The tidymodels team fielded a short survey to gather community feedback on development priorities and possible next steps. This report summarizes the survey results.
Let’s start by exploring the characteristics of the survey respondents.
library(tidyverse)
library(qualtRics)
library(glue)
survey_id <- "SV_ezYI0F3V9K5Tr3D"
survey_raw <- fetch_survey(survey_id, verbose = FALSE, force_request = TRUE)
survey_select <- survey_raw %>%
select(Q5_1:Q5_12, Q1002)
labels_df <- enframe(sjlabelled::get_label(survey_select)) %>%
transmute(qid = name,
priority = str_trim(value))
tidy_survey <- survey_select %>%
pivot_longer(Q5_1:Q5_12, names_to = "qid", values_to = "dollars") %>%
inner_join(labels_df) %>%
filter(priority != "Other")
survey_raw %>%
count(StartDate = as.Date(StartDate)) %>%
ggplot(aes(StartDate, n)) +
geom_col(alpha = 0.8) +
labs(x = NULL,
y = "Number of survey responses",
title = "Survey responses over time",
subtitle = glue("There are ", {nrow(survey_raw)}, " total responses"))
survey_raw %>%
mutate(Q1002 = fct_relabel(Q1002, str_wrap, width = 20)) %>%
count(Q1002) %>%
ggplot(aes(x = n, y = Q1002)) +
geom_col(alpha = 0.8) +
scale_x_continuous(expand = c(0,0)) +
labs(x = "Number of survey responses",
y = NULL,
title = "Familiarity with tidymodels",
subtitle = glue("Of the respondents, ",
{percent(mean(str_detect(survey_raw$Q1002, "a few times")))},
" say they have used tidymodels a few times"))
survey_raw %>%
filter(`Duration (in seconds)` < 5e4) %>%
mutate(Q1002 = fct_relabel(Q1002, str_wrap, width = 20)) %>%
ggplot(aes(Q1002, `Duration (in seconds)`, fill = Q1002)) +
geom_boxplot(show.legend = FALSE, alpha = 0.7) +
scale_y_log10() +
labs(x = NULL,
y = "Time to take the survey (seconds)",
title = "Survey length in seconds",
subtitle = glue(
"The median time to take the survey was ",
{round(median(survey_raw$`Duration (in seconds)`) / 60, 2)},
" minutes")
)
The main question on the survey asked:
If you had a hypothetical $100 to spend on tidymodels development, how would you allocate those resources right now?
The possible priorities were presented in a randomized order to respondents, except for the “Other” option at the bottom.
tidy_survey %>%
mutate(priority = str_wrap(priority, width = 20)) %>%
group_by(priority) %>%
summarise(dollars_mean = mean(dollars)) %>%
mutate(priority = fct_reorder(priority, dollars_mean)) %>%
ggplot(aes(dollars_mean, priority)) +
geom_col(alpha = 0.8) +
scale_x_continuous(labels = dollar_format(),
expand = c(0,0)) +
labs(x = "Mean hypothetical dollars allocated",
y = NULL,
title = "What are the average dollars allocated to each priority?",
subtitle = "Model stacking and model monitoring had the highest mean scores")
library(tidytext)
tidy_survey %>%
mutate(priority = str_wrap(priority, width = 20),
Q1002 = fct_relabel(Q1002, str_wrap, width = 50)) %>%
group_by(Q1002, priority) %>%
summarise(dollars_mean = mean(dollars)) %>%
ungroup %>%
mutate(priority = reorder_within(priority, dollars_mean, as.character(Q1002))) %>%
ggplot(aes(dollars_mean, priority, fill = Q1002)) +
geom_col(alpha = 0.8, show.legend = FALSE) +
facet_wrap(~Q1002, scales = "free_y") +
scale_x_continuous(labels = dollar_format(),
expand = c(0,0)) +
scale_y_reordered() +
labs(x = "Mean hypothetical dollars allocated",
y = NULL,
title = "What are the average dollars allocated to each priority?",
subtitle = "Model stacking and model monitoring had the highest mean scores for all groups")