Inertia for nltk k means clustering using cosine_similarity

Programming
, ,
1

Does NLTK KMeans provide an inertia measure similar to that of sklearn?

I have used NLTK for KMeans clustering and would like to change the distance metric. Does NLTK KMeans provide an inertia measure similar to that of scikit-learn?

The code below shows how people usually calculate inertia with sklearn KMeans:

inertia = []
for n_clusters in range(2, 26, 1):
  clusterer = KMeans(n_clusters=n_clusters)
  preds = clusterer.fit_predict(features)
  centers = clusterer.cluster_centers_
  inertia.append(clusterer.inertia_)

plt.plot([i for i in range(2,26,1)], inertia, 'bx-')
plt.xlabel('k')
plt.ylabel('Sum_of_squared_distances')
plt.title('Elbow Method For Optimal k')
plt.show()
2

No, NLTK KMeans does not provide an inertia measure similar to that of scikit-learn.