vizualise-cluster.py

#plot the scatters
'''
X[y_pred==0] - will list records which belongs to cluster 0
output:
       Qty  UnitPrice
1     1911       3.39
'''

plt.scatter(X[y_pred == 0].iloc[:, 0], X[y_pred == 0].iloc[:, 1], s=5, c="red")
plt.scatter(X[y_pred == 1].iloc[:, 0], X[y_pred == 1].iloc[:, 1], s=5, c="green")
plt.scatter(X[y_pred == 2].iloc[:, 0], X[y_pred == 2].iloc[:, 1], s=5, c="blue")
plt.scatter(X[y_pred == 3].iloc[:, 0], X[y_pred == 3].iloc[:, 1], s=5, c="purple")

# centroids X, Y Coordinates can be get through kmeans.cluster_centers_
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=100, c="black", marker="*")

# I limit the y value to get rid of the outlier records
plt.ylim([0,20])
plt.xlabel("Sold Quantity")
plt.ylabel("Unit Price")
plt.show()