explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-05-30 02:33:07 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update docstrings and formatting

Browse Source
This commit is contained in:
ines 2017-10-31 23:23:34 +01:00
parent 0de8d213a3
commit ba2e6c8c6f
1 changed files with 26 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
spacy/vectors.pyx
View File

@ -28,7 +28,7 @@ cdef class Vectors:
instance of numpy.ndarray (for CPU vectors) or cupy.ndarray instance of numpy.ndarray (for CPU vectors) or cupy.ndarray
(for GPU vectors). `vectors.key2row` is a dictionary mapping word hashes to (for GPU vectors). `vectors.key2row` is a dictionary mapping word hashes to
rows in the vectors.data table. rows in the vectors.data table.
Multiple keys can be mapped to the same vector, and not all of the rows in Multiple keys can be mapped to the same vector, and not all of the rows in
the table need to be assigned --- so len(list(vectors.keys())) may be the table need to be assigned --- so len(list(vectors.keys())) may be
greater or smaller than vectors.shape[0]. greater or smaller than vectors.shape[0].
@ -39,9 +39,10 @@ cdef class Vectors:
def __init__(self, *, shape=None, data=None, keys=None): def __init__(self, *, shape=None, data=None, keys=None):
"""Create a new vector store. """Create a new vector store.
shape (tuple): Size of the table, as (# entries, # columns) shape (tuple): Size of the table, as (# entries, # columns)
data (numpy.ndarray): The vector data. data (numpy.ndarray): The vector data.
keys (iterable): A sequence of keys, aligned with the data.
RETURNS (Vectors): The newly created object. RETURNS (Vectors): The newly created object.
""" """
if data is None: if data is None:
@ -57,7 +58,7 @@ cdef class Vectors:
if keys is not None: if keys is not None:
for i, key in enumerate(keys): for i, key in enumerate(keys):
self.add(key, row=i) self.add(key, row=i)
@property @property
def shape(self): def shape(self):
"""Get `(rows, dims)` tuples of number of rows and number of dimensions """Get `(rows, dims)` tuples of number of rows and number of dimensions
@ -102,7 +103,7 @@ cdef class Vectors:
"""Set a vector for the given key. """Set a vector for the given key.
key (int): The key to set the vector for. key (int): The key to set the vector for.
vector (numpy.ndarray): The vector to set. vector (ndarray): The vector to set.
""" """
i = self.key2row[key] i = self.key2row[key]
self.data[i] = vector self.data[i] = vector
@ -110,9 +111,9 @@ cdef class Vectors:
self._unset.remove(i) self._unset.remove(i)
def __iter__(self): def __iter__(self):
"""Yield vectors from the table. """Iterate over the keys in the table.
YIELDS (ndarray): A vector. YIELDS (int): A key in the table.
""" """
yield from self.key2row yield from self.key2row
@ -132,14 +133,14 @@ cdef class Vectors:
return key in self.key2row return key in self.key2row
def resize(self, shape, inplace=False): def resize(self, shape, inplace=False):
'''Resize the underlying vectors array. If inplace=True, the memory """Resize the underlying vectors array. If inplace=True, the memory
is reallocated. This may cause other references to the data to become is reallocated. This may cause other references to the data to become
invalid, so only use inplace=True if you're sure that's what you want. invalid, so only use inplace=True if you're sure that's what you want.
If the number of vectors is reduced, keys mapped to rows that have been If the number of vectors is reduced, keys mapped to rows that have been
deleted are removed. These removed items are returned as a list of deleted are removed. These removed items are returned as a list of
(key, row) tuples. `(key, row)` tuples.
''' """
if inplace: if inplace:
self.data.resize(shape, refcheck=False) self.data.resize(shape, refcheck=False)
else: else:
@ -153,16 +154,22 @@ cdef class Vectors:
self.key2row.pop(key) self.key2row.pop(key)
removed_items.append((key, row)) removed_items.append((key, row))
return removed_items return removed_items
def keys(self): def keys(self):
'''Iterate over the keys in the table.''' """A sequence of the keys in the table.
yield from self.key2row.keys()
RETURNS (iterable): The keys.
"""
return self.key2row.keys()
def values(self): def values(self):
'''Iterate over vectors that have been assigned to at least one key. """Iterate over vectors that have been assigned to at least one key.
Note that some vectors may be unassigned, so the number of vectors Note that some vectors may be unassigned, so the number of vectors
returned may be less than the length of the vectors table.''' returned may be less than the length of the vectors table.
YIELDS (ndarray): A vector in the table.
"""
for row, vector in enumerate(range(self.data.shape[0])): for row, vector in enumerate(range(self.data.shape[0])):
if row not in self._unset: if row not in self._unset:
yield vector yield vector
@ -208,12 +215,12 @@ cdef class Vectors:
if row in self._unset: if row in self._unset:
self._unset.remove(row) self._unset.remove(row)
return row return row
def most_similar(self, queries, *, return_scores=False, return_rows=False, def most_similar(self, queries, *, return_scores=False, return_rows=False,
batch_size=1024): batch_size=1024):
'''For each of the given vectors, find the single entry most similar '''For each of the given vectors, find the single entry most similar
to it, by cosine. to it, by cosine.
Queries are by vector. Results are returned as an array of keys, Queries are by vector. Results are returned as an array of keys,
or a tuple of (keys, scores) if return_scores=True. If `queries` is or a tuple of (keys, scores) if return_scores=True. If `queries` is
large, the calculations are performed in chunks, to avoid consuming large, the calculations are performed in chunks, to avoid consuming
@ -221,9 +228,9 @@ cdef class Vectors:
trade-off during the calculations. trade-off during the calculations.
''' '''
xp = get_array_module(self.data) xp = get_array_module(self.data)
vectors = self.data / xp.linalg.norm(self.data, axis=1, keepdims=True) vectors = self.data / xp.linalg.norm(self.data, axis=1, keepdims=True)
best_rows = xp.zeros((queries.shape[0],), dtype='i') best_rows = xp.zeros((queries.shape[0],), dtype='i')
scores = xp.zeros((queries.shape[0],), dtype='f') scores = xp.zeros((queries.shape[0],), dtype='f')
# Work in batches, to avoid memory problems. # Work in batches, to avoid memory problems.