, such as an unknown_token token and a padding token.
"""
# Map a pre-trained token embedding archive file and its SHA-1 hash.
@@ -687,25 +649,6 @@ class CustomEmbedding(_TokenEmbedding):
embedding vectors, such as loaded from a pre-trained token embedding file. If None, all the
tokens from the loaded embedding vectors, such as loaded from a pre-trained token embedding
file, will be indexed.
-
-
- Properties
- ----------
- token_to_idx : dict mapping str to int
- A dict mapping each token to its index integer.
- idx_to_token : list of strs
- A list of indexed tokens where the list indices and the token indices are aligned.
- unknown_token : hashable object
- The representation for any unknown token. In other words, any unknown token will be indexed
- as the same representation.
- reserved_tokens : list of strs or None
- A list of reserved tokens that will always be indexed.
- vec_len : int
- The length of the embedding vector for each token.
- idx_to_vec : mxnet.ndarray.NDArray
- For all the indexed tokens in this embedding, this NDArray maps each token's index to an
- embedding vector. The largest valid index maps to the initialized embedding vector for every
- reserved token, such as an unknown_token token and a padding token.
"""
def __init__(self, pretrained_file_path, elem_delim=' ', encoding='utf8',
@@ -735,25 +678,6 @@ class CompositeEmbedding(_TokenEmbedding):
token_embeddings : instance or list of `mxnet.contrib.text.embedding._TokenEmbedding`
One or multiple pre-trained token embeddings to load. If it is a list of multiple
embeddings, these embedding vectors will be concatenated for each token.
-
-
- Properties
- ----------
- token_to_idx : dict mapping str to int
- A dict mapping each token to its index integer.
- idx_to_token : list of strs
- A list of indexed tokens where the list indices and the token indices are aligned.
- unknown_token : hashable object
- The representation for any unknown token. In other words, any unknown token will be indexed
- as the same representation.
- reserved_tokens : list of strs or None
- A list of reserved tokens that will always be indexed.
- vec_len : int
- The length of the embedding vector for each token.
- idx_to_vec : mxnet.ndarray.NDArray
- For all the indexed tokens in this embedding, this NDArray maps each token's index to an
- embedding vector. The largest valid index maps to the initialized embedding vector for every
- reserved token, such as an unknown_token token and a padding token.
"""
def __init__(self, vocabulary, token_embeddings):
diff --git a/python/mxnet/contrib/text/vocab.py b/python/mxnet/contrib/text/vocab.py
index 9e44acb1019..ede2ca53571 100644
--- a/python/mxnet/contrib/text/vocab.py
+++ b/python/mxnet/contrib/text/vocab.py
@@ -63,12 +63,8 @@ class Vocabulary(object):
`reserved_tokens` must be of the same hashable type. Examples: str, int, and tuple.
- Properties
+ Attributes
----------
- token_to_idx : dict mapping str to int
- A dict mapping each token to its index integer.
- idx_to_token : list of strs
- A list of indexed tokens where the list indices and the token indices are aligned.
unknown_token : hashable object
The representation for any unknown token. In other words, any unknown token will be indexed
as the same representation.
@@ -143,10 +139,16 @@ def __len__(self):
@property
def token_to_idx(self):
+ """
+ dict mapping str to int: A dict mapping each token to its index integer.
+ """
return self._token_to_idx
@property
def idx_to_token(self):
+ """
+ list of strs: A list of indexed tokens where the list indices and the token indices are aligned.
+ """
return self._idx_to_token
@property
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services