How to create nested list from flatten list? - python

I wrote a function to create a nested list.
For example:
input= ['a','b','c','','d','e','f','g','','d','s','d','a','']
I want to create a sublist before ''
As a return I want a nested list like:
[['a','b','c'],['d','e','f','g'],['d','s','d','a']]

Try the following implementation
>>> def foo(inlist, delim = ''):
start = 0
try:
while True:
stop = inlist.index(delim, start)
yield inlist[start:stop]
start = stop + 1
except ValueError:
# if '' may not be the end delimiter
if start < len(inlist):
yield inlist[start:]
return
>>> list(foo(inlist))
[['a', 'b', 'c'], ['d', 'e', 'f', 'g'], ['d', 's', 'd', 'a']]
Another possible implementation could be by itertools.groupby. But then you have to filter the result to remove the ['']. But though it might look to be one-liner yet the above implementation is more pythonic as its intuitive and readable
>>> from itertools import ifilter, groupby
>>> list(ifilter(lambda e: '' not in e,
(list(v) for k,v in groupby(inlist, key = lambda e:e == ''))))
[['a', 'b', 'c'], ['d', 'e', 'f', 'g'], ['d', 's', 'd', 'a']]

I'd use itertools.groupby:
l = ['a','b','c','','d','e','f','g','','d','s','d','a','']
from itertools import groupby
[list(g) for k, g in groupby(l, bool) if k]
gives
[['a', 'b', 'c'], ['d', 'e', 'f', 'g'], ['d', 's', 'd', 'a']]

def nester(nput):
out = [[]]
for n in nput:
if n == '':
out.append([])
else:
out[-1].append(n)
if out[-1] == []:
out = out[:-1]
return out
edited to add check for empty list at end

Related

How to return a shuffled list considering mutually exclusive items?

Say I have a list of options and I want to pick a certain number randomly.
In my case, say the options are in a list ['a', 'b', 'c', 'd', 'e'] and I want my script to return 3 elements.
However, there is also the case of two options that cannot appear at the same time. That is, if option 'a' is picked randomly, then option 'b' cannot be picked. And the same applies the other way round.
So valid outputs are: ['a', 'c', 'd'] or ['c', 'd', 'b'], while things like ['a', 'b', 'c'] would not because they contain both 'a' and 'b'.
To fulfil these requirements, I am fetching 3 options plus another one to compensate a possible discard. Then, I keep a set() with the mutually exclusive condition and keep removing from it and check if both elements have been picked or not:
import random
mutually_exclusive = set({'a', 'b'})
options = ['a', 'b', 'c', 'd', 'e']
num_options_to_return = 3
shuffled_options = random.sample(options, num_options_to_return + 1)
elements_returned = 0
for item in shuffled_options:
if elements_returned >= num_options_to_return:
break
if item in mutually_exclusive:
mutually_exclusive.remove(item)
if not mutually_exclusive:
# if both elements have appeared, then the set is empty so we cannot return the current value
continue
print(item)
elements_returned += 1
However, I may be overcoding and Python may have better ways to handle these requirements. Going through random's documentation I couldn't find ways to do this out of the box. Is there a better solution than my current one?
One way to do this is use itertools.combinations to create all of the possible results, filter out the invalid ones and make a random.choice from that:
>>> from itertools import combinations
>>> from random import choice
>>> def is_valid(t):
... return 'a' not in t or 'b' not in t
...
>>> choice([
... t
... for t in combinations('abcde', 3)
... if is_valid(t)
... ])
...
('c', 'd', 'e')
Maybe a bit naive, but you could generate samples until your condition is met:
import random
options = ['a', 'b', 'c', 'd', 'e']
num_options_to_return = 3
mutually_exclusive = set({'a', 'b'})
while True:
shuffled_options = random.sample(options, num_options_to_return)
if all (item not in mutually_exclusive for item in shuffled_options):
break
print(shuffled_options)
You can restructure your options.
import random
options = [('a', 'b'), 'c', 'd', 'e']
n_options = 3
selected_option = random.sample(options, n_options)
result = [item if not isinstance(item, tuple) else random.choice(item)
for item in selected_option]
print(result)
I would implement it with sets:
import random
mutually_exclusive = {'a', 'b'}
options = ['a', 'b', 'c', 'd', 'e']
num_options_to_return = 3
while True:
s = random.sample(options, num_options_to_return)
print('Sample is', s)
if not mutually_exclusive.issubset(s):
break
print('Discard!')
print('Final sample:', s)
Prints (for example):
Sample is ['a', 'b', 'd']
Discard!
Sample is ['b', 'a', 'd']
Discard!
Sample is ['e', 'a', 'c']
Final sample: ['e', 'a', 'c']
I created the below function and I think it's worth sharing it too ;-)
def random_picker(options, n, mutually_exclusives=None):
if mutually_exclusives is None:
return random.sample(options, n)
elif any(len(pair) != 2 for pair in mutually_exclusives):
raise ValueError('Lenght of pairs of mutually_exclusives iterable, must be 2')
res = []
while len(res) < n:
item_index = random.randint(0, len(options) - 1)
item = options[item_index]
if any(item == exc and pair[-(i - 1)] in res for pair in mutually_exclusives
for i, exc in enumerate(pair)):
continue
res.append(options.pop(item_index))
return res
Where:
options is the list of available options to pick from.
n is the number of items you want to be picked from options
mutually_exclusives is an iterable containing tuples pairs of mutually exclusive items
You can use it as follows:
>>> random_picker(['a', 'b', 'c', 'd', 'e'], 3)
['c', 'e', 'a']
>>> random_picker(['a', 'b', 'c', 'd', 'e'], 3, [('a', 'b')])
['d', 'b', 'e']
>>> random_picker(['a', 'b', 'c', 'd', 'e'], 3, [('a', 'b'), ('a', 'c')])
['e', 'd', 'a']
import random
l = [['a','b'], ['c'], ['d'], ['e']]
x = [random.choice(i) for i in random.sample(l,3)]
here l is a two-dimensional list, where the fist level reflects an and relation and the second level an or relation.

replace duplicate values in a list with 'x'?

I am trying to understand the process of creating a function that can replace duplicate strings in a list of strings. for example, I want to convert this list
mylist = ['a', 'b', 'b', 'a', 'c', 'a']
to this
mylist = ['a', 'b', 'x', 'x', 'c', 'x']
initially, I know I need create my function and iterate through the list
def replace(foo):
newlist= []
for i in foo:
if foo[i] == foo[i+1]:
foo[i].replace('x')
return foo
However, I know there are two problems with this. the first is that I get an error stating
list indices must be integers or slices, not str
so I believe I should instead be operating on the range of this list, but I'm not sure how to implement it. The other being that this would only help me if the duplicate letter comes directly after my iteration (i).
Unfortunately, that's as far as my understanding of the problem reaches. If anyone can provide some clarification on this procedure for me, I would be very grateful.
Go through the list, and keep track of what you've seen in a set. Replace things you've seen before in the list with 'x':
mylist = ['a', 'b', 'b', 'a', 'c', 'a']
seen = set()
for i, e in enumerate(mylist):
if e in seen:
mylist[i] = 'x'
else:
seen.add(e)
print(mylist)
# ['a', 'b', 'x', 'x', 'c', 'x']
Simple Solution.
my_list = ['a', 'b', 'b', 'a', 'c', 'a']
new_list = []
for i in range(len(my_list)):
if my_list[i] in new_list:
new_list.append('x')
else:
new_list.append(my_list[i])
print(my_list)
print(new_list)
# output
#['a', 'b', 'b', 'a', 'c', 'a']
#['a', 'b', 'x', 'x', 'c', 'x']
The other solutions use indexing, which isn't necessarily required.
Really simply, you could check if the value is in the new list, else you can append x. If you wanted to use a function:
old = ['a', 'b', 'b', 'a', 'c']
def replace_dupes_with_x(l):
tmp = list()
for char in l:
if char in tmp:
tmp.append('x')
else:
tmp.append(char)
return tmp
new = replace_dupes_with_x(old)
You can use the following solution:
from collections import defaultdict
mylist = ['a', 'b', 'b', 'a', 'c', 'a']
ret, appear = [], defaultdict(int)
for c in mylist:
appear[c] += 1
ret.append(c if appear[c] == 1 else 'x')
Which will give you:
['a', 'b', 'x', 'x', 'c', 'x']

Splitting a python list into smaller lists at spaces

I have a list which consists of alphabets and spaces:
s = ['a','b',' ',' ','b','c',' ','d','e','f','g','h',' ','i','j'];
I need to split it into smaller individual lists:
s=[['a','b'],['b','c'],['d','e','f','g','h'],['i','j']]
I am new to python.
The entire code:
#To get the longest alphabetical substring from a given string
s = input("Enter any string: ")
alpha_string = []
for i in range(len(s)-1): #if length is 5: 0,1,2,3
if(s[i] <= s[i+1]):
if i == len(s)-2:
alpha_string.append(s[i])
alpha_string.append(s[i+1])
else:
alpha_string.append(s[i])
if(s[i] > s[i+1] and s[i-1] <= s[i]):
alpha_string.append(s[i])
alpha_string.append(" ")
if(s[i] > s[i+1] and s[i-1] > s[i]):
alpha_string.append(" ")
print(alpha_string)
#Getting the position of each space in the list
position = []
for j in range(len(alpha_string)):
if alpha_string[j] == " ":
position.append([j])
print(position)
#Using the position of each space to create slices into the list
start = 0
final_string = []
for k in range(len(position)):
final_string.append(alpha_string[start:position[k]])
temp = position[k]
start = temp
print(final_string)`
Try a list comprehension as follows
print([list(i) for i in ''.join(s).split(' ') if i != ''])
[['a', 'b'], ['b', 'c'], ['d', 'e', 'f', 'g', 'h'], ['i', 'j']]
Here generator will be perfect :
s = ['a','b',' ',' ','b','c',' ','d','e','f','g','h',' ','i','j'];
def generator_approach(list_):
list_s=[]
for i in list_:
if i==' ':
if list_s:
yield list_s
list_s=[]
else:
list_s.append(i)
yield list_s
closure=generator_approach(s)
print(list(closure))
output:
[['a', 'b'], ['b', 'c'], ['d', 'e', 'f', 'g', 'h'], ['i', 'j']]
Or simply in one line, result = [list(item) for item in ''.join(s).split()]
This is one functional way.
s = ['a','b',' ',' ','b','c',' ','d','e','f','g','h',' ','i','j']
res = list(map(list, ''.join(s).split()))
# [['a', 'b'], ['b', 'c'], ['d', 'e', 'f', 'g', 'h'], ['i', 'j']]
from itertools import groupby
s = ['a','b',' ',' ','b','c',' ','d','e','f','g','h',' ','i','j']
t = [list(g) for k, g in groupby(s, str.isspace) if not k]
print(t)
OUTPUT
[['a', 'b'], ['b', 'c'], ['d', 'e', 'f', 'g', 'h'], ['i', 'j']]
This doesn't require the strings to be single letter like many of the join() and split() solutions:
>>> from itertools import groupby
>>>
>>> s = ['abc','bcd',' ',' ','bcd','cde',' ','def','efg','fgh','ghi','hij',' ','ijk','jkl']
>>>
>>> [list(g) for k, g in groupby(s, str.isspace) if not k]
[['abc', 'bcd'], ['bcd', 'cde'], ['def', 'efg', 'fgh', 'ghi', 'hij'], ['ijk', 'jkl']]
>>>
I can never pass up an opportunity to (ab)use groupby()

A program to mutate Nested Lists

Could someone help me do two things:
Review the code and see if it could be written in a better way.
Finish this program. I got stuck in trying to put the list back the way it is. i.e. a nested list of lists.
Here we go:
t = ['a', 'b', ['c', 'd'], ['e'], 'f']
def capitalize_list(t):
L = []
N = []
for i in range(len(t)):
if type(t[i]) == str:
L.append(t[i].capitalize())
if type(t[i]) == list:
L.extend(t[i])
for s in L:
N.append(s.capitalize())
print N
capitalize_list(t)
This code prints:
['A', 'B', 'C', 'D', 'E', 'F']
I need it to print:
['A', 'B', ['C', 'D'], ['E'], 'F']
You can use recursion:
def capitalize_list(t):
N = []
for i in range(len(t)):
if type(t[i]) == str:
N.append(t[i].capitalize())
if type(t[i]) == list:
N.append(capitalize_list(t[i]))
return N
Output:
['A', 'B', ['C', 'D'], ['E'], 'F']
An alternative way of doing this recursively:
def capitalize(item):
if type(item) is str:
return item.capitalize()
if type(item) is list:
return map(capitalize, item)
You could even do
def capitalize(item):
try:
return item.capitalize()
except AttributeError:
return map(capitalize, item)
-- which would use the capitalize method for any object that has it (such as a normal or unicode string) and attempt to iterate through any object that does not.

Most Pythonic Way to Split an Array by Repeating Elements

I have a list of items that I want to split based on a delimiter. I want all delimiters to be removed and the list to be split when a delimiter occurs twice. For example, if the delimiter is 'X', then the following list:
['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g']
Would turn into:
[['a', 'b'], ['c', 'd'], ['f', 'g']]
Notice that the last set is not split.
I've written some ugly code that does this, but I'm sure there is something nicer. Extra points if you can set an arbitrary length delimiter (i.e. split the list after seeing N delimiters).
I don't think there's going to be a nice, elegant solution to this (I'd love to be proven wrong of course) so I would suggest something straightforward:
def nSplit(lst, delim, count=2):
output = [[]]
delimCount = 0
for item in lst:
if item == delim:
delimCount += 1
elif delimCount >= count:
output.append([item])
delimCount = 0
else:
output[-1].append(item)
delimCount = 0
return output
>>> nSplit(['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g'], 'X', 2)
[['a', 'b'], ['c', 'd'], ['f', 'g']]
Here's a way to do it with itertools.groupby():
import itertools
class MultiDelimiterKeyCallable(object):
def __init__(self, delimiter, num_wanted=1):
self.delimiter = delimiter
self.num_wanted = num_wanted
self.num_found = 0
def __call__(self, value):
if value == self.delimiter:
self.num_found += 1
if self.num_found >= self.num_wanted:
self.num_found = 0
return True
else:
self.num_found = 0
def split_multi_delimiter(items, delimiter, num_wanted):
keyfunc = MultiDelimiterKeyCallable(delimiter, num_wanted)
return (list(item
for item in group
if item != delimiter)
for key, group in itertools.groupby(items, keyfunc)
if not key)
items = ['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g']
print list(split_multi_delimiter(items, "X", 2))
I must say that cobbal's solution is much simpler for the same results.
Use a generator function to maintain state of your iterator through the list, and the count of the number of separator chars seen so far:
l = ['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g']
def splitOn(ll, x, n):
cur = []
splitcount = 0
for c in ll:
if c == x:
splitcount += 1
if splitcount == n:
yield cur
cur = []
splitcount = 0
else:
cur.append(c)
splitcount = 0
yield cur
print list(splitOn(l, 'X', 2))
print list(splitOn(l, 'X', 1))
print list(splitOn(l, 'X', 3))
l += ['X','X']
print list(splitOn(l, 'X', 2))
print list(splitOn(l, 'X', 1))
print list(splitOn(l, 'X', 3))
prints:
[['a', 'b'], ['c', 'd'], ['f', 'g']]
[['a', 'b'], [], ['c', 'd'], [], ['f'], ['g']]
[['a', 'b', 'c', 'd', 'f', 'g']]
[['a', 'b'], ['c', 'd'], ['f', 'g'], []]
[['a', 'b'], [], ['c', 'd'], [], ['f'], ['g'], [], []]
[['a', 'b', 'c', 'd', 'f', 'g']]
EDIT: I'm also a big fan of groupby, here's my go at it:
from itertools import groupby
def splitOn(ll, x, n):
cur = []
for isdelim,grp in groupby(ll, key=lambda c:c==x):
if isdelim:
nn = sum(1 for c in grp)
while nn >= n:
yield cur
cur = []
nn -= n
else:
cur.extend(grp)
yield cur
Not too different from my earlier answer, just lets groupby take care of iterating over the input list, creating groups of delimiter-matching and not-delimiter-matching characters. The non-matching characters just get added onto the current element, the matching character groups do the work of breaking up new elements. For long lists, this is probably a bit more efficient, as groupby does all its work in C, and still only iterates over the list once.
a = ['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g']
b = [[b for b in q if b != 'X'] for q in "".join(a).split("".join(['X' for i in range(2)]))]
this gives
[['a', 'b'], ['c', 'd'], ['f', 'g']]
where the 2 is the number of elements you want. there is most likely a better way to do this.
Very ugly, but I wanted to see if I could pull this off as a one-liner and I thought I would share. I beg you not to actually use this solution for anything of any importance though. The ('X', 3) at the end is the delimiter and the number of times it should be repeated.
(lambda delim, count: map(lambda x:filter(lambda y:y != delim, x), reduce(lambda x, y: (x[-1].append(y) if y != delim or x[-1][-count+1:] != [y]*(count-1) else x.append([])) or x, ['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g'], [[]])))('X', 2)
EDIT
Here's a breakdown. I also eliminated some redundant code that was far more obvious when written out like this. (changed above also)
# Wrap everything in a lambda form to avoid repeating values
(lambda delim, count:
# Filter all sublists after construction
map(lambda x: filter(lambda y: y != delim, x), reduce(
lambda x, y: (
# Add the value to the current sub-list
x[-1].append(y) if
# but only if we have accumulated the
# specified number of delimiters
y != delim or x[-1][-count+1:] != [y]*(count-1) else
# Start a new sublist
x.append([]) or x,
['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g'], [[]])
)
)('X', 2)
Here's a clean nice solution using zip and generators
#1 define traditional sequence split function
#if you only want it for lists, you can use indexing to make it shorter
def split(it, x):
to_yield = []
for y in it:
if x == y:
yield to_yield
to_yield = []
else:
to_yield.append(y)
if to_yield:
yield to_yield
#2 zip the sequence with its tail
#you could use itertools.chain to avoid creating unnecessary lists
zipped = zip(l, l[1:] + [''])
#3. remove ('X',not 'X')'s from the resulting sequence, and leave only the first position of each
# you can use list comprehension instead of generator expression
filtered = (x for x,y in zipped if not (x == 'X' and y != 'X'))
#4. split the result using traditional split
result = [x for x in split(filtered, 'X')]
This way split() is more reusable.
It's surprising python doesn't have one built in.
edit:
You can easily adjust it for longer split sequences, repeating steps 2-3 and zipping filtered with l[i:] for 0< i <= n.
import re
map(list, re.sub('(?<=[a-z])X(?=[a-z])', '', ''.join(lst)).split('XX'))
This does a list -> string -> list conversion and assumes that the non-delimiter characters are all lower case letters.
Here's another way of doing this:
def split_multi_delimiter(items, delimiter, num_wanted):
def remove_delimiter(objs):
return [obj for obj in objs if obj != delimiter]
ranges = [(index, index+num_wanted) for index in xrange(len(items))
if items[index:index+num_wanted] == [delimiter] * num_wanted]
last_end = 0
for range_start, range_end in ranges:
yield remove_delimiter(items[last_end:range_start])
last_end = range_end
yield remove_delimiter(items[last_end:])
items = ['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g']
print list(split_multi_delimiter(items, "X", 2))
In [6]: input = ['a', 'b', 'X', 'X', 'cc', 'XX', 'd', 'X', 'ee', 'X', 'X', 'f']
In [7]: [s.strip('_').split('_') for s in '_'.join(input).split('X_X')]
Out[7]: [['a', 'b'], ['cc', 'XX', 'd', 'X', 'ee'], ['f']]
This assumes you can use a reserved character such as _ which is not found in the input.
Too clever by half, and only offered because the obvious right way to do it seems so brute-force and ugly:
class joiner(object):
def __init__(self, N, data = (), gluing = False):
self.data = data
self.N = N
self.gluing = gluing
def __add__(self, to_glue):
# Process an item from itertools.groupby, by either
# appending the data to the last item, starting a new item,
# or changing the 'gluing' state according to the number of
# consecutive delimiters that were found.
N = self.N
data = self.data
item = list(to_glue[1])
# A chunk of delimiters;
# return a copy of self with the appropriate gluing state.
if to_glue[0]: return joiner(N, data, len(item) < N)
# Otherwise, handle the gluing appropriately, and reset gluing state.
a, b = (data[:-1], data[-1] if data else []) if self.gluing else (data, [])
return joiner(N, a + (b + item,))
def split_on_multiple(data, delimiter, N):
# Split the list into alternating groups of delimiters and non-delimiters,
# then use the joiner to join non-delimiter groups when the intervening
# delimiter group is short.
return sum(itertools.groupby(data, delimiter.__eq__), joiner(N)).data
Regex, I choose you!
import re
def split_multiple(delimiter, input):
pattern = ''.join(map(lambda x: ',' if x == delimiter else ' ', input))
filtered = filter(lambda x: x != delimiter, input)
result = []
for k in map(len, re.split(';', ''.join(re.split(',',
';'.join(re.split(',{2,}', pattern)))))):
result.append([])
for n in range(k):
result[-1].append(filtered.__next__())
return result
print(split_multiple('X',
['a', 'b', 'X', 'X', 'c', 'd', 'X', 'X', 'f', 'X', 'g']))
Oh, you said Python, not Perl.

Categories