Created
July 20, 2019 20:36
-
-
Save GuiMarthe/1228809f84be61bbb99c0e0728a640a4 to your computer and use it in GitHub Desktop.
A simple procedure for sampling a distribution to look like another. A method through binning and another by kde estimation. The binning idea came from this stats exchange question and the kde method came from other studies of mine.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(tidyverse) | |
library(broom) | |
df <- | |
tibble( | |
label = factor(c(rep("group1", 8E4), rep("group2", 1E4))), | |
var = c(rnorm(n = 8E4, mean =2, sd= 5), c( rnorm(n = 5E3,mean =-2, sd= 0.5), rnorm(n=5E3, mean = 1, sd = 0.5))) | |
) | |
df %>% | |
ggplot(aes(var)) + | |
geom_histogram(aes(fill = label), bins=100, position = 'identity', alpha=0.8) | |
# densities by binning | |
df <- | |
df %>% | |
mutate(bins = cut(var, breaks = 100)) | |
df %>% | |
group_by(label, bins) %>% | |
summarise(total = n()) %>% | |
mutate(prop = total/sum(total)) %>% | |
select(-total) %>% | |
spread(label, prop, fill = 0) -> densities | |
df %>% | |
filter(label == 'group1') %>% | |
left_join(densities, by = 'bins') %>% | |
mutate(weight = group2/group1) %>% | |
sample_n(20000, replace = T, weight = weight) %>% | |
mutate(label = 'group1 (sampled)') %>% | |
bind_rows(df) %>% | |
ggplot(aes(var)) + | |
geom_histogram(aes(fill = label), bins=100, position = 'identity', alpha=0.8) | |
# density by kde | |
kde_function_group1 <- df %>% filter(label == 'group1') %>% pull(var) %>% density(.) %>% approxfun(.) | |
kde_function_group2 <- df %>% filter(label == 'group2') %>% pull(var) %>% density(.) %>% approxfun(.) | |
df %>% | |
filter(label == 'group1') %>% | |
mutate(g2d = kde_function_group2(var), g1d = kde_function_group1(var), | |
weight = coalesce(g2d/g1d, 0) #sample importance | |
) %>% | |
sample_n(20000, replace = T, weight = weight) %>% | |
mutate(label = 'group1 (sampled)') %>% | |
bind_rows(df) %>% | |
ggplot(aes(var)) + | |
geom_histogram(aes(fill = label), bins=100, position = 'identity', alpha=0.8) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment