I have a python dictionary like this example:
small example:
dict = {'chr2:173370685-173370692': 'TACCAAG', 'chr5:118309829-118309836': 'TCTCCTT', 'chr12:104659651-104659658': 'GACCAAA'}
I only need the value part of every item which is a sequence of letters and the letters are A, T, C or G and also the length of each sequence is 7 so, for every sequence of letters there are 7 positions. I want to get the frequency of the 4 mentioned letters in every position (we have 7 positions). for every position I will make a dictionary in which the letters are key and the frequency of every letter is value. and at the end I want to make a dictionary for all seven positions and the fist dictionary would be the value of the final dictionary.
here is the expected output for the small example:
expected output:
final = {one: {'T': 2, 'A': 1, 'C': 0, 'G': 0}, two: {'T': 0, 'A': 2, 'C': 1, 'G': 0}, three: {'T': 1, 'A': 0, 'C': 2, 'G': 0}, four: {'T': 0, 'A': 0, 'C': 3, 'G': 0}, five: {'T': 0, 'A': 2, 'C': 1, 'G': 0}, six: {'T': 1, 'A': 2, 'C': 0, 'G': 0}, seven: {'T': 1, 'A': 1, 'C': 0, 'G': 1}}
to get this output I wrote a code in python but it does not return what exactly I want. do you know how to fix the following code?
one=[]
two=[]
three=[]
four=[]
five=[]
six=[]
seven=[]
mylist = dict.values()
for threeq in mylist:
one.append(threeq[0])
two.append(threeq[1])
three.append(threeq[2])
four.append(threeq[3])
five.append(threeq[4])
six.append(threeq[5])
seven.append(threeq[6])
from collections import Counter
one=Counter(one)
two=Counter(two)
three=Counter(three)
four=Counter(four)
five=Counter(five)
six=Counter(six)
seven=Counter(seven)
Here is a way to do it, using Counter:
from collections import Counter
data = {'chr2:173370685-173370692': 'TACCAAG', 'chr5:118309829-118309836': 'TCTCCTT', 'chr12:104659651-104659658': 'GACCAAA'}
out = {i:Counter(col) for i, col in enumerate(zip(*(data.values()))) }
# we can add the missing keys whose count is 0:
for count in out.values():
count.update(dict.fromkeys('ATGC', 0))
print(out)
# {0: Counter({'T': 2, 'G': 1, 'A': 0, 'C': 0}), 1: Counter({'A': 2, 'C': 1, 'T': 0, 'G': 0}),
# 2: Counter({'C': 2, 'T': 1, 'A': 0, 'G': 0}), 3: Counter({'C': 3, 'A': 0, 'T': 0, 'G': 0}),
# 4: Counter({'A': 2, 'C': 1, 'T': 0, 'G': 0}), 5: Counter({'A': 2, 'T': 1, 'G': 0, 'C': 0}),
# 6: Counter({'G': 1, 'T': 1, 'A': 1, 'C': 0})}
I left the original indices as integers, it's probably easier to use them than strings like 'one', 'two'... But if you really want to:
numbers_as_strings = ['one', 'two', 'three', 'four', 'five', 'six', 'seven']
out = {numbers_as_strings[key]:value for key, value in out.items()}
print(out)
# {'one': Counter({'T': 2, 'G': 1, 'A': 0, 'C': 0}),
# 'two': Counter({'A': 2, 'C': 1, 'T': 0, 'G': 0}) ....
Try this:
values = list(dict.values())
r = {}
for i in range(7):
r[i+1] = {'T': 0, 'A': 0, 'C': 0, 'G': 0}
for v in values:
r[i+1][v[i]] += 1
dict = {'chr2:173370685-173370692': 'TACCAAG', 'chr5:118309829-118309836': 'TCTCCTT', 'chr12:104659651-104659658': 'GACCAAA'}
options=['T','A','C','G']
innerdicts=['one','two','three','four','five','six','seven']
def getposcount(idx,letter,dict):
count=0
for v in dict.values():
if v[idx]==letter:
count+=1
return count
d = {x:{y:getposcount(innerdicts.index(x),y,dict) for y in options} for x in innerdicts}
print(d)
Output
{'six': {'T': 1, 'A': 2, 'G': 0, 'C': 0}, 'one': {'T': 2, 'A': 0, 'G': 1, 'C': 0}, 'two': {'T': 0, 'A': 2, 'G': 0, 'C': 1}, 'five': {'T': 0, 'A': 2, 'G': 0, 'C': 1}, 'three': {'T': 1, 'A': 0, 'G': 0, 'C': 2}, 'seven': {'T': 1, 'A': 1, 'G': 1, 'C': 0}, 'four': {'T': 0, 'A': 0, 'G': 0, 'C': 3}}
If you are willing to accept the integers as keys, you can do:
from collections import Counter
def counts_with_zero(count, keys='TACG'):
return {key: count.get(key, 0) for key in keys}
d = {'chr2:173370685-173370692': 'TACCAAG', 'chr5:118309829-118309836': 'TCTCCTT',
'chr12:104659651-104659658': 'GACCAAA'}
values = list(d.values())
result = {i: counts_with_zero(Counter(column)) for i, column in enumerate(zip(*values), 1)}
print(result)
Output
{1: {'A': 0, 'C': 0, 'G': 1, 'T': 2},
2: {'A': 2, 'C': 1, 'G': 0, 'T': 0},
3: {'A': 0, 'C': 2, 'G': 0, 'T': 1},
4: {'A': 0, 'C': 3, 'G': 0, 'T': 0},
5: {'A': 2, 'C': 1, 'G': 0, 'T': 0},
6: {'A': 2, 'C': 0, 'G': 0, 'T': 1},
7: {'A': 1, 'C': 0, 'G': 1, 'T': 1}}
I am in the mid-way of writing a code to find all possible solutions of a input similar like "a&b|c!d|a", where a,b,c,d all are booleans and &-and, |-or !-not are the operators. By solution I mean the set of values of these variables which makes the input expression give True.
I am able to print all possible combinations of the variables, but I am not able to retain them (in this case, in a list) for later use.
What's wrong in the way I am doing it? Are there better ways to store them?
generate_combination is the method in which I am trying to do this.
Code:
import operator
# global all_combinations
all_combinations=[]
answers=[]
def solve(combination, input, rank):
try:
substituted_str=""
for i in input:
if i in combination:
substituted_str+=combination[i]
else:
substituted_str+=i
print substituted_str
# for item in rank:
except:
pass
def generate_combination(variables,comb_dict, length, current_index):
if len(comb_dict)==length:
print comb_dict #Each combination , coming out right
all_combinations.append(comb_dict)
print all_combinations,"\n" #This is not working as expected
else:
for i in [1,0]:
comb_dict[variables[current_index]]=i
generate_combination(variables,comb_dict, length,current_index+1)
comb_dict.pop(variables[current_index], None)
def main(input,variables,order):
rank=sorted(order.items(), key=operator.itemgetter(1))
generate_combination(variables, {}, len(variables), 0)
for combination in all_combinations:
print combination
ans=solve(combination, input, rank)
ans=[]
answers.extend(ans)
# for answer in answers:
# print answer
def nothing():
pass
if __name__ == '__main__':
# print "Enter your symbols for :\n"
# And=raw_input("And = ")
# Or=raw_input("Or = ")
# Not=raw_input("Not = ")
# input_str=raw_input("Enter the expression :")
And,Or,Not,input_str='&','|','!','a&b|c!d|a'
input_str=input_str.replace(" ","")
mapping={And:"&", Or:"|", Not:"!"}
order={"&":3, "|":2, "!":1}
variables=[]
processed_str=""
for i in input_str:
if i in mapping:
processed_str+=mapping[i]
else:
processed_str+=i
variables.append(i)
variables=list(set(variables))
print "Reconstituted string : ",processed_str
print "Variables : ",variables,"\n"
main(processed_str,variables,order)
Current Output:
Reconstituted string : a&b|c!d|a
Variables : ['a', 'c', 'b', 'd']
{'a': 1, 'c': 1, 'b': 1, 'd': 1}
[{'a': 1, 'c': 1, 'b': 1, 'd': 1}]
{'a': 1, 'c': 1, 'b': 1, 'd': 0}
[{'a': 1, 'c': 1, 'b': 1, 'd': 0}, {'a': 1, 'c': 1, 'b': 1, 'd': 0}]
{'a': 1, 'c': 1, 'b': 0, 'd': 1}
[{'a': 1, 'c': 1, 'b': 0, 'd': 1}, {'a': 1, 'c': 1, 'b': 0, 'd': 1}, {'a': 1, 'c': 1, 'b': 0, 'd': 1}]
{'a': 1, 'c': 1, 'b': 0, 'd': 0}
[{'a': 1, 'c': 1, 'b': 0, 'd': 0}, {'a': 1, 'c': 1, 'b': 0, 'd': 0}, {'a': 1, 'c': 1, 'b': 0, 'd': 0}, {'a': 1, 'c': 1, 'b': 0, 'd': 0}]
{'a': 1, 'c': 0, 'b': 1, 'd': 1}
[{'a': 1, 'c': 0, 'b': 1, 'd': 1}, {'a': 1, 'c': 0, 'b': 1, 'd': 1}, {'a': 1, 'c': 0, 'b': 1, 'd': 1}, {'a': 1, 'c': 0, 'b': 1, 'd': 1}, {'a': 1, 'c': 0, 'b': 1, 'd': 1}]
{'a': 1, 'c': 0, 'b': 1, 'd': 0}
[{'a': 1, 'c': 0, 'b': 1, 'd': 0}, {'a': 1, 'c': 0, 'b': 1, 'd': 0}, {'a': 1, 'c': 0, 'b': 1, 'd': 0}, {'a': 1, 'c': 0, 'b': 1, 'd': 0}, {'a': 1, 'c': 0, 'b': 1, 'd': 0}, {'a': 1, 'c': 0, 'b': 1, 'd': 0}]
{'a': 1, 'c': 0, 'b': 0, 'd': 1}
[{'a': 1, 'c': 0, 'b': 0, 'd': 1}, {'a': 1, 'c': 0, 'b': 0, 'd': 1}, {'a': 1, 'c': 0, 'b': 0, 'd': 1}, {'a': 1, 'c': 0, 'b': 0, 'd': 1}, {'a': 1, 'c': 0, 'b': 0, 'd': 1}, {'a': 1, 'c': 0, 'b': 0, 'd': 1}, {'a': 1, 'c': 0, 'b': 0, 'd': 1}]
{'a': 1, 'c': 0, 'b': 0, 'd': 0}
[{'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}, {'a': 1, 'c': 0, 'b': 0, 'd': 0}]
{'a': 0, 'c': 1, 'b': 1, 'd': 1}
[{'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}, {'a': 0, 'c': 1, 'b': 1, 'd': 1}]
{'a': 0, 'c': 1, 'b': 1, 'd': 0}
[{'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}, {'a': 0, 'c': 1, 'b': 1, 'd': 0}]
{'a': 0, 'c': 1, 'b': 0, 'd': 1}
[{'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}, {'a': 0, 'c': 1, 'b': 0, 'd': 1}]
{'a': 0, 'c': 1, 'b': 0, 'd': 0}
[{'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}, {'a': 0, 'c': 1, 'b': 0, 'd': 0}]
{'a': 0, 'c': 0, 'b': 1, 'd': 1}
[{'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}, {'a': 0, 'c': 0, 'b': 1, 'd': 1}]
{'a': 0, 'c': 0, 'b': 1, 'd': 0}
[{'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}, {'a': 0, 'c': 0, 'b': 1, 'd': 0}]
{'a': 0, 'c': 0, 'b': 0, 'd': 1}
[{'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}, {'a': 0, 'c': 0, 'b': 0, 'd': 1}]
{'a': 0, 'c': 0, 'b': 0, 'd': 0}
[{'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}, {'a': 0, 'c': 0, 'b': 0, 'd': 0}]
I think the problem is that all the items in your all_combinations list are pointed to the same comb_dict, you are overwriting each element in every call of generate_combination.
Try to make a copy of the comb_dict:
all_combinations.append(comb_dict.copy())