Using group_by() and nest() I can create list columns in R that are very useful for fitting models to multiple datasets.
How can I achieve the same outcome in polars in Python, such that each element of the data column is a small dataframe?
library(tidyverse)df <- structure(list(dataset_id = c(1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L), day = c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L), recipe = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), levels = c("A", "B"), class = "factor"), cum_trials = c(1000, 2000, 1000, 2000, 1000, 2000, 1000, 2000), cum_events = c(644L, 1287L, 643L, 1262L, 645L, 1312L, 655L, 1301L), cum_rate = c(0.644, 0.643, 0.643, 0.619, 0.645, 0.667, 0.655, 0.646)), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, -8L))df_list <- df |> group_by(dataset_id, day) |> nest()df_list
df_list$data[[1]]