What is the Python (numpy or scipy or Pandas) equivalent for R's adjboxStats function?

Question

I do use R to get the outliers for data set and I do use this snippet in R and it works like it's advertised to!

library("robustbase")
adjboxStats(c(11232.1, 234.2, 3445532344.3, 34302.3, 203.9, 232223.3, 3434.55), coef = 2.5, a = -4, b = 3, do.conf = TRUE, do.out = TRUE)

and I get this output:

$stats
[1]    203.900   1834.375  11232.100 133262.800 232223.300

$n
[1] 7

$conf
[1] -67254.84  89719.04

$fence
[1]   -6963.467 5097118.725

$out
[1] 3445532344

this is the versions of across language between R and python, the only issue with it it won't continue the execution and i have to kill the process every-time I run the script.

from rpy import *
r.library("robustbase")
import rpy2.robjects as robjects
r("adjboxStats")(r.c(11232.1, 234.2, 3445532344.3, 34302.3, 203.9, 232223.3, 3434.55), coef = 2.5, a = -4, b = 3, do_conf = True, do_out = True)

see my previous question was here for more info.

is there's away to get this working in pure python?

Thank you!

Answer 1

The hanging appears to happen when you import both rpy and rpy2 . If you just do:

from rpy import *
r.library("robustbase")
r("adjboxStats")(r.c(11232.1, 234.2, 3445532344.3, 34302.3, 203.9, 232223.3, 3434.55), coef = 2.5, a = -4, b = 3, do_conf = True, do_out = True)

This code should work.