refactor rede -> speech, redner -> speaker

vignettes/funwithdata.Rmd

@@ -42,8 +42,8 @@ res <- read_from_csv('../csv/')
 and unpack our tibbles
 ```{r}
 comments <- res$comments
-reden <- res$reden
-redner <- res$redner
+speeches <- res$speeches
+speaker <- res$speaker
 talks <- res$talks
 ```
 
@@ -51,11 +51,11 @@ talks <- res$talks
 
 Now we can start analysing our parsed dataset, e.g. find out which party gives the most talks:
 ```{r, fig.width=7}
-join_redner(res$reden, res) %>%
+join_speaker(res$speeches, res) %>%
     group_by(fraktion) %>%
     summarize(n = n()) %>%
     arrange(n) %>%
-    bar_plot_fraktionen(title="Number of speeches given by fraction",
+    bar_plot_fractions(title="Number of speeches given by fraction",
                         ylab="Number of speeches")
 ```
 
@@ -64,13 +64,13 @@ or counting the occurences of a given word:
 ```{r, fig.width=7}
 find_word(res, "Kohleausstieg") %>%
     filter(occurences > 0) %>%
-    join_redner(res) %>%
+    join_speaker(res) %>%
     select(content, fraktion) %>%
     filter(!is.na(fraktion)) %>%
     group_by(fraktion) %>%
     summarize(n = n()) %>%
     arrange(desc(n)) %>%
-    bar_plot_fraktionen(title = "Parties using the word 'Kohleausstieg' the most (absolutely)",
+    bar_plot_fractions(title = "Parties using the word 'Kohleausstieg' the most (absolutely)",
                         ylab = "Number of uses of 'Kohleausstieg'",
                         flipped = F)
 ```
@@ -78,11 +78,11 @@ find_word(res, "Kohleausstieg") %>%
 ### Who gives the most speeches?
 
 ```{r}
-res$reden %>%
-    group_by(redner) %>%
+res$speeches %>%
+    group_by(speaker) %>%
     summarize(n = n()) %>%
     arrange(-n) %>%
-    left_join(res$redner, by=c("redner" = "id")) %>%
+    left_join(res$speaker, by=c("speaker" = "id")) %>%
     head(10)
 ```
 
@@ -91,10 +91,10 @@ res$reden %>%
 ```{r}
 res$talks %>%
     mutate(content_len = str_length(content)) %>%
-    group_by(redner) %>%
+    group_by(speaker) %>%
     summarize(avg_content_len = mean(content_len)) %>%
     arrange(-avg_content_len) %>%
-    left_join(res$redner, by=c("redner" = "id")) %>%
+    left_join(res$speaker, by=c("speaker" = "id")) %>%
     head(10)
 ```
 
@@ -102,7 +102,7 @@ res$talks %>%
 
 ```{r}
 res$applause %>%
-    left_join(res$redner, by=c("on_redner" = "id")) %>%
+    left_join(res$speaker, by=c("on_speaker" = "id")) %>%
     select(on_fraktion = fraktion, where(is.logical)) %>%
     group_by(on_fraktion) %>%
     arrange(on_fraktion) %>%
@@ -119,7 +119,7 @@ For plotting our results we reorganize them a bit and produce a bar plot:
 ```{r, fig.width=7}
 pivot_longer(tb, where(is.numeric), "by_fraktion", "count") %>%
     filter(!is.na(on_fraktion)) %>%
-    bar_plot_fraktionen(x_variable = on_fraktion,
+    bar_plot_fractions(x_variable = on_fraktion,
                         y_variable = value,
                         fill = by_fraktion,
                         title = "Number of rounds of applauses from fractions to fractions",
@@ -134,7 +134,7 @@ pivot_longer(tb, where(is.numeric), "by_fraktion", "count") %>%
 
 ```{r}
 res$comments %>%
-    left_join(res$redner, by=c("on_redner" = "id")) %>%
+    left_join(res$speaker, by=c("on_speaker" = "id")) %>%
     select(by_fraktion = fraktion.x, on_fraktion = fraktion.y) %>%
     group_by(on_fraktion) %>%
     summarize(`AfD` = sum(str_detect(by_fraktion, "AfD"), na.rm=T),
@@ -149,7 +149,7 @@ Analogously we plot the results:
 ```{r, fig.width=7}
 pivot_longer(tb, where(is.numeric), "by_fraktion", "count") %>%
     filter(!is.na(on_fraktion)) %>%
-    bar_plot_fraktionen(x_variable = on_fraktion,
+    bar_plot_fractions(x_variable = on_fraktion,
                         y_variable = value,
                         fill = by_fraktion,
                         title = "Number of comments from fractions to fractions",

vignettes/hitlercomparison.Rmd

@@ -31,8 +31,8 @@ Second, those `.xml` files, need to be parsed into `R` `tibbles`. This is accomp
 ```r
 read_all("../records/") %>% repair() -> res
 
-reden <- res$reden
-redner <- res$redner
+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
@@ -43,8 +43,8 @@ For development purposes, we load the tables from csv files.
 tables <- read_from_csv('../csv/')
 
 comments <- tables$comments
-reden <- tables$reden
-redner <- tables$redner
+speeches <- tables$speeches
+speaker <- tables$speaker
 talks <- tables$talks
 ```
 
@@ -60,7 +60,7 @@ hitlerwords <- tibble(Worte)
 Now we extract the words that were used with higher frequency by one party and compare them with `hitlerwords`.
 ```{r}
 talks %>% 
-  left_join(redner, by=c(redner='id')) %>% 
+  left_join(speaker, by=c(speaker='id')) %>% 
   group_by(fraktion) %>%
   summarize(full_text=str_c(content, collapse="\n")) -> talks_by_fraktion
 ```
@@ -169,5 +169,5 @@ hitler_comparison
 ```
 Finally, we want to plot our results:
 ```{r, fig.width=7}
-bar_plot_fraktionen(hitler_comparison, y_variable = percent, title="Coincidence of party vocabulary with nazi vocabulary", ylab="unique 'nazi' words per total (unique) fraction words [%]")
+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 [%]")
 ```