sacramento2022census.Rmd

---
title: "norcalmultiyeardata"
output: html_document
date: "2023-06-16"
---

##libraries
```{r}
library(tidyverse)
library(tidycensus)
library(sf)
library(ggplot2)
library(scales)
```

##load ACS variable key
```{r}
acs2018 <- load_variables(2018, "acs5", cache=TRUE)

acs2022 <-load_variables(2022, "acs1", cache = TRUE)
```

##define years, counties
```{r}
my_counties <- c("Sacramento", "Yolo", "Placer", "El Dorado", "Sutter", "Amador", "Yuba")
```

##census variables
```{r}
race_variables2021 <- c(
  white_alone = "B02001_002",
  black_alone = "B02001_003",
  na_alone = "B02001_004",
  asian_alone = "B02001_004",
  nhpi_alone = "B02001_006",
  other_alone = "B02001_007",
  two_or_more = "B02001_008")
```

## a loop
```{r}
multi_year <- map_dfr(years,
                      ~ get_acs(
                        geography = "county",
                        variables = race_variables2021,
                        state = "CA", 
                        county = my_counties,
                        year = .x,
                        survey = "acs1",
                        geometry = FALSE,
                      ),
                      .id = "year") %>% select (-moe) %>% arrange(variable, NAME) %>% print()
```


## exporting my tibble as a csv
```{r}
write.csv(multi_year, "2018_2021norcalracedata.csv")
```

i was going to try and do the brunt of the story work in R, however the vintage 2022 estimates aren't currently available on the census API. go figure. 

## pulling the stuff i need
```{r}
v2010 <- load_variables(2010, "acs1", cache = TRUE)
v2011 <- load_variables(2011, "acs5", cache = TRUE)
v2012 <- load_variables(2012, "acs5", cache = TRUE)
v2013 <- load_variables(2013, "acs5", cache = TRUE)
v2014 <- load_variables(2014, "acs5", cache = TRUE)
v2015 <- load_variables(2015, "acs5", cache = TRUE)
v2016 <- load_variables(2016, "acs5", cache = TRUE)
v2017 <- load_variables(2017, "acs5", cache = TRUE)
v2018 <- load_variables(2018, "acs5", cache = TRUE)
v2019 <- load_variables(2019, "acs5", cache = TRUE)
v2021 <- load_variables(2021, "acs5", cache = TRUE)

dcs <-load_variables(2020,"dhc", cache = TRUE)

years <- lst(2010,2011,2012,2013,2014,2015,2016,2017,2018,2019,2020,2021)

my_variables <- c(
  median_age = "B01002A_001",
  median_male_age = "B01002A_002",
  median_female_age = "B01002A_003"
)

my_variablesdcs <-c(
  median_age = "P13_001N",
  male_median_age = "P13_002N",
  female_median_age = "P13_003N"
)


medianage_ca <- map_dfr(years,
                      ~ get_acs(
                        geography = "state",
                        variables = my_variables,
                        state = "CA", 
                        year = .x,
                        survey = "acs5",
                        geometry = FALSE,
                      ),
                      .id = "year") %>% select (-moe) %>% arrange(variable, NAME) %>% print()
```

```{r}
write.csv(medianage_ca,"medianage_ca.csv")
```