Related
The aim of this program is to build a 3x3 matrix which then reduces additional rows, but, for some reason, after the second row is added to M in the while loop, it replaces it with the new row, rather than adding a third row, and, then, reducing additional (most likely 3) vectors after that. Here's the code:
from sympy import *
init_printing(use_unicode= True)
A = []
def reduceOneRow(M):
k = 0
for i in range(k,min(M.shape)-1):
if M[i,i]!=0 or i ==2:
for j in range(k,min(M.shape)-1):
T = Matrix([M.row(j+1)-(M[j+1,i]/M[i,i])*M.row(i)])
A.append(M[j+1]/M[i,i])
M.row_del(j+1)
M = M.row_insert(j+1,T)
k = k+1
else:
i = i+1
return M
# M = Matrix([[1,1,1],[1,4,7],[3,2,5]])
# reduceOneRow(M)
# A
#The following block of code generates a list of monomials, but not in reverse
#lexicagraphical order. This can be fixed later. Ultimately, I'd like to
#make it it's own function
sigma = symbols('x1:4')
D = [1]
for d in D:
for s in sigma:
if s*d not in D:
D.append(s*d)
if len(D) > 20:
break
# print(D)
# print(D[9].subs([('x1',4),('x2',2),('x3',3)]))
#We begin with the set up described in C1
P = [(1,2,3),(4,5,6),(7,8,9)]
G = []
Q = []
S = []
L = [1]
M = Matrix([])
#Here we being step C2.
while L != []:#what follows this while statement is the loop C2-C5 and back
t = L[0]
L.remove(L[0])
K = Matrix([]) #K is a kind of bucket matrix
if t==1: #this block generates the firs line in M. It had to be separate
for j in range(len(P)):#because of the way sympy works. 1 is int, rather
K = K.col_insert(j,Matrix([1])) #than a symbol
else: #here we generate all other rows of M, using K for the name of the rows
for p in P:
K = K.col_insert(0,Matrix([t.subs([(sigma[0],p[0]),(sigma[1],p[1]),(sigma[2],p[2])])]))
# K = K.col_insert(i,Matrix([t.subs([(sigma[0],p[0]),(sigma[1],p[1]),(sigma[2],p[2])]))
M = M.row_insert(min(M.shape)+1,K) #K gets added to M
M
A = []
reduceOneRow(M)#row reduces M and produces the ai in C3
sum = 0
for n in range(len(A)):
sum = sum + A[n]*S[n]
V = M.row(-1)
if V == zeros(1,len(V)):
G.append(t - sum)
M.row_del(-1)
else:
S.append(t-sum)
Q.append(t)
for i in range(1,4):
#if not t*D[i] == Q[0]:
L.append(t*D[i])
L
print('G =',' ',G,' ','Q =',Q)
I figure it out. I changed 'reduceRowOne(M)' to 'M = reduceRowOne'. Ugh.
Thank you all who took a look at this!
Im trying to solve the following Codewars problem: https://www.codewars.com/kata/sum-of-pairs/train/python
Here is my current implementation in Python:
def sum_pairs(ints, s):
right = float("inf")
n = len(ints)
m = {}
dup = {}
for i, x in enumerate(ints):
if x not in m.keys():
m[x] = i # Track first index of x using hash map.
elif x in m.keys() and x not in dup.keys():
dup[x] = i
for x in m.keys():
if s - x in m.keys():
if x == s-x and x in dup.keys():
j = m[x]
k = dup[x]
else:
j = m[x]
k = m[s-x]
comp = max(j,k)
if comp < right and j!= k:
right = comp
if right > n:
return None
return [s - ints[right],ints[right]]
The code seems to produce correct results, however the input can consist of array with up to 10 000 000 elements, so the execution times out for large inputs. I need help with optimizing/modifying the code so that it can handle sufficiently large arrays.
Your code inefficient for large list test cases so it gives timeout error. Instead you can do:
def sum_pairs(lst, s):
seen = set()
for item in lst:
if s - item in seen:
return [s - item, item]
seen.add(item)
We put the values in seen until we find a value that produces the specified sum with one of the seen values.
For more information go: Referance link
Maybe this code:
def sum_pairs(lst, s):
c = 0
while c<len(lst)-1:
if c != len(lst)-1:
x= lst[c]
spam = c+1
while spam < len(lst):
nxt= lst[spam]
if nxt + x== s:
return [x, nxt]
spam += 1
else:
return None
c +=1
lst = [5, 6, 5, 8]
s = 14
print(sum_pairs(lst, s))
Output:
[6, 8]
This answer unfortunately still times out, even though it's supposed to run in O(n^3) (since it is dominated by the sort, the rest of the algorithm running in O(n)). I'm not sure how you can obtain better than this complexity, but I thought I might put this idea out there.
def sum_pairs(ints, s):
ints_with_idx = enumerate(ints)
# Sort the array of ints
ints_with_idx = sorted(ints_with_idx, key = lambda (idx, num) : num)
diff = 1000000
l = 0
r = len(ints) - 1
# Indexes of the sum operands in sorted array
lSum = 0
rSum = 0
while l < r:
# Compute the absolute difference between the current sum and the desired sum
sum = ints_with_idx[l][1] + ints_with_idx[r][1]
absDiff = abs(sum - s)
if absDiff < diff:
# Update the best difference
lSum = l
rSum = r
diff = absDiff
elif sum > s:
# Decrease the large value
r -= 1
else:
# Test to see if the indexes are better (more to the left) for the same difference
if absDiff == diff:
rightmostIdx = max(ints_with_idx[l][0], ints_with_idx[r][0])
if rightmostIdx < max(ints_with_idx[lSum][0], ints_with_idx[rSum][0]):
lSum = l
rSum = r
# Increase the small value
l += 1
# Retrieve indexes of sum operands
aSumIdx = ints_with_idx[lSum][0]
bSumIdx = ints_with_idx[rSum][0]
# Retrieve values of operands for sum in correct order
aSum = ints[min(aSumIdx, bSumIdx)]
bSum = ints[max(aSumIdx, bSumIdx)]
if aSum + bSum == s:
return [aSum, bSum]
else:
return None
The code intends to print a frequency table for a random input discrete data. Here's the code :
from math import log10
from random import randint
N = int(input("Enter number of observations:\n"))
l = [ randint(1,100) for var in range (N) ]
print(l)
l.sort()
print(l)
k = 1 + (3.332*log10(N))
k1 = round(k)
print ("Number of intervals should be = ",k1)
x = N//k1 + 1
print("S.No\t\tIntervals\t\tFrequency")
c = 1 #count
while c <= k:
a = (c-1)*x
b = c*x
count = 0
for v in range(a,b) in l:
count += 1
print(c,"\t\t","{}-{}".format(a,b),"\t\t",count)
c += 1
This shows the above cited error, how to resolve this?
The issue is that range(a,b) sets up a list of integers from a to b-1. What you are asking for is for the code to go through l and pick out numbers matching those criteria, which looks instead like:
for v in l:
if ((v>=a) and (v<b)):
count += 1
If you really want to use range, and your data are going to stay integers, then it would look like:
for v in l:
if v in range(int(a),int(b)):
count += 1
Also
x = N//k1 + 1
should be
x = 100//k1 + 1
The longest arithmetic progression subsequence problem is as follows. Given an array of integers A, devise an algorithm to find the longest arithmetic progression in it. In other words find a sequence i1 < i2 < … < ik, such that A[i1], A[i2], …, A[ik] form an arithmetic progression, and k is maximal. The following code solves the problem in O(n^2) time and space. (Modified from http://www.geeksforgeeks.org/length-of-the-longest-arithmatic-progression-in-a-sorted-array/ . )
#!/usr/bin/env python
import sys
def arithmetic(arr):
n = len(arr)
if (n<=2):
return n
llap = 2
L = [[0]*n for i in xrange(n)]
for i in xrange(n):
L[i][n-1] = 2
for j in xrange(n-2,0,-1):
i = j-1
k = j+1
while (i >=0 and k <= n-1):
if (arr[i] + arr[k] < 2*arr[j]):
k = k + 1
elif (arr[i] + arr[k] > 2*arr[j]):
L[i][j] = 2
i -= 1
else:
L[i][j] = L[j][k] + 1
llap = max(llap, L[i][j])
i = i - 1
k = j + 1
while (i >=0):
L[i][j] = 2
i -= 1
return llap
arr = [1,4,5,7,8,10]
print arithmetic(arr)
This outputs 4.
However I would like to be able to find arithmetic progressions where up to one value is missing. So if arr = [1,4,5,8,10,13] I would like it to report that there is a progression of length 5 with one value missing.
Can this be done efficiently?
Adapted from my answer to Longest equally-spaced subsequence. n is the length of A, and d is the range, i.e. the largest item minus the smallest item.
A = [1, 4, 5, 8, 10, 13] # in sorted order
Aset = set(A)
for d in range(1, 13):
already_seen = set()
for a in A:
if a not in already_seen:
b = a
count = 1
while b + d in Aset:
b += d
count += 1
already_seen.add(b)
# if there is a hole to jump over:
if b + 2 * d in Aset:
b += 2 * d
count += 1
while b + d in Aset:
b += d
count += 1
# don't record in already_seen here
print "found %d items in %d .. %d" % (count, a, b)
# collect here the largest 'count'
I believe that this solution is still O(n*d), simply with larger constants than looking without a hole, despite the two "while" loops inside the two nested "for" loops. Indeed, fix a value of d: then we are in the "a" loop that runs n times; but each of the inner two while loops run at most n times in total over all values of a, giving a complexity O(n+n+n) = O(n) again.
Like the original, this solution is adaptable to the case where you're not interested in the absolute best answer but only in subsequences with a relatively small step d: e.g. n might be 1'000'000, but you're only interested in subsequences of step at most 1'000. Then you can make the outer loop stop at 1'000.
I was solving the Find the min problem on facebook hackercup using python, my code works fine for sample inputs but for large inputs(10^9) it is taking hours to complete.
So, is it possible that the solution of that problem can't be computed within 6 minutes using python? Or may be my approaches are too bad?
Problem statement:
After sending smileys, John decided to play with arrays. Did you know that hackers enjoy playing with arrays? John has a zero-based index array, m, which contains n non-negative integers. However, only the first k values of the array are known to him, and he wants to figure out the rest.
John knows the following: for each index i, where k <= i < n, m[i] is the minimum non-negative integer which is not contained in the previous *k* values of m.
For example, if k = 3, n = 4 and the known values of m are [2, 3, 0], he can figure out that m[3] = 1.
John is very busy making the world more open and connected, as such, he doesn't have time to figure out the rest of the array. It is your task to help him.
Given the first k values of m, calculate the nth value of this array. (i.e. m[n - 1]).
Because the values of n and k can be very large, we use a pseudo-random number generator to calculate the first k values of m. Given positive integers a, b, c and r, the known values of m can be calculated as follows:
m[0] = a
m[i] = (b * m[i - 1] + c) % r, 0 < i < k
Input
The first line contains an integer T (T <= 20), the number of test
cases.
This is followed by T test cases, consisting of 2 lines each.
The first line of each test case contains 2 space separated integers,
n, k (1 <= k <= 10^5, k < n <= 10^9).
The second line of each test case contains 4 space separated integers
a, b, c, r (0 <= a, b, c <= 10^9, 1 <= r <= 10^9).
I tried two approaches but both failed to return results in 6 minutes, Here's my two approaches:
first:
import sys
cases=sys.stdin.readlines()
def func(line1,line2):
n,k=map(int,line1.split())
a,b,c,r =map(int,line2.split())
m=[None]*n #initialize the list
m[0]=a
for i in xrange(1,k): #set the first k values using the formula
m[i]= (b * m[i - 1] + c) % r
#print m
for j in range(0,n-k): #now set the value of m[k], m[k+1],.. upto m[n-1]
temp=set(m[j:k+j]) # create a set from the K values relative to current index
i=-1 #start at 0, lowest +ve integer
while True:
i+=1
if i not in temp: #if that +ve integer is not present in temp
m[k+j]=i
break
return m[-1]
for ind,case in enumerate(xrange(1,len(cases),2)):
ans=func(cases[case],cases[case+1])
print "Case #{0}: {1}".format(ind+1,ans)
Second:
import sys
cases=sys.stdin.readlines()
def func(line1,line2):
n,k=map(int,line1.split())
a,b,c,r =map(int,line2.split())
m=[None]*n #initialize
m[0]=a
for i in xrange(1,k): #same as above
m[i]= (b * m[i - 1] + c) % r
#instead of generating a set in each iteration , I used a
# dictionary this time.
#Now, if the count of an item is 0 then it
#means the item is not present in the previous K items
#and can be added as the min value
temp={}
for x in m[0:k]:
temp[x]=temp.get(x,0)+1
i=-1
while True:
i+=1
if i not in temp:
m[k]=i #set the value of m[k]
break
for j in range(1,n-k): #now set the values of m[k+1] to m[n-1]
i=-1
temp[m[j-1]] -= 1 #decrement it's value, as it is now out of K items
temp[m[k+j-1]]=temp.get(m[k+j-1],0)+1 # new item added to the current K-1 items
while True:
i+=1
if i not in temp or temp[i]==0: #if i not found in dict or it's val is 0
m[k+j]=i
break
return m[-1]
for ind,case in enumerate(xrange(1,len(cases),2)):
ans=func(cases[case],cases[case+1])
print "Case #{0}: {1}".format(ind+1,ans)
The last for-loop in second approach can also be written as :
for j in range(1,n-k):
i=-1
temp[m[j-1]] -= 1
if temp[m[j-1]]==0:
temp.pop(m[j-1]) #same as above but pop the key this time
temp[m[k+j-1]]=temp.get(m[k+j-1],0)+1
while True:
i+=1
if i not in temp:
m[k+j]=i
break
sample input :
5
97 39
34 37 656 97
186 75
68 16 539 186
137 49
48 17 461 137
98 59
6 30 524 98
46 18
7 11 9 46
output:
Case #1: 8
Case #2: 38
Case #3: 41
Case #4: 40
Case #5: 12
I already tried codereview, but no one replied there yet.
After at most k+1 steps, the last k+1 numbers in the array will be 0...k (in some order). Subsequently, the sequence is predictable: m[i] = m[i-k-1]. So the way to solve this problem is run your naive implementation for k+1 steps. Then you've got an array with 2k+1 elements (the first k were generated from the random sequence, and the other k+1 from iterating).
Now, the last k+1 elements are going to repeat infinitely. So you can just return the result for m[n] immediately: it's m[k + (n-k-1) % (k+1)].
Here's some code that implements it.
import collections
def initial_seq(k, a, b, c, r):
v = a
for _ in xrange(k):
yield v
v = (b * v + c) % r
def find_min(n, k, a, b, c, r):
m = [0] * (2 * k + 1)
for i, v in enumerate(initial_seq(k, a, b, c, r)):
m[i] = v
ks = range(k+1)
s = collections.Counter(m[:k])
for i in xrange(k, len(m)):
m[i] = next(j for j in ks if not s[j])
ks.remove(m[i])
s[m[i-k]] -= 1
return m[k + (n - k - 1) % (k + 1)]
print find_min(97, 39, 34, 37, 656, 97)
print find_min(186, 75, 68, 16, 539, 186)
print find_min(137, 49, 48, 17, 461, 137)
print find_min(1000000000, 100000, 48, 17, 461, 137)
The four cases run in 4 seconds on my machine, and the last case has the largest possible n.
Here is my O(k) solution, which is based on the same idea as above, but runs much faster.
import os, sys
f = open(sys.argv[1], 'r')
T = int(f.readline())
def next(ary, start):
j = start
l = len(ary)
ret = start - 1
while j < l and ary[j]:
ret = j
j += 1
return ret
for t in range(T):
n, k = map(int, f.readline().strip().split(' '))
a, b, c, r = map(int, f.readline().strip().split(' '))
m = [0] * (4 * k)
s = [0] * (k+1)
m[0] = a
if m[0] <= k:
s[m[0]] = 1
for i in xrange(1, k):
m[i] = (b * m[i-1] + c) % r
if m[i] < k+1:
s[m[i]] += 1
p = next(s, 0)
m[k] = p + 1
p = next(s, p+2)
for i in xrange(k+1, n):
if m[i-k-1] > p or s[m[i-k-1]] > 1:
m[i] = p + 1
if m[i-k-1] <= k:
s[m[i-k-1]] -= 1
s[m[i]] += 1
p = next(s, p+2)
else:
m[i] = m[i-k-1]
if p == k:
break
if p != k:
print 'Case #%d: %d' % (t+1, m[n-1])
else:
print 'Case #%d: %d' % (t+1, m[i-k + (n-i+k+k) % (k+1)])
The key point here is, m[i] will never exceeds k, and if we remember the consecutive numbers we can find in previous k numbers from 0 to p, then p will never reduce.
If number m[i-k-1] is larger than p, then it's obviously we should set m[i] to p+1, and p will increase at least 1.
If number m[i-k-1] is smaller or equal to p, then we should consider whether the same number exists in m[i-k:i], if not, m[i] should set equal to m[i-k-1], if yes, we should set m[i] to p+1 just as the "m[i-k-1]-larger-than-p" case.
Whenever p is equal to k, the loop begin, and the loop size is (k+1), so we can jump out of the calculation and print out the answer now.
I enhanced the performance through adding map.
import sys, os
import collections
def min(str1, str2):
para1 = str1.split()
para2 = str2.split()
n = int(para1[0])
k = int(para1[1])
a = int(para2[0])
b = int(para2[1])
c = int(para2[2])
r = int(para2[3])
m = [0] * (2*k+1)
m[0] = a
s = collections.Counter()
s[a] += 1
rs = {}
for i in range(k+1):
rs[i] = 1
for i in xrange(1,k):
v = (b * m[i - 1] + c) % r
m[i] = v
s[v] += 1
if v < k:
if v in rs:
rs[v] -= 1
if rs[v] == 0:
del rs[v]
for j in xrange(0,k+1):
for t in rs:
if not s[t]:
m[k+j] = t
if m[j] < k:
if m[j] in rs:
rs[m[j]] += 1
else:
rs[m[j]] = 0
rs[t] -= 1
if rs[t] == 0:
del rs[t]
s[t] = 1
break
s[m[j]] -= 1
return m[k + ((n-k-1)%(k+1))]
if __name__=='__main__':
lines = []
user_input = raw_input()
num = int(user_input)
for i in xrange(num):
input1 = raw_input()
input2 = raw_input()
print "Case #%s: %s"%(i+1, min(input1, input2))