def score_sentence_level(gold, pred):
pearson = pearsonr(gold, pred)
mae = mean_absolute_error(gold, pred)
rmse = np.sqrt(mean_squared_error(gold, pred))
spearman = spearmanr(rankdata(gold, method="ordinal"),
rankdata(pred, method="ordinal"))
delta_avg = delta_average(gold, rankdata(pred, method="ordinal"))
return (pearson[0], mae, rmse), (spearman[0], delta_avg)
def sentence_level_scores(
true_targets: List[float],
predicted_targets: List[float]) -> Tuple[Tuple, Tuple]:
pearson = pearsonr(true_targets, predicted_targets)
mae = mean_absolute_error(true_targets, predicted_targets)
rmse = np.sqrt(mean_squared_error(true_targets, predicted_targets))
spearman = spearmanr(
rankdata(true_targets, method="ordinal"), # NOQA
rankdata(predicted_targets, method="ordinal"), # NOQA
)
delta_avg = delta_average(true_targets,
rankdata(predicted_targets, method="ordinal"))
return (pearson[0], mae, rmse), (spearman[0], delta_avg)