create genderequality, add documentation read_from_csv

R/analyze.R

@@ -12,6 +12,8 @@ join_speaker <- function(tb, res, fraction_only = F) {
     else joined
 }
 
+#'Assignment of the official colors to the parties
+#'
 #' @export
 party_colors <- c(
   AfD="#1A9FDD",

R/parse.R

@@ -223,6 +223,10 @@ write_to_csv <- function(tables, path="csv/", create=F) {
     write.table(tables$applause, str_c(path, "applause.csv"))
 }
 
+#'Create a Tibble out of the CSV-Document
+#'
+#'@param path The path that shows which Documents you want to use.
+#'
 #' @export
 read_from_csv <- function(path="csv/") {
     list(speaker = read.table(str_c(path, "speaker.csv")) %>%

man/read_from_csv.Rd

@@ -0,0 +1,14 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/parse.R
+\name{read_from_csv}
+\alias{read_from_csv}
+\title{Create a Tibble out of the CSV-Document}
+\usage{
+read_from_csv(path = "csv/")
+}
+\arguments{
+\item{path}{The path that shows which Documents you want to use.}
+}
+\description{
+Create a Tibble out of the CSV-Document
+}

vignettes/genderequality.Rmd

@@ -0,0 +1,94 @@
+---
+title: "genderequality"
+output: rmarkdown::html_vignette
+vignette: >
+  %\VignetteIndexEntry{genderequality}
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}
+---
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>"
+)
+```
+
+```{r setup}
+library(hateimparlament)
+library(dplyr)
+library(ggplot2)
+library(stringr)
+library(tidyr)
+library(rvest)
+```
+
+## Preparation of data
+
+First, you need to download all records of the current legislative period.
+```r
+fetch_all("../records/") # path to directory where records should be stored
+```
+Second, those `.xml` files, need to be parsed into `R` `tibbles`. This is accomplished by:
+```r
+read_all("../records/") %>% repair() -> res
+```
+We also used `repair` to fix a bunch of formatting issues in the records and unpacked
+the result into more descriptive variables.
+
+For development purposes, we load the tables from csv files.
+```{r}
+res <- read_from_csv('../csv/')
+```
+and unpack our tibbles
+```{r}
+comments <- res$comments
+speeches <- res$speeches
+speaker <- res$speaker
+talks <- res$talks
+```
+
+Bevor we can do our analysis, we have to assign a gender to our politicans.
+
+```{r}
+extract_href <- function(sel, html) {
+  html %>%
+    html_node(sel) %>%
+    html_attr("href")
+}
+
+first_content_p_text <- function(url) {
+  res <- NA
+  i <- 1
+  while(is.na(res)) {
+    read_html(url) %>% 
+      html_node(str_glue("#mw-content-text > div.mw-parser-output > p:nth-child({i})"))  %>% 
+      html_text() -> res
+    i <- i + 1
+  }
+  res
+}
+
+abgeordneten_list_html <- read_html(
+  "https://de.wikipedia.org/wiki/Liste_der_Mitglieder_des_Deutschen_Bundestages_(19._Wahlperiode)")
+
+selectors <- str_glue("#mw-content-text > div.mw-parser-output > table:nth-child(20) > tbody > tr:nth-child({2:709}) > td:nth-child(2) > a")
+link_part2 <- sapply(selectors, extract_href, abgeordneten_list_html)
+link <- str_c("https://de.wikipedia.org", link_part2)
+
+text <- sapply(link, first_content_p_text)
+text %>% 
+  str_extract(" ist ein.") %>% 
+  str_replace(" ist eine", "female") %>% 
+  str_replace(" ist ein ", "male") ->
+  gender
+
+text %>% 
+  str_extract("^([:upper:]?[:lower:]+[\\s\\-]?)*") %>% 
+  str_trim() -> 
+  names
+
+gender <- tibble(name = names,
+                 gender = gender)
+```
+