code debugging

.Rhistory

@@ -1,50 +1,3 @@
-year_from <- ls_index[1]
-year_to <- ls_index[2]
-}
-# Convert the input to a data.frame for later merging
-df_input <- data_input %>% as.data.frame()
-names(df_input) <- ls_index[1]
-data_output <-
-select(region_table, !!ls_index) %>%
-distinct() %>%
-left_join(df_input, .) %>%
-# using left_join to keep the order of the input data
-pull(!!year_to)
-# Because '2pinyin' can not be used as a variable name
-if (topinyin) {
-if (is.character(data_output)) {
-data_output <-
-py(
-char = data_output,
-dic = pydic(convert_to = "toneless", dic = "pinyin2")
-)
-}
-}
-return(data_output)
-}
-# original geocodes. It's 2019 version
-corruption$prefecture_id
-knitr::opts_chunk$set(message = FALSE, warning = FALSE)
-library(regioncode)
-data("corruption")
-# original geocodes. It's 2019 version
-corruption$prefecture_id
-corruption <- sample_n(na.exclude(corruption), 10)
-corruption <- dplyr::sample_n(na.exclude(corruption), 10)
-View(corruption)
-set.seed(313)
-corruption <- dplyr::sample_n(na.exclude(corruption), 10)
-View(corruption)
-set.seed(313)
-corruption <- dplyr::sample_n(na.exclude(corruption), 10) %>%
-select(province:countyid)
-library(dplry)
-library(dplyr)
-set.seed(313)
-corruption <- dplyr::sample_n(na.exclude(corruption), 10) %>%
-select(province:countyid)
-set.seed(313)
-corruption <- dplyr::sample_n(na.exclude(corruption), 10) %>%
 select(province:county_id)
 View(corruption)
 save(corruption, "../data/corruption.rda")
@@ -510,3 +463,50 @@ View(region_table)
 names(region_data)
 names(region_table)
 load("D:/Seafile/WW_research/01_Research/R_package/regioncode/R/sysdata.rda")
+library(regioncode)
+load("D:/Seafile/WW_research/01_Research/R_package/regioncode/R/sysdata.rda")
+names(region_data)
+save(corruption, region_data, file = here::here("R", "sysdata.rda"))
+load("D:/Seafile/WW_research/01_Research/R_package/regioncode/R/sysdata.rda")
+knitr::opts_chunk$set(message = FALSE, warning = FALSE)
+if(!require(regioncode)) install.packages("regioncode")
+library(regioncode)
+data("corruption")
+# Original 2019 version
+corruption$prefecture_id
+# 1999 version
+regioncode(data_input = corruption$prefecture_id,
+convert_to = "code", # default set
+year_from = 2019,
+year_to = 1989)
+# The original name
+corruption$prefecture
+# Codes to name
+regioncode(data_input = corruption$prefecture_id,
+convert_to = "name",
+year_from = 2019,
+year_to = 1989)
+# Name to codes of the same year
+regioncode(data_input = corruption$prefecture,
+convert_to = "code",
+year_from = 2019,
+year_to = 2019)
+# Name to name of a different year
+regioncode(data_input = corruption$prefecture,
+convert_to = "name",
+year_from = 2019,
+year_to = 1989)
+tibble(
+preference = corruption$prefecture,
+rank = regioncode(data_input = corruption$prefecture,
+year_from = 2011,
+year_to = 1989,
+convert_to="rank")
+)
+tidyr::tibble(
+preference = corruption$prefecture,
+rank = regioncode(data_input = corruption$prefecture,
+year_from = 2011,
+year_to = 1989,
+convert_to="rank")
+)

.Rproj.user/shared/notebooks/paths

@@ -1,3 +1,4 @@
+D:/Seafile/WW_research/01_Research/R_package/regioncode/DESCRIPTION="F2A6D482"
 D:/Seafile/WW_research/01_Research/R_package/regioncode/R/corruption.R="A63D693B"
 D:/Seafile/WW_research/01_Research/R_package/regioncode/R/globals.R="8687F590"
 D:/Seafile/WW_research/01_Research/R_package/regioncode/R/regioncode.R="4D95B977"

vignettes/regioncode-vignette.Rmd

@@ -23,9 +23,10 @@ editor_options:
 knitr::opts_chunk$set(message = FALSE, warning = FALSE)
 
 if(!require(regioncode)) install.packages("regioncode")
+library(tidyverse)
 ```
 
-Inspired by Vincent Arel-Bundock's amazing [`countrycode`](https://joss.theoj.org/papers/10.21105/joss.00848) package, we created `regioncode`, a package to achieve similar functions but specifically within China.
+Inspired by Vincent Arel-Bundock's [`countrycode`](https://joss.theoj.org/papers/10.21105/joss.00848) package, we created `regioncode`, a package to achieve similar functions but specifically within China.
 `regioncode` aims to enable seamlessly converting regions' formal names, common-used names, and administrative division codes between each other in modern China (1986--2019).
 
 ## Why `regioncode`?
@@ -47,15 +48,19 @@ To install:
 
 # Basic Usage
 
-We uses a randomly drawn sample of Yuhua Wang's [`China’s Corruption Investigations Dataset`](https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/9QZRAD) to illustrate how the package works.
-In the data, the division codes were recorded with the 2019 version, and we added prefectural abbreviations for the sake of illustration.
+We uses a randomly sample from the [`China's Corruption Investigations Dataset`](https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/9QZRAD) to illustrate how the functions work.
 
-In `regioncode` package, we named administrative division codes as `code`, regions' formal names as `name`, and their commonly used abbreviation as `sname`.
+
+In `regioncode` package, we named administrative division codes as `code`, regions' formal names as `name`, and their commonly used abbreviation ("short name") as `sname`.
 The current version enables mutual conversion between any pair of them.
-To do so, users just need to pass a character vector of names or a numeric vector of geocodes into the function.
-In the current version, the function can produce three types of output at both the prefectural and provincial levels: codes (`code`), names (`name`) and area (`area`, such as 华北, 东北, 华南, etc.).
-One just needs to specify which type of the output they want in the argument `convert_to` and corresponding years of the input and output.
-For example, the following codes convert the 2019 geocodes in the `corruption` data to their 1989 version:
+To do so, users just need to pass a character vector of names or a numeric vector of geocodes into the function and specify which type of the output they want in the argument `convert_to` to gain the type of output of interest.
+In the current version,three types of output are available: 
+
+1. Geocodes (`code`)
+1. Names of the given cities/provinces (`name`)
+1. Area the given cities/provinces belong (`area`, such as 华北, 东北, 华南, etc.).
+
+In the following example, the 2019 geocodes in the toy data to their 1989 version:
 
 ```{r code2code}
 library(regioncode)
@@ -65,11 +70,23 @@ data("corruption")
 # Original 2019 version
 corruption$prefecture_id
 
-# 1999 version
-regioncode(data_input = corruption$prefecture_id, 
+# 1989 version
+temp <- regioncode(data_input = corruption$prefecture_id, 
            convert_to = "code", # default set
            year_from = 2019,
            year_to = 1989)
+
+# tibble(
+#   code2019 = corruption$prefecture_id,
+#   code1989 = regioncode(data_input = corruption$prefecture_id, 
+#            convert_to = "code", # default set
+#            year_from = 2019,
+#            year_to = 1989),
+#   name1989 = regioncode(data_input = corruption$prefecture_id, 
+#            convert_to = "name", # default set
+#            year_from = 2019,
+#            year_to = 1989)
+# )
 ```
 
 Note that if a region was initially geocoded in e.g., 1989 and included in a new region, in 2019, the new region geocode will be used hereafter.