Optimizing for FNC and TB scores

[profricecake]

Hi @mdo and @jrb, I have a question about calculating exposure.

Earlier in this thread @mdo uses this:

@mdo

((pred @ features)**2).sum()

And in a different thread (Model Diagnostics: Feature Exposure) @jrb used something a little different:

@jrb

def feature_exposures(df):
    feature_names = [f for f in df.columns
                     if f.startswith("feature")]
    exposures = []
    for f in feature_names:
        fe = spearmanr(df[PREDICTION_NAME], df[f])[0]
        exposures.append(fe)
    return np.array(exposures)

def feature_exposure(df):
    return np.sqrt(np.mean(np.square(feature_exposures(df))))

Both go up as exposure goes up, and both stop at zero if exposure is zero. But to me, @jrb’s version has the nice additional quality of being bound to lie between 0-1.0 no matter how many features are being considered.

Are there other reasons you might choose one over the other? Such as accuracy, or speed, or … ?

Thanks,

prc