Python in R

Define correct Python (change this on your computer):

library(reticulate)
use_python("/home/familie_kimeswenger/venv/python_3_12/bin/python3", required = TRUE)
py_config()

## python:         /home/familie_kimeswenger/venv/python_3_12/bin/python3
## libpython:      /usr/lib/python3.12/config-3.12-x86_64-linux-gnu/libpython3.12.so
## pythonhome:     /home/familie_kimeswenger/venv/python_3_12:/home/familie_kimeswenger/venv/python_3_12
## version:        3.12.3 (main, Mar  3 2026, 12:15:18) [GCC 13.3.0]
## numpy:          /home/familie_kimeswenger/venv/python_3_12/lib/python3.12/site-packages/numpy
## numpy_version:  1.26.4
## 
## NOTE: Python version was forced by use_python() function

Load packages in R:

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   4.0.0     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.2.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Load packages in Python

import pandas as pd

Import data in e.g. Python

py_data_toy = pd.read_csv("toy.csv")
py_data_toy["austrian"] = py_data_toy["austrian"].astype(bool)
py_data_toy["marital_status"] = pd.Categorical(py_data_toy["marital_status"], categories=["single", "divorced", "married"])
py_data_toy["age_cat"] = pd.Categorical(py_data_toy["age_cat"], categories = ["child", "adolescent", "adult"], ordered = True)
py_data_toy.head()

##     name  austrian marital_status  ...  temperature test_score  height
## 0  Franz     False       divorced  ...         37.0        NaN   180.4
## 1   Sepp     False         single  ...         38.5       80.0   160.5
## 2  Maria      True         single  ...         36.0        5.0   158.9
## 3  Georg      True         single  ...         35.4       30.0   130.2
## 4   Karl     False        married  ...         39.0        1.0   174.3
## 
## [5 rows x 8 columns]

Do something in Python …

We can use py_data_toy in R chunks too (converted as data.frame):

r_data_toy <- py$py_data_toy
r_data_toy |> 
  head()

##     name austrian marital_status year_birth    age_cat temperature test_score
## 1  Franz    FALSE       divorced       1990      adult        37.0        NaN
## 2   Sepp    FALSE         single       2009 adolescent        38.5         80
## 3  Maria     TRUE         single       2005      adult        36.0          5
## 4  Georg     TRUE         single       2019      child        35.4         30
## 5   Karl    FALSE        married       1930      adult        39.0          1
## 6 Ulrike     TRUE        married       1980      adult        38.0          9
##   height
## 1  180.4
## 2  160.5
## 3  158.9
## 4  130.2
## 5  174.3
## 6  172.1

And next we can use ggplot:

r_data_toy |> # data
  ggplot(aes(y = year_birth)) + # aesthetics (define what is on y axis) is used for all geom objects
  geom_boxplot() # define geom object (plot type here boxplot)

## Warning: Removed 1 row containing non-finite outside the scale range
## (`stat_boxplot()`).

Do something in R:

r_summary <- r_data_toy |> 
  group_by(age_cat) |> 
  summarise(
    mean_height = mean(height),
    mean_temperature = mean(temperature),
    .groups = "drop" # not necessary here
  )

r_summary

## # A tibble: 4 × 3
##   age_cat    mean_height mean_temperature
##   <ord>            <dbl>            <dbl>
## 1 child             130.             35.4
## 2 adolescent        160.             38.5
## 3 adult             NaN              37.4
## 4 <NA>              NaN              39.5

Use it in Python:

py_summary = r.r_summary
py_summary

##       age_cat  mean_height  mean_temperature
## 0       child        130.2         35.400000
## 1  adolescent        160.5         38.500000
## 2       adult          NaN         37.370588
## 3         NaN          NaN         39.500000