最长公共子序列

求最长公共子序列

# -- coding: utf-8 -- 
import os
import glob
import sys
import cv2
import shutil
import numpy as np
import random


def lcs(X, Y):
    m, n = len(X), len(Y)
    L = [[0 for x in range(n + 1)] for x in range(m + 1)]

    # build dp
    for i in range(m + 1):
        for j in range(n + 1):
            if i == 0 or j == 0:
                L[i][j] = 0
            elif X[i - 1] == Y[j - 1]:
                L[i][j] = L[i - 1][j - 1] + 1
            else:
                L[i][j] = max(L[i - 1][j], L[i][j - 1])
    index = L[m][n]

    # backtrace
    i, j = m, n
    match = []
    while i > 0 and j > 0:
        if X[i - 1] == Y[j - 1]:
            match.append((i-1, j-1))
            i -= 1
            j -= 1
            index -= 1
        elif L[i - 1][j] > L[i][j - 1]:
            i -= 1
        else:
            j -= 1
    match.reverse()

    # 求common
    common = []
    for i, j in match:
        common.append(X[i])

    # 求union
    union = []
    newX = []
    newY = []
    wild = "#"
    anchors = [(-1, -1)]
    for pair in match:
        anchors.append(pair)
    anchors.append((m, n))
    for i in range(1, len(anchors)):
        xs, ys = anchors[i-1]
        xs += 1
        ys += 1
        xe, ye = anchors[i]
        for k in range(xs, xe):
            union.append(X[k])
            newX.append(X[k])
            newY.append(wild)
        for k in range(ys, ye):
            union.append(Y[k])
            newX.append(wild)
            newY.append(Y[k])
        if i != len(anchors)-1:
            union.append(X[xe])
            newX.append(X[xe])
            newY.append(X[xe])
    return match, common, union, newX, newY


def sample_sequence(full, r=0.75):
    new = []
    for i in full:
        if random.random() < r:
            new.append(i)
    return new


if __name__ == '__main__':
    # Driver program
    real = ['7-8', '3-4', '12-2', '19-17', '12-16', '14-19', '2-5', '12-18', '9-7', '17-3', '15-15', '13-13', '14-7', '4-17', '9-14', '5-4', '6-8', '1-5', '18-14', '12-20']
    s1 = sample_sequence(real)
    s2 = sample_sequence(real)
    match, common, union, newX, newY = lcs(s1, s2)
    for i in range(len(union)):
        print(newX[i].ljust(8, ' '), newY[i].ljust(8, ' '), union[i].ljust(8, ' '))