Update 2021-08-04-violin.Rmd

danton267 · danton267 · commit 9be20f183325 · 2021-09-28T05:37:21.000+01:00
diff --git a/ggplot2/2021-08-04-violin.Rmd b/ggplot2/2021-08-04-violin.Rmd
@@ -51,7 +51,7 @@ library(ggplot2)
 district_density <- read.csv("https://raw.githubusercontent.com/plotly/datasets/master/district_density.csv", stringsAsFactors = FALSE)
 district_density$cluster <- factor(district_density$cluster, levels=c("Pure urban", "Urban-suburban mix", "Dense suburban", "Sparse suburban", "Rural-suburban mix", "Pure rural"))
 district_density$region <- factor(district_density$region, levels=c("West", "South", "Midwest", "Northeast"))
-
+3
 p <- ggplot(district_density,aes(x=cluster, y=dem_margin, fill=cluster)) +
   geom_violin(colour=NA) +
   geom_hline(yintercept=0, alpha=0.5) +
@@ -200,118 +200,12 @@ p <- p + geom_violin(draw_quantiles = c(0.25, 0.5, 0.75))
 plotly::ggplotly(p)
 ```
 
-
-# Example
-
-
-```{r}
-library(plotly)
-library(ggplot2)
-
-p <-   
- if (require("ggplot2movies")) {
-  # Scale transformations occur before the density statistics are computed.
-  # Coordinate transformations occur afterwards.  Observe the effect on the
-  # number of outliers.
-  m <- ggplot(movies, aes(y = votes, x = rating, group = cut_width(rating, 0.5)))
-  m + geom_violin()
-  m +
-    geom_violin() +
-    scale_y_log10()
-  m +
-    geom_violin() +
-    coord_trans(y = "log10")
-  m +
-    geom_violin() +
-    scale_y_log10() + coord_trans(y = "log10")
-
-  # Violin plots with continuous x:
-  # Use the group aesthetic to group observations in violins
-  ggplot(movies, aes(year, budget)) +
-    geom_violin()
-  ggplot(movies, aes(year, budget)) +
-    geom_violin(aes(group = cut_width(year, 10)), scale = "width")
-}
-
-plotly::ggplotly(p)
-```
-
-### Basic violin plot
-A basic violin plot showing how Democratic vote share in the 2018 elections to the US House of Representatives varied by level of density. A horizontal bar is added, to divide candidates who lost from those who won.
-
-Source: [Dave Wassermann and Ally Flinn](https://docs.google.com/spreadsheets/d/1WxDaxD5az6kdOjJncmGph37z0BPNhV1fNAH_g7IkpC0/htmlview?sle=true#gid=0) for the election results and CityLab for its [Congressional Density Index](https://github.com/theatlantic/citylab-data/tree/master/citylab-congress). Regional classifications are according to the Census Bureau.
-
-```{r}
-library(plotly)
-library(ggplot2)
-
-district_density <- read.csv("https://raw.githubusercontent.com/plotly/datasets/master/district_density.csv", stringsAsFactors = FALSE)
-district_density$cluster <- factor(district_density$cluster, levels=c("Pure urban", "Urban-suburban mix", "Dense suburban", "Sparse suburban", "Rural-suburban mix", "Pure rural"))
-district_density$region <- factor(district_density$region, levels=c("West", "South", "Midwest", "Northeast"))
-
-p <- ggplot(district_density,aes(x=cluster, y=dem_margin, fill=cluster)) +
-  geom_violin(colour=NA) +
-  geom_hline(yintercept=0, alpha=0.5) +
-  labs(title = "Democratic performance in the 2018 House elections, by region and density",
-       x = "Density Index\nfrom CityLab",
-       y = "Margin of Victory/Defeat")
-
-ggplotly(p)
-```
-
-
 ### Add facetting
 Including facetting by region.
 
-```{r}
-library(plotly)
-library(ggplot2)
-
-district_density <- read.csv("https://raw.githubusercontent.com/plotly/datasets/master/district_density.csv", stringsAsFactors = FALSE)
-district_density$cluster <- factor(district_density$cluster, levels=c("Pure urban", "Urban-suburban mix", "Dense suburban", "Sparse suburban", "Rural-suburban mix", "Pure rural"))
-district_density$region <- factor(district_density$region, levels=c("West", "South", "Midwest", "Northeast"))
-
-p <- ggplot(district_density,aes(x=cluster, y=dem_margin, fill=cluster)) +
-  geom_violin(colour=NA) +
-  geom_hline(yintercept=0, alpha=0.5) +
-  facet_wrap(~region) +
-  labs(title = "Democratic performance in the 2018 House elections, by region and density",
-       x = "Density Index\nfrom CityLab",
-       y = "Margin of Victory/Defeat") +
-  coord_flip()
-
-ggplotly(p)
-```
-
-### Customized Appearance
 Add colour to the facet titles, centre-align the title, rotate the y-axis title, change the font, and get rid of the unnecessary legend. Note that `coord_flip()` flips the axes for the variables and the titles, but does not flip `theme()` elements.
 
-```{r}
-library(plotly)
-library(ggplot2)
-
-district_density <- read.csv("https://raw.githubusercontent.com/plotly/datasets/master/district_density.csv", stringsAsFactors = FALSE)
-district_density$cluster <- factor(district_density$cluster, levels=c("Pure urban", "Urban-suburban mix", "Dense suburban", "Sparse suburban", "Rural-suburban mix", "Pure rural"))
-district_density$region <- factor(district_density$region, levels=c("West", "South", "Midwest", "Northeast"))
-
-p <- ggplot(district_density,aes(x=cluster, y=dem_margin, fill=cluster)) +
-  geom_violin(colour=NA) +
-  geom_hline(yintercept=0, alpha=0.5) +
-  facet_wrap(~region) +
-  labs(title = "Democratic performance in the 2018 House elections, by region and density",
-       x = "Density Index\nfrom CityLab",
-       y = "Margin of Victory/Defeat") +
-  coord_flip() +
-  theme(axis.title.y = element_text(angle = 0, vjust=0.5),
-        plot.title = element_text(hjust = 0.5),
-        strip.background = element_rect(fill="lightblue"),
-        text = element_text(family = 'Fira Sans'),
-        legend.position = "none")
-
-ggplotly(p)
-```
 
-### Rotated Axis Text
 Rotated the x-axis text 45 degrees, and used `facet_grid` to create a 4x1 facet (compared to `facet_wrap`, which defaults to 2x2).
 
 ```{r}
