[英]Is there any easy way to fit probability mass function to a given dataset?
Assume we have a list of numbers (samples)假设我们有一个数字列表(样本)
data = [0,0,1,2,3]数据 = [0,0,1,2,3]
I would like to fit a probability mass function for this dataset, in such a way that if I do something like我想为这个数据集拟合概率质量 function,如果我做类似的事情
pmf.fit(data) pmf.fit(数据)
and by executing something like并通过执行类似
pmf.eval(0) pmf.eval(0)
I get我明白了
0.2 0.2
as return作为回报
and和
by executing通过执行
pmf.eval(-1) pmf.eval(-1)
I get我明白了
0 0
as return.作为回报。
Note that I am working with a discrete random variable here, so I am not fitting a pdf...请注意,我在这里使用的是离散随机变量,所以我不适合 pdf...
I finally figured out myself我终于想通了自己
random_array = [0,0,1,2,3] random_array = [0,0,1,2,3]
unique, counts = np.unique(random_array, return_counts=True)独特的,计数 = np.unique(random_array,return_counts = True)
random_variable = sp.stats.rv_discrete(a = 0, b = np.inf, values = (unique, counts/np.sum(counts))) random_variable = sp.stats.rv_discrete(a = 0, b = np.inf, values = (unique, counts/np.sum(counts)))
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.