From 0012618328f28917f19ca21c19335dbb723d607a Mon Sep 17 00:00:00 2001 From: Javier Turek Date: Wed, 17 Feb 2021 09:02:27 -0800 Subject: [PATCH] Update rsrm.py --- brainiak/funcalign/rsrm.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/brainiak/funcalign/rsrm.py b/brainiak/funcalign/rsrm.py index 959f8a4f5..9e2d419ad 100644 --- a/brainiak/funcalign/rsrm.py +++ b/brainiak/funcalign/rsrm.py @@ -108,7 +108,7 @@ class RSRM(BaseEstimator, TransformerMixin): def __init__(self, n_iter=10, features=50, gamma=1.0, rand_seed=0): self.n_iter = n_iter self.features = features - self.lam = gamma + self.gamma = gamma self.rand_seed = rand_seed def fit(self, X): @@ -123,7 +123,7 @@ def fit(self, X): logger.info('Starting RSRM') # Check that the regularizer value is positive - if 0.0 >= self.lam: + if 0.0 >= self.gamma: raise ValueError("Gamma parameter should be positive.") # Check the number of subjects @@ -216,7 +216,7 @@ def _transform_new_data(self, X, subject): R = None for i in range(self.n_iter): R = self.w_[subject].T.dot(X - S) - S = self._shrink(X - self.w_[subject].dot(R), self.lam) + S = self._shrink(X - self.w_[subject].dot(R), self.gamma) return R, S def transform_subject(self, X): @@ -249,7 +249,7 @@ def transform_subject(self, X): s = np.zeros_like(X) for i in range(self.n_iter): w = self._update_transform_subject(X, s, self.r_) - s = self._shrink(X - w.dot(self.r_), self.lam) + s = self._shrink(X - w.dot(self.r_), self.gamma) return w, s @@ -286,17 +286,17 @@ def _rsrm(self, X): R = self._update_shared_response(X, S, W, features) if logger.isEnabledFor(logging.INFO): - objective = self._objective_function(X, W, R, S, self.lam) + objective = self._objective_function(X, W, R, S, self.gamma) logger.info('Objective function %f' % objective) # Main loop for i in range(self.n_iter): W = self._update_transforms(X, S, R) - S = self._update_individual(X, W, R, self.lam) + S = self._update_individual(X, W, R, self.gamma) R = self._update_shared_response(X, S, W, features) # Print objective function every iteration if logger.isEnabledFor(logging.INFO): - objective = self._objective_function(X, W, R, S, self.lam) + objective = self._objective_function(X, W, R, S, self.gamma) logger.info('Objective function %f' % objective) return W, R, S