Feature importance in deep learning

Deep Learning
16

Just going to tag on this a little bit, I re-fractured the code to where now you just need to input the learner.

def feature_importance(learner): 
  # based on: https://medium.com/@mp.music93/neural-networks-feature-importance-with-fastai-5c393cf65815
    data = learner.data.train_ds.x
    cat_names = data.cat_names
    cont_names = data.cont_names
    loss0=np.array([learner.loss_func(learner.pred_batch(batch=(x,y.to("cpu"))), y.to("cpu")) for x,y in iter(learner.data.valid_dl)]).mean()
    fi=dict()
    types=[cat_names, cont_names]
    for j, t in enumerate(types):
      for i, c in enumerate(t):
        loss=[]
        for x,y in iter(learner.data.valid_dl):
          col=x[j][:,i]    #x[0] da hier cat-vars
          idx = torch.randperm(col.nelement())
          x[j][:,i] = col.view(-1)[idx].view(col.size())
          y=y.to('cpu')
          loss.append(learner.loss_func(learner.pred_batch(batch=(x,y)), y))
        fi[c]=np.array(loss).mean()-loss0
    d = sorted(fi.items(), key=lambda kv: kv[1], reverse=True)
    return pd.DataFrame({'cols': [l for l, v in d], 'imp': np.log1p([v for l, v in d])})
7 Likes