diff --git a/pes_to_spec/__init__.py b/pes_to_spec/__init__.py index 5f570b94cfed4d61f71bb2662183295df81f4978..1f1123e7fdf98c4a55066351cbb13b8a9b6162ff 100644 --- a/pes_to_spec/__init__.py +++ b/pes_to_spec/__init__.py @@ -2,4 +2,4 @@ Estimate high-resolution photon spectrometer data from low-resolution non-invasive measurements. """ -VERSION = "0.2.2" +VERSION = "0.2.3" diff --git a/pes_to_spec/model.py b/pes_to_spec/model.py index d04881b96351fa87407b546f54686c2eb0363644..695dc689a0de450137035c752e2fd207dff01b73 100644 --- a/pes_to_spec/model.py +++ b/pes_to_spec/model.py @@ -645,18 +645,6 @@ class MultiOutputWithStd(MetaEstimatorMixin, BaseEstimator): y_std = np.sqrt(sigmas_squared_data + self.fast_inv_alpha) return y, y_std - #n_jobs = self.n_jobs - #y = Parallel(n_jobs=n_jobs, prefer="threads")( - # delayed(e.predict)(X, return_std) for e in self.estimators_ - # #delayed(e.predict)(X) for e in self.estimators_ - #) - #if return_std: - # y, unc = zip(*y) - # return np.asarray(y).T, np.asarray(unc).T - - #return np.asarray(y).T - - class UncorrelatedDeviation(OutlierMixin, BaseEstimator): """ Detect outliers from uncorrelated inputs. @@ -1055,12 +1043,8 @@ class Model(TransformerMixin, BaseEstimator): def is_inlier(in_data, ch: str) -> np.ndarray: data_pca = self.channel_pca[ch].transform(in_data) return self.ood[ch].predict(data_pca) - - #result = Parallel(n_jobs=-1)( - # delayed(is_inlier)(low_res_selected[ch], ch) for ch in channels - #) - #result = dict(result) - return {ch: is_inlier(low_res_selected[ch], ch) for ch in channels} + result = {ch: is_inlier(low_res_selected[ch], ch) for ch in channels} + return result def check_compatibility(self, low_res_data: Dict[str, np.ndarray]) -> np.ndarray: """