def analogy(self, pos, neg, n=10, metric="cosine"):
"""
Analogy similarity.
Parameters
----------
pos : list
neg : list
Returns
-------
Tuple of 2 numpy.array:
1. position in self.vocab
2. cosine similarity
Example
-------
`king - man + woman = queen` will be: `pos=['king', 'woman'], neg=['man']`
"""
exclude = pos + neg
pos = [(word, 1.0) for word in pos]
neg = [(word, -1.0) for word in neg]
mean = []
for word, direction in pos + neg:
mean.append(direction * self[word])
mean = np.array(mean).mean(axis=0)
metrics = distance(self.vectors, mean, metric=metric)
best = metrics.argsort()[::-1][:n + len(exclude)]
exclude_idx = [np.where(best == self.ix(word)) for word in exclude if self.ix(word) in best]
new_best = np.delete(best, exclude_idx)
best_metrics = metrics[new_best]
return new_best[:n], best_metrics[:n]
def closest(self, vector, n=10, metric="cosine"):
"""Returns the closest n words to a vector
Parameters
-------
vector : numpy.array
n : int (default 10)
Returns
-------
Tuple of 2 numpy.array:
1. position in self.vocab
2. cosine similarity
"""
distances = distance(self.vectors, vector, metric=metric)
best = np.argsort(distances)[::-1][1:n + 1]
best_metrics = distances[best]
return best, best_metrics
def closest(self, vector, n=10, metric="cosine"):
"""Returns the closest n words to a vector
Parameters
-------
vector : numpy.array
n : int (default 10)
Returns
-------
Tuple of 2 numpy.array:
1. position in self.vocab
2. cosine similarity
"""
distances = distance(self.vectors, vector, metric=metric)
best = np.argsort(distances)[::-1][1:n + 1]
best_metrics = distances[best]
return best, best_metrics
def distance(self, *args, **kwargs):
"""
Compute the distance distance between two vectors or more (all combinations) of words
Parameters
----------
words : one or more words
n : int (default 10)
number of neighbors to return
metric : string (default "cosine")
What metric to use
"""
metric = kwargs.get("metric", "cosine") # Default is cosine
combinations = list(itertools.combinations(args, r=2))
ret = []
for word1, word2 in combinations:
dist = distance(self[word1], self[word2], metric=metric)
ret.append((word1, word2, dist))
return ret
def distance(self, *args, **kwargs):
"""
Compute the distance distance between two vectors or more (all combinations) of words
Parameters
----------
words : one or more words
n : int (default 10)
number of neighbors to return
metric : string (default "cosine")
What metric to use
"""
metric = kwargs.get("metric", "cosine") # Default is cosine
combinations = list(itertools.combinations(args, r=2))
ret = []
for word1, word2 in combinations:
dist = distance(self[word1], self[word2], metric=metric)
ret.append((word1, word2, dist))
return ret
def analogy(self, pos, neg, n=10, metric="cosine"):
"""
Analogy similarity.
Parameters
----------
pos : list
neg : list
Returns
-------
Tuple of 2 numpy.array:
1. position in self.vocab
2. cosine similarity
Example
-------
`king - man + woman = queen` will be: `pos=['king', 'woman'], neg=['man']`
"""
exclude = pos + neg
pos = [(word, 1.0) for word in pos]
neg = [(word, -1.0) for word in neg]
mean = []
for word, direction in pos + neg:
mean.append(direction * self[word])
mean = np.array(mean).mean(axis=0)
metrics = distance(self.vectors, mean, metric=metric)
best = metrics.argsort()[::-1][:n + len(exclude)]
exclude_idx = [
np.where(best == self.ix(word)) for word in exclude
if self.ix(word) in best
]
new_best = np.delete(best, exclude_idx)
best_metrics = metrics[new_best]
return new_best[:n], best_metrics[:n]
