vec_proj_pca.py

# Only keep a certain number of eigen vectors based on 
# the "explained variance percentage" which tells us how 
# much information (variance) can be attributed to each 
# of the principal components

exp_var_percentage = 0.97 # Threshold of 97% explained variance

tot = sum(eig_vals)
var_exp = [(i / tot)*100 for i in sorted(eig_vals, reverse=True)]
cum_var_exp = np.cumsum(var_exp)

num_vec_to_keep = 0

for index, percentage in enumerate(cum_var_exp):
  if percentage > exp_var_percentage:
    num_vec_to_keep = index + 1
    break