def compute_distances(self, x1, x2):
"""
The method uses a function implemented in Cython. Data (`x1` and `x2`)
is accompanied by two tables. One is a 2-d table in which elements of
`x1` (`x2`) are replaced by 0's and 1's. The other is a vector
indicating rows (or column) with nan values.
The function in Cython uses a fast loop without any conditions to
compute distances between rows without missing values, and a slower
loop for those with missing values.
"""
nonzeros1 = np.not_equal(x1, 0).view(np.int8)
if self.axis == 1:
nans1 = _distance.any_nan_row(x1)
if x2 is None:
nonzeros2, nans2 = nonzeros1, nans1
else:
nonzeros2 = np.not_equal(x2, 0).view(np.int8)
nans2 = _distance.any_nan_row(x2)
return _distance.jaccard_rows(
nonzeros1, nonzeros2,
x1, x1 if x2 is None else x2,
nans1, nans2,
self.ps,
x2 is not None)
else:
nans1 = _distance.any_nan_row(x1.T)
return _distance.jaccard_cols(
nonzeros1, x1, nans1, self.ps)
def compute_distances(self, x1, x2):
"""
The method uses a function implemented in Cython. Data (`x1` and `x2`)
is accompanied by two tables. One is a 2-d table in which elements of
`x1` (`x2`) are replaced by 0's and 1's. The other is a vector
indicating rows (or column) with nan values.
The function in Cython uses a fast loop without any conditions to
compute distances between rows without missing values, and a slower
loop for those with missing values.
"""
nonzeros1 = np.not_equal(x1, 0).view(np.int8)
if self.axis == 1:
nans1 = _distance.any_nan_row(x1)
if x2 is None:
nonzeros2, nans2 = nonzeros1, nans1
else:
nonzeros2 = np.not_equal(x2, 0).view(np.int8)
nans2 = _distance.any_nan_row(x2)
return _distance.jaccard_rows(nonzeros1, nonzeros2, x1,
x1 if x2 is None else x2, nans1,
nans2, self.ps, x2 is not None)
else:
nans1 = _distance.any_nan_row(x1.T)
return _distance.jaccard_cols(nonzeros1, x1, nans1, self.ps)
def _compute_dense(self, x1, x2):
"""
The method uses a function implemented in Cython. Data (`x1` and `x2`)
is accompanied by two tables. One is a 2-d table in which elements of
`x1` (`x2`) are replaced by 0's and 1's. The other is a vector
indicating rows (or column) with nan values.
The function in Cython uses a fast loop without any conditions to
compute distances between rows without missing values, and a slower
loop for those with missing values.
"""
# view is false positive, pylint: disable=no-member
nonzeros1 = np.not_equal(x1, 0).view(np.int8)
if self.axis == 1:
weights = [5, 45, 50] if x2 is None else [5, 5, 45, 45]
callbacks = StepwiseCallbacks(self.callback, weights)
nans1 = _distance.any_nan_row(x1, callbacks.next())
if x2 is None:
nonzeros2, nans2 = nonzeros1, nans1
else:
nonzeros2 = np.not_equal(x2, 0).view(np.int8)
nans2 = _distance.any_nan_row(x2, callbacks.next())
return _distance.jaccard_rows(nonzeros1, nonzeros2, x1,
x1 if x2 is None else x2, nans1,
nans2, self.ps, x2 is not None,
callbacks.next(), callbacks.next())
else:
callbacks = StepwiseCallbacks(self.callback, [10, 90])
nans1 = _distance.any_nan_row(x1.T, callbacks.next())
return _distance.jaccard_cols(nonzeros1, x1, nans1, self.ps,
callbacks.next())