Bring It All Together (Advanced Data Wrangling)

# Load Packages ----------------------------------------------------------

library(tidyverse)
library(janitor)

# Import Data ------------------------------------------------------------

survey_data_raw <-
  read_tsv("data-raw/2020-combined-survey-final.tsv") |>
  clean_names()

coding_languages <-
  survey_data_raw |>
  mutate(id = row_number()) |>
  select(id, qcoding_languages) |>
  separate_longer_delim(
    cols = qcoding_languages,
    delim = ", "
  ) |>
  filter(qcoding_languages != "R")

demographics <-
  survey_data_raw |>
  mutate(id = row_number()) |>
  select(id, qyear_born:qcountry)

# Export Data ------------------------------------------------------------

coding_languages |>
  write_rds("data/coding_languages.rds")

demographics |>
  write_rds("data/demographics.rds")

---
title: R Community Survey
format: html
execute: 
  echo: false
  warning: false
  message: false
---


```{r}
library(tidyverse)
```


```{r}
coding_languages <-
  read_rds("data/coding_languages.rds")

demographics <-
  read_rds("data/demographics.rds")
```

Here is a chart showing the most common languages other than R in the survey data.

```{r}
coding_languages |>
  count(qcoding_languages) |>
  slice_max(
    order_by = n,
    n = 10
  ) |>
  ggplot(
    aes(
      x = n,
      y = qcoding_languages
    )
  ) +
  geom_col()
```

Here is a chart showing the most common languages other than R in the survey data.

```{r}
coding_languages |>
  left_join(demographics, join_by(id)) |>
  group_by(qdegree) |>
  count(qcoding_languages) |>
  slice_max(
    order_by = n,
    n = 3
  ) |>
  ungroup() |>
  filter(
    qdegree %in%
      c(
        "Bachelor’s degree (e.g. BA, BS)",
        "Master’s degree (e.g. MA, MS, MEd)",
        "Doctorate (e.g. PhD, EdD)"
      )
  ) |>
  ggplot(
    aes(
      x = n,
      y = qcoding_languages
    )
  ) +
  geom_col() +
  facet_wrap(vars(qdegree), ncol = 1)
```