From 502dc4578140904018d3e208e3286b7072288b84 Mon Sep 17 00:00:00 2001 From: JosuaKugler Date: Sat, 7 Aug 2021 02:00:09 +0200 Subject: [PATCH] refactor again because of check complaining --- .gitignore | 2 +- R/fetch.R | 2 +- R/parse.R | 6 +++--- {data => inst}/hitler_texts/german_words | 0 {data => inst}/hitler_texts/goebbels_sportpalast | 0 {data => inst}/hitler_texts/hitler_rede_1 | 0 {data => inst}/hitler_texts/hitler_rede_2 | 0 {data => inst}/hitler_texts/hitler_rede_3 | 0 {data => inst}/hitler_texts/hitler_rede_4 | 0 {data => inst}/hitler_texts/hitler_rede_5 | 0 {data => inst}/hitler_texts/hitler_rede_6 | 0 {data => inst}/hitler_texts/hitler_rede_7 | 0 {data => inst}/hitler_texts/hitler_words | 0 {data => inst}/hitler_texts/mein_kampf | 0 {data => inst}/hitler_texts/parse.py | 0 man/fetch_all.Rd | 2 +- man/read_all.Rd | 2 +- man/read_from_csv.Rd | 2 +- man/write_to_csv.Rd | 2 +- vignettes/funwithdata.Rmd | 6 +++--- vignettes/genderequality.Rmd | 2 +- vignettes/hitlercomparison.Rmd | 8 ++++---- 22 files changed, 17 insertions(+), 17 deletions(-) rename {data => inst}/hitler_texts/german_words (100%) rename {data => inst}/hitler_texts/goebbels_sportpalast (100%) rename {data => inst}/hitler_texts/hitler_rede_1 (100%) rename {data => inst}/hitler_texts/hitler_rede_2 (100%) rename {data => inst}/hitler_texts/hitler_rede_3 (100%) rename {data => inst}/hitler_texts/hitler_rede_4 (100%) rename {data => inst}/hitler_texts/hitler_rede_5 (100%) rename {data => inst}/hitler_texts/hitler_rede_6 (100%) rename {data => inst}/hitler_texts/hitler_rede_7 (100%) rename {data => inst}/hitler_texts/hitler_words (100%) rename {data => inst}/hitler_texts/mein_kampf (100%) rename {data => inst}/hitler_texts/parse.py (100%) diff --git a/.gitignore b/.gitignore index c77aadd..dace677 100644 --- a/.gitignore +++ b/.gitignore @@ -4,7 +4,7 @@ /inst/reports/ !/inst/reports/*.pdf !/inst/reports/*.tex -/data/csv/* +/inst/csv/* /parlament_49_53_texts/ .Rproj.user *.Rproj diff --git a/R/fetch.R b/R/fetch.R index 9482eb0..a6262f4 100644 --- a/R/fetch.R +++ b/R/fetch.R @@ -41,7 +41,7 @@ fetch_batch <- function(offset, download_dir) { #' if create is TRUE, the directory given in download_dir is created #' #' @export -fetch_all <- function(download_dir="data/records/", create=FALSE) { +fetch_all <- function(download_dir="inst/records/", create=FALSE) { # check if download_dir path is a directory path if (str_sub(download_dir, -1) != .Platform$file.sep) download_dir <- str_c(download_dir, .Platform$file.sep) diff --git a/R/parse.R b/R/parse.R index 498dae7..f656b2c 100644 --- a/R/parse.R +++ b/R/parse.R @@ -8,7 +8,7 @@ #' @param path character #' #' @export -read_all <- function(path="data/records/") { +read_all <- function(path="inst/records/") { cat("Reading all records from", path, "\n") available_protocols <- list.files(path) res <- pblapply(available_protocols, read_one, path=path) @@ -212,7 +212,7 @@ parse_speakerlist <- function(speakerliste_xml) { #' @param create set TRUE if the path does not exist yet and you want to create it #' #' @export -write_to_csv <- function(tables, path="data/csv/", create=F) { +write_to_csv <- function(tables, path="inst/csv/", create=F) { check_directory(path, create) write.table(tables$speaker, str_c(path, "speaker.csv")) write.table(tables$speeches, str_c(path, "speeches.csv")) @@ -229,7 +229,7 @@ write_to_csv <- function(tables, path="data/csv/", create=F) { #' reading the tables from a csv is way faster than reading and repairing the data every single time #' #' @export -read_from_csv <- function(path="data/csv/") { +read_from_csv <- function(path="inst/csv/") { list(speaker = read.table(str_c(path, "speaker.csv")) %>% tibble() %>% mutate(id = as.character(id)), diff --git a/data/hitler_texts/german_words b/inst/hitler_texts/german_words similarity index 100% rename from data/hitler_texts/german_words rename to inst/hitler_texts/german_words diff --git a/data/hitler_texts/goebbels_sportpalast b/inst/hitler_texts/goebbels_sportpalast similarity index 100% rename from data/hitler_texts/goebbels_sportpalast rename to inst/hitler_texts/goebbels_sportpalast diff --git a/data/hitler_texts/hitler_rede_1 b/inst/hitler_texts/hitler_rede_1 similarity index 100% rename from data/hitler_texts/hitler_rede_1 rename to inst/hitler_texts/hitler_rede_1 diff --git a/data/hitler_texts/hitler_rede_2 b/inst/hitler_texts/hitler_rede_2 similarity index 100% rename from data/hitler_texts/hitler_rede_2 rename to inst/hitler_texts/hitler_rede_2 diff --git a/data/hitler_texts/hitler_rede_3 b/inst/hitler_texts/hitler_rede_3 similarity index 100% rename from data/hitler_texts/hitler_rede_3 rename to inst/hitler_texts/hitler_rede_3 diff --git a/data/hitler_texts/hitler_rede_4 b/inst/hitler_texts/hitler_rede_4 similarity index 100% rename from data/hitler_texts/hitler_rede_4 rename to inst/hitler_texts/hitler_rede_4 diff --git a/data/hitler_texts/hitler_rede_5 b/inst/hitler_texts/hitler_rede_5 similarity index 100% rename from data/hitler_texts/hitler_rede_5 rename to inst/hitler_texts/hitler_rede_5 diff --git a/data/hitler_texts/hitler_rede_6 b/inst/hitler_texts/hitler_rede_6 similarity index 100% rename from data/hitler_texts/hitler_rede_6 rename to inst/hitler_texts/hitler_rede_6 diff --git a/data/hitler_texts/hitler_rede_7 b/inst/hitler_texts/hitler_rede_7 similarity index 100% rename from data/hitler_texts/hitler_rede_7 rename to inst/hitler_texts/hitler_rede_7 diff --git a/data/hitler_texts/hitler_words b/inst/hitler_texts/hitler_words similarity index 100% rename from data/hitler_texts/hitler_words rename to inst/hitler_texts/hitler_words diff --git a/data/hitler_texts/mein_kampf b/inst/hitler_texts/mein_kampf similarity index 100% rename from data/hitler_texts/mein_kampf rename to inst/hitler_texts/mein_kampf diff --git a/data/hitler_texts/parse.py b/inst/hitler_texts/parse.py similarity index 100% rename from data/hitler_texts/parse.py rename to inst/hitler_texts/parse.py diff --git a/man/fetch_all.Rd b/man/fetch_all.Rd index 0b52206..65261ff 100644 --- a/man/fetch_all.Rd +++ b/man/fetch_all.Rd @@ -4,7 +4,7 @@ \alias{fetch_all} \title{Download available records} \usage{ -fetch_all(download_dir = "data/records/", create = FALSE) +fetch_all(download_dir = "inst/records/", create = FALSE) } \arguments{ \item{download_dir}{character} diff --git a/man/read_all.Rd b/man/read_all.Rd index b29d11d..9e7874b 100644 --- a/man/read_all.Rd +++ b/man/read_all.Rd @@ -4,7 +4,7 @@ \alias{read_all} \title{Parse xml records} \usage{ -read_all(path = "data/records/") +read_all(path = "inst/records/") } \arguments{ \item{path}{character} diff --git a/man/read_from_csv.Rd b/man/read_from_csv.Rd index cd3fbc4..0ea2ef2 100644 --- a/man/read_from_csv.Rd +++ b/man/read_from_csv.Rd @@ -4,7 +4,7 @@ \alias{read_from_csv} \title{create a tibble from the csv file} \usage{ -read_from_csv(path = "data/csv/") +read_from_csv(path = "inst/csv/") } \arguments{ \item{path}{directory to read files from diff --git a/man/write_to_csv.Rd b/man/write_to_csv.Rd index 5cd1af7..0de80cd 100644 --- a/man/write_to_csv.Rd +++ b/man/write_to_csv.Rd @@ -4,7 +4,7 @@ \alias{write_to_csv} \title{Write the parsed and repaired results into separate csv files} \usage{ -write_to_csv(tables, path = "data/csv/", create = F) +write_to_csv(tables, path = "inst/csv/", create = F) } \arguments{ \item{tables}{list of tables to convert into a csv files.} diff --git a/vignettes/funwithdata.Rmd b/vignettes/funwithdata.Rmd index 5bf5fee..db0c74e 100644 --- a/vignettes/funwithdata.Rmd +++ b/vignettes/funwithdata.Rmd @@ -26,18 +26,18 @@ library(tidyr) First, you need to download all records of the current legislative period. ```r -fetch_all("../data/records/") # path to directory where records should be stored +fetch_all("../inst/records/") # path to directory where records should be stored ``` Second, those `.xml` files, need to be parsed into `R` `tibbles`. This is accomplished by: ```r -read_all("../data/records/") %>% repair() -> res +read_all("../inst/records/") %>% repair() -> res ``` We also used `repair` to fix a bunch of formatting issues in the records and unpacked the result into more descriptive variables. For development purposes, we load the tables from csv files. ```{r} -res <- read_from_csv('../data/csv/') +res <- read_from_csv('../inst/csv/') ``` and unpack our tibbles ```{r} diff --git a/vignettes/genderequality.Rmd b/vignettes/genderequality.Rmd index cbd97ce..44e919b 100644 --- a/vignettes/genderequality.Rmd +++ b/vignettes/genderequality.Rmd @@ -38,7 +38,7 @@ the result into more descriptive variables. For development purposes, we load the tables from csv files. ```{r} -res <- read_from_csv('../data/csv/') +res <- read_from_csv('../inst/csv/') ``` and unpack our tibbles ```{r} diff --git a/vignettes/hitlercomparison.Rmd b/vignettes/hitlercomparison.Rmd index 9dde553..3ac5846 100644 --- a/vignettes/hitlercomparison.Rmd +++ b/vignettes/hitlercomparison.Rmd @@ -25,11 +25,11 @@ library(ggplot2) First, you need to download all records of the current legislative period. ```r -fetch_all("../data/records/") # path to directory where records should be stored +fetch_all("../inst/records/") # path to directory where records should be stored ``` Second, those `.xml` files, need to be parsed into `R` `tibbles`. This is accomplished by: ```r -read_all("../data/records/") %>% repair() -> res +read_all("../inst/records/") %>% repair() -> res speeches <- res$speeches speaker <- res$speaker @@ -40,7 +40,7 @@ the result into more descriptive variables. For development purposes, we load the tables from csv files. ```{r} -tables <- read_from_csv('../data/csv/') +tables <- read_from_csv('../inst/csv/') comments <- tables$comments speeches <- tables$speeches @@ -50,7 +50,7 @@ talks <- tables$talks Further, we need to load a list of words that were used by Hitler but not by standard German texts. ```{r} -fil <- file('../data/hitler_texts/hitler_words') +fil <- file('../inst/hitler_texts/hitler_words') Worte <- readLines(fil) hitlerwords <- tibble(Worte) ```