def _train(self, X, y, n_samples, _):
iter_idx = np.arange(n_samples)
np.random.shuffle(iter_idx)
for t, data_idx in enumerate(iter_idx):
curr_x = X[data_idx, :]
curr_y = y[data_idx]
wtx = np.dot(curr_x, self.w_)
curr_p = sigmoid(wtx)
log_likelihood = logloss(curr_p, curr_y)
self.train_tracker_.track(log_likelihood)
self._update(curr_y, curr_p, curr_x)
def _train(self, X, y, n_samples, n_features):
iter_idx = np.arange(n_samples)
np.random.shuffle(iter_idx)
for t, data_idx in enumerate(iter_idx):
curr_x = X[data_idx, :]
curr_y = y[data_idx]
wtx = 0.
curr_w = {}
for idxi in range(n_features):
curr_w[idxi] = self._get_w(idxi)
wtx += (curr_w[idxi] * curr_x[idxi])
curr_p = sigmoid(wtx)
log_likelihood = logloss(curr_p, curr_y)
self.train_tracker_.track(log_likelihood)
self._update(curr_y, curr_p, curr_x, curr_w)
def _train(self, X, y, n_samples, _):
iter_idx = np.arange(n_samples)
np.random.shuffle(iter_idx)
g_sum = np.zeros(self.n_factors)
g_sum_sqr = np.zeros(self.n_factors)
for t, data_idx in enumerate(iter_idx):
curr_x = X[data_idx, :]
curr_y = y[data_idx]
curr_y_adj = -1. if curr_y == 0. else 1.
p = self._predict_with_feedback(curr_x, g_sum, g_sum_sqr)
# TODO: multiplier can go out of control if the learning rate is too big, why?
multiplier = -curr_y_adj * (1. - 1./(1. + exp(-curr_y_adj*p))) * self.class_weight_[curr_y]
log_likelihood = logloss(p, curr_y)
self.train_tracker_.track(log_likelihood)
self._update(curr_x, g_sum, multiplier)