Sort data points by hierarchical clustering

hclust_sort.py

from sklearn.datasets import make_biclusters
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

def resort_rows_hclust(U):
    """Sorts the rows of a matrix by hierarchical clustering

    Parameters:
        U (ndarray) : matrix of data

    Returns:
        prm (ndarray) : permutation of the rows
    """

    from scipy.cluster import hierarchy
    Z = hierarchy.ward(U)
    return hierarchy.leaves_list(hierarchy.optimal_leaf_ordering(Z, U))

data = make_biclusters(shape=(300, 300), n_clusters=5, noise=5, shuffle=True, random_state=0)[0]
plt.imshow(data, aspect='auto')

ii = resort_rows_hclust(data)
jj = resort_rows_hclust(data.T)

new_data = data.copy()
new_data = new_data[ii]
new_data = new_data[:,jj]

plt.imshow(new_data, aspect='auto')

Expected output: