census-lesson.qmd

---
title: "census lesson"
format: html
---

## modified for check

```{r}
library(tidycensus)
library(dplyr)
library(tidyr)
library(ggplot2)
```


```{r}
census_api_key("0b213304aba6e6f5f5b4a5ed66e13ccc2478dfc4", install = TRUE)
```

# Decennial population by State

```{r}
pop_2020 <- get_decennial(
    geography = "state",
    variable = "P1_001N",
    year = 2020)
```

```{r}
pop_2010 <- get_decennial(
  geography = "state", 
  variables = "P001001",
  year = 2010)
```

```{r}
table_p2_2020 <- get_decennial(
    geography = "state",
    table = "P2",
    year = 2020)
```

```{r}
unique(table_p2_2020$variable)
```

```{r}
vars_pl_2020 <-  load_variables(2020, "pl")

## for 20210
vars_pl_2010 <-  load_variables(2010, "pl")
```

```{r}
vars_dhc_2020 <-  load_variables(2020, "dhc")

## Note you have to specify the file with sumfile =
household_2020 <- get_decennial(
    geography = "state",
    variable = "H10_001N",
    year = 2020,
    sumfile = "dhc")
```

```{r}
delta_hispanic <- get_decennial(
  geography = "county",
  state = "CA",
  county = c("Alameda", "Contra Costa", "Sacramento", "San Joaquin", "Solano", "Yolo"),
  variables = "P2_002N",
  year = 2020)
```

```{r}
## Vector with race variables codes
race_vars <- c(
  Hispanic = "P2_002N",
  White = "P2_005N",
  Black = "P2_006N",
  Native = "P2_007N",
  Asian = "P2_008N",
  HIPI = "P2_009N") ## Native Hawaiian and other Pacific Islander

delta_race <- get_decennial(
  geography = "county",
  state = "CA",
  county = c("Alameda", "Contra Costa", "Sacramento", "San Joaquin", "Solano", "Yolo"),
  variables = race_vars,
  summary_var = "P2_001N",
  year = 2020)
```

```{r}
delta_track_hw <- get_decennial(
  geography = "tract",
  variables = c(hispanic = "P2_002N",
                white = "P2_005N"),
  summary_var = "P2_001N",
  state = "CA",
  county = c("Alameda", "Contra Costa", "Sacramento", "San Joaquin", "Solano", "Yolo"),
  year = 2020)
```


```{r}
delta_track_clean <- delta_track_hw %>% 
    mutate(percent = 100 * (value / summary_value)) %>% 
    separate(NAME, into = c("tract", "county", "state"),
           sep = ", ")
```


```{r}
ggplot(delta_track_clean, 
       aes(x = percent, fill = county)) + 
  geom_density(alpha = 0.3)+
    facet_wrap(~variable)+
    theme_light()
```

```{r}
## 1-year survey
median_income_1yr <- get_acs(
  geography = "county",
  variables = "B19013_001",
  state = "CA",
  year = 2021,
  survey = "acs1")

## 5-year survey. Defaults to the 2017-2021 5-year ACS
median_income_5yr <- get_acs(
  geography = "county",
  variables = "B19013_001",
  state = "CA")
```

```{r}
## variables for 5-year 2017-2021 ACS
vars <- load_variables(2021, "acs5")
```