def vanDongenSpectral(args):
neighbors, min_d, components, metric, dataset, scaler, k = args
print(dataset + ', ' + metric + ', ' + scaler + ', n_components=' +
str(components) + ', n_neighbors=' + str(neighbors) + ', min_dist=' +
str(min_d) + ', k=' + str(k))
# Se estandariza usando el scaler correspondiente
df = scalers[scaler].fit_transform(datasets[dataset])
# Se aplica UMAP
um = UMAP(n_components=components,
n_neighbors=neighbors,
min_dist=min_d,
metric=metric)
embedding = um.fit_transform(df)
# Se aplica KMeans al embedding
km = KMeans(n_clusters=k, random_state=0).fit(embedding)
# Se calcula la matriz de confusion
tmp = pd.DataFrame({'Generos': metadata.genre, 'data': km.labels_})
ct = pd.crosstab(tmp['Generos'], tmp['data'])
return vanDongen(ct)
# Se calculan las validaciones internas
sil = get_silhouette_avg(embedding, k)
sse = get_sse(embedding, k)
# Se aplica KMeans
km = KMeans(n_clusters=k,
random_state=0).fit(embedding)
# Se calcula la matriz de confusión
tmp = pd.DataFrame({
'Generos': metadata.genre,
'data': km.labels_
})
ct = pd.crosstab(tmp['Generos'], tmp['data'])
# Se calculan las validaciones externas
vd = vanDongen(ct)
rand = adjusted_rand_score(metadata.genre,
km.labels_)
# Se guardan los resultados de la corrida
results.append([
dataset, metric, scaler, components, min_d,
neighbors, k, sil, sse, vd, rand
])
df_results = pd.DataFrame(results, columns=columns)
df_results
df_results.to_csv('spectral_' + metrics[0] + '.csv', index=False)