Function to get the data reduced with the minimal number of components when using PCA decomposition.

min_pca.md

def get_min_pca(scaled_data, min_var_explained=0.95, verbose=False):
  """
  Decompose `scaled_data` into principal components.
  Return the number of components above `min_var_explained` threshold,
  the threshold value and the transformed data.
  Args
  ----
  scaled_data: numpy array: scaled data
  min_var_explained: float, default 0.95: variance explained threshold
  verbose: Bool, default False: print results
  Return
  ------
  pcs, min_var_explained and reduced scaled data
  
  """
  pca_all = PCA(n_components=min_var_explained, svd_solver='full')
  pca_all.fit(scaled_data)
  reduced = pca_all.transform(scaled_data)
  pcs = pca_all.n_components_
  if verbose:
    print(f'Components for {min_var_explained:.0%} of variance explained:\n{pcs}')
    
  return pcs, min_var_explained, reduced