1_censobrDataExtraction.Rmd

---
title: "Para Data Extraction Notebook"
output: html_notebook
---

```{r}
# Load necessary libraries
library(censobr)
library(arrow)
library(dplyr)
library(ggplot2)
```

## Download Census Tract data

```{r}
tract_basico <- read_tracts(
  year = 2010,
  dataset = "Basico",
  showProgress = TRUE,
  cache = FALSE
)
```

```{r}
tract_income <- read_tracts(
  year = 2010,
  dataset = "DomicilioRenda",
  showProgress = TRUE
)
```

```{r}
tract_pessoa <- read_tracts(
  year = 2010,
  dataset = "Pessoa",
  showProgress = TRUE
)
```

```{r}
# See data dictionary for population dataset
# data_dictionary(year = 2010, dataset = "tracts", showProgress = FALSE)
```

```{r}
# Select columns
tract_basico <- tract_basico |> select("code_tract", "V002") # Population
tract_income <- tract_income |> select("code_tract", "V003") # Income (Reais)
tract_idade <- tract_pessoa |>
  select(
    "code_tract", "pessoa01_V021", "pessoa01_V022", "pessoa01_V023",
    "pessoa01_V024", "pessoa01_V025", "pessoa01_V026", "pessoa01_V027",
    "pessoa01_V028", "pessoa01_V029", "pessoa01_V030", "pessoa01_V031",
    "pessoa01_V032", "pessoa01_V033", "pessoa01_V034", "pessoa01_V035",
    "pessoa01_V036", "pessoa01_V037", "pessoa01_V038", "pessoa01_V039",
    "pessoa01_V040", "pessoa01_V041", "pessoa01_V042", "pessoa01_V043",
    "pessoa01_V044", "pessoa01_V045", "pessoa01_V046", "pessoa01_V047",
    "pessoa01_V048", "pessoa01_V049", "pessoa01_V050", "pessoa01_V051",
    "pessoa01_V052"
  ) # Population by age
```


```{r}
# Merge all variables in one single data frame
tracts_df_temp <- left_join(tract_basico, tract_income)
tracts_df <- left_join(tracts_df_temp, tract_idade) |> collect()
```


```{r}
# Calculate income per capita (Reais)
tracts_df <- tracts_df |> mutate(income_pc = V003 / V002)
head(tracts_df)
```

```{r}
write.csv(tracts_df, "censobr_tract_income_para.csv", row.names = TRUE)
```