6. Metrics

6.1. Distances

6.1.1. Wasserstein

In mathematics, the Wasserstein distance or Kantorovich–Rubinstein metric is a distance function defined between probability distributions on a given metric space M.

from scipy.stats import wasserstein_distance, beta

wasserstein_distance([1,2,3,4],[1,2,3,4,4])
x = np.linspace(0, 1, 100)
dist1 = stats.beta.pdf(x,5,5)
dist2 = stats.beta.pdf(x,8,5)
ws_distance = wasserstein_distance(dist1,dist2)

6.1.2. Sklearn Metrics

To import or get the short name of all metrics in sklearn.

from sklearn.metrics import SCORERS
SCORERS.keys()