Created
January 10, 2019 21:36
-
-
Save c0mpiler/674e82096897cc051625a947855a432d to your computer and use it in GitHub Desktop.
Resort alpha-sorted numpy matrix to cluster-sort order
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import numpy as np | |
import time | |
from datetime import timedelta | |
def cluster_sort(genus1, genus2): | |
start_time = time.monotonic() | |
n1 = 'names1.txt' | |
n2 = 'names2.txt' | |
nn1 = 'new_names1.txt' | |
nn2 = 'new_names2.txt' | |
distance_matrix = 'distance.npy' | |
sorted_matrix = 'sorted.npy' | |
orig_mtx = np.load(distance_matrix) | |
names1_dict = {} | |
names2_dict = {} | |
new_names1_dict = {} | |
new_names2_dict = {} | |
new_mtx = np.zeros(orig_mtx.size, dtype=np.float64) | |
new_mtx = new_mtx.ravel() | |
with open(n1, 'r') as names1, open(n2, 'r') as names2, open(nn1, 'r') as new_names1, open(nn2, 'r') as new_names2 : | |
i = 0 | |
for line in names1: | |
names1_dict[line.strip()] = i | |
i = i + 1 | |
i = 0 | |
for line in names2: | |
names2_dict[line.strip()] = i | |
i = i + 1 | |
i = 0 | |
for line in new_names1: | |
new_names1_dict[i] = line.strip() | |
i = i + 1 | |
i = 0 | |
for line in new_names2: | |
new_names2_dict[i] = line.strip() | |
i = i + 1 | |
rows = orig_mtx.shape[0] | |
cols = orig_mtx.shape[1] | |
for x in range(rows): | |
for y in range(cols): | |
val = orig_mtx[names1_dict[new_names1_dict[x]]][names2_dict[new_names2_dict[y]]] | |
new_mtx[x * cols + y] = val | |
new_mtx = np.reshape(new_mtx, orig_mtx.shape) | |
np.save(sorted_matrix, new_mtx) | |
# print("\nNew matrix\n---------------------") | |
# print(new_mtx[0]) | |
# print(new_mtx[1]) | |
# print(new_mtx[2]) | |
# print(new_mtx[3]) | |
# print("\n---------------------\n") | |
end_time = time.monotonic() | |
print("\nSorting Complete! " + str(timedelta(seconds=end_time - start_time))) | |
def main(): | |
parser = argparse.ArgumentParser() | |
parser.add_argument('-g1', dest='genus1', help='Genus 1', required=True) | |
parser.add_argument('-g2', dest='genus2', help='Genus 2', required=True) | |
args = parser.parse_args() | |
cluster_sort(args.genus1, args.genus2) | |
return 0 | |
if __name__ == "__main__": | |
sys.exit(main()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment