extracting index from a nested list - python

I would like to be able to get the index of each number in a nested list so for example i have the following list:
T = ['apple', [10, 5, ['orange']], 3]
and i would like to extract the values as such:
List of numbers: [10,5,3]
address of numbers: [[1, 0], [1, 1], [2]]
so for example, the number '3' is the third value in the list (index 2), where as the number '5' is the second value in the second list so it will be [1,1].
I've written the following recursive function with a for loop inside:
indices = []
List_numbers = []
Address_numbers = []
def Numbers(T):
for index, elem in enumerate(T):
if isinstance(elem, int):
List_numbers.append(elem)
Address_numbers.append(indices + [index])
if isinstance(elem, list):
indices.append(index)
Fruits(elem)
print('List of numbers: ' + str(List_numbers))
print('Address of numbers: ' + str(Address_numbers))
The problem with this code, is when it reaches the last value and needs to exit the list it keeps the same index so the address is outputs is this:
List of numbers: [10, 5, 3]
Address of numbers: [[1, 0], [1, 1], [1, 2, 2]]
I've tried everything to fix it but im honestly not sure how it would be possible to fix this, can anyone help?

Use a recursive function to extract index from nested list.
Using recursion you can extract index from nested list to any depth:
T = ['apple', [10, 5, ['orange']], 3]
total_numbers = []
indexes = []
def find_index_of_numbers(lisst, level):
for index, value in enumerate(lisst):
if isinstance(value, int):
total_numbers.append(value)
indexes.append([level, index])
elif isinstance(value, list):
find_index_of_numbers(value, level + 1)
find_index_of_numbers(T, 0)
print("My list--->", T)
print("Numbers--->", total_numbers)
print("Indexes--->", indexes)
Output
My list---> ['apple', [10, 5, ['orange']], 3]
Numbers---> [10, 5, 3]
Indexes---> [[1, 0], [1, 1], [0, 2]]

Related

How to append elements in a list within a list?

I'd like to append elements to a sub-list within a main-list. The number of elements to be appended corresponds to the sub-list position in the main-list.
My code:
# define the maximum level of the game
max_level = 3
# create list with length = level
lsx = []
# append empty lists in lsy for every element in lsx
empty = []
lsy = []
def create_list(max_level):
for i in range(max_level):
integer = random.randint(1,5)
lsx.append(integer)
for j in lsx:
lsy.append(empty)
return(lsy)
create_list(max_level)
Output:
[[], [], []]
Desired output:
[[1], [1, 2], [1, 2, 3]]
You don't need (and shouldn't) use globals. When appending empty to lsy multiple times you are appending the same object - changing one will change other as well.
You can create the nested lists inside the loop:
import random
def create_list(max_level):
# top level list
res = []
for i in range(max_level):
# nested list
next_l = []
for j in range(i+1):
next_l.append(random.randint(1, 5))
res.append(next_l)
return res
print(create_list(3))
Output:
[[5], [4, 3], [2, 3, 2]]
Well, this could work
def create_list(max_level):
res = []
for i in range(max_level):
i += 1
res.append(list(range(i+1))[1:])
return res
Output
>>> create_list(5)
[[1], [1, 2], [1, 2, 3], [1, 2, 3, 4], [1, 2, 3, 4, 5]]

Subsets With Duplicates, issues with only returning empty list

I am working on a question as following:
Given a set of numbers that might contain duplicates, find all of its distinct subsets.
You can use the following as an example :
Example 1:
Input: [1, 3, 3]
Output: [], [1], [3], [1,3], [3,3], [1,3,3]
Example 2:
Input: [1, 5, 3, 3]
Output: [], [1], [5], [3], [1,5], [1,3], [5,3], [1,5,3], [3,3],
[1,3,3], [3,3,5], [1,5,3,3]
My approach is
class Solution:
def distinct_subset(self, nums):
n = len(nums)
previousEnd = 0
output = []
for i in range(n):
# judge if the current element is equal to the previous element
# if so, only update the elements generated in the previous iteration
if i > 0 and nums[i] == nums[i-1]:
previousStart = previousEnd + 1
else:
previousStart = 0
perviousEnd = len(output)
# create a temp array to store the output from the previous iteration
temp = list(output[previousStart:previousEnd])
# add current element to all the array generated by the previous iteration
output += [j + [nums[i]] for j in temp]
return output
def main():
print("Here is the list of subsets: " + str(Solution().distinct_subset([1, 3, 3])))
print("Here is the list of subsets: " + str(Solution().distinct_subset([1, 5, 3, 3])))
main()
However, my approach will only return []:
Here is the list of subsets: []
Here is the list of subsets: []
Process finished with exit code 0
I am not sure why did I go wrong. The algorithm supposes to update the output in each iteration. But now it failed.
Please feel free to share your ideas. Thanks for your help in advanced.
Yes, I ran your code and it appears no matter what you do the function will always return an output of an empty list, because nothing is actually changing in the list, it is always blank.
Forgive me, but I had to look up what 'all distinct subsets' meant, and I stumbled across this code, but it seems to do exactly what you are asking.
# Python3 program to find all subsets of
# given set. Any repeated subset is
# considered only once in the output
def printPowerSet(arr, n):
# Function to find all subsets of given set.
# Any repeated subset is considered only
# once in the output
_list = []
# Run counter i from 000..0 to 111..1
for i in range(2**n):
subset = ""
# consider each element in the set
for j in range(n):
# Check if jth bit in the i is set.
# If the bit is set, we consider
# jth element from set
if (i & (1 << j)) != 0:
subset += str(arr[j]) + "|"
# if subset is encountered for the first time
# If we use set<string>, we can directly insert
if subset not in _list and len(subset) > 0:
_list.append(subset)
# consider every subset
for subset in _list:
# split the subset and print its elements
arr = subset.split('|')
for string in arr:
print(string, end = " ")
print()
# Driver Code
if __name__ == '__main__':
arr = [10, 12, 12, 17]
n = len(arr)
printPowerSet(arr, n)
However, as you can see the above code does not use classes just a single function. If that works great, if you are required to use a class, let me know you will need to change the above code obviously.
I assume the below is what you are looking for:
[1, 3, 3] to [1,3]
[1, 5, 3, 3] to [1,5,3]
The set(list) function will do that for you real easy, however it doesn't handle compound data structure well.
Below code will work for compound data from, one level deep:
[[1, 1], [0, 1], [0, 1], [0, 0], [1, 0], [1, 1], [1, 1]]
to:
[[1, 1], [0, 1], [0, 0], [1, 0]]
code:
def get_unique(list):
temp = []
for i in list:
if i not in temp:
temp.append(i)
yield i
print(*get_unique(list))
I've trimmed the above code to give you your desired outputs, still not in a class though, is this okay?...
def distinct_subset(user_input):
n = len(user_input)
output = []
for i in range(2 ** n):
subset = ""
for j in range(n):
if (i & (1 << j)) != 0:
subset += str(user_input[j]) + ", "
if subset[:-2] not in output and len(subset) > 0:
output.append(subset[:-2])
return output
def main():
print("Here is the list of subsets: " + str(distinct_subset([1, 3, 3])))
print("Here is the list of subsets: " + str(distinct_subset([1, 5, 3, 3])))
main()
You're looking for distinct combinations of the powerset of your list.
Using itertools to generate the combinations and a set to eliminate duplicates, you could write the function like this:
from itertools import combinations
def uniqueSubsets(A):
A = sorted(A)
return [*map(list,{subset for size in range(len(A)+1)
for subset in combinations(A,size)})]
print(uniqueSubsets([1,3,3]))
# [[1, 3], [3, 3], [1], [3], [], [1, 3, 3]]
print(uniqueSubsets([1,5,3,3]))
# [1, 3] [3, 3] [1] [3] [3, 3, 5] [1, 3, 5] [1, 5] [5] [] [1, 3, 3, 5] [1, 3, 3] [3, 5]
If you have a lot of duplicates, it may be more efficient to filter them out as you go. Here is a recursive generator function that short-circuits the expansion when a combination has already been seen. It generates combinations by removing one element at a time (starting from the full size) and recursing to get shorter combinations.
def uniqueSubsets(A,seen=None):
if seen is None: seen,A = set(),sorted(A)
for i in range(len(A)): # for each position in the list
subset = (*A[:i],*A[i+1:]) # combination without that position
if subset in seen: continue # that has not been seen before
seen.add(subset)
yield from uniqueSubsets(subset,seen) # get shorter combinations
yield list(A)
print(*uniqueSubsets([1,3,3]))
# [] [3] [3, 3] [1] [1, 3] [1, 3, 3]
print(*uniqueSubsets([1,5,3,3]))
# [] [3] [3, 3] [5] [5, 3] [5, 3, 3] [1] [1, 3] [1, 3, 3] [1, 5] [1, 5, 3] [1, 5, 3, 3]
In both cases we are sorting the list in order to ensure that the combinations will always present the values in the same order for the set() to recognize them. (otherwise lists such as [3,3,1,3] could still produce duplicates)

Segmenting a list of lists in Python

I have a list of lists all of the same length. I would like to segment the first list into contiguous runs of a given value. I would then like to segment the remaining lists to match the segments generated from the first list.
For example:
Given value: 2
Given list of lists: [[0,0,2,2,2,1,1,1,2,3], [1,2,3,4,5,6,7,8,9,10], [1,1,1,1,1,1,1,1,1,1]
Return: [ [[2,2,2],[2]], [[3,4,5],[9]], [[1,1,1],[1]] ]
The closest I have gotten is to get the indices by:
>>> import itertools
>>> import operator
>>> x = 2
>>> L = [[0,0,2,2,2,1,1,1,2,3],[1,2,3,4,5,6,7,8,9,10],[1,1,1,1,1,1,1,1,1,1]]
>>> I = [[i for i,value in it] for key,it in itertools.groupby(enumerate(L[0]), key=operator.itemgetter(1)) if key == x]
>>> print I
[[2, 3, 4], [8]]
This code was modified from another question on this site.
I would like to find the most efficient way possible, since these lists may be very long.
EDIT:
Maybe if I place the lists one on top of each other it might be clearer:
[[0,0,[2,2,2],1,1,1,[2],3], -> [2,2,2],[2]
[1,2,[3,4,5],6,7,8,[9],10],-> [3,4,5],[9]
[1,1,[1,1,1],1,1,1,[1],1]] -> [1,1,1],[1]
You can use groupby to create a list of groups in the form of a tuple of starting index and length of the group, and use this list to extract the values from each sub-list:
from itertools import groupby
from operator import itemgetter
def match(L, x):
groups = [(next(g)[0], sum(1 for _ in g) + 1)
for k, g in groupby(enumerate(L[0]), key=itemgetter(1)) if k == x]
return [[lst[i: i + length] for i, length in groups] for lst in L]
so that:
match([[0,0,2,2,2,1,1,1,2,3], [1,2,3,4,5,6,7,8,9,10], [1,1,1,1,1,1,1,1,1,1]], 2)
returns:
[[[2, 2, 2], [2]], [[3, 4, 5], [9]], [[1, 1, 1], [1]]]
l=[[0,0,2,2,2,1,1,1,2,3], [1,2,3,4,5,6,7,8,9,10], [1,1,1,1,1,1,1,1,1,1]]
temp=l[0]
value=2
dict={}
k=-1
prev=-999
for i in range(0,len(temp)):
if(temp[i]==value):
if(prev!=-999 and prev==i-1):
if(k in dict):
dict[k].append(i)
else:
dict[k]=[i]
else:
k+=1
if(k in dict):
dict[k].append(i)
else:
dict[k]=[i]
prev=i
output=[]
for i in range(0,len(l)):
single=l[i]
final=[]
for keys in dict: #{0: [2, 3, 4], 1: [8]}
ans=[]
desired_indices=dict[keys]
for j in range(0,len(desired_indices)):
ans.append(single[desired_indices[j]])
final.append(ans)
output.append(final)
print(output) #[[[2, 2, 2], [2]], [[3, 4, 5], [9]], [[1, 1, 1], [1]]]
This seems to be one of the approach, this first creates the dictionary of contagious elements and then looks for that keys in every list and stores in output.

Separating same numbers from the list and making the list of such lists [duplicate]

From this list:
N = [1,2,2,3,3,3,4,4,4,4,5,5,5,5,5]
I'm trying to create:
L = [[1],[2,2],[3,3,3],[4,4,4,4],[5,5,5,5,5]]
Any value which is found to be the same is grouped into it's own sublist.
Here is my attempt so far, I'm thinking I should use a while loop?
global n
n = [1,2,2,3,3,3,4,4,4,4,5,5,5,5,5] #Sorted list
l = [] #Empty list to append values to
def compare(val):
""" This function receives index values
from the n list (n[0] etc) """
global valin
valin = val
global count
count = 0
for i in xrange(len(n)):
if valin == n[count]: # If the input value i.e. n[x] == n[iteration]
temp = valin, n[count]
l.append(temp) #append the values to a new list
count +=1
else:
count +=1
for x in xrange (len(n)):
compare(n[x]) #pass the n[x] to compare function
Use itertools.groupby:
from itertools import groupby
N = [1,2,2,3,3,3,4,4,4,4,5,5,5,5,5]
print([list(j) for i, j in groupby(N)])
Output:
[[1], [2, 2], [3, 3, 3], [4, 4, 4, 4], [5, 5, 5, 5, 5]]
Side note: Prevent from using global variable when you don't need to.
Someone mentions for N=[1, 2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 5, 1] it will get [[1], [2, 2], [3, 3, 3], [4, 4, 4, 4], [5, 5, 5, 5, 5], [1]]
In other words, when numbers of the list isn't in order or it is a mess list, it's not available.
So I have better answer to solve this problem.
from collections import Counter
N = [1,2,2,3,3,3,4,4,4,4,5,5,5,5,5]
C = Counter(N)
print [ [k,]*v for k,v in C.items()]
You can use itertools.groupby along with a list comprehension
>>> l = [1,2,2,3,3,3,4,4,4,4,5,5,5,5,5]
>>> [list(v) for k,v in itertools.groupby(l)]
[[1], [2, 2], [3, 3, 3], [4, 4, 4, 4], [5, 5, 5, 5, 5]]
This can be assigned to the variable L as in
L = [list(v) for k,v in itertools.groupby(l)]
You're overcomplicating this.
What you want to do is: for each value, if it's the same as the last value, just append it to the list of last values; otherwise, create a new list. You can translate that English directly to Python:
new_list = []
for value in old_list:
if new_list and new_list[-1][0] == value:
new_list[-1].append(value)
else:
new_list.append([value])
There are even simpler ways to do this if you're willing to get a bit more abstract, e.g., by using the grouping functions in itertools. But this should be easy to understand.
If you really need to do this with a while loop, you can translate any for loop into a while loop like this:
for value in iterable:
do_stuff(value)
iterator = iter(iterable)
while True:
try:
value = next(iterator)
except StopIteration:
break
do_stuff(value)
Or, if you know the iterable is a sequence, you can use a slightly simpler while loop:
index = 0
while index < len(sequence):
value = sequence[index]
do_stuff(value)
index += 1
But both of these make your code less readable, less Pythonic, more complicated, less efficient, easier to get wrong, etc.
You can do that using numpy too:
import numpy as np
N = np.array([1,2,2,3,3,3,4,4,4,4,5,5,5,5,5])
counter = np.arange(1, np.alen(N))
L = np.split(N, counter[N[1:]!=N[:-1]])
The advantage of this method is when you have another list which is related to N and you want to split it in the same way.
Another slightly different solution that doesn't rely on itertools:
#!/usr/bin/env python
def group(items):
"""
groups a sorted list of integers into sublists based on the integer key
"""
if len(items) == 0:
return []
grouped_items = []
prev_item, rest_items = items[0], items[1:]
subgroup = [prev_item]
for item in rest_items:
if item != prev_item:
grouped_items.append(subgroup)
subgroup = []
subgroup.append(item)
prev_item = item
grouped_items.append(subgroup)
return grouped_items
print group([1,2,2,3,3,3,4,4,4,4,5,5,5,5,5])
# [[1], [2, 2], [3, 3, 3], [4, 4, 4, 4], [5, 5, 5, 5, 5]]

Picking up an item from a list of lists

I'm pretty new in python and have am difficulty doing the next assignment.
I am receiving a list of lists with numbers and the word none, for example:
[[1,None],[2,4],[1.5,2]]
My problem is when I go through None (I need to sum up the lists) I need to replace it by the max number in the same place in the other lists.
So my result should be None = max(4,2) and receive :
[[1,4],[2,4],[1.5,2]]
If I go through a for loop I don't understand how can I go to the other sub lists and check them out (especially when I don't know how many subs lists I have)
Use a nested list comprehension with conditional
>>> l = [[1,None],[2,4],[1.5,2]]
>>> def findMax(j):
... return max(i[j] for i in l)
...
>>> [[j if j is not None else findMax(k) for k,j in enumerate(i)] for i in l]
[[1, 4], [2, 4], [1.5, 2]]
Here the list comprehension checks if each element is None or not. If not it will print the number, else it will fnd the maximum and print that element.
Another way using map is
>>> l = [[1,None],[2,4],[1.5,2]]
>>> maxVal = max(map(max, l))
>>> [[j if j is not None else maxVal for k,j in enumerate(i)] for i in l]
[[1, 4], [2, 4], [1.5, 2]]
Here is a hint: In Python, a for in loop iterates through all the elements in some iterable. If you have a list of lists, that means each element in the list can also have a for loop applied to it, as in a for loop inside a for loop. You could use this if and only if the maximum depth of a list is 2:
def get_deep_max(deeplst):
new = []
for elem in deeplst:
for num in elem:
new.append(num)
return max(new)
Try writing the code for replacing the none value yourself for practice.
Code:
for idx1, sublist in enumerate(list1):
for idx2, element in enumerate(sublist):
if element is None:
try:
sublist[idx2] = max(list1[idx1+1])
except IndexError:
pass
The problem is that if there is a None in the last list you didn’t specify what the code should do. I just added a try and except. You can replace pass with what you want the code to do.
My suggestion:
x = [[1,None],[2,4],[1.5,2]] #your list
highest_num = None # assume that 0 can be the highest number in a different situation
for each in x:`# find the highest number
for another in each:
if another > highest_num:
highest_num = another
for each in xrange(len(x)): # find the None and replace it with the highest number
for another in xrange(len(x[each])):
if x[each][another] is None:
x[each][another] = highest_num
from contextlib import suppress
l = [[1,None],[2,4],[1.5,2]]
for sub in l:
with suppress(ValueError):
i = sub.index(None) # find index of None in sublist (or ValueError)
sub[i] = max(s[i] for s in l if s[i] is not None) # replace sublist item with max of sublists in same index
break
print(l)
# [[1, 4], [2, 4], [1.5, 2]]
This one is a bit cleaner to read than the others IMO
l = [[1,None],[2,4],[1.5,2]]
maxVal = max(map(max, l)) # maps the function 'max' over all the sub-lists
for subl in l:
for idx,elem in enumerate(subl): # use enumerate to get the index and element
if elem is None:
subl[idx] = maxVal
print l
# [[1, 4], [2, 4], [1.5, 2]]
Here is my suggestion:
l = [[1, None], [2, 4], [1.5, 2]]
# l = [[1, None], [2, 4], [1.5, 2]]
l1 = zip(*l)
# l1 = [(1, 2, 1.5), (None, 4, 2)]
m = map(max, l1)
# m = [2, 4]
l2 = [map(lambda y: m[i] if y is None else y, x) for i,x in enumerate(l1)]
# l2 = [[1, 2, 1.5], [4, 4, 2]]
ret = zip(*l2)
# ret = [(1, 4), (2, 4), (1.5, 2)]

Categories

Resources