gpt-gmm-grid-gmm.py

from sklearn.manifold import TSNE
from sklearn.mixture import GaussianMixture
from sklearn.model_selection import GridSearchCV

matrix = np.array(review_data['ada_embedding'].to_list())

# Grid search to find best n_components - number of clusters
components, aic, bic = [], [], []

for i in range(3,11):
    gmm = GaussianMixture(n_components=i)
    gmm.fit(matrix)
    
    components.append(i)
    
    aic.append(
        gmm.aic(matrix)
    )
    bic.append(
        gmm.bic(matrix)
    )

df_search = pd.DataFrame({
    "Components": components,
    "AIC": aic,
    "BIC": bic
})

sns.set_style("darkgrid")
sns.lineplot(data=df_search, x="Components", y="AIC", markers=True)