state['n_components'],
state['whiten'],
state['copy'],
state['batch_size'],
)
# Set the attributes
pca.explained_variance_ = np.array(
state['explained_variance_'])
pca.explained_variance_ratio_ = np.array(
state['explained_variance_ratio_'])
pca.var_ = np.array(state['var_'])
pca.noise_variance_ = np.float64(state['noise_variance_'])
pca.singular_values_ = np.array(state['singular_values_'])
pca.mean_ = np.array(state['mean_'])
pca.components_ = np.array(state['components_'])
pca.n_samples_seen_ = np.int64(state['n_samples_seen_'])
#pca.n_features_in_ = int(state['n_features_in_'])
pca.n_components_ = int(state['n_components_'])
#pca.batch_size_ = int(state['batch_size_'])
logging.info('Loaded the PCA object')
logging.info('Attempting to transform data & save')
# Attempt to get points to save train MEVM
points = pca.transform(h5['points'][:])
