from pyclustering.cluster.clarans import clarans;
from pyclustering.utils import timedcall;
from sklearn import datasets

#import iris dataset from sklearn library
iris =  datasets.load_iris();

#get the iris data. It has 4 features, 3 classes and 150 data points.
data = iris.data

"""!
The pyclustering library clarans implementation requires
list of lists as its input dataset.
Thus we convert the data from numpy array to list.
"""
data = data.tolist()

#get a glimpse of dataset
print("A peek into the dataset : ",data[:4])


"""!
@brief Constructor of clustering algorithm CLARANS.
@details The higher the value of maxneighbor, the closer is CLARANS to K-Medoids, and the longer is each search of a local minima.

@param[in] data: Input data that is presented as list of points (objects), each point should be represented by list or tuple.
@param[in] number_clusters: amount of clusters that should be allocated.
@param[in] numlocal: the number of local minima obtained (amount of iterations for solving the problem).
@param[in] maxneighbor: the maximum number of neighbors examined.
"""
clarans_instance = clarans(data, 3, 6, 4);

#calls the clarans method 'process' to implement the algortihm
(ticks, result) = timedcall(clarans_instance.process);
print("Execution time : ", ticks, "\n");

#returns the clusters
clusters = clarans_instance.get_clusters();

#returns the mediods
medoids = clarans_instance.get_medoids();


print("Index of the points that are in a cluster : ",clusters)
print("The target class of each datapoint : ",iris.target)
print("The index of medoids that algorithm found to be best : "medoids)