Merge branch 'master' of https://git.flavigny.de/christian/hateimparlament

NAMESPACE

@@ -1,9 +1,10 @@
 # Generated by roxygen2: do not edit by hand
 
-export(bar_plot_fraktionen)
+export(bar_plot_fractions)
 export(fetch_all)
 export(find_word)
-export(join_redner)
+export(join_speaker)
+export(party_colors)
 export(read_all)
 export(read_from_csv)
 export(repair)

R/analyze.R

@@ -6,9 +6,9 @@ find_word <- function(res, word) {
 }
 
 #' @export
-join_redner <- function(tb, res, fraktion_only = F) {
-    joined <- left_join(tb, res$redner, by=c("redner" = "id"))
-    if (fraktion_only) select(joined, "fraktion")
+join_speaker <- function(tb, res, fraction_only = F) {
+    joined <- left_join(tb, res$speaker, by=c("speaker" = "id"))
+    if (fraction_only) select(joined, "fraction")
     else joined
 }
 
@@ -29,10 +29,10 @@ party_order <- factor(c("Fraktionslos", "AfD&Fraktionslos",
                         "FDP", "AfD", NA_character_))
 
 #' @export
-bar_plot_fraktionen <- function(tb,
-                                x_variable = NULL, # default is fraktion
+bar_plot_fractions <- function(tb,
+                                x_variable = NULL, # default is fraction
                                 y_variable = NULL, # default is n
-                                fill = NULL, # default is fraktion
+                                fill = NULL, # default is fraction
                                 title = NULL,
                                 xlab = "Fraction",
                                 ylab = "n",
@@ -46,9 +46,9 @@ bar_plot_fraktionen <- function(tb,
     x_variable <- enexpr(x_variable)
 
     # set default values
-    if (is.null(fill)) fill <- expr(fraktion)
+    if (is.null(fill)) fill <- expr(fraction)
     if (is.null(y_variable)) y_variable <- expr(n)
-    if (is.null(x_variable)) x_variable <- expr(fraktion)
+    if (is.null(x_variable)) x_variable <- expr(fraction)
 
     # either reorder fraction factor by variable value
     if (reorder) maps <- aes(x = reorder(!!x_variable, -!!y_variable),
@@ -82,7 +82,7 @@ word_usage_by_date <- function(res, patterns, name, tidy=F) {
         else name <- patterns[[i]]
         tb <- mutate(tb, {{name}} := str_count(content, patterns[[i]]))
     }
-    left_join(tb, res$reden, by=c("rede_id" = "id")) %>%
+    left_join(tb, res$speeches, by=c("speech_id" = "id")) %>%
         group_by(date) %>%
         summarize(across(where(is.numeric), sum)) %>%
         arrange(date) -> tb

R/parse.R

@@ -16,16 +16,16 @@ read_all <- function(path="records/") {
     if (length(available_protocols) == 0)
         stop("The given directory is empty or does not exist.")
 
-    lapply(res, `[[`, "redner") %>%
+    lapply(res, `[[`, "speaker") %>%
         bind_rows() %>%
         distinct() ->
-        redner
+        speaker
     
-    lapply(res, `[[`, "reden") %>%
+    lapply(res, `[[`, "speeches") %>%
         bind_rows() %>%
         distinct() %>%
         mutate(date = as.Date(date, format="%d.%m.%Y")) ->
-        reden
+        speeches
 
     lapply(res, `[[`, "talks") %>%
         bind_rows() %>%
@@ -42,16 +42,16 @@ read_all <- function(path="records/") {
         comments
     filter(commentsandapplause, type == "applause") %>%
         select(-type, -kommentator, -content) %>%
-        mutate("CDU_CSU" = str_detect(fraktion, "CDU/CSU"),
-               "SPD" = str_detect(fraktion, "SPD"),
-               "FDP" = str_detect(fraktion, "FDP"),
-               "DIE_LINKE" = str_detect(fraktion, "DIE LINKE"),
-               "BUENDNIS_90_DIE_GRUENEN" = str_detect(fraktion, "BÜNDNIS 90/DIE GRÜNEN"),
-               "AfD" = str_detect(fraktion, "AfD")) %>%
-        select(-fraktion) ->
+        mutate("CDU_CSU" = str_detect(fraction, "CDU/CSU"),
+               "SPD" = str_detect(fraction, "SPD"),
+               "FDP" = str_detect(fraction, "FDP"),
+               "DIE_LINKE" = str_detect(fraction, "DIE LINKE"),
+               "BUENDNIS_90_DIE_GRUENEN" = str_detect(fraction, "BÜNDNIS 90/DIE GRÜNEN"),
+               "AfD" = str_detect(fraction, "AfD")) %>%
+        select(-fraction) ->
         applause
 
-    list(redner = redner, reden = reden, talks = talks, comments = comments, applause = applause)
+    list(speaker = speaker, speeches = speeches, talks = talks, comments = comments, applause = applause)
 }
 
 # this reads all currently parseable data from one xml
@@ -64,18 +64,18 @@ read_one <- function(name, path) {
     cs <- xml_children(x)
 
     verlauf <- xml_find_first(x, "sitzungsverlauf")
-    rednerl <- xml_find_first(x, "rednerliste")
+    speakerl <- xml_find_first(x, "rednerliste")
 
-    xml_children(rednerl) %>%
-        parse_rednerliste() ->
-        redner
+    xml_children(speakerl) %>%
+        parse_speakerlist() ->
+        speaker
 
     xml_children(verlauf) %>%
         xml_find_all("rede") %>%
-        parse_redenliste(date) ->
+        parse_speechlist(date) ->
         res
 
-    list(redner = redner, reden = res$reden, talks = res$talks, comments = res$comments)
+    list(speaker = speaker, speeches = res$speeches, talks = res$talks, comments = res$comments)
 }
 
 xml_get <- function(node, name) {
@@ -84,52 +84,52 @@ xml_get <- function(node, name) {
     else res
 }
 
-# parse one redner
-parse_redner <- function(redner_xml) {
-    redner_id <- xml_attr(redner_xml, "id")
-    nm <- xml_child(redner_xml)
+# parse one speaker
+parse_speaker <- function(speaker_xml) {
+    speaker_id <- xml_attr(speaker_xml, "id")
+    nm <- xml_child(speaker_xml)
     vorname <- xml_get(nm, "vorname")
     nachname <- xml_get(nm, "nachname")
-    fraktion <- xml_get(nm, "fraktion")
+    fraction <- xml_get(nm, "fraction")
     titel <- xml_get(nm, "titel")
     rolle <- xml_find_all(nm, "rolle")
     if (length(rolle) > 0) {
         rolle_lang <- xml_get(rolle, "rolle_lang")
         rolle_kurz <- xml_get(rolle, "rolle_kurz")
     } else rolle_kurz <- rolle_lang <- NA_character_
-    c(id = redner_id, vorname = vorname, nachname = nachname, fraktion = fraktion, titel = titel,
+    c(id = speaker_id, vorname = vorname, nachname = nachname, fraction = fraction, titel = titel,
       rolle_kurz = rolle_kurz, rolle_lang = rolle_lang)
 }
 
-# parse one rede
-# returns: - a rede (with rede id and redner id)
-#          - all talks appearing in the rede (with corresponding content)
-parse_rede <- function(rede_xml, date) {
-    rede_id <- xml_attr(rede_xml, "id")
-    cs <- xml_children(rede_xml)
-    cur_redner <- NA_character_
-    principal_redner <- NA_character_
+# parse one speech
+# returns: - a speech (with speech id and speaker id)
+#          - all talks appearing in the speech (with corresponding content)
+parse_speech <- function(speech_xml, date) {
+    speech_id <- xml_attr(speech_xml, "id")
+    cs <- xml_children(speech_xml)
+    cur_speaker <- NA_character_
+    principal_speaker <- NA_character_
     cur_content <- ""
-    reden <- list()
+    speeches <- list()
     comments <- list()
     for (node in cs) {
         if (xml_name(node) == "p" || xml_name(node) == "name") {
             klasse <- xml_attr(node, "klasse")
-            if ((!is.na(klasse) && klasse == "redner") || xml_name(node) == "name") {
-                if (!is.na(cur_redner)) {
-                    rede <- c(rede_id = rede_id,
-                              redner = cur_redner,
+            if ((!is.na(klasse) && klasse == "speaker") || xml_name(node) == "name") {
+                if (!is.na(cur_speaker)) {
+                    speech <- c(speech_id = speech_id,
+                              speaker = cur_speaker,
                               content = cur_content)
-                    reden <- c(reden, list(rede))
+                    speeches <- c(speeches, list(speech))
                     cur_content <- ""
                 } 
-                if (is.na(principal_redner) && xml_name(node) != "name") {
-                    principal_redner <- xml_child(node) %>% xml_attr("id")
+                if (is.na(principal_speaker) && xml_name(node) != "name") {
+                    principal_speaker <- xml_child(node) %>% xml_attr("id")
                 }
                 if (xml_name(node) == "name") {
-                    cur_redner <- "BTP"
+                    cur_speaker <- "BTP"
                 } else {
-                    cur_redner <- xml_child(node) %>% xml_attr("id")
+                    cur_speaker <- xml_child(node) %>% xml_attr("id")
                 }
             } else {
                 cur_content <- paste0(cur_content, xml_text(node), sep="\n")
@@ -141,65 +141,65 @@ parse_rede <- function(rede_xml, date) {
                 str_sub(2, -2) %>%
                 str_split("–") %>%
                 `[[`(1) %>%
-                lapply(parse_comment, rede_id = rede_id, on_redner = cur_redner) ->
+                lapply(parse_comment, speech_id = speech_id, on_speaker = cur_speaker) ->
                 cs
             comments <- c(comments, cs)
         }
     }
-    rede <- c(rede_id = rede_id,
-              redner = cur_redner,
+    speech <- c(speech_id = speech_id,
+              speaker = cur_speaker,
               content = cur_content)
-    reden <- c(reden, list(rede))
-    list(rede = c(id = rede_id, redner = principal_redner, date = date),
-         parts = reden,
+    speeches <- c(speeches, list(speech))
+    list(speech = c(id = speech_id, speaker = principal_speaker, date = date),
+         parts = speeches,
          comments = comments)
 }
 
-fraktionspattern <- "BÜNDNIS(SES)?\\W*90/DIE\\W*GRÜNEN|CDU/CSU|AfD|SPD|DIE LINKE|FDP|LINKEN"
-fraktionsnames <- c("BÜNDNIS 90/DIE GRÜNEN", "CDU/CSU", "AfD", "SPD", "DIE LINKE", "FDP")
+fractionpattern <- "BÜNDNIS(SES)?\\W*90/DIE\\W*GRÜNEN|CDU/CSU|AfD|SPD|DIE LINKE|FDP|LINKEN"
+fractionnames <- c("BÜNDNIS 90/DIE GRÜNEN", "CDU/CSU", "AfD", "SPD", "DIE LINKE", "FDP")
 
-parse_comment <- function(comment, rede_id, on_redner) {
-    base <- c(rede_id = rede_id, on_redner = on_redner)
+parse_comment <- function(comment, speech_id, on_speaker) {
+    base <- c(speech_id = speech_id, on_speaker = on_speaker)
     # classify comment
     if(str_detect(comment, "Beifall")) {
-        str_extract_all(comment, fraktionspattern) %>%
+        str_extract_all(comment, fractionpattern) %>%
             `[[`(1) %>%
-            sapply(partial(flip(head), 1) %.% agrep, x=fraktionsnames, max=0.2, value=T) %>%
+            sapply(partial(flip(head), 1) %.% agrep, x=fractionnames, max=0.2, value=T) %>%
             str_c(collapse=",") ->
             by
-        c(base, type = "applause", fraktion = by, kommentator = NA_character_, content = comment)
+        c(base, type = "applause", fraction = by, kommentator = NA_character_, content = comment)
     } else {
         ps <- str_match(comment, "(.*) \\[(.*?)\\]: (.*)")[1,]
-        c(base, type = "comment", fraktion = ps[3], kommentator = ps[2], content = ps[4])
+        c(base, type = "comment", fraction = ps[3], kommentator = ps[2], content = ps[4])
     }
 }
 
-# creates a tibble of reden and a tibble of talks from a list of xml nodes representing reden
-parse_redenliste <- function(redenliste_xml, date) {
-    d <- sapply(redenliste_xml, parse_rede, date = date)
-    reden <- simplify2array(d["rede", ])
+# creates a tibble of speeches and a tibble of talks from a list of xml nodes representing speeches
+parse_speechlist <- function(speechlist_xml, date) {
+    d <- sapply(speechlist_xml, parse_speech, date = date)
+    speeches <- simplify2array(d["speech", ])
     parts <- simplify2array %$% unlist(d["parts", ], recursive=FALSE)
     comments <- simplify2array %$% unlist(d["comments", ], recursive=FALSE)
-    list(reden = tibble(id = reden["id",], redner = reden["redner",],
-                        date = reden["date",]),
-         talks = tibble(rede_id = parts["rede_id", ],
-                        redner = parts["redner", ],
+    list(speeches = tibble(id = speeches["id",], speaker = speeches["speaker",],
+                        date = speeches["date",]),
+         talks = tibble(speech_id = parts["speech_id", ],
+                        speaker = parts["speaker", ],
                         content = parts["content", ]),
-         comments = tibble(rede_id = comments["rede_id",],
-                           on_redner = comments["on_redner",],
+         comments = tibble(speech_id = comments["speech_id",],
+                           on_speaker = comments["on_speaker",],
                            type = comments["type",],
-                           fraktion = comments["fraktion",],
+                           fraction = comments["fraction",],
                            kommentator = comments["kommentator",],
                            content = comments["content", ]))
 }
 
-# create a tibble of redner from a list of xml nodes representing redner
-parse_rednerliste <- function(rednerliste_xml) {
-    d <- sapply(rednerliste_xml, parse_redner)
+# create a tibble of speaker from a list of xml nodes representing speaker
+parse_speakerliste <- function(speakerliste_xml) {
+    d <- sapply(speakerliste_xml, parse_speaker)
     tibble(id = d["id",],
            vorname = d["vorname",],
            nachname = d["nachname",],
-           fraktion = d["fraktion",],
+           fraction = d["fraction",],
            titel = d["titel",],
            rolle_kurz = d["rolle_kurz",],
            rolle_lang = d["rolle_lang",])
@@ -208,8 +208,8 @@ parse_rednerliste <- function(rednerliste_xml) {
 #' @export
 write_to_csv <- function(tables, path="csv/", create=F) {
     check_directory(path, create)
-    write.table(tables$redner, str_c(path, "redner.csv"))
-    write.table(tables$reden, str_c(path, "reden.csv"))
+    write.table(tables$speaker, str_c(path, "speaker.csv"))
+    write.table(tables$speeches, str_c(path, "speeches.csv"))
     write.table(tables$talks, str_c(path, "talks.csv"))
     write.table(tables$comments, str_c(path, "comments.csv"))
     write.table(tables$applause, str_c(path, "applause.csv"))
@@ -217,12 +217,12 @@ write_to_csv <- function(tables, path="csv/", create=F) {
 
 #' @export
 read_from_csv <- function(path="csv/") {
-    list(redner = read.table(str_c(path, "redner.csv")) %>%
+    list(speaker = read.table(str_c(path, "speaker.csv")) %>%
              tibble() %>%
              mutate(id = as.character(id)),
-         reden = read.table(str_c(path, "reden.csv")) %>%
+         speeches = read.table(str_c(path, "speeches.csv")) %>%
              tibble() %>%
-             mutate(redner = as.character(redner)),
+             mutate(speaker = as.character(speaker)),
          talks = tibble %$% read.table(str_c(path, "talks.csv")),
          comments = tibble %$% read.table(str_c(path, "comments.csv")),
          applause = tibble %$% read.table(str_c(path, "applause.csv")))

R/repair.R

@@ -1,4 +1,4 @@
-fraktionen <- c("AFD" = "AfD",
+fractions <- c("AFD" = "AfD",
                 "AFD&FRAKTIONSLOS" = "AfD&Fraktionslos",
                 "BÜNDNIS90/" = "BÜNDNIS 90 / DIE GRÜNEN",
                 "BÜNDNIS90/DIEGRÜNEN" = "BÜNDNIS 90 / DIE GRÜNEN",
@@ -8,9 +8,9 @@ fraktionen <- c("AFD" = "AfD",
                 "CDU/CSU" = "CDU/CSU",
                 "FDP" = "FDP")
 
-repair_fraktion <- function(fraktion) {
-    cleaned <- str_to_upper %$% str_replace_all(fraktion, "\\s", "")
-    fraktionen[cleaned]
+repair_fraction <- function(fraction) {
+    cleaned <- str_to_upper %$% str_replace_all(fraction, "\\s", "")
+    fractions[cleaned]
 }
 
 # takes vector of titel and keeps longest
@@ -22,28 +22,28 @@ longest_titel <- function(titel) {
 # takes character vector, removes duplicates and collapses
 collect_unique <- function(xs) xs %>% clear_na() %>% unique() %>% str_c(collapse="&") %>% na_if("")
 
-# expects a tibble of redner and repairs
-repair_redner <- function(redner) {
-    if (nrow(redner) == 0) return(redner)
-    redner %>%
+# expects a tibble of speaker and repairs
+repair_speaker <- function(speaker) {
+    if (nrow(speaker) == 0) return(speaker)
+    speaker %>%
         filter(id != "10000") %>% # invalid id's
-        mutate(fraktion = Vectorize(repair_fraktion)(fraktion)) %>% # fix fraktion
+        mutate(fraction = Vectorize(repair_fraction)(fraction)) %>% # fix fraction
         group_by(id) %>%
         summarize(vorname = head(vorname, 1),
                   nachname = head(nachname, 1),
-                  fraktion = collect_unique(fraktion),
+                  fraction = collect_unique(fraction),
                   titel = longest_titel(titel),
                   rolle_kurz = collect_unique(str_squish(rolle_kurz)),
                   rolle_lang = collect_unique(str_squish(rolle_lang))) %>%
         ungroup() #%>%
         # arrange(id) %>%
-        # distinct(vorname, nachname, fraktion, titel)
+        # distinct(vorname, nachname, fraction, titel)
 }
 
-repair_reden <- function(reden) {
-    if (nrow(reden) == 0) return(reden)
+repair_speeches <- function(speeches) {
+    if (nrow(speeches) == 0) return(speeches)
     # TODO: fill with content
-    reden
+    speeches
 }
 
 repair_talks <- function(talks) {
@@ -65,9 +65,9 @@ repair_talks <- function(talks) {
 #' Tries to match the name_variable column with speaker names
 #' 
 #' returns a lookup table
-lookup_redner <- function(tb, redner, name_variable) {
+lookup_speaker <- function(tb, speaker, name_variable) {
     tobereplaced <- "[-–—‑­­-­­­ ]"
-    redner %>%
+    speaker %>%
         unite(name, vorname, nachname, sep=".*") %>%
         mutate(name = str_replace_all(name, tobereplaced, ".*")) ->
         rs
@@ -80,7 +80,7 @@ lookup_redner <- function(tb, redner, name_variable) {
     }
     tb %>%
         distinct({{name_variable}}) %>%
-        mutate(redner = Vectorize(find_match)(str_replace_all({{name_variable}}, tobereplaced, "")))
+        mutate(speaker = Vectorize(find_match)(str_replace_all({{name_variable}}, tobereplaced, "")))
 }
 
 repair_comments <- function(comments, redner) {
@@ -104,11 +104,11 @@ repair_comments <- function(comments, redner) {
 #' @export
 repair <- function(parse_output, repair_comments = FALSE) {
 
-    list(redner = repair_redner(parse_output$redner),
-         reden = repair_reden(parse_output$reden),
+    list(redner = repair_speaker(parse_output$speaker),
+         reden = repair_speeches(parse_output$speeches),
          talks = repair_talks(parse_output$talks),
          comments = if(repair_comments) repair_comments(parse_output$comments,
-                                                        parse_output$redner)
+                                                        parse_output$speaker)
                     else parse_output$comments,
          applause = parse_output$applause
          )

README.md

@@ -44,7 +44,7 @@ parse.R parsed einzelne Protokolle und erstellt 3 Tibbles
 
 ### Redner
 
-Struktur: `id` , `vorname` , `nachname` , `fraktion` , `titel` , `rolle_kurz`, `rolle_lang`
+Struktur: `id` , `vorname` , `nachname` , `fraction` , `titel` , `rolle_kurz`, `rolle_lang`
 
 Die Rollen sind beispielsweise "Bundeskanzlerin". Leider gegendert und deshalb wahrscheinlich
 nervig zu analysieren.

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$reden, res) %>%
-    group_by(fraktion) %>%
+join_speaker(res$speeches, res) %>%
+    group_by(fraction) %>%
     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) %>%
-    select(content, fraktion) %>%
-    filter(!is.na(fraktion)) %>%
-    group_by(fraktion) %>%
+    join_speaker(res) %>%
+    select(content, fraction) %>%
+    filter(!is.na(fraction)) %>%
+    group_by(fraction) %>%
     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)
 ```
 
@@ -102,10 +102,10 @@ res$talks %>%
 
 ```{r}
 res$applause %>%
-    left_join(res$redner, by=c("on_redner" = "id")) %>%
-    select(on_fraktion = fraktion, where(is.logical)) %>%
-    group_by(on_fraktion) %>%
-    arrange(on_fraktion) %>%
+    left_join(res$speaker, by=c("on_speaker" = "id")) %>%
+    select(on_fraction = fraction, where(is.logical)) %>%
+    group_by(on_fraction) %>%
+    arrange(on_fraction) %>%
     summarize("AfD" = sum(`AfD`),
               "BÜNDNIS 90 / DIE GRÜNEN" = sum(`BUENDNIS_90_DIE_GRUENEN`),
               "CDU/CSU" = sum(`CDU_CSU`),
@@ -117,11 +117,11 @@ res$applause %>%
 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,
+pivot_longer(tb, where(is.numeric), "by_fraction", "count") %>%
+    filter(!is.na(on_fraction)) %>%
+    bar_plot_fractions(x_variable = on_fraction,
                         y_variable = value,
-                        fill = by_fraktion,
+                        fill = by_fraction,
                         title = "Number of rounds of applauses from fractions to fractions",
                         xlab = "Applauded fraction",
                         ylab = "Rounds of applauses",
@@ -134,24 +134,24 @@ pivot_longer(tb, where(is.numeric), "by_fraktion", "count") %>%
 
 ```{r}
 res$comments %>%
-    left_join(res$redner, by=c("on_redner" = "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),
-              `BÜNDNIS 90 / DIE GRÜNEN` = sum(str_detect(by_fraktion, "BÜNDNIS 90/DIE GRÜNEN"), na.rm=T),
-              `CDU/CSU` = sum(str_detect(by_fraktion, "CDU/CSU"), na.rm = T),
-              `DIE LINKE` = sum(str_detect(by_fraktion, "DIE LINKE"), na.rm=T),
-              `FDP` = sum(str_detect(by_fraktion, "FDP"), na.rm=T),
-              `SPD` = sum(str_detect(by_fraktion, "SPD"), na.rm=T)) -> tb
+    left_join(res$speaker, by=c("on_speaker" = "id")) %>%
+    select(by_fraction = fraction.x, on_fraction = fraction.y) %>%
+    group_by(on_fraction) %>%
+    summarize(`AfD` = sum(str_detect(by_fraction, "AfD"), na.rm=T),
+              `BÜNDNIS 90 / DIE GRÜNEN` = sum(str_detect(by_fraction, "BÜNDNIS 90/DIE GRÜNEN"), na.rm=T),
+              `CDU/CSU` = sum(str_detect(by_fraction, "CDU/CSU"), na.rm = T),
+              `DIE LINKE` = sum(str_detect(by_fraction, "DIE LINKE"), na.rm=T),
+              `FDP` = sum(str_detect(by_fraction, "FDP"), na.rm=T),
+              `SPD` = sum(str_detect(by_fraction, "SPD"), na.rm=T)) -> tb
 ```
 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,
+pivot_longer(tb, where(is.numeric), "by_fraction", "count") %>%
+    filter(!is.na(on_fraction)) %>%
+    bar_plot_fractions(x_variable = on_fraction,
                         y_variable = value,
-                        fill = by_fraktion,
+                        fill = by_fraction,
                         title = "Number of comments from fractions to fractions",
                         xlab = "Commented fraction",
                         ylab = "Number of comments",

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
 ```
 
@@ -60,54 +60,54 @@ 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')) %>% 
-  group_by(fraktion) %>%
-  summarize(full_text=str_c(content, collapse="\n")) -> talks_by_fraktion
+  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_fraktion$full_text[[1]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[2]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[3]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[4]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[5]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[6]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[7]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[8]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$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_fraktion$full_text[[9]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
+Worte <- str_extract_all(talks_by_fraction$full_text[[9]], "\\b[a-zA-ZäöüÄÖÜß]+\\b")[[1]]
 natotal = length(Worte)
 tibble(Worte) %>% group_by(Worte) %>% count() %>% mutate(freq =n/natotal) -> na_words
 
@@ -117,34 +117,34 @@ 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 `fraktion`.
+Now we want to extract the words that are more frequently used by a specific fraction.
 ```{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
-select(afd_high_frequent, fraktion_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)
+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, 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
-select(afdundfraktionslos_high_frequent, fraktion_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, 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
-select(grüne_high_frequent, fraktion_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, 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
-select(cdu_high_frequent, fraktion_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, 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
-select(linke_high_frequent, fraktion_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, 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
-select(fdp_high_frequent, fraktion_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, 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
-select(fraktionslos_high_frequent, fraktion_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, 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
-select(spd_high_frequent, fraktion_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, 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
-select(na_high_frequent, fraktion_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`.
@@ -161,7 +161,7 @@ spd_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerw
 na_high_frequent %>% mutate(Worte = str_to_lower(Worte)) %>% inner_join(hitlerwords) -> na_hitler_comparison
 
 #not unique
-tibble(fraktion = c("AfD", "AfD&Fraktionslos", "BÜNDNIS 90 / DIE GRÜNEN", "CDU/CSU", "DIE LINKE", "FDP", "Fraktionslos", "SPD"),
+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
@@ -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 [%]")
 ```