Analyse in genderequality

README.md

@@ -14,7 +14,7 @@ tables <- read_all()
 tables <- repair(tables)
 write_to_csv(tables)
 ```
-Wir verwenden NIEMALS source, etc.! Außerdem NIEMALD library(...) verwenden, sondern
+Wir verwenden NIEMALS source, etc.! Außerdem NIEMALS library(...) verwenden, sondern
 um neue pakete hinzuzufuegen (als dependency), verwende:
 ```r
 use_package("my-good-old-package")
@@ -40,7 +40,7 @@ Bevor analysiert werden kann, muss fetch.R ausgeführt werden, um alle Protokoll
 
 ## Tabellen
 
-parse.R parsed einzelne Protokolle und erstellt 3 Tibbles
+parse.R parsed einzelne Protokolle und erstellt 5 Tibbles
 
 ### Redner
 

vignettes/genderequality.Rmd

@@ -92,5 +92,134 @@ gender <- tibble(speaker = names,
                  gender = gender)
 
 
+speaker %>% 
+  unite("speaker", vorname, nachname, sep = " ") %>% 
+  right_join(gender, by = "speaker") -> 
+  speaker_with_gender
+
 ```
 
+#Analyse
+
+First, let's look at the relative distribution of the sexes throughout the whole Bundestag.
+
+```{r}
+speaker_with_gender %>% 
+  select(gender) %>%
+  group_by(gender) %>% 
+  summarise("count" = n()) %>% 
+  filter(gender %in% c("male", "female")) %>% 
+  mutate(portion = 100*count/sum(count)) -> 
+  plot1
+
+bp <- ggplot(plot1, aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity")
+pie <- bp + coord_polar("y", start=0)
+pie + 
+  scale_fill_manual(values=c("pink", "blue")) +
+  ggtitle("Relative distribution of sexes") +
+  xlab("") +
+  ylab("")
+```
+
+Next we look at the individual distributions between men and women in relation to the individual parties.
+
+```{r}
+
+speaker_with_gender %>% 
+  select(fraction, gender) %>% 
+  group_by(fraction, gender) %>% 
+  summarise("count" = n()) %>% 
+  filter(gender %in% c("male", "female")) %>% 
+  filter(!is.na(fraction)) %>% 
+  group_by(fraction) %>% 
+  mutate(portion = 100*count/sum(count)) -> 
+  plot2
+
+plot2 %>% 
+  filter(fraction == "AfD") %>% 
+  ggplot(aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity") -> 
+  bp
+pie1 <- bp + coord_polar("y", start=0) + ggtitle("AfD") + xlab("") + ylab("")
+plot2 %>% 
+  filter(fraction == "BÜNDNIS 90 / DIE GRÜNEN") %>% 
+  ggplot(aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity") -> 
+  bp
+pie2 <- bp + coord_polar("y", start=0) + ggtitle("DIE GRÜNEN") + xlab("") + ylab("")
+plot2 %>% 
+  filter(fraction == "CDU/CSU") %>% 
+  ggplot(aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity") -> 
+  bp
+pie3 <- bp + coord_polar("y", start=0) + ggtitle("CDU/CSU") + xlab("") + ylab("")
+plot2 %>% 
+  filter(fraction == "DIE LINKE") %>% 
+  ggplot(aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity") -> 
+  bp
+pie4 <- bp + coord_polar("y", start=0) + ggtitle("DIE LINKE") + xlab("") + ylab("")
+plot2 %>% 
+  filter(fraction == "FDP") %>% 
+  ggplot(aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity") -> 
+  bp
+pie5 <- bp + coord_polar("y", start=0) + ggtitle("FDP") + xlab("") + ylab("")
+plot2 %>% 
+  filter(fraction == "SPD") %>% 
+  ggplot(aes(x = "", y = portion, fill = gender))+
+  geom_bar(width = 1, stat = "identity") -> 
+  bp
+pie6 <- bp + coord_polar("y", start=0) + ggtitle("SPD") + xlab("") + ylab("")
+
+gridExtra::grid.arrange(pie1,pie2,pie3,pie4,pie5,pie6,nrow=2)
+```
+
+
+
+```{r}
+
+speeches %>%
+  group_by(speaker) %>%
+  summarize(n = n()) %>%
+  ungroup() %>% 
+  arrange(-n) %>%
+  left_join(speaker, by=c("speaker" = "id")) %>% 
+  unite(name, vorname, nachname, sep = " ") %>% 
+  inner_join(gender, by=c("name"= "speaker")) %>% 
+  group_by(gender) %>% 
+  summarise(absolute=sum(n)) %>%
+  filter(gender %in% c("female", "male")) %>%
+  mutate(absolute2=absolute/sum(absolute)) %>% 
+  mutate(portion=c(0.32, 0.68)) %>% 
+  mutate(relative=absolute*(1-portion)) %>% 
+  mutate(relative2=relative/sum(relative)) -> 
+  plot3
+```
+
+```{r}
+barplot(plot3$absolute2,
+        ylab = "amount of speeches",
+        main = "Absolute comparison of speech shares",
+        las = 1, 
+        names.arg = c("women", "men"), 
+        col = c("pink", "darkblue"),
+        font.main = 4,
+        cex.axis = 0.7)
+```
+
+```{r}
+barplot(plot3$relative2,
+        ylab = "amount of speeches",
+        main = "Relative comparison of speech shares",
+        las = 1, 
+        names.arg = c("women", "men"), 
+        col = c("pink", "darkblue"),
+        font.main = 4,
+        cex.axis = 0.7)
+```
+
+
+
+