How to remove pair of small and capital letters in a string? - python

Basically what I'm trying to do is create a code that removes a pair of lower and capital letters. e.g. :
AbBax -» x
cCdatabasacCADde -» database
I've tried doing this but it gives me an error, maybe my train of thought is wrong.
def decode(c_p):
t_cp=[]
for i in c_p:
t_cp+=[I,]
#here I added each character from the string to a list so it would be easier to analyse each character
new_c_p=""
for c in range(len(t_cp)-1):
if not t_cp[c]==chr(ord(c)) and t_cp[c+1]==chr(ord(c) + 32) or not t_cp[c]==chr(ord(c) + 32) and t_cp[c+1]==chr(ord(c)) :
#here I analyse the index c and c+1 to know if the first character corresponds to the next in capital or vice-versa, if doesn't correspond, I add that character into new_c_p
new_c_p+=c
return new_c_p

Here's a slightly simpler approach:
def decode(c_p):
while True:
for i, pair in enumerate(zip(c_p, c_p[1:])):
up, lo = sorted(pair)
if up.lower() == lo and up == lo.upper():
c_p = c_p[:i] + c_p[i+2:]
break
else:
return c_p
decode("cCdatabasacCADde")
# 'database'
And here is an even better one that does not start all the way from the beginning every time and has actually linear time and space complexity:
def decode(c_p):
stack = []
for c in c_p:
if not stack:
stack.append(c)
else:
up, lo = sorted((stack[-1], c))
if up.lower() == lo and lo.upper() == up:
stack.pop()
else:
stack.append(c)
return "".join(stack)

Related

Ignoring Changed Index Check (Python)

I have made a script:
our_word = "Success"
def duplicate_encode(word):
char_list = []
final_str = ""
changed_index = []
base_wrd = word.lower()
for k in base_wrd:
char_list.append(k)
for i in range(0, len(char_list)):
count = 0
for j in range(i + 1, len(char_list)):
if j not in changed_index:
if char_list[j] == char_list[i]:
char_list[j] = ")"
changed_index.append(j)
count += 1
else:
continue
if count > 0:
char_list[i] = ")"
else:
char_list[i] = "("
print(changed_index)
print(char_list)
final_str = "".join(char_list)
return final_str
print(duplicate_encode(our_word))
essentialy the purpose of this script is to convert a string to a new string where each character in the new string is "(", if that character appears only once in the original string, or ")", if that character appears more than once in the original string. I have made a rather layered up script (I am relatively new to the python language so didn't want to use any helpful in-built functions) that attempts to do this. My issue is that where I check if the current index has been previously edited (in order to prevent it from changing), it seems to ignore it. So instead of the intended )())()) I get )()((((. I'd really appreciate an insightful answer to why I am getting this issue and ways to work around this, since I'm trying to gather an intuitive knowledge surrounding python. Thanks!
word = "Success"
print(''.join([')' if word.lower().count(c) > 1 else '(' for c in word.lower()]))
The issue here has nothing to do with your understanding of Python. It's purely algorithmic. If you retain this 'layered' algorithm, it is essential that you add one more check in the "i" loop.
our_word = "Success"
def duplicate_encode(word):
char_list = list(word.lower())
changed_index = []
for i in range(len(word)):
count = 0
for j in range(i + 1, len(word)):
if j not in changed_index:
if char_list[j] == char_list[i]:
char_list[j] = ")"
changed_index.append(j)
count += 1
if i not in changed_index: # the new inportant check to avoid reversal of already assigned ')' to '('
char_list[i] = ")" if count > 0 else "("
return "".join(char_list)
print(duplicate_encode(our_word))
Your algorithm can be greatly simplified if you avoid using char_list as both the input and output. Instead, you can create an output list of the same length filled with ( by default, and then only change an element when a duplicate is found. The loops will simply walk along the entire input list once for each character looking for any matches (other than self-matches). If one is found, the output list can be updated and the inner loop will break and move on to the next character.
The final code should look like this:
def duplicate_encode(word):
char_list = list(word.lower())
output = list('(' * len(word))
for i in range(len(char_list)):
for j in range(len(char_list)):
if i != j and char_list[i] == char_list[j]:
output[i] = ')'
break
return ''.join(output)
for our_word in (
'Success',
'ChJsTk(u cIUzI htBp#qX)OTIHpVtHHhQ',
):
result = duplicate_encode(our_word)
print(our_word)
print(result)
Output:
Success
)())())
ChJsTk(u cIUzI htBp#qX)OTIHpVtHHhQ
))(()(()))))())))()()((())))()))))

Recursive Decompression of Strings

I'm trying to decompress strings using recursion. For example, the input:
3[b3[a]]
should output:
baaabaaabaaa
but I get:
baaaabaaaabaaaabbaaaabaaaabaaaaa
I have the following code but it is clearly off. The first find_end function works as intended. I am absolutely new to using recursion and any help understanding / tracking where the extra letters come from or any general tips to help me understand this really cool methodology would be greatly appreciated.
def find_end(original, start, level):
if original[start] != "[":
message = "ERROR in find_error, must start with [:", original[start:]
raise ValueError(message)
indent = level * " "
index = start + 1
count = 1
while count != 0 and index < len(original):
if original[index] == "[":
count += 1
elif original[index] == "]":
count -= 1
index += 1
if count != 0:
message = "ERROR in find_error, mismatched brackets:", original[start:]
raise ValueError(message)
return index - 1
def decompress(original, level):
# set the result to an empty string
result = ""
# for any character in the string we have not looked at yet
for i in range(len(original)):
# if the character at the current index is a digit
if original[i].isnumeric():
# the character of the current index is the number of repetitions needed
repititions = int(original[i])
# start = the next index containing the '[' character
x = 0
while x < (len(original)):
if original[x].isnumeric():
start = x + 1
x = len(original)
else:
x += 1
# last = the index of the matching ']'
last = find_end(original, start, level)
# calculate a substring using `original[start + 1:last]
sub_original = original[start + 1 : last]
# RECURSIVELY call decompress with the substring
# sub = decompress(original, level + 1)
# concatenate the result of the recursive call times the number of repetitions needed to the result
result += decompress(sub_original, level + 1) * repititions
# set the current index to the index of the matching ']'
i = last
# else
else:
# concatenate the letter at the current index to the result
if original[i] != "[" and original[i] != "]":
result += original[i]
# return the result
return result
def main():
passed = True
ORIGINAL = 0
EXPECTED = 1
# The test cases
provided = [
("3[b]", "bbb"),
("3[b3[a]]", "baaabaaabaaa"),
("3[b2[ca]]", "bcacabcacabcaca"),
("5[a3[b]1[ab]]", "abbbababbbababbbababbbababbbab"),
]
# Run the provided tests cases
for t in provided:
actual = decompress(t[ORIGINAL], 0)
if actual != t[EXPECTED]:
print("Error decompressing:", t[ORIGINAL])
print(" Expected:", t[EXPECTED])
print(" Actual: ", actual)
print()
passed = False
# print that all the tests passed
if passed:
print("All tests passed")
if __name__ == '__main__':
main()
From what I gathered from your code, it probably gives the wrong result because of the approach you've taken to find the last matching closing brace at a given level (I'm not 100% sure, the code was a lot). However, I can suggest a cleaner approach using stacks (almost similar to DFS, without the complications):
def decomp(s):
stack = []
for i in s:
if i.isalnum():
stack.append(i)
elif i == "]":
temp = stack.pop()
count = stack.pop()
if count.isnumeric():
stack.append(int(count)*temp)
else:
stack.append(count+temp)
for i in range(len(stack)-2, -1, -1):
if stack[i].isnumeric():
stack[i] = int(stack[i])*stack[i+1]
else:
stack[i] += stack[i+1]
return stack[0]
print(decomp("3[b]")) # bbb
print(decomp("3[b3[a]]")) # baaabaaabaaa
print(decomp("3[b2[ca]]")) # bcacabcacabcaca
print(decomp("5[a3[b]1[ab]]")) # abbbababbbababbbababbbababbbab
This works on a simple observation: rather tha evaluating a substring after on reading a [, evaluate the substring after encountering a ]. That would allow you to build the result AFTER the pieces have been evaluated individually as well. (This is similar to the prefix/postfix evaluation using programming).
(You can add error checking to this as well, if you wish. It would be easier to check if the string is semantically correct in one pass and evaluate it in another pass, rather than doing both in one go)
Here is the solution with the similar idea from above:
we go through string putting everything on stack until we find ']', then we go back until '[' taking everything off, find the number, multiply and put it back on stack
It's much less consuming as we don't add strings, but work with lists
Note: multiply number can't be more than 9 as we parse it as one element string
def decompress(string):
stack = []
letters = []
for i in string:
if i != ']':
stack.append(i)
elif i == ']':
letter = stack.pop()
while letter != '[':
letters.append(letter)
letter = stack.pop()
word = ''.join(letters[::-1])
letters = []
stack.append(''.join([word for j in range(int(stack.pop()))]))
return ''.join(stack)

How to rearrange a string's characters such that none of it's adjacent characters are the same, using Python

In my attempt to solve the above question, I've written the following code:
Logic: Create a frequency dict for each character in the string (key= character, value= frequency of the character). If any character's frequency is greater than ceil(n/2), there is no solution. Else, print the most frequent character followed by reducing its frequency in the dict/
import math, operator
def rearrangeString(s):
# Fill this in.
n = len(s)
freqDict = {}
for i in s:
if i not in freqDict.keys():
freqDict[i] = 1
else:
freqDict[i] += 1
for j in list(freqDict.values()):
if j > math.ceil(n / 2):
return None
return maxArrange(freqDict)[:-4]
temp = ""
def maxArrange(inp):
global temp
n = len(inp)
if list(inp.values()) != [0] * n:
resCh = max(inp.items(), key=operator.itemgetter(1))[0]
if resCh is not None and resCh != temp:
inp[resCh] -= 1
# Terminates with None
temp = resCh
return resCh + str(maxArrange(inp))
# Driver
print(rearrangeString("abbccc"))
# cbcabc
print(rearrangeString("abbcccc"))
In the first try, with input abbccc, it gives the right answer, i.e. cbcabc, but fails for the input abbcccc, returning ccbcabc, without handling it using the temp variable, else returning cbcabc and skipping c altogether when handled using temp
How should I modify the logic, or is there a better approach?

Optimize python code to avoid runtime error

Given a string that might have multiple occurrences of the same character, return the closest same character of any indicated character in the string.
Given the string s and n number of queries. In each query, you are given an index a (where 0 <= a <= |s| ) of a character, and you need to print the index of the closet same character. If there are multiple answers, print the smallest one. Otherwise, print -1.
For example, string s = 'youyouy', with a given query 3: there are two matching character at indices 0 and 6, each 3 away, we choose the smallest one which is 0.
Here is my plan:
I put the string in a dictionary, the key is distinct letters in a string, values are letters corresponding indexes. When given a query, find the corresponding letter in the dictionary and return the closest value to the query.
def closest(s, queries):
res = []
dict2={}
#dict2 - letter - indexs
for i in range(len(s)):
if s[i] not in dict2:
dict2[s[i]]=[i]
else:
dict2[s[i]].append(i)
for num in queries:
#closet- denotes closet letter index
closet = math.inf
#num is out of range , append -1
if num > (len(s)-1):
res.append(-1)
continue
#this is the only one letter, append -1
letter=s[num]
if len(dict2[letter])==1:
res.append(-1)
continue
#temp = list for that letters
temp=dict2[s[num]]
index=temp.index(num) . #in the list, letter index's index in list
if index==0:
closet=temp[1]
elif index==(len(temp)-1):
closet=temp[index-1]
else:
distance1=num-temp[index-1] . #left
distance2=temp[index+1]-num . #right
if distance1 <= distance2:
closet=temp[index-1]
else:
closet=temp[index+1]
if closet == math.inf:
res.append(-1)
else:
res.append(closet)
return res
I got two runtime error. I am wondering if you could help me out to maybe reduce some run time ?
Also, I am looking for another suggestions! I have used Python for a while, and I am looking for a job (university new grad). Is java usually running faster than Python? Should I switch to Java?
Im trying to do as simple as i can , but i look like a bit complex. Though you question is avoiding runtime error , i want to present my idea
s='oooyyouoy'
k='0123456789'
def cloest(string,pos):
c = string[pos]
p1 , p2 = s[:pos] , s[pos+1:]
# reserve left part and find the closet one , add 1 because len(p1)=final_position + 1
l = len(p1) - (p1[::-1].find(c) + 1)
# find without reserve and add 1 because s[pos+1:]
r = (p2.find(c) + 1) + pos
# judge which one is closer if same chose left one
result = l if (pos - l) <= (r - pos) else r
if result == pos:
return -1
else:
return result
print(cloest(s,4))

The Alphabet and Recursion

I'm almost done with my program, but I've made a subtle mistake. My program is supposed to take a word, and by changing one letter at a time, is eventually supposed to reach a target word, in the specified number of steps. I had been trying at first to look for similarities, for example: if the word was find, and the target word lose, here's how my program would output in 4 steps:
['find','fine','line','lone','lose]
Which is actually the output I wanted. But if you consider a tougher set of words, like Java and work, the output is supposed to be in 6 steps.
['java', 'lava', 'lave', 'wave', 'wove', 'wore', 'work']
So my mistake is that I didn't realize you could get to the target word, by using letters that don't exist in the target word or original word.
Here's my Original Code:
import string
def changeling(word,target,steps):
alpha=string.ascii_lowercase
x=word##word and target has been changed to keep the coding readable.
z=target
if steps==0 and word!= target:##if the target can't be reached, return nothing.
return []
if x==z:##if target has been reached.
return [z]
if len(word)!=len(target):##if the word and target word aren't the same length print error.
print "error"
return None
i=1
if lookup
if lookup(z[0]+x[1:]) is True and z[0]+x[1:]!=x :##check every letter that could be from z, in variations of, and check if they're in the dictionary.
word=z[0]+x[1:]
while i!=len(x):
if lookup(x[:i-1]+z[i-1]+x[i:]) and x[:i-1]+z[i-1]+x[i:]!=x:
word=x[:i-1]+z[i-1]+x[i:]
i+=1
if lookup(x[:len(x)-1]+z[len(word)-1]) and x[:len(x)-1]+z[len(x)-1]!=x :##same applies here.
word=x[:len(x)-1]+z[len(word)-1]
y = changeling(word,target,steps-1)
if y :
return [x] + y##used to concatenate the first word to the final list, and if the list goes past the amount of steps.
else:
return None
Here's my current code:
import string
def changeling(word,target,steps):
alpha=string.ascii_lowercase
x=word##word and target has been changed to keep the coding readable.
z=target
if steps==0 and word!= target:##if the target can't be reached, return nothing.
return []
if x==z:##if target has been reached.
return [z]
holderlist=[]
if len(word)!=len(target):##if the word and target word aren't the same length print error.
print "error"
return None
i=1
for items in alpha:
i=1
while i!=len(x):
if lookup(x[:i-1]+items+x[i:]) is True and x[:i-1]+items+x[i:]!=x:
word =x[:i-1]+items+x[i:]
holderlist.append(word)
i+=1
if lookup(x[:len(x)-1]+items) is True and x[:len(x)-1]+items!=x:
word=x[:len(x)-1]+items
holderlist.append(word)
y = changeling(word,target,steps-1)
if y :
return [x] + y##used to concatenate the first word to the final list, and if the/
list goes past the amount of steps.
else:
return None
The differences between the two is that the first checks every variation of find with the letters from lose. Meaning: lind, fond, fisd, and fine. Then, if it finds a working word with the lookup function, it calls changeling on that newfound word.
As opposed to my new program, which checks every variation of find with every single letter in the alphabet.
I can't seem to get this code to work. I've tested it by simply printing what the results are of find:
for items in alpha:
i=1
while i!=len(x):
print (x[:i-1]+items+x[i:])
i+=1
print (x[:len(x)-1]+items)
This gives:
aind
fand
fiad
fina
bind
fbnd
fibd
finb
cind
fcnd
ficd
finc
dind
fdnd
fidd
find
eind
fend
fied
fine
find
ffnd
fifd
finf
gind
fgnd
figd
fing
hind
fhnd
fihd
finh
iind
find
fiid
fini
jind
fjnd
fijd
finj
kind
fknd
fikd
fink
lind
flnd
fild
finl
mind
fmnd
fimd
finm
nind
fnnd
find
finn
oind
fond
fiod
fino
pind
fpnd
fipd
finp
qind
fqnd
fiqd
finq
rind
frnd
fird
finr
sind
fsnd
fisd
fins
tind
ftnd
fitd
fint
uind
fund
fiud
finu
vind
fvnd
fivd
finv
wind
fwnd
fiwd
finw
xind
fxnd
fixd
finx
yind
fynd
fiyd
finy
zind
fznd
fizd
finz
Which is perfect! Notice that each letter in the alphabet goes through my word at least once. Now, what my program does is use a helper function to determine if that word is in a dictionary that I've been given.
Consider this, instead of like my first program, I now receive multiple words that are legal, except when I do word=foundword it means I'm replacing the previous word each time. Which is why I'm trying holderlist.append(word).
I think my problem is that I need changeling to run through each word in holderlist, and I'm not sure how to do that. Although that's only speculation.
Any help would be appreciated,
Cheers.
I might be slightly confused about what you need, but by borrowing from this post I belive I have some code that should be helpful.
>>> alphabet = 'abcdefghijklmnopqrstuvwxyz'
>>> word = 'java'
>>> splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
>>> splits
[('', 'java'), ('j', 'ava'), ('ja', 'va'), ('jav', 'a'), ('java', '')]
>>> replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b]
>>> replaces
['aava', 'bava', 'cava', 'dava', 'eava', 'fava', 'gava', 'hava', 'iava', 'java', 'kava', 'lava', 'mava', 'nava', 'oava', 'pava', 'qava', 'rava', 'sava', 'tava', 'uava', 'vava', 'wav
a', 'xava', 'yava', 'zava', 'java', 'jbva', 'jcva', 'jdva', 'jeva', 'jfva', 'jgva', 'jhva', 'jiva', 'jjva', 'jkva', 'jlva', 'jmva', 'jnva', 'jova', 'jpva', 'jqva', 'jrva', 'jsva', '
jtva', 'juva', 'jvva', 'jwva', 'jxva', 'jyva', 'jzva', 'jaaa', 'jaba', 'jaca', 'jada', 'jaea', 'jafa', 'jaga', 'jaha', 'jaia', 'jaja', 'jaka', 'jala', 'jama', 'jana', 'jaoa', 'japa'
, 'jaqa', 'jara', 'jasa', 'jata', 'jaua', 'java', 'jawa', 'jaxa', 'jaya', 'jaza', 'java', 'javb', 'javc', 'javd', 'jave', 'javf', 'javg', 'javh', 'javi', 'javj', 'javk', 'javl', 'ja
vm', 'javn', 'javo', 'javp', 'javq', 'javr', 'javs', 'javt', 'javu', 'javv', 'javw', 'javx', 'javy', 'javz']
Once you have a list of all possible replaces, you can simply do
valid_words = [valid for valid in replaces if lookup(valid)]
Which should give you all words that can be formed by replacing 1 character in word. By placing this code in a separate method, you could take a word, obtain possible next words from that current word, and recurse over each of those words. For example:
alphabet = 'abcdefghijklmnopqrstuvwxyz'
def next_word(word):
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b]
return [valid for valid in replaces if lookup(valid)]
Is this enough help? I think your code could really benefit by separating tasks into smaller chunks.
Fixed your code:
import string
def changeling(word, target, steps):
alpha=string.ascii_lowercase
x = word #word and target has been changed to keep the coding readable.
z = target
if steps == 0 and word != target: #if the target can't be reached, return nothing.
return []
if x == z: #if target has been reached.
return [z]
holderlist = []
if len(word) != len(target): #if the word and target word aren't the same length print error.
raise BaseException("Starting word and target word not the same length: %d and %d" % (len(word),
i = 1
for items in alpha:
i=1
while i != len(x):
if lookup(x[:i-1] + items + x[i:]) is True and x[:i-1] + items + x[i:] != x:
word = x[:i-1] + items + x[i:]
holderlist.append(word)
i += 1
if lookup(x[:len(x)-1] + items) is True and x[:len(x)-1] + items != x:
word = x[:len(x)-1] + items
holderlist.append(word)
y = [changeling(pos_word, target, steps-1) for pos_word in holderlist]
if y:
return [x] + y #used to concatenate the first word to the final list, and if the list goes past the amount of steps.
else:
return None
Where len(word) and len(target), it'd be better to raise an exception than print something obscure, w/o a stack trace and non-fatal.
Oh and backslashes(\), not forward slashes(/), are used to continue lines. And they don't work on comments

Categories