我有一个由title:substrings
构建的字典,其中前三个条目如下:
'1' : ['G', 'GA', 'GAA', 'GAAA', 'GAAAA', 'GAAAAA', 'GAAAAAG', 'GAAAAAGU', 'GAAAAAGUA', 'GAAAAAGUAU', 'GAAAAAGUAUG', 'GAAAAAGUAUGC', 'GAAAAAGUAUGCA', 'GAAAAAGUAUGCAA', 'GAAAAAGUAUGCAAG', 'GAAAAAGUAUGCAAGA', 'GAAAAAGUAUGCAAGAA', 'GAAAAAGUAUGCAAGAAC']
'2' : ['G', 'GA', 'GAG', 'GAGA', 'GAGAG', 'GAGAGA', 'GAGAGAG', 'GAGAGAGA', 'GAGAGAGAC', 'GAGAGAGACA', 'GAGAGAGACAU', 'GAGAGAGACAUA', 'GAGAGAGACAUAG', 'GAGAGAGACAUAGA', 'GAGAGAGACAUAGAG', 'GAGAGAGACAUAGAGG']
'3' : ['G', 'GU', 'GUC', 'GUCU', 'GUCUU', 'GUCUUU', 'GUCUUUG', 'GUCUUUGU', 'GUCUUUGU"', 'GUCUUUGU"G', 'GUCUUUGU"GU', 'GUCUUUGU"GUA', 'GUCUUUGU"GUAC', 'GUCUUUGU"GUACA', 'GUCUUUGU"GUACAU', 'GUCUUUGU"GUACAUC']
我找到了很多答案,关于如何将它们转换为列表并创建一个for循环来检查1中的项目是否在其他项目中,如果是这样,则删除它们,但我不认为这对我来说是可行的,因为这个字典是生成而不是我手写的。因此我不太明白我应该如何处理这个问题。
答案 0 :(得分:1)
您可以构建一个索引,其中每个值列出它所在的键。如果该列表大于1,则删除该值。
static public int Partition(int [] numbers, int left, int right)
{
int pivot = numbers[left];
while (true)
{
while (numbers[left] < pivot)
left++;
while (numbers[right] > pivot)
right--;
if (left < right)
{
int temp = numbers[right];
numbers[right] = numbers[left];
numbers[left] = temp;
}
else
{
return right;
}
}
}
static public void QuickSort_Recursive(int [] arr, int left, int right)
{
// For Recusrion
if(left < right)
{
int pivot = Partition(arr, left, right);
if(pivot > 1)
QuickSort_Recursive(arr, left, pivot - 1);
if(pivot + 1 < right)
QuickSort_Recursive(arr, pivot + 1, right);
}
}
答案 1 :(得分:0)
从列表中删除任意项会导致在需要扩展时性能不佳。通常最好从旧的列表中创建新列表,并省略要删除的项目。
此处,您要删除的项目是计数大于1的值
>>> mydict = {
... '1' : ['G', 'GA', 'GAA', 'GAAA', 'GAAAA', 'GAAAAA', 'GAAAAAG', 'GAAAAAGU', 'GAAAAAGUA', 'GAAAAAGUAU', 'GAAAAAGUAUG', 'GAAAAAGUAUGC', 'GAAAAAGUAUGCA', 'GAAAAAGUAUGCAA', 'GAAAAAGUAUGCAAG', 'GAAAAAGUAUGCAAGA', 'GAAAAAGUAUGCAAGAA', 'GAAAAAGUAUGCAAGAAC'],
... '2' : ['G', 'GA', 'GAG', 'GAGA', 'GAGAG', 'GAGAGA', 'GAGAGAG', 'GAGAGAGA', 'GAGAGAGAC', 'GAGAGAGACA', 'GAGAGAGACAU', 'GAGAGAGACAUA', 'GAGAGAGACAUAG', 'GAGAGAGACAUAGA', 'GAGAGAGACAUAGAG', 'GAGAGAGACAUAGAGG'],
... '3' : ['G', 'GU', 'GUC', 'GUCU', 'GUCUU', 'GUCUUU', 'GUCUUUG', 'GUCUUUGU', 'GUCUUUGU"', 'GUCUUUGU"G', 'GUCUUUGU"GU', 'GUCUUUGU"GUA', 'GUCUUUGU"GUAC', 'GUCUUUGU"GUACA', 'GUCUUUGU"GUACAU', 'GUCUUUGU"GUACAUC']
... }
>>> from collections import Counter
>>> from itertools import chain
>>> c = Counter(chain.from_iterable(mydict.values()))
>>> {k: [x for x in v if c[x] == 1] for k, v in mydict.items()}
{'1': ['GAA', 'GAAA', 'GAAAA', 'GAAAAA', 'GAAAAAG', 'GAAAAAGU', 'GAAAAAGUA', 'GAAAAAGUAU', 'GAAAAAGUAUG', 'GAAAAAGUAUGC', 'GAAAAAGUAUGCA', 'GAAAAAGUAUGCAA', 'GAAAAAGUAUGCAAG', 'GAAAAAGUAUGCAAGA', 'GAAAAAGUAUGCAAGAA', 'GAAAAAGUAUGCAAGAAC'],
'3': ['GU', 'GUC', 'GUCU', 'GUCUU', 'GUCUUU', 'GUCUUUG', 'GUCUUUGU', 'GUCUUUGU"', 'GUCUUUGU"G', 'GUCUUUGU"GU', 'GUCUUUGU"GUA', 'GUCUUUGU"GUAC', 'GUCUUUGU"GUACA', 'GUCUUUGU"GUACAU', 'GUCUUUGU"GUACAUC'],
'2': ['GAG', 'GAGA', 'GAGAG', 'GAGAGA', 'GAGAGAG', 'GAGAGAGA', 'GAGAGAGAC', 'GAGAGAGACA', 'GAGAGAGACAU', 'GAGAGAGACAUA', 'GAGAGAGACAUAG', 'GAGAGAGACAUAGA', 'GAGAGAGACAUAGAG', 'GAGAGAGACAUAGAGG']}