changes

vignettes/hitlercomparison.Rmd

@@ -69,41 +69,49 @@ For each party, we want to get a tibble of words with frequency.
 ```{r}
 #AfD
 Worte <- str_extract_all(talks_by_fraktion$full_text[[1]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> afd_words
+afdtotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/afdtotal) -> afd_words
 
 #AfD&Fraktionslos
 Worte <- str_extract_all(talks_by_fraktion$full_text[[2]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> afdundfraktionslos_words
+afdundfraktionslostotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/afdundfraktionslostotal) -> afdundfraktionslos_words
+
 #BÜNDNIS 90 / DIE GRÜNEN
 Worte <- str_extract_all(talks_by_fraktion$full_text[[3]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> grüne_words
+grünetotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/grünetotal) -> grüne_words
+
 #CDU/CSU
 Worte <- str_extract_all(talks_by_fraktion$full_text[[4]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> cdu_words
+cdutotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/cdutotal) -> cdu_words
+
 #DIE LINKE
 Worte <- str_extract_all(talks_by_fraktion$full_text[[5]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> linke_words
+linketotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/linketotal) -> linke_words
+
 #FDP
 Worte <- str_extract_all(talks_by_fraktion$full_text[[6]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> fdp_words
+fdptotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/fdptotal) -> fdp_words
+
 #Fraktionslos
 Worte <- str_extract_all(talks_by_fraktion$full_text[[7]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> fraktionslos_words
+fraktionslostotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/fraktionslostotal) -> fraktionslos_words
+
 #SPD
 Worte <- str_extract_all(talks_by_fraktion$full_text[[8]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> spd_words
+spdtotal = length(Worte)
+tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/spdtotal) -> spd_words
+
 #NA
 Worte <- str_extract_all(talks_by_fraktion$full_text[[9]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
-total = length(Worte)
-tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/total) -> na_words
+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)
@@ -114,10 +122,64 @@ Now we want to extract the words that are more frequently used by a specific `fr
 ```{r}
 afd_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> afd_high_frequent
 
+afdundfraktionslos_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> afdundfraktionslos_high_frequent
+
+grüne_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> grüne_high_frequent
+
+cdu_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> cdu_high_frequent
+
+linke_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> linke_high_frequent
+
+fdp_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> fdp_high_frequent
+
+fraktionslos_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> fraktionslos_high_frequent
+
+spd_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> spd_high_frequent
+
+na_words %>% transmute(freq, fraktion_n = n) %>% left_join(all_words) %>% transmute(fraktion_freq = freq, total_freq = part, fraktion_n, total_n = n, rel_quotient = fraktion_freq/total_freq, abs_quotient = fraktion_n/total_n) %>% arrange(-abs_quotient, -fraktion_n) %>% filter(rel_quotient > 1) -> na_high_frequent
+
 ```
 
 We compare these words with `hitlerwords`.
 
 ```{r}
-afd_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords)
+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(fraktion = c("AfD", "AfD und Fraktionslose", "Grüne", "CDU", "Linke", "FDP", "Fraktionslos", "SPD", "NA"),
+       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), nrow(na_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), nrow(na_words))
+      ) %>% mutate(relative = absolute/total) -> hitler_compare
+```
+
+Dead code:
+```r
+1000*nrow(afd_hitler_comparison) / nrow(afd_words)
+1000*nrow(afdundfraktionslos_hitler_comparison) / nrow(afdundfraktionslos_words)
+1000*nrow(grüne_hitler_comparison) / nrow(grüne_words)
+1000*nrow(cdu_hitler_comparison) / nrow(cdu_words)
+1000*nrow(linke_hitler_comparison) / nrow(linke_words)
+1000*nrow(fdp_hitler_comparison) / nrow(fdp_words)
+1000*nrow(fraktionslos_hitler_comparison) / nrow(fraktionslos_words)
+1000*nrow(spd_hitler_comparison) / nrow(spd_words)
+1000*nrow(na_hitler_comparison) / nrow(na_words)
+
+
+1000*sum(afd_hitler_comparison$fraktion_n) / afdtotal
+1000*sum(afdundfraktionslos_hitler_comparison$fraktion_n) / afdundfraktionslostotal
+1000*sum(grüne_hitler_comparison$fraktion_n) / grünetotal
+1000*sum(cdu_hitler_comparison$fraktion_n) / cdutotal
+1000*sum(linke_hitler_comparison$fraktion_n) / linketotal
+1000*sum(fdp_hitler_comparison$fraktion_n) / fdptotal
+1000*sum(fraktionslos_hitler_comparison$fraktion_n) / fraktionslostotal
+1000*sum(spd_hitler_comparison$fraktion_n) / spdtotal
+1000*sum(na_hitler_comparison$fraktion_n) / natotal
 ```