def elbow_manual(n_clusters,X):
sample,features=X.shape
e=10**(-10)
X = DataFrameImputer().fit_transform(X)
SSE=[]
SSE1=[]
for i in range(1,n_clusters):
Y=labeling(i,X,0.6)
centers,labels=ss_kmeans_pp(Y,i,e)
centers_sk,labels_sk=kmean_sklearn(i,X)
# en utilisant lloyd
SSE.append(np.sum(np.min(cdist(X,centers,'euclidean'),axis=1)))
# en utilisant sklearn
SSE1.append(np.sum(np.min(cdist(X,centers_sk,'euclidean'),axis=1)))
K=np.arange(1,n_clusters)
plt.plot(K,SSE,label='méthode manuel',color='blue')
plt.plot(K,SSE1,label='méthode sklearn',color='orange')
plt.xticks(np.arange(1, n_clusters, 1))
kn = KneeLocator(K, SSE1, curve='convex', direction='decreasing')
# plotting dashed_vline on knee
plt.vlines(kn.knee, plt.ylim()[0], plt.ylim()[1], linestyles='dashed')
plt.show()
plt.legend()
# Main
# =============================================================================
if __name__ == "__main__":
# Uploading ML dataset
base = pd.read_csv('BigML_Dataset.csv', sep=',')
X = base.iloc[:, 1:]
# Imputing based on mean for numeric, and most frequent for strings
X = DataFrameImputer().fit_transform(X)
X.fillna(X.mean())
quanti_X = X.drop(['shops_used'], axis='columns')
k, e = 5, 10**(-10)
#kmeans++
t0 = time()
centers, clusters = kmeans_pp(quanti_X, k, e)
t1 = time()
print('En utilisant kmeans++ : %f' % (t1 - t0))
#comparaison avec kmeans de sklearn
t2 = time()
resultat = kmean_sklearn(k, quanti_X)
t3 = time()
print('En utilisant kmeans++ de sklearn : %f' % (t3 - t2))
N = 100
distance_moyenne = inertie_intra(k, quanti_X, e, N)
print('Inertie_intra en utilisant kmeans++:', distance_moyenne)
return centers, clusters
# =============================================================================
# Main
# =============================================================================
if __name__ == "__main__":
# Uploading ML dataset
base = pd.read_csv('BigML_Dataset.csv', sep=',')
X = base.iloc[:, 1:]
# Imputing based on mean for numeric, and most frequent for strings
X = DataFrameImputer().fit_transform(X)
X.fillna(X.mean())
k, e = 5, 10**(-10)
#kmeans++
t0 = time()
centers, clusters = kmeans_pp(X, k, e)
t1 = time()
print('En utilisant kmeans++ : %f' % (t1 - t0))
#comparaison avec kmeans de sklearn
t2 = time()
resultat = kmean_sklearn(k, X)
t3 = time()
print('En utilisant kmeans++ de sklearn : %f' % (t3 - t2))