fix funwithdata vignette, generalize bar plot helper

R/analyze.R

@@ -12,21 +12,27 @@ join_redner <- function(tb, res, fraktion_only = F) {
     else joined
 }
 
+#' @export
 party_colors <- c(
-  SPD="#DF0B25",
-  "CDU/CSU"="#000000", 
   AfD="#1A9FDD",
-  "AfD&Fraktionslos"="#1A9FDD",
-  "DIE LINKE"="#BC3475",
-  "BÜNDNIS 90 / DIE GRÜNEN"="#4A932B",
   FDP="#FEEB34",
+  "CDU/CSU"="#000000", 
+  SPD="#DF0B25",
+  "BÜNDNIS 90 / DIE GRÜNEN"="#4A932B",
+  "DIE LINKE"="#BC3475",
+  "AfD&Fraktionslos"="#1A9FDD",
   Fraktionslos="#FEEB34"
 )
 
 #' @export
-bar_plot_fraktionen <- function(tb) {
+bar_plot_fraktionen <- function(tb, variable, fill, title=NULL, xlab = "Fraction",
-    ggplot(tb, aes(x = reorder(fraktion, -n), y = n, fill = fraktion)) +
+                                ylab="n", filllab="Fraction") {
+    ggplot(tb, aes(x = reorder(fraktion, -{{variable}}), y = {{variable}}, fill = {{fill}})) +
         scale_fill_manual(values = party_colors) +
+        xlab(xlab) +
+        ylab(ylab) +
+        labs(fill = filllab) +
+        ggtitle(title) +
         geom_bar(stat = "identity")
 }
 

vignettes/funwithdata.Rmd

@@ -18,6 +18,8 @@ knitr::opts_chunk$set(
 library(hateimparlament)
 library(dplyr)
 library(ggplot2)
+library(stringr)
+library(tidyr)
 ```
 
 ## Preparation of data
@@ -48,25 +50,28 @@ talks <- res$talks
 ## Analysis
 
 Now we can start analysing our parsed dataset, e.g. find out which party gives the most talks:
-```{r, fig.width=8}
+```{r, fig.width=7}
 join_redner(res$reden, res) %>%
     group_by(fraktion) %>%
     summarize(n = n()) %>%
     arrange(n) %>%
-    bar_plot_fraktionen()
+    bar_plot_fraktionen(n, fill = fraktion, title="Number of speeches given by fraction", ylab="Number of speeches")
 ```
 
-### Count a word occurence
+or counting the occurences of a given word:
 
-```{r, fig.width=8}
+```{r, fig.width=7}
-find_word(res, "hitler") %>%
+find_word(res, "Kohleausstieg") %>%
     filter(occurences > 0) %>%
     join_redner(res) %>%
     select(content, fraktion) %>%
+    filter(!is.na(fraktion)) %>%
     group_by(fraktion) %>%
     summarize(n = n()) %>%
     arrange(desc(n)) %>%
-    bar_plot_fraktionen()
+    bar_plot_fraktionen(n, fill = fraktion,
+                           title = "Parties using the word 'Kohleausstieg' the most (absolutely)",
+                           ylab = "Number of uses of 'Kohleausstieg'")
 ```
 
 ### Who gives the most speeches?
@@ -105,9 +110,24 @@ res$applause %>%
               "CDU/CSU" = sum(`CDU_CSU`),
               "DIE LINKE" = sum(`DIE_LINKE`),
               "FDP" = sum(`FDP`),
-              "SPD" = sum(`SPD`))
+              "SPD" = sum(`SPD`)) -> tb
 ```
 
+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)) %>%
+    rename(fraktion = on_fraktion) %>%
+    bar_plot_fraktionen(value,
+                        fill = by_fraktion,
+                        title = "Number of rounds of applauses from fractions to fractions",
+                        xlab = "Applauded fraction",
+                        ylab = "Rounds of applauses",
+                        filllab = "Applauding fraction")
+```
+
+
 ### Which party comments the most on which parties?
 
 ```{r}
@@ -120,12 +140,25 @@ res$comments %>%
               `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))
+              `SPD` = sum(str_detect(by_fraktion, "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)) %>%
+    rename(fraktion = on_fraktion) %>%
+    bar_plot_fraktionen(value,
+                        fill = by_fraktion,
+                        title = "Number of comments from fractions to fractions",
+                        xlab = "Commented fraction",
+                        ylab = "Number of comments",
+                        filllab = "Commenting fraction")
 ```
 
 ### When are which topics discussed the most?
 
-```{r, fig.width=8}
+```{r, fig.width=7}
 pandemic_pattern <- "(?i)virus|corona|covid|lockdown"
 climate_pattern <- "(?i)klimawandel|erderwärmung|co2|treibhaus|methan|kyoto-protokoll|klimaabkommen"
 pension_pattern <- "(?i)rente|pension|altersarmut"