---
title: "Analysis of vocabulary"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Analysis of vocabulary}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)
```

```{r setup}
library(hateimparlament)
library(dplyr)
library(stringr)
library(ggplot2)
```

## 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

speeches <- res$speeches
speaker <- res$speaker
talks <- res$talks
```
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}
tables <- read_from_csv('../csv/')

comments <- tables$comments
speeches <- tables$speeches
speaker <- tables$speaker
talks <- tables$talks
```

Further, we need to load a list of words that were used by Hitler but not by standard German texts.
```{r}
fil <- file('../hitler_texts/hitler_words')
Worte <- readLines(fil)
hitlerwords <- tibble(Worte)
```

## Analysis

Now we extract the words that were used with higher frequency by one party and compare them with `hitlerwords`.
```{r}
talks %>% 
  left_join(speaker, by=c(speaker='id')) %>% 
  group_by(fraction) %>%
  summarize(full_text=str_c(content, collapse="\n")) -> talks_by_fraction
```
For each party, we want to get a tibble of words with frequency.
```{r}
#AfD
Worte <- str_extract_all(talks_by_fraction$full_text[[1]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
afdtotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/afdtotal) -> afd_words

#AfD&Fraktionslos
Worte <- str_extract_all(talks_by_fraction$full_text[[2]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
afdundfraktionslostotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/afdundfraktionslostotal) -> afdundfraktionslos_words

#BÜNDNIS 90 / DIE GRÜNEN
Worte <- str_extract_all(talks_by_fraction$full_text[[3]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
grünetotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/grünetotal) -> grüne_words

#CDU/CSU
Worte <- str_extract_all(talks_by_fraction$full_text[[4]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
cdutotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/cdutotal) -> cdu_words

#DIE LINKE
Worte <- str_extract_all(talks_by_fraction$full_text[[5]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
linketotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/linketotal) -> linke_words

#FDP
Worte <- str_extract_all(talks_by_fraction$full_text[[6]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
fdptotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/fdptotal) -> fdp_words

#Fraktionslos
Worte <- str_extract_all(talks_by_fraction$full_text[[7]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
fraktionslostotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/fraktionslostotal) -> fraktionslos_words

#SPD
Worte <- str_extract_all(talks_by_fraction$full_text[[8]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
spdtotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/spdtotal) -> spd_words

#NA
Worte <- str_extract_all(talks_by_fraction$full_text[[9]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
natotal = length(Worte)
tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/natotal) -> na_words

#alle
all_words <- bind_rows(afd_words, afdundfraktionslos_words, grüne_words, cdu_words, linke_words, fdp_words, fraktionslos_words, spd_words, na_words)
total <- sum(all_words$n)
all_words %>% group_by(Worte) %>% summarize(n = sum(n), part= sum(n)/total) -> all_words
```

Now we want to extract the words that are more frequently used by a specific fraction.
```{r}
afd_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> afd_high_frequent
select(afd_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

afdundfraktionslos_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> afdundfraktionslos_high_frequent
select(afdundfraktionslos_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

grüne_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> grüne_high_frequent
select(grüne_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

cdu_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> cdu_high_frequent
select(cdu_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

linke_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> linke_high_frequent
select(linke_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

fdp_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> fdp_high_frequent
select(fdp_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

fraktionslos_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> fraktionslos_high_frequent
select(fraktionslos_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

spd_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> spd_high_frequent
select(spd_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)

na_words %>% transmute(freq, fraction_n = n) %>% left_join(all_words) %>% transmute(fraction_freq = freq, total_freq = part, fraction_n, total_n = n, rel_quotient = fraction_freq/total_freq, abs_quotient = fraction_n/total_n) %>% arrange(-abs_quotient, -fraction_n) %>% filter(rel_quotient > 1) -> na_high_frequent
select(na_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)
```

We compare these words with `hitlerwords`.

```{r}
afd_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> afd_hitler_comparison
afdundfraktionslos_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> afdundfraktionslos_hitler_comparison
grüne_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> grüne_hitler_comparison
cdu_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> cdu_hitler_comparison
linke_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> linke_hitler_comparison
fdp_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> fdp_hitler_comparison
fraktionslos_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> fraktionslos_hitler_comparison
spd_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> spd_hitler_comparison
na_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> na_hitler_comparison

#not unique
tibble(fraction = c("AfD", "AfD&Fraktionslos", "BÜNDNIS 90 / DIE GRÜNEN", "CDU/CSU", "DIE LINKE", "FDP", "Fraktionslos", "SPD"),
       absolute = c(nrow(afd_hitler_comparison), nrow(afdundfraktionslos_hitler_comparison), nrow(grüne_hitler_comparison), nrow(cdu_hitler_comparison), nrow(linke_hitler_comparison), nrow(fdp_hitler_comparison), nrow(fraktionslos_hitler_comparison), nrow(spd_hitler_comparison)),
       total = c(nrow(afd_words), nrow(afdundfraktionslos_words), nrow(grüne_words), nrow(cdu_words), nrow(linke_words), nrow(fdp_words), nrow(fraktionslos_words), nrow(spd_words))
      ) %>% mutate(percent = 100*absolute/total) -> hitler_comparison
hitler_comparison
```
Finally, we want to plot our results:
```{r, fig.width=7}
bar_plot_fractions(hitler_comparison, y_variable = percent, title="Coincidence of party vocabulary with nazi vocabulary", ylab="unique 'nazi' words per total (unique) fraction words [%]")
```