christian/hateimparlament
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add plots in genderequality and clean up hitlercomparison

Browse Source
This commit is contained in:
JosuaKugler
2021-08-08 22:35:08 +02:00
parent 1546f84d80
commit 1db9e3f59a
2 changed files with 54 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vignettes/genderequality.Rmd
+37 -56
View File
@@ -97,7 +97,7 @@ speaker %>%
speaker_with_gender speaker_with_gender
``` ```
#Analyse ## Analyse
First, let's look at the relative distribution of the sexes throughout the whole Bundestag. First, let's look at the relative distribution of the sexes throughout the whole Bundestag.
@@ -120,9 +120,9 @@ pie +
ylab("") ylab("")
``` ```
Next we look at the individual distributions between men and women in the different fractions. Next, we look at the individual distributions between men and women in the different fractions.
```{r} ```{r, fig.width=7}
speaker_with_gender %>% speaker_with_gender %>%
group_by(fraction) %>% group_by(fraction) %>%
summarize(n = n()) -> summarize(n = n()) ->
@@ -137,58 +137,41 @@ speaker_with_gender %>%
bar_plot_fractions(women_per_fraction, x_variable=fraction, y_variable=q, title="Frauenanteil nach Partei") bar_plot_fractions(women_per_fraction, x_variable=fraction, y_variable=q, title="Frauenanteil nach Partei")
``` ```
```r Prepared with this knowledge, we can now analyse the relative amount of speeches by gender and fraction.
speaker_with_gender %>%
select(fraction, gender) %>% ```{r, fig.width=7}
group_by(fraction, gender) %>% speaker_with_gender %>% transmute(speaker_id = id, gender, fraction) -> simple_speaker_with_gender
summarise("count" = n()) %>% speeches %>%
filter(gender %in% c("male", "female")) %>% transmute(id, speaker_id = speaker) %>%
filter(!is.na(fraction)) %>% inner_join(simple_speaker_with_gender) %>%
group_by(fraction) %>% group_by(fraction) %>%
mutate(portion = 100*count/sum(count)) -> summarize(speeches=n()) ->
plot2 fraction_speeches_size
plot2 %>% speeches %>%
filter(fraction == "AfD") %>% transmute(id, speaker_id = speaker) %>%
ggplot(aes(x = "", y = portion, fill = gender))+ inner_join(simple_speaker_with_gender) %>%
geom_bar(width = 1, stat = "identity") -> filter(gender=='female') %>%
bp group_by(fraction) %>%
pie1 <- bp + coord_polar("y", start=0) + ggtitle("AfD") + xlab("") + ylab("") summarize(female_speeches=n()) %>%
plot2 %>% left_join(fraction_speeches_size) %>%
filter(fraction == "BÜNDNIS 90 / DIE GRÜNEN") %>% left_join(women_per_fraction) %>%
ggplot(aes(x = "", y = portion, fill = gender))+ mutate(q_speeches = female_speeches/speeches) -> speech_distribution
geom_bar(width = 1, stat = "identity") -> #bar_plot_fractions(speech_distribution, x_variable=fraction, y_variable=q_speeches, title="Redeanteil Frauen nach Partei")
bp
pie2 <- bp + coord_polar("y", start=0) + ggtitle("DIE GRÜNEN") + xlab("") + ylab("")
plot2 %>% party_order <- factor(c("Fraktionslos", "AfD&Fraktionslos",
filter(fraction == "CDU/CSU") %>% "DIE LINKE", "BÜNDNIS 90 / DIE GRÜNEN", "SPD", "CDU/CSU",
ggplot(aes(x = "", y = portion, fill = gender))+ "FDP", "AfD", NA_character_))
geom_bar(width = 1, stat = "identity") ->
bp speech_distribution %>%
pie3 <- bp + coord_polar("y", start=0) + ggtitle("CDU/CSU") + xlab("") + ylab("") mutate("Frauenanteil" = q, "Redenanteil Frauen" = q_speeches) %>%
plot2 %>% pivot_longer(c(Frauenanteil, "Redenanteil Frauen"), "type") %>%
filter(fraction == "DIE LINKE") %>% ggplot(aes(x=factor(fraction, levels = party_order), y=value, fill=factor(type, levels = factor(c("Frauenanteil", "Redenanteil Frauen"))))) + scale_fill_manual(values= c("Frauenanteil"="gray", "Redenanteil Frauen"="red")) + coord_flip() + geom_bar(stat="identity", position="dodge") + labs(fill="Kategorie")
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)
``` ```
Now let's analyze whether there are any differences in the amount of speeches given. For comparison, let's analyze the total differences in the amount of speeches given.
```{r} ```{r}
speeches %>% speeches %>%
@@ -208,8 +191,9 @@ speeches %>%
mutate(relative2=relative/sum(relative)) -> mutate(relative2=relative/sum(relative)) ->
plot3 plot3
``` ```
At first lets take a look at the absolute difference in the amount of speeches by the two sexes. At first lets take a look at the absolute difference in the amount of speeches by the two sexes.
```{r} ```{r,fig.width=7}
barplot(plot3$absolute2, barplot(plot3$absolute2,
ylab = "amount of speeches", ylab = "amount of speeches",
main = "Absolute comparison of speech shares", main = "Absolute comparison of speech shares",
@@ -219,8 +203,9 @@ barplot(plot3$absolute2,
font.main = 4, font.main = 4,
cex.axis = 0.7) cex.axis = 0.7)
``` ```
Since there are more men represented in the German Bundestag, we now consider the relative proportions of speeches, depending on the ratio of men and women. Since there are more men represented in the German Bundestag, we now consider the relative proportions of speeches, depending on the ratio of men and women.
```{r} ```{r, fig.width=7}
barplot(plot3$relative2, barplot(plot3$relative2,
ylab = "amount of speeches", ylab = "amount of speeches",
main = "Relative comparison of speech shares", main = "Relative comparison of speech shares",
@@ -230,7 +215,3 @@ barplot(plot3$relative2,
font.main = 4, font.main = 4,
cex.axis = 0.7) cex.axis = 0.7)
``` ```
vignettes/hitlercomparison.Rmd
+16 -2
View File
@@ -119,8 +119,22 @@ all_words %>% group_by(Worte) %>% summarize(n = sum(n), part= sum(n)/total) -> a
Now we want to extract the words that are more frequently used by a specific fraction. Now we want to extract the words that are more frequently used by a specific fraction.
```{r} ```{r}
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 afd_words %>%
select(afd_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80) 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, 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 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) select(afdundfraktionslos_high_frequent, fraction_n, total_n, abs_quotient, rel_quotient) %>% filter(total_n > 80)