first draft of a tidy tuesday

Author: lsinks

posts/2023-05-09-tidytuesday-childcare/childcare.qmd

@@ -0,0 +1,86 @@
+---
+title: "TidyTuesday Week 19: Portal Project"
+description: "TidyTuesday: Rodents of Portal Arizona"
+twitter-card:
+  image: "thumbnail.png"
+author:
+  - name: Louise E. Sinks
+    url: https://lsinks.github.io/
+date: 05-09-2023
+categories: [R, TidyTuesday, R-code, Code-Along, Data-Viz, data validation, exploratory data analysis] # self-defined categories
+citation:
+  url: https://lsinks.github.io/posts/2023-05-09-tidytuesday-childcare/childcare 
+image: "thumbnail.png"
+draft: true # setting this to `true` will prevent your post from appearing on your listing page until you're ready!
+---
+
+Today's TidyTuesday is about childcare prices.
+
+```{r}
+
+library(tidyverse)
+library(gt)
+library(skimr)
+```
+
+Loading the data in the usual way.
+
+```{r}
+tuesdata <- tidytuesdayR::tt_load(2023, week = 19)
+
+childcare_costs <- tuesdata$childcare_costs
+counties <- tuesdata$counties
+```
+
+There are two data files. The dataframe counties has information about county and state, while childcare_costs has a variety of economic data for each county over several years (2008 - 2018). The two dataframes can be joined on county_fips_code, which is a unique identifier for every county. If you look at the TidyTuesday notes, they actually started out in a single file and were split up.
+
+```{r}
+labor_rates <- childcare_costs %>%
+  select(study_year, county_fips_code, flfpr_20to64, flfpr_20to64_under6, mc_infant, mfcc_infant )
+```
+
+```{r}
+labor_rates_2 <- labor_rates %>%
+  left_join(counties)
+```
+
+```{r}
+#| column: page
+
+my_skim <- skim_with(numeric = sfl(p25 = NULL, p50 = NULL, p75 = NULL)) 
+
+my_skim(labor_rates_2)
+```
+
+Employment gap between all women and women with young children
+
+```{r}
+labor_rates_2 <- labor_rates_2 %>%
+  mutate(gap = flfpr_20to64 - flfpr_20to64_under6)
+```
+
+average cost of infant care
+
+```{r}
+labor_rates_2 <- labor_rates_2 %>%
+  mutate(cost = (mc_infant + mfcc_infant)/2)
+```
+
+plot gap vs. cost for 2018
+
+```{r}
+labor_rates_2 %>%
+ # filter(study_year == 2018) %>%
+  ggplot(aes(cost, gap, color = study_year)) +
+  geom_point() + geom_smooth()
+```
+
+correlation
+
+```{r}
+
+labor_rates_2_2018 <- labor_rates_2 %>%
+ filter(study_year == 2018)
+cor(labor_rates_2_2018$gap, labor_rates_2_2018$cost, use = "pairwise.complete.obs")
+
+```