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

NAMESPACE

@@ -1,6 +1,8 @@
 # Generated by roxygen2: do not edit by hand
 
 export(fetch_all)
+export(find_word)
+export(join_redner)
 export(read_all)
 export(read_from_csv)
 export(repair)

R/analyze.R

@@ -0,0 +1,31 @@
+#' @export
+find_word <- function(res, word) {
+    talks <- res$talks
+    mutate(talks, occurences = sapply(str_match_all(talks$content, regex(word, ignore_case = TRUE)),
+           nrow))
+}
+
+#' @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")
+    else joined
+}
+
+party_colors <- c(
+  SPD="#DF0B25",
+  "CDU/CSU"="#000000", 
+  AfD="#1A9FDD",
+  "AfD&Fraktionslos"="#1A9FDD",
+  "DIE LINKE"="#BC3475",
+  "BÜNDNIS 90 / DIE GRÜNEN"="#4A932B",
+  FDP="#FEEB34",
+  Fraktionslos="#FEEB34"
+)
+
+#' @export
+bar_plot_fraktionen <- function(tb) {
+    ggplot(tb, aes(x = reorder(fraktion, -n), y = n, fill = fraktion)) +
+    scale_fill_manual(values = party_colors) +
+    geom_bar(stat = "identity")
+}

README.md

@@ -22,6 +22,11 @@ Um dokumentationen neu zu laden / zu erstellen (ruft roxgen auf)
 document()
 ```
 
+Baue vignetten
+```r
+rmarkdown::render("vignettes/bla.Rmd")
+```
+
 # Herunterladen
 
 Bevor analysiert werden kann, muss fetch.R ausgeführt werden, um alle Protokolle herunterzuladen.

vignettes/funwithdata.Rmd

@@ -29,32 +29,42 @@ 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
-
-reden <- res$reden
-redner <- res$redner
-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$comments
-reden <- tables$reden
-redner <- tables$redner
-talks <- tables$talks
+res <- read_from_csv('../csv/')
+```
+and unpack our tibbles
+```{r}
+comments <- res$comments
+reden <- res$reden
+redner <- res$redner
+talks <- res$talks
 ```
 
 ## Analysis
 
 Now we can start analysing our parsed dataset, e.g. find out which party gives the most talks:
-```{r}
-left_join(reden, redner, by=c("redner" = "id")) %>%
+```{r, fig.width=10}
+join_redner(reden, res) %>%
     group_by(fraktion) %>%
     summarize(n = n()) %>%
-    ggplot(aes(x = fraktion, y = n)) +
-    geom_bar(stat = "identity")
+    arrange(n) %>%
+    bar_plot_fraktionen()
 ```
 
+### Count a word occurence
+
+```{r, fig.width=10}
+find_word(res, "hitler") %>%
+    filter(occurences > 0) %>%
+    join_redner(res) %>%
+    select(content, fraktion) %>%
+    group_by(fraktion) %>%
+    summarize(n = n()) %>%
+    arrange(desc(n)) %>%
+    bar_plot_fraktionen()
+```