make_data.Rmd

---
title: "Making the dictionary"
csl: the-american-naturalist.csl
output:
  html_document:
    theme: cerulean
    toc: yes
  pdf_document:
    toc: yes
<!-- bibliography: references.bib -->
editor_options: 
  chunk_output_type: console
---

<!--
IMAGES:
Insert them with: ![alt text](image.png)
You can also resize them if needed: convert image.png -resize 50% image.png
If you want to center the image, go through HTML code:
<div style="text-align:center"><img src ="image.png"/></div>

REFERENCES:
For references: Put all the bibTeX references in the file "references.bib"
in the current folder and cite the references as @key or [@key] in the text.
Uncomment the bibliography field in the above header and put a "References"
title wherever you want to display the reference list.
-->

<style type="text/css">
.main-container {
  max-width: 1370px;
  margin-left: auto;
  margin-right: auto;
}
</style>

```{r general_options, include = FALSE}
knitr::knit_hooks$set(
  margin = function(before, options, envir) {
    if (before) par(mgp = c(1.5, .5, 0), bty = "n", plt = c(.105, .97, .13, .97))
    else NULL
  },
  prompt = function(before, options, envir) {
    options(prompt = if (options$engine %in% c("sh", "bash")) "$ " else "> ")
  })

knitr::opts_chunk$set(margin = TRUE, prompt = TRUE, comment = "",
                      collapse = TRUE, cache = FALSE, autodep = TRUE,
                      dev.args = list(pointsize = 11), fig.height = 3.5,
                      fig.width = 4.24725, fig.retina = 2, fig.align = "center")

options(width = 137)
```

```{r}
library(dplyr)
```

```{r}
if (!dir.exists("data")) dir.create("data")
```

```{r}
pacs <- "../pacs/data/pacs.csv" %>% 
  readr::read_csv(col_types = paste(c("icfnD", rep("c", 5), rep("D", 4), rep("f", 3)), collapse = "")) %>% 
  filter(province == "Vientiane [prefecture]") %>% 
  select(district, village) %>% 
  unique() %>% 
  arrange(village, district) %>% 
  write.csv("data/pacs.csv", FALSE, row.names = FALSE)
```

```{r}
census <- "../census/data/census.csv" %>% 
  readr::read_csv(col_types = paste(c("ddccciiiiilllc", rep("d", 246)), collapse = "")) %>% 
  select(District_Name, Village_Name) %>%
  unique() %>% 
  arrange(Village_Name, District_Name) %>% 
  write.csv("data/census.csv", FALSE, row.names = FALSE)
```

```{r}
setdiff(tolower(census$Village_Name), pacs$village) %>% 
  sort()
```

```{r}
sort(unique(tolower(pacs$village)))
```

```{r}
sort(unique(tolower(census$Village_Name)))
```

```{r}
dictionary <- readxl::read_excel("../../cleaned_data/Dictionnaire correspondance Census SIG liaison.xlsx")
```