Ngram_range = (1,1)
Samples = 40000
Distribution 
Clusters left 16219
Score samples = 5000
- Silhouette Score: 0.3714598392780462
- Calinski-Harabasz Index: 531.2487680337874
- Davies-Bouldin Index: 0.3510776700047736
Ngram_range = (3,4)
Samples = 40000
Clusters left 20780
- Silhouette Score: 0.3731614464962901
- Calinski-Harabasz Index: 1710.8685446622549
- Davies-Bouldin Index: 0.26170137702074264
Ngram_range(1,4)
Samples = 40000
Clusters left 21078
- Silhouette Score: 0.394332678120356
- Calinski-Harabasz Index: 2121.956261477304
- Davies-Bouldin Index: 0.2418388814956972
Ngram_range(1,6)
Samples = 40000
Clusters left 20959
- Silhouette Score: 0.3873160908743396
- Calinski-Harabasz Index: 1844.4039985962393
- Davies-Bouldin Index: 0.25929544332685023
Ngram_range = (1,6)
- Silhouette Score: 0.3760824861012863
- Calinski-Harabasz Index: 1314.3402354925827
- Davies-Bouldin Index: 0.30394380049564845
Ngram_range = (1,5)
- Silhouette Score: 0.375777584363468
- Calinski-Harabasz Index: 1134.77627081612
- Davies-Bouldin Index: 0.3099807140343013