def fit(self, X):
if self.hash_args:
self.index = puffinn.Index(self.metric, X.shape[1], self.space,\
hash_function=self.hash_function, hash_source=self.hash_source,\
hash_args=self.hash_args)
else:
self.index = puffinn.Index(self.metric, X.shape[1], self.space,\
hash_function=self.hash_function, hash_source=self.hash_source)
for i, x in enumerate(X):
self.index.insert(x.tolist())
self.index.rebuild(10)
def fit(self, X):
if self.hash_args:
self.index = puffinn.Index(self.metric, len(X[0]), self.space,\
hash_function=self.hash_function, hash_source=self.hash_source,\
hash_args=self.hash_args)
else:
self.index = puffinn.Index(self.metric, len(X[0]), self.space,\
hash_function=self.hash_function, hash_source=self.hash_source)
for i, x in enumerate(X):
if self.metric == 'angular':
x = x.tolist()
self.index.insert(x)
self.index.rebuild(10)
def fit(self, X):
if self.metric == 'angular':
dimensions = len(X[0])
else:
dimensions = 0
for x in X:
dimensions = max(dimensions, max(x)+1)
if self.hash_args:
self.index = puffinn.Index(self.metric, dimensions, self.space,\
hash_function=self.hash_function, hash_source=self.hash_source,\
hash_args=self.hash_args)
else:
self.index = puffinn.Index(self.metric, dimensions, self.space,\
hash_function=self.hash_function, hash_source=self.hash_source)
for i, x in enumerate(X):
x = x.tolist()
self.index.insert(x)
self.index.rebuild()
def fit(self, X, y=None) -> PuffinnLSH:
""" Build the puffinn LSH index and insert data from X.
Parameters
----------
X: np.array
Data to be indexed
y: any
Ignored
Returns
-------
self: Puffinn
An instance of Puffinn with a built index
"""
if y is None:
X = check_array(X)
else:
X, y = check_X_y(X, y)
self.y_train_ = y
if self.metric not in self.valid_metrics:
warnings.warn(
f'Invalid metric "{self.metric}". Using "euclidean" instead')
self.metric = 'euclidean'
try:
self.effective_metric = self.metric_map[self.metric]
except KeyError:
self.effective_metric = self.metric
# Reduce default memory consumption for unit tests
if "pytest" in sys.modules:
self.memory = 3 * 1024**2
# Construct the index
index = puffinn.Index(
self.effective_metric,
X.shape[1],
self.memory,
)
if self.verbose:
iter_X = tqdm(X, desc='Indexing', total=len(X))
else:
iter_X = X
for v in iter_X:
index.insert(v.tolist())
index.rebuild(num_threads=self.n_jobs)
self.index_ = index
self.X_train_ = X # remove, once we can retrieve vectors from the index itself
return self
def fit(self, X, y=None):
""" Build the puffinn LSH index and insert data from X.
Parameters
----------
X: np.array
Data to be indexed
y: any
Ignored
Returns
-------
self: Puffinn
An instance of Puffinn with a built index
"""
if y is None:
X = check_array(X)
else:
X, y = check_X_y(X, y)
self.y_train_ = y
if self.metric not in self.valid_metrics:
warnings.warn(
f'Invalid metric "{self.metric}". Using "euclidean" instead')
self.metric = 'euclidean'
try:
self._effective_metric = self.metric_map[self.metric]
except KeyError:
self._effective_metric = self.metric
# Larger memory means many iterations (time-recall trade-off)
memory = max(np.multiply(*X.shape) * 8 * 500, 1024**2)
if self.memory is not None:
memory = max(self.memory, memory)
# Construct the index
index = puffinn.Index(
self._effective_metric,
X.shape[1],
memory,
)
disable_tqdm = False if self.verbose else True
for v in tqdm(X, desc='Indexing', disable=disable_tqdm):
index.insert(v.tolist())
index.rebuild()
self.index_ = index
self.n_indexed_ = X.shape[0]
self.X_indexed_norm_ = np.linalg.norm(X, ord=2, axis=1).reshape(-1, 1)
return self
def create_index():
index = puffinn.Index('angular', 10, 1024**2)
print(index)
return True