Seminar3

In this Seminar we will try to recreate Economists Graph

Link for the blog https://databeauty.com/blog/tutorial/2017/03/03/recreate-economist-graph-by-ggplot2.html

library(ggplot2)
setwd("~/AUCA courses/Intro to Data Science with R/Seminar3")
dat <- read.csv("EconomistData.csv")
ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point()

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point(size=2, shape=23)

• geom_text(): adds text directly to the plot
• geom_label(): draws a rectangle underneath the text, making it easier to read.
• annotate(): useful for adding small text annotations at a particular location on the plot
• annotation_custom(): Adds static annotations that are the same in every panel

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point(size=2, shape=23)+geom_text(label=rownames(dat))

rownames(dat) <- dat[,2]
ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point(size=2, shape=23)+geom_text(label=rownames(dat))

pointsToLabel <- c("Russia", "Kyrgyzstan", "Uzbekistan", "France", "Germany", "Moldova", "Tajikistan")
ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point(size=2, shape=5)+geom_text(aes(label=Country), data = subset(dat, Country %in% pointsToLabel))

library(ggrepel)
ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point(size=2)+geom_text_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=1)

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_point(size=2)+geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=1)

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40)+geom_point(size=2)

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(size=2)

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development")

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development") + theme_bw()

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development") + theme_dark()

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development") + theme_bw() +geom_smooth()

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

ggplot(data = dat, aes(x=CPI, y=HDI))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(aes(color = Region),size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development") + theme_bw() +geom_smooth()

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

ggplot(data = dat, aes(x=CPI, y=HDI))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(aes(color = Region),size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development") + theme_bw() +geom_smooth(method=lm, color="red", se=FALSE)

## `geom_smooth()` using formula 'y ~ x'

library(hrbrthemes)
ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = subset(dat, Country %in% pointsToLabel), force=40, size=2.5, min.segment.length = 0)+
  geom_point(size=2) + labs(x="Corruption Percieved Index", y="Human Development Index", title="Corruption and Human Development") + theme_ipsum()

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): семейство
## шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): семейство
## шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): семейство
## шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): семейство
## шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## семейство шрифтов не найдено в базе данных шрифтов Windows

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = dat %>% filter(HDI<0.5), force=20, size=2.5)+
  geom_point(size=2)

## Warning: ggrepel: 35 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

library(dplyr)
ggplot(data = dat, aes(x=CPI, y=HDI, color = Region))+
  geom_label_repel(aes(label=Country), data = dat %>% filter(HDI<0.4), force=20, size=2.5, max.overlaps = Inf)+
  geom_point(size=2)