Dynamic programming solution to maximizing an expression by placing parentheses - python

I'm trying to implement an algorithm from Algorithmic Toolbox course on Coursera that takes an arithmetic expression such as 5+8*4-2 and computes its largest possible value. However, I don't really understand the choice of indices in the last part of the shown algorithm; my implementation fails to compute values using the ones initialized in 2 tables (which are used to store maximized and minimized values of subexpressions).
The evalt function just takes the char, turns it into the operand and computes a product of two digits:
def evalt(a, b, op):
if op == '+':
return a + b
#and so on
MinMax computes the minimum and the maximum values of subexpressions
def MinMax(i, j, op, m, M):
mmin = 10000
mmax = -10000
for k in range(i, j-1):
a = evalt(M[i][k], M[k+1][j], op[k])
b = evalt(M[i][k], m[k+1][j], op[k])
c = evalt(m[i][k], M[k+1][j], op[k])
d = evalt(m[i][k], m[k+1][j], op[k])
mmin = min(mmin, a, b, c, d)
mmax = max(mmax, a, b, c, d)
return(mmin, mmax)
And this is the body of the main function
def get_maximum_value(dataset):
op = dataset[1:len(dataset):2]
d = dataset[0:len(dataset)+1:2]
n = len(d)
#iniitializing matrices/tables
m = [[0 for i in range(n)] for j in range(n)] #minimized values
M = [[0 for i in range(n)] for j in range(n)] #maximized values
for i in range(n):
m[i][i] = int(d[i]) #so that the tables will look like
M[i][i] = int(d[i]) #[[i, 0, 0...], [0, i, 0...], [0, 0, i,...]]
for s in range(n): #here's where I get confused
for i in range(n-s):
j = i + s
m[i][j], M[i][j] = MinMax(i,j,op,m,M)
return M[0][n-1]

Sorry to bother, here's what had to be improved:
for s in range(1,n)
in the main function, and
for k in range(i, j):
in MinMax function. Now it works.

The following change should work.
for s in range(1,n):
for i in range(0,n-s):

Related

Determining if there exists numbers n1, n2 in a, b and n3 in c such that n1 + n2 = n3 [ftt, polynomial multiplication]

Hello I am working on a problem that seems to be out of my league so any tips, pointers to reading materials etc. are really appreciated. That being said here is the problem:
given 3 subsets of numbers a, b, c ⊆ {0, ..., n}. In nlog(n) check if there exists numbers n1, n2 in a, b and n3 in c where n1 + n2 = n3.
I am given the hint to convert a and b to polynomial coefficients and to use polynomial multiplication using ftt to multiply the coefficients of a and b.
Now where I am stuck is after getting the result of the polynomial multiplication, what do I do next?
Thank you in advanced.
from numpy.fft import fft, ifft
from numpy import real, imag
def polynomial_multiply(a_coeff_list, b_coeff_list):
# Return the coefficient list of the multiplication
# of the two polynomials
# Returned list must be a list of floating point numbers.
# list from complex to reals by using the
# real function in numpy
len_a = len(a_coeff_list)
len_b = len(b_coeff_list)
for i in range(len_a-1):
b_coeff_list.append(0)
for i in range(len_b-1):
a_coeff_list.append(0)
a_fft = fft(a_coeff_list)
b_fft = fft(b_coeff_list)
c = []
for i in range(len(a_fft)):
c.append(a_fft[i] * b_fft[i])
inverse_c = ifft(c)
return real(inverse_c)
# inputs sets a, b, c
# return True if there exist n1 in a, n2 in B such that n1+n2 in C
# return False otherwise
# number n which signifies the maximum number in a, b, c
def check_sum_exists(a, b, c, n):
a_coeffs = [0]*n
b_coeffs = [0]*n
# convert sets a, b into polynomials as provided in the hint
# a_coeffs and b_coeffs should contain the result
i = 0
for item in a:
a_coeffs[i] = item
i += 1
i = 0
for item in b:
b_coeffs[i] = item
i += 1
# multiply them together
c_coeffs = polynomial_multiply(a_coeffs, b_coeffs)
# now this is where i am lost
# how to determine with c_coeffs?
return False
# return True/False
Thanks to all who helped. I figured it out and hopefully this can help anyone who runs into a similar problem. The issue I had was I incorrectly assigned the coefficients for a_coeffs and b_coeffs.
Here is the solution which passed the tests for those interested.
from numpy.fft import fft, ifft
from numpy import real, imag
def check_sum_exists(a, b, c, n):
a_coeffs = [0] * n
b_coeffs = [0] * n
# convert sets a, b into polynomials as provided in the hint
# a_coeffs and b_coeffs should contain the result
for coeff in a:
a_coeffs[coeff] = 1
for coeff in b:
b_coeffs[coeff] = 1
# multiply them together
c_coeffs = polynomial_multiply(a_coeffs, b_coeffs)
# use the result to solve the problem at hand
for coeff in c:
if c_coeffs[coeff] >= .5:
return True
return False
# return True/False
def polynomial_multiply(a_coeff_list, b_coeff_list):
# Return the coefficient list of the multiplication
# of the two polynomials
# Returned list must be a list of floating point numbers.
# Please convert list from complex to reals by using the
# real function in numpy.
for i in range(len(a_coeff_list) - 1):
b_coeff_list.append(0)
for i in range(len(b_coeff_list) - 1):
a_coeff_list.append(0)
a_fft = fft(a_coeff_list)
b_fft = fft(b_coeff_list)
c = []
for i in range(len(a_fft)):
c.append(a_fft[i] * b_fft[i])
return real(ifft(c))

Problem implementing Merge Sort from pseudo code python

Im trying to implement merge sort in Python based on the following pseudo code. I know there are many implementations out there, but I have not been able to find one that followis this pattern with a for loop at the end as opposed to while loop(s). Also, setting the last values in the subarrays to infinity is something I haven't seen in other implementation. NOTE: The following pseudo code has 1 based index i.e. index starts at 1. So I think my biggest issue is getting the indexing right. Right now its just not sorting properly and its really hard to follow with the debugger. My implementation is at the bottom.
Current Output:
Input: [9, 8, 7, 6, 5, 4, 3, 2, 1, 0]
Merge Sort: [0, 0, 0, 3, 0, 5, 5, 5, 8, 0]
def merge_sort(arr, p, r):
if p < r:
q = (p + (r - 1)) // 2
merge_sort(arr, p, q)
merge_sort(arr, q + 1, r)
merge(arr, p, q, r)
def merge(A, p, q, r):
n1 = q - p + 1
n2 = r - q
L = [0] * (n1 + 1)
R = [0] * (n2 + 1)
for i in range(0, n1):
L[i] = A[p + i]
for j in range(0, n2):
R[j] = A[q + 1 + j]
L[n1] = 10000000 #dont know how to do infinity for integers
R[n2] = 10000000 #dont know how to do infinity for integers
i = 0
j = 0
for k in range(p, r):
if L[i] <= R[j]:
A[k] = L[i]
i += 1
else:
A[k] = R[j]
j += 1
return A
First of all you need to make sure if the interval represented by p and r is open or closed at its endpoints. The pseudocode (for loops include last index) establishes that the interval is closed at both endpoints: [p, r].
With last observation in mind you can note that for k in range(p, r): doesn't check last number so the correct line is for k in range(p, r + 1):.
You can represent "infinity" in you problem by using the maximum element of A in the range [p, r] plus one. That will make the job done.
You not need to return the array A because all changes are being done through its reference.
Also, q = (p + (r - 1)) // 2 isn't wrong (because p < r) but correct equation is q = (p + r) // 2 as the interval you want middle integer value of two numbers.
Here is a rewrite of the algorithm with “modern” conventions, which are the following:
Indices are 0-based
The end of a range is not part of that range; in other words, intervals are closed on the left and open on the right.
This is the resulting code:
INF = float('inf')
def merge_sort(A, p=0, r=None):
if r is None:
r = len(A)
if r - p > 1:
q = (p + r) // 2
merge_sort(A, p, q)
merge_sort(A, q, r)
merge(A, p, q, r)
def merge(A, p, q, r):
L = A[p:q]; L.append(INF)
R = A[q:r]; R.append(INF)
i = 0
j = 0
for k in range(p, r):
if L[i] <= R[j]:
A[k] = L[i]
i += 1
else:
A[k] = R[j]
j += 1
A = [433, 17, 585, 699, 942, 483, 235, 736, 629, 609]
merge_sort(A)
print(A)
# → [17, 235, 433, 483, 585, 609, 629, 699, 736, 942]
Notes:
Python has a handy syntax for copying a subrange.
There is no int infinity in Python, but we can use the float one, because ints and floats can always be compared.
There is one difference between this algorithm and the original one, but it is irrelevant. Since the “midpoint” q does not belong to the left range, L is shorter than R when the sum of their lengths is odd. In the original algorithm, q belongs to L, and so L is the longer of the two in this case. This does not change the correctness of the algorithm, since it simply swaps the roles of L and R. If for some reason you need not to have this difference, then you must calculate q like this:
q = (p + r + 1) // 2
In mathematics, we represent all real numbers which are greater than or equal to i and smaller than j by [i, j). Notice the use of [ and ) brackets here. I have used i and j in the same way in my code to represent the region that I am dealing with currently.
ThThe region [i, j) of an array covers all indexes (integer values) of this array which are greater or equal to i and smaller than j. i and j are 0-based indexes. Ignore the first_array and second_array the time being.
Please notice, that i and j define the region of the array that I am dealing with currently.
Examples to understand this better
If your region spans over the whole array, then i should be 0 and j should be the length of array [0, length).
The region [i, i + 1) has only index i in it.
The region [i, i + 2) has index i and i + 1 in it.
def mergeSort(first_array, second_array, i, j):
if j > i + 1:
mid = (i + j + 1) // 2
mergeSort(second_array, first_array, i, mid)
mergeSort(second_array, first_array, mid, j)
merge(first_array, second_array, i, mid, j)
One can see that I have calculated middle point as mid = (i + j + 1) // 2 or one can also use mid = (i + j) // 2 both will work. I will divide the region of the array that I am currently dealing with into 2 smaller regions using this calculated mid value.
In line 4 of the code, MergeSort is called on the region [i, mid) and in line 5, MergeSort is called on the region [mid, j).
You can access the whole code here.

Similar subroutine statement

I have a code in Python.
My maincode calla a function matrixD:
def matrixD(n,x):
C=[]
for i in range(n):
C += [1.0]
C[0]=2.0
C[n-1]=2.0
D=[[0] * n for i in range(n)]
for i in range(n):
for j in range(n):
if i==j and i!=0 and i!=(n-1):
D[i][i] = -x[i]/(2.0*(1.0-x[i]**2))
else:
if i!=j:
D[i][j] = (C[i]/C[j])*(-1.0)**(i+1+j+1)/(x[i]-x[j])
# D[i][j] = 2.0
D[0][0] = (2.0*float(n-1)**2 + 1.0)/6.0
D[n-1][n-1] = -(2.0*float(n-1)**2 + 1.0)/6.0
return D
This function returns the value of D (a matrix).
But in this way D is not a global variable.
How can I make D a global variable?
Every time when I want to use D, I want to call the function and is not the ideal.
I want some similar subroutine in Fortran. You call just one time and you have a global variable.
*I am very new at Python

Dynamic Programming w/ PyTorch: Longest Common Subsequence

I am currently wondering how could we make a efficient implementation of LCS problem.
I found a way to find consecutive match (i.e. ngrams match) with tensor operation by comparing and shifting.
With two sequences x (len: n), y (len: m), the matrix:
e = x.eq(y.unsqueeze(1)) # [n x m]
we have: e[i, j] == 1 <=> x[i] == y[j], a n-gram match will be visible as a diagonal of ones.
Thus we can do the following:
# match_1 = [n x m] of {0, 1}
match_1 = x.eq(y.unsqueeze(1))
# match_2 = [(n-1) x (m-1)] matrix of {0, 1}
match_2 = match_1[:-1, :-1] * match_1[1:, 1:]
# etcetc
The LCS problem is more complicated as we allow gaps. It can be implemented using dynamic programing, in O(n x m), but it is not really protable to Pytorch right?
I tried, it’s super slow.
# considering two "sentences" (LongTensors of word indices)
# _ts, _tr of respective length n and m
table = torch.zeros(n+1, m+1)
_ts, _tr = ts, tr
for i in range(1, n+1):
for j in range(1, m+1):
if _ts[i-1] == _tr[j-1]:
_table[i, j] = _table[i-1, j-1] + 1
else:
_table[i, j] = max(_table[i-1, j], _table[i, j-1])
lcs = _table[n][m]
Any idea to make it more efficient?

Navigating a grid

I stumbled upon a problem at Project Euler, https://projecteuler.net/problem=15
. I solved this by combinatorics but was left wondering if there is a dynamic programming solution to this problem or these kinds of problems overall. And say some squares of the grid are taken off - is that possible to navigate? I am using Python. How should I do that? Any tips are appreciated. Thanks in advance.
You can do a simple backtrack and explore an implicit graph like this: (comments explain most of it)
def explore(r, c, n, memo):
"""
explore right and down from position (r,c)
report a rout once position (n,n) is reached
memo is a matrix which saves how many routes exists from each position to (n,n)
"""
if r == n and c == n:
# one path has been found
return 1
elif r > n or c > n:
# crossing the border, go back
return 0
if memo[r][c] is not None:
return memo[r][c]
a= explore(r+1, c, n, memo) #move down
b= explore(r, c+1, n, memo) #move right
# return total paths found from this (r,c) position
memo[r][c]= a + b
return a+b
if __name__ == '__main__':
n= 20
memo = [[None] * (n+1) for _ in range(n+1)]
paths = explore(0, 0, n, memo)
print(paths)
Most straight-forwardly with python's built-in memoization util functools.lru_cache. You can encode missing squares as a frozenset (hashable) of missing grid points (pairs):
from functools import lru_cache
#lru_cache(None)
def paths(m, n, missing=None):
missing = missing or frozenset()
if (m, n) in missing:
return 0
if (m, n) == (0, 0):
return 1
over = paths(m, n-1, missing=missing) if n else 0
down = paths(m-1, n, missing=missing) if m else 0
return over + down
>>> paths(2, 2)
6
# middle grid point missing: only two paths
>>> paths(2, 2, frozenset([(1, 1)]))
2
>>> paths(20, 20)
137846528820
There is also a mathematical solution (which is probably what you used):
def factorial(n):
result = 1
for i in range(1, n + 1):
result *= i
return result
def paths(w, h):
return factorial(w + h) / (factorial(w) * factorial(h))
This works because the number of paths is the same as the number of ways to choose to go right or down over w + h steps, where you go right w times, which is equal to w + h choose w, or (w + h)! / (w! * h!).
With missing grid squares, I think there is a combinatoric solution, but it's very slow if there are many missing squares, so dynamic programming would probably be better there.
For example, the following should work:
missing = [
[0, 1],
[0, 0],
[0, 0],
]
def paths_helper(x, y, path_grid, missing):
if path_grid[x][y] is not None:
return path_grid[x][y]
if missing[x][y]:
path_grid[x][y] = 0
return 0
elif x < 0 or y < 0:
return 0
else:
path_count = (paths_helper(x - 1, y, path_grid, missing) +
paths_helper(x, y - 1, path_grid, missing))
path_grid[x][y] = path_count
return path_count
def paths(missing):
arr = [[None] * w for _ in range(h)]
w = len(missing[0])
h = len(missing)
return paths_helper(w, h, arr, missing)
print paths()

Categories

Resources