python - 无序列表中相对概率的累积和

Question

population_d = {'0,0,1,0,1,1,0,1,1,1,1,0,0,0,0,1': 6, 
'0,0,1,1,1,0,0,1,1,0,1,1,0,0,0,1': 3, 
'0,1,1,0,1,1,0,0,1,1,1,0,0,1,0,0': 5, 
'1,0,0,1,1,1,0,0,1,1,0,1,1,0,0,0': 1}

def ProbabilityList(population_d):
    fitness = population_d.values()
    total_fit = (sum(fitness))
    relative_fitness = [f/total_fit for f in fitness]
    probabilities = [sum(relative_fitness[:i+1]) for i in range(len(relative_fitness))]
    return (probabilities)

我试图计算这种数据结构的累积概率，但是，我需要保持值的顺序，以便将它们索引到另一个列表中相同位置的各个个体。

程序按顺序执行操作，为最后一个位置赋予更高的权重，在这种情况下，这将是最低的适应度。

有谁知道是否有一种方法可以以正确的方式(适应度值的新月顺序)执行累积和，而不改变它们在输出列表中的位置？

非常感谢!

Answer 1

population_d = {'0,0,1,0,1,1,0,1,1,1,1,0,0,0,0,1': 6, 
                '0,0,1,1,1,0,0,1,1,0,1,1,0,0,0,1': 3, 
                '0,1,1,0,1,1,0,0,1,1,1,0,0,1,0,0': 5, 
                '1,0,0,1,1,1,0,0,1,1,0,1,1,0,0,0': 1}

在您的字典中，您将健身(？)值与唯一标识符相关联。据推测，这些标识符来自程序和数据集中的其他地方。我没有尝试依赖字典的构建顺序来保留这种关系，而是维护了关联并构建了一个新字典，其值是对适应度从低到高排序后获得的累积和。

import operator
def ProbabilityList(population_d):
    fitness = population_d.values()
    total_fit = (sum(fitness))

    #create list of (individual, fitness) tuples
    items = population_d.items()

    #sort by fitness value
    items = sorted(items, key = operator.itemgetter(1))
    #some people prefer
    #items = sorted(items, key = lambda item: item[1])
    #print(items)

    #maintain association and calculate relative fitness
    relative_fitness = [(ind,fit/total_fit) for (ind,fit) in items]
    #print(relative_fitness)

    cumsum = 0
    probabilities = {}
    for ind, fit in relative_fitness:
        cumsum += fit
        probabilities[ind] = cumsum
    return (probabilities)

d = ProbabilityList(population_d)
for k, v in d.items():
    print('key:{}, fitness:{}, cumsum:{}'.format(k, population_d[k], v))

>>>
key:1,0,0,1,1,1,0,0,1,1,0,1,1,0,0,0, fitness:1, cumsum:0.06666666666666667
key:0,0,1,1,1,0,0,1,1,0,1,1,0,0,0,1, fitness:3, cumsum:0.26666666666666666
key:0,1,1,0,1,1,0,0,1,1,1,0,0,1,0,0, fitness:5, cumsum:0.6
key:0,0,1,0,1,1,0,1,1,1,1,0,0,0,0,1, fitness:6, cumsum:1.0
>>>

<小时/>

希望通过字典，您能够将累积总和与代码其他部分中的原始个体联系起来。

<小时/>

我发现您一直在询问与此数据集和项目相关的其他问题。您可能想投入一些时间学习Pandas或者甚至考虑将数据保存在数据库中，而不是分散在整个项目中的单个容器中。