def fit(self, X, y):
"""Fit the model
Parameters
----------
X: 2d array, shape (n_samples, n_features)
Data array
y: 2d array, shape (n_pairs, 3)
Array containing pairs elements indices and associated label.
The indices of pairs elements are contained in ``y[:, :2]``, while the
labels are given by ``y[:, 2]``. Labels are in {-1, 1}. The elements
of the i-th pair are ``X[y[i, 0]]`` and ``X[y[i, 1]]``.
"""
# pylint: disable=E1101
X = np.asarray(X)
y = np.asarray(y)
pairs = y[:, :2].astype("int")
labels = y[:, 2]
# initialize with whiten PCA
L0 = pca(X, self.n_components)
# Normalize to have unit average distance
L0 /= np.sqrt(compute_distances(X, pairs, proj_mat=L0).mean())
b0 = 1.0
self._diff = compute_differences(X, pairs)
self._labels = labels
n_pairs = len(pairs)
n_samples, self.n_features = X.shape
if self.kernel:
self._U = np.zeros((n_pairs, n_samples))
self._U[range(n_pairs), pairs[:, 0]] = 1.0
self._U[range(n_pairs), pairs[:, 1]] = -1.0
self._U = csr_matrix(self._U)
x0 = MatThreshold(L0, b0)
if self.callback is not None:
self.callback(x0)
L, self.threshold_ = lgbopt.fmin_gd(self._compute_obj,
self._compute_grad,
x0,
callback=self.callback,
inner=MatThreshold.dot,
**self.opt_args)[0]
self.coefs_ = L.T
del self._diff, self._labels
if self.kernel:
del self._U
return self
def fit(self, X, y):
"""Fit the model
Parameters
----------
X: 2d array, shape (n_samples, n_features)
Data array
y: 2d array, shape (n_pairs, 3)
Array containing pairs elements indices and associated label.
The indices of pairs elements are contained in ``y[:, :2]``, while the
labels are given by ``y[:, 2]``. Labels are in {-1, 1}. The elements
of the i-th pair are ``X[y[i, 0]]`` and ``X[y[i, 1]]``.
"""
# pylint: disable=E1101
X = np.asarray(X)
y = np.asarray(y)
pairs = y[:, :2].astype("int")
labels = y[:, 2]
# initialize with whiten PCA
L0 = pca(X, self.n_components)
# Normalize to have unit average distance
L0 /= np.sqrt(compute_distances(X, pairs, proj_mat=L0).mean())
b0 = 1.0
self._diff = compute_differences(X, pairs)
self._labels = labels
n_pairs = len(pairs)
n_samples, self.n_features = X.shape
if self.kernel:
self._U = np.zeros((n_pairs, n_samples))
self._U[range(n_pairs), pairs[:, 0]] = 1.0
self._U[range(n_pairs), pairs[:, 1]] = -1.0
self._U = csr_matrix(self._U)
x0 = MatThreshold(L0, b0)
if self.callback is not None:
self.callback(x0)
L, self.threshold_ = lgbopt.fmin_gd(
self._compute_obj, self._compute_grad, x0,
callback=self.callback, inner=MatThreshold.dot,
**self.opt_args)[0]
self.coefs_ = L.T
del self._diff, self._labels
if self.kernel:
del self._U
return self
def fit(self, X, y):
"""Fit the model
Parameters
----------
X: 2d array, shape (n_samples, n_features)
Data array
y: 2d array, shape (n_pairs, 3)
Array containing pairs elements indices and associated label.
The indices of pairs elements are contained in ``y[:, :2]``, while the
labels are given by ``y[:, 2]``. Labels are in {-1, 1}. The elements
of the i-th pair are ``X[y[i, 0]]`` and ``X[y[i, 1]]``.
"""
# pylint: disable=E1101
X1 = np.asarray(X[0])
X2 = np.asarray(X[1])
y = np.asarray(y)
pairs = y[:, :2].astype("int")
labels = y[:, 2]
# initialize with whiten PCA
L0 = pca(np.hstack(X), self.n_components)
A0 = L0[:, :X1.shape[1]]
B0 = L0[:, X1.shape[1]:]
# Normalize to have unit average distance
dist = np.sqrt(
compute_cm_distances(X1, X2, pairs, proj_mat1=A0,
proj_mat2=B0).mean())
b0 = 1.0
A0 /= dist
B0 /= dist
self._labels = labels
n_pairs = len(pairs)
n_samples, self.n_features1 = X1.shape
if self.kernel:
self._U = np.zeros((n_pairs, n_samples))
self._U[range(n_pairs), pairs[:, 0]] = 1.0
self._U = csr_matrix(self._U)
self._V = np.zeros((n_pairs, n_samples))
self._V[range(n_pairs), pairs[:, 1]] = 1.0
self._V = csr_matrix(self._V)
self._X1 = X1
self._X2 = X2
self._pairs = pairs
x0 = Mat2Threshold(A0, B0, b0)
if self.callback is not None:
self.callback(x0)
A, B, self.threshold_ = lgbopt.fmin_gd(self._compute_obj,
self._compute_grad,
x0,
callback=self.callback,
inner=Mat2Threshold.dot,
**self.opt_args)[0]
self.coefs_ = [A.T, B.T]
del self._labels, self._X1, self._X2, self._pairs
if self.kernel:
del self._U, self._V
return self
def fit(self, X, y):
"""Fit the model
Parameters
----------
X: 2d array, shape (n_samples, n_features)
Data array
y: 2d array, shape (n_pairs, 3)
Array containing pairs elements indices and associated label.
The indices of pairs elements are contained in ``y[:, :2]``, while the
labels are given by ``y[:, 2]``. Labels are in {-1, 1}. The elements
of the i-th pair are ``X[y[i, 0]]`` and ``X[y[i, 1]]``.
"""
# pylint: disable=E1101
X1 = np.asarray(X[0])
X2 = np.asarray(X[1])
y = np.asarray(y)
pairs = y[:, :2].astype("int")
labels = y[:, 2]
# initialize with whiten PCA
L0 = pca(np.hstack(X), self.n_components)
A0 = L0[:, :X1.shape[1]]
B0 = L0[:, X1.shape[1]:]
# Normalize to have unit average distance
dist = np.sqrt(compute_cm_distances(X1, X2, pairs,
proj_mat1=A0,
proj_mat2=B0).mean())
b0 = 1.0
A0 /= dist
B0 /= dist
self._labels = labels
n_pairs = len(pairs)
n_samples, self.n_features1 = X1.shape
if self.kernel:
self._U = np.zeros((n_pairs, n_samples))
self._U[range(n_pairs), pairs[:, 0]] = 1.0
self._U = csr_matrix(self._U)
self._V = np.zeros((n_pairs, n_samples))
self._V[range(n_pairs), pairs[:, 1]] = 1.0
self._V = csr_matrix(self._V)
self._X1 = X1
self._X2 = X2
self._pairs = pairs
x0 = Mat2Threshold(A0, B0, b0)
if self.callback is not None:
self.callback(x0)
A, B, self.threshold_ = lgbopt.fmin_gd(
self._compute_obj, self._compute_grad, x0,
callback=self.callback, inner=Mat2Threshold.dot,
**self.opt_args)[0]
self.coefs_ = [A.T, B.T]
del self._labels, self._X1, self._X2, self._pairs
if self.kernel:
del self._U, self._V
return self
