def fit(self, X, y):
n_samples = X.shape[0]
rs = check_random_state(self.random_state)
self.label_binarizer_ = LabelBinarizer(neg_label=-1, pos_label=1)
Y = self.label_binarizer_.fit_transform(y)
self.classes_ = self.label_binarizer_.classes_.astype(np.int32)
n_vectors = Y.shape[1]
dual_coef = np.zeros((n_vectors, n_samples), dtype=np.float64)
if self.warm_start and self.dual_coef_ is not None:
dual_coef[:, self.support_indices_] = self.dual_coef_
self.dual_coef_ = dual_coef
coef = np.empty(0, dtype=np.float64)
kernel = self._get_kernel()
kcache = KernelCache(kernel, n_samples, self.cache_mb, 1, self.verbose)
self.support_vectors_ = X
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
for i in xrange(n_vectors):
_dual_cd(self, coef, self.dual_coef_[i],
X, Y[:, i], kcache, False,
self.selection, self.search_size,
self.termination, self.sv_upper_bound,
self.C, self.loss, self.max_iter, rs, self.tol,
self.shrinking, self.callback, verbose=self.verbose)
sv = np.sum(self.dual_coef_ != 0, axis=0, dtype=bool)
self.support_indices_ = np.arange(n_samples)[sv]
if self.kernel != "precomputed":
self.dual_coef_ = np.ascontiguousarray(self.dual_coef_[:, sv])
mask = safe_mask(X, sv)
self.support_vectors_ = X[mask]
if self.verbose >= 1:
print "Number of support vectors:", np.sum(sv)
return self
def fit(self, X, y):
n_samples, n_features = X.shape
rs = check_random_state(self.random_state)
self.label_binarizer_ = LabelBinarizer(neg_label=-1, pos_label=1)
Y = self.label_binarizer_.fit_transform(y)
n_vectors = Y.shape[1]
if not self.warm_start or self.coef_ is None:
self.coef_ = np.zeros((n_vectors, n_features),
dtype=np.float64)
self.dual_coef_ = np.zeros((n_vectors, n_samples),
dtype=np.float64)
kernel = get_kernel("linear")
kcache = KernelCache(kernel, n_samples, 0, 0, self.verbose)
for i in xrange(n_vectors):
_dual_cd(self, self.coef_[i], self.dual_coef_[i],
X, Y[:, i], kcache, True,
"permute", 60, self.termination, self.sv_upper_bound,
self.C, self.loss, self.max_iter, rs, self.tol,
self.shrinking, self.callback, verbose=self.verbose)
return self
