3liud

fig = plt.figure(figsize=(20,15))
ax = fig.add_subplot(111, projection='3d')

ax.scatter(df2['Age'][df2['Label']==0], df2['Annual Income (k$)'][df2['Label']==0], 
           df2['Spending Score (1-100)'][df2['Label']==0], c='green', s=50)
ax.scatter(df2['Age'][df2['Label']==1], df2['Annual Income (k$)'][df2['Label']==1], 
           df2['Spending Score (1-100)'][df2['Label']==1], c='blue', s=50)
ax.scatter(df2['Age'][df2['Label']==2], df2['Annual Income (k$)'][df2['Label']==2], 
           df2['Spending Score (1-100)'][df2['Label']==2], c='black', s=50)
ax.scatter(df2['Age'][df2['Label']==3], df2['Annual Income (k$)'][df2['Label']==3], 

3liud

df2_clusters = df2['Label'].value_counts()
df2_clusters

3liud

km = KMeans(n_clusters=5)
km.fit(df2)
y = km.predict(df2)
df2['Label'] = y
df2.head()

3liud

plt.figure(figsize=(13, 6))
plt.plot(range(1, 11), errors)
plt.plot(range(1,11), errors, linewidth=3, color='blue', marker='8')
plt.xlabel('No. of Clusters')
plt.ylabel('WCSS')
plt.xticks(np.arange(1,11,1))
plt.show()

3liud

errors = []
for i in range(1, 11):
    kmeans = KMeans(n_clusters=i)
    kmeans.fit(df2)
    errors.append(kmeans.inertia_)

3liud

df2 = df[['Annual Income (k$)', 'Spending Score (1-100)', 'Age']]
df2.head()

3liud

sns.scatterplot(x='Annual Income (k$)', y='Spending Score (1-100)', data=df1, hue='Label', s=50,
               palette =['red', 'green', 'black', 'brown', 'orange']);

3liud

df1_clusters = df1['Label'].value_counts()
df1_clusters

3liud

km = KMeans(n_clusters=5)
km.fit(df1)
y = km.predict(df1)
df1['Label'] = y
df1.head()

3liud

# plot
plt.figure(figsize=(13, 6))
plt.plot(range(1, 11), errors)
plt.plot(range(1,11), errors, linewidth=3, color='blue', marker='8')
plt.xlabel('No. of Clusters')
plt.ylabel('WCSS')
plt.xticks(np.arange(1,11,1))
plt.show()