def ComputeEdges(self, seqs):
edge_dict = dict()
for i in range(len(seqs)):
for j in range(i + 1, len(seqs)):
edge_dict[(i,
j)] = utils.HammingDistance(seqs[i].seq,
seqs[j].seq)
return edge_dict
def _ConstructGraph(self, seqs):
graph = Graph()
graph.add_vertices(len(seqs))
edges = []
edge_weights = dict()
for i in range(len(seqs)):
for j in range(i + 1, len(seqs)):
edges.append((i, j))
edge_weights[(i, j)] = utils.HammingDistance(seqs[i], seqs[j])
graph.add_edges(edges)
return graph, edge_weights
def NormalizedHammingDistance(bin_text, keysize): """Computes the normalized average Hamming distance between consecutive pairs of bin_text blocks of KEYSIZE bytes. The lowest this result is, the more are consecutive blocks of KEYSIZE bytes likely to be similar to each other; this means that they were likely encoded with the same set of characters, and therefore the key could be of KEYSIZE length (in bytes). """ hamming_distance = 0 # Number of blocks of KEYSIZE bytes in the text. num_blocks = int(len(bin_text) / (keysize * 8)) # Keeps track of the first bit of the pair of chunks we # are considering start_block_index = 0 # Takes the first pair of blocks of KEYSIZE bytes, then # the second pair, etc... (no overlapping). For each pair, # compare the Hamming distance between the two blocks and sum # it to our accumulator. # For some keysizes there are leftover data at the end that # cannot be divided in two chunks of the required size; in that # case we ignore them and stop before. end_block = len(bin_text) - (keysize * 16) while start_block_index <= end_block: # Each binary chunk is therefore of size keysize*8. chunk1 = bin_text[start_block_index : start_block_index + keysize*8] chunk2 = bin_text[start_block_index + keysize*8 : start_block_index + keysize*16] hamming_distance += utils.HammingDistance(chunk1, chunk2) start_block_index += (keysize * 16) # The normalized distance is the Hamming distance divided by the # number of blocks and the key size. return (hamming_distance / (num_blocks * keysize))
#!/usr/bin/env python
'''
Content: solution to a programming assignment for the Bioinformatics Algorithms (Part 1) on Coursera.
Associated textbook: "Bioinformatics Algorithms: An Active-Learning Approach" by Phillip Compeau & Pavel Pevzner.
Assignment: hosted in Stepik.org
Problem Title: Hamming Distance Problem
URL: https://stepik.org/lesson/9/step/3?course=Stepic-Interactive-Text-for-Week-2&unit=8224
Code Challenge: Hamming Distance Problem: Compute the Hamming distance between two strings.
Input: Two strings of equal length.
Output: The Hamming distance between these strings.
'''
import sys
import utils
import numpy as np
if __name__ == '__main__':
seq1 = sys.stdin.readline()[:-1]
seq2 = sys.stdin.readline()[:-1]
print(utils.HammingDistance(seq1,seq2))