Below I demonstrate a workflow for fitting the same model to many datasets in R by nesting datasets by test_id, and then fitting the same model to each dataset, and extracting a statistic from each model.

My goal is to create the equivalent workflow in Python, using polars, but I will use pandas if necessary.

Demonstration in R

library(tidyverse)SIMS <- 3TRIALS <- 1e3PROB_A <- .65PROB_B <- .67df <- bind_rows(    tibble(        recipe = "A",         trials = TRIALS,        events = rbinom(n=SIMS, size=trials, prob=PROB_A),        rate = events/trials) |>         mutate(test_id = 1:n()),    tibble(        recipe = "B",         trials = TRIALS,        events = rbinom(n=SIMS, size=trials, prob=PROB_B),        rate = events/trials) |>         mutate(test_id = 1:n()))df

df_nest <- df |>     group_by(test_id) |>     nest()df_nest

Define two functions to map over my nested data:

glm_foo <- function(.data){    glm(formula = rate ~ recipe,         data = .data,         weights = trials,         family = binomial) }glm_foo(df_nest$data[[1]])fit_and_extract <- function(.data){    m <- glm(formula = rate ~ recipe,         data = .data,         weights = trials,         family = binomial)     m2$coefficients['recipeB']}fit_and_extract(df_nest$data[[1]])

df_nest |>     mutate(        model = map(.x = data, .f = glm_foo),        trt_b = map_dbl(.x = data, .f = fit_and_extract))

#Python SectionI can create the same nested data structure in polars, but I am unsure of how to fit the model to each nested dataset within the list column called data.

import polars as plfrom polars import colimport numpy as npSIMS = 3TRIALS = int(1e3)PROB_A = .65PROB_B = .67df_a = pl.DataFrame({'recipe': "A", 'trials': TRIALS,'events': np.random.binomial(n=TRIALS, p=PROB_A, size=SIMS),'test_id': np.arange(SIMS)})df_b = pl.DataFrame({'recipe': "B", 'trials': TRIALS,'events': np.random.binomial(n=TRIALS, p=PROB_B, size=SIMS),'test_id': np.arange(SIMS)})df = (pl.concat([df_a, df_b], rechunk=True)    .with_columns(        fails = col('trials') - col('events')        ))df

df_agg = df.group_by('test_id').agg(data = pl.struct('events', 'fails', 'recipe'))df_agg.sort('test_id')

At this point my mental model of pandas starts to crumble. There are so many mapping options and I'm not really sure how to trouble shoot at this stage.

df_agg.with_columns(    (        pl.struct(["data"]).map_batches(            lambda x: smf.glm('events + fails ~ recipe', family=sm.families.Binomial(), data=x.struct.field('data').to_pandas()).fit()        )    ).alias("model"))

ComputeError: PatsyError: Error evaluating factor: TypeError: cannot use __getitem__ on Series of dtype List(Struct({'events': Int64, 'fails': Int64, 'recipe': String})) with argument 'recipe' of type 'str'events + fails ~ recipe