Bin (discretize) data points for seeding mean shift clustering method

bin_points.py

import numpy as np
from collections import defaultdict 

def bin_points(X, bin_size, min_bin_freq):
    bin_sizes = defaultdict(int)
    for point in X:
        binned_point = np.cast[np.int32](point / bin_size)
        bin_sizes[tuple(binned_point)] += 1

    bin_seeds = np.array([point for point, freq in bin_sizes.iteritems() if freq >= min_bin_freq], dtype=np.float32)
    bin_seeds = bin_seeds * bin_size
    return bin_seeds