Directions

Explore the world with Alita

Data for demo

Back to the spellbook

1. Stacked column chart

Create a data frame

Type <- c("A", "B", "C")
Percentage <- c(50, 30, 20)

type_df <- data.frame(Type, Percentage)
type_df

##   Type Percentage
## 1    A         50
## 2    B         30
## 3    C         20

Plot the stacked column chart

library(ggplot2)

stacked_chart <- ggplot(type_df) + aes(x = "", y = Percentage, fill = Type) +
  geom_col(width = 0.5) +
  geom_text(aes(label = Percentage),
            position = position_stack(vjust = 0.5))

stacked_chart

2. Pie chart

Use the stacked chart created to do a pie chart

pie_chart <- stacked_chart + coord_polar("y", start=0) +
  xlab("")
pie_chart

3. Table percentages and charts

Load the data We will use the country data

country_df <- read.csv("country_demo_2.csv", header = TRUE)
head(country_df)

##   X     country continent year lifeExp      pop gdpPercap
## 1 1 Afghanistan      Asia 1952  28.801  8425333  779.4453
## 2 2 Afghanistan      Asia 1957  30.332  9240934  820.8530
## 3 3 Afghanistan      Asia 1962  31.997 10267083  853.1007
## 4 4 Afghanistan      Asia 1967  34.020 11537966  836.1971
## 5 5 Afghanistan      Asia 1972  36.088 13079460  739.9811
## 6 6 Afghanistan      Asia 1977  38.438 14880372  786.1134

t(t(table(country_df$country)))

##                           
##                            [,1]
##   Afghanistan                12
##   Albania                    12
##   Algeria                    12
##   Angola                     12
##   Argentina                  12
##   Australia                  12
##   Austria                    12
##   Bahrain                    12
##   Bangladesh                 12
##   Belgium                    12
##   Benin                      12
##   Bolivia                    12
##   Bosnia and Herzegovina     12
##   Botswana                   12
##   Brazil                     12
##   Bulgaria                   12
##   Burkina Faso               12
##   Burundi                    12
##   Cambodia                   12
##   Cameroon                   12
##   Canada                     12
##   Central African Republic   12
##   Chad                       12
##   Chile                      12
##   China                      12
##   Colombia                   12
##   Comoros                    12
##   Congo, Dem. Rep.           12
##   Congo, Rep.                12
##   Costa Rica                 12
##   Cote d'Ivoire              12
##   Croatia                    12
##   Cuba                       12
##   Czech Republic             12
##   Denmark                    12
##   Djibouti                   12
##   Dominican Republic         12
##   Ecuador                    12
##   Egypt                      12
##   El Salvador                12
##   Equatorial Guinea          12
##   Eritrea                    12
##   Ethiopia                   12
##   Finland                    12
##   France                     12
##   Gabon                      12
##   Gambia                     12
##   Germany                    12
##   Ghana                      12
##   Greece                     12
##   Guatemala                  12
##   Guinea                     12
##   Guinea-Bissau              12
##   Haiti                      12
##   Honduras                   12
##   Hong Kong, China           12
##   Hungary                    12
##   Iceland                    12
##   India                      12
##   Indonesia                  12
##   Iran                       12
##   Iraq                       12
##   Ireland                    12
##   Iron City                   1
##   Israel                     12
##   Italy                      12
##   Jamaica                    12
##   Japan                      12
##   Jordan                     12
##   Kenya                      12
##   Korea, Dem. Rep.           12
##   Korea, Rep.                12
##   Kuwait                     12
##   Lebanon                    12
##   Lesotho                    12
##   Liberia                    12
##   Libya                      12
##   Madagascar                 12
##   Malawi                     12
##   Malaysia                   12
##   Mali                       12
##   Mauritania                 12
##   Mauritius                  12
##   Mexico                     12
##   Mongolia                   12
##   Montenegro                 12
##   Morocco                    12
##   Mozambique                 12
##   Myanmar                    12
##   Namibia                    12
##   Nepal                      12
##   Netherlands                12
##   New Zealand                12
##   Nicaragua                  12
##   Niger                      12
##   Nigeria                    12
##   Norway                     12
##   Oman                       12
##   Pakistan                   12
##   Panama                     12
##   Paraguay                   12
##   Peru                       12
##   Philippines                12
##   Poland                     12
##   Portugal                   12
##   Puerto Rico                12
##   Reunion                    12
##   Romania                    12
##   Rwanda                     12
##   Sao Tome and Principe      12
##   Saudi Arabia               12
##   Senegal                    12
##   Serbia                     12
##   Sierra Leone               12
##   Singapore                  12
##   Slovak Republic            12
##   Slovenia                   12
##   Somalia                    12
##   South Africa               12
##   Spain                      12
##   Sri Lanka                  12
##   Sudan                      12
##   Swaziland                  12
##   Sweden                     12
##   Switzerland                12
##   Syria                      12
##   Taiwan                     12
##   Tanzania                   12
##   Thailand                   12
##   Togo                       12
##   Trinidad and Tobago        12
##   Tunisia                    12
##   Turkey                     12
##   Uganda                     12
##   United Kingdom             12
##   United States              12
##   Uruguay                    12
##   Venezuela                  12
##   Vietnam                    12
##   West Bank and Gaza         12
##   Yemen, Rep.                12
##   Zalem                       1
##   Zambia                     12
##   Zimbabwe                   12

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

table(country_df$continent)

## 
##   Africa Americas     Asia   Europe  Oceania 
##      624      302      396      360       24

names(country_df)

## [1] "X"         "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

names(country_df)[1] <- "ID"

Get percentage frequencies

library(janitor)

## 
## Attaching package: 'janitor'

## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test

tabyl(country_df$continent)

##  country_df$continent   n   percent
##                Africa 624 0.3657679
##              Americas 302 0.1770223
##                  Asia 396 0.2321219
##                Europe 360 0.2110199
##               Oceania  24 0.0140680

continent_df <- as.data.frame(tabyl(country_df$continent))
class(continent_df)

## [1] "data.frame"

names(continent_df) <- c("Continent", "Number", "Percentage")
continent_df

##   Continent Number Percentage
## 1    Africa    624  0.3657679
## 2  Americas    302  0.1770223
## 3      Asia    396  0.2321219
## 4    Europe    360  0.2110199
## 5   Oceania     24  0.0140680

continent_df$Percentage <- round(continent_df$Percentage*100,2)
continent_df

##   Continent Number Percentage
## 1    Africa    624      36.58
## 2  Americas    302      17.70
## 3      Asia    396      23.21
## 4    Europe    360      21.10
## 5   Oceania     24       1.41

Create a stacked chart using the country data

stacked_chart_continent <- ggplot(continent_df) + aes(x = "", y = Percentage, fill = Continent) +
  geom_col(width = 0.5) +
  geom_text(aes(label = Percentage),
            position = position_stack(vjust = 0.5)) +
  ggtitle("Proportion of Records") + xlab("")

stacked_chart_continent

Create a pie stacked chart using the country data

pie_chart_continent <- stacked_chart_continent + coord_polar("y", start=0) +
  xlab("")
pie_chart_continent

pie_chart_continent_grey <- stacked_chart_continent + coord_polar("y", start=0) +
  xlab("") + scale_fill_grey()
pie_chart_continent_grey

4. Histograms with statistics

Create a histogram using the country data

ggplot(country_df) + aes(lifeExp) +
  geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Kurtosis and Skewness

library(moments)
kurtosis(country_df$lifeExp)

## [1] 1.873037

skewness(country_df$lifeExp)

## [1] -0.2513104

A histogram of life expectancy

ggplot(country_df) + aes(lifeExp) +
  geom_histogram(fill = "Orange", colour = "blue") + 
  xlab("Life Expectancy") +
  ylab("Count") + 
  ggtitle("Histogram of Life Expectancy, 1952 - 2007") +
  annotate("text", x = 40, y = 150, label = "Kurtosis = 1.87") +
  annotate("text", x = 40, y = 130, label = "Skewness = -0.25")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Label the data points

names(country_df)

## [1] "ID"        "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

country_df %>% filter(country == "Iron City")

##     ID   country continent year lifeExp     pop gdpPercap
## 1 1705 Iron City  Americas 2007  50.123 6666666  35666.42

country_df %>% filter(country == "Zalem")

##     ID country continent year lifeExp pop gdpPercap
## 1 1706   Zalem  Americas 2007  80.123 666   10666.5

ggplot(country_df) + aes(lifeExp) +
  geom_histogram(fill = "Orange", colour = "blue") + 
  xlab("Life Expectancy") +
  ylab("Count") + 
  ggtitle("Histogram of Life Expectancy, 1952 - 2007") +
  annotate("text", x = 40, y = 150, label = "Kurtosis = 1.87") +
  annotate("text", x = 40, y = 130, label = "Skewness = -0.25") +
  geom_vline(xintercept = 50.123, linetype = "dashed", color = "red") +
  annotate("text", x = 36, y = 100, label = "Iron City's Life Expectancy \n is 50 years old")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

5. Descriptive statistics

Filter for specific records. In this case, we will explore Alita’s worlds, Iron City and Zalem.

table(country_df$continent)

## 
##   Africa Americas     Asia   Europe  Oceania 
##      624      302      396      360       24

names(country_df)

## [1] "ID"        "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

country_df %>% filter(country == "Iron City")

##     ID   country continent year lifeExp     pop gdpPercap
## 1 1705 Iron City  Americas 2007  50.123 6666666  35666.42

country_df %>% filter(country == "Zalem")

##     ID country continent year lifeExp pop gdpPercap
## 1 1706   Zalem  Americas 2007  80.123 666   10666.5

Calculate the mean and median

mean(country_df$pop)

## [1] 29570418

median(country_df$pop)

## [1] 7021053

R does not have a mode function, so we will create one.

getmode <- function(v) {
  uniqv <- unique(v)
  uniqv[which.max(tabulate(match(v, uniqv)))]
}

Calculate the mode using the mode function.

getmode(country_df$continent)

## [1] Africa
## Levels: Africa Americas Asia Europe Oceania

6. Pivot tables

Pivot tables are very useful to explore the data and get aggregates

Mean population by continent

aggregate(pop ~ continent,
          data = country_df, FUN = mean)

##   continent      pop
## 1    Africa  9916003
## 2  Americas 24364589
## 3      Asia 77038722
## 4    Europe 17169765
## 5   Oceania  8874672

Median population by continent

aggregate(pop ~ continent,
          data = country_df, FUN = median)

##   continent      pop
## 1    Africa  4579311
## 2  Americas  6227510
## 3      Asia 14530831
## 4    Europe  8551125
## 5   Oceania  6403492

Mean population by continent and year

aggregate(pop ~ continent + year,
          data = country_df, FUN = mean)

##    continent year       pop
## 1     Africa 1952   4570010
## 2   Americas 1952  13806098
## 3       Asia 1952  42283556
## 4     Europe 1952  13937362
## 5    Oceania 1952   5343003
## 6     Africa 1957   5093033
## 7   Americas 1957  15478157
## 8       Asia 1957  47356988
## 9     Europe 1957  14596345
## 10   Oceania 1957   5970988
## 11    Africa 1962   5702247
## 12  Americas 1962  17330810
## 13      Asia 1962  51404763
## 14    Europe 1962  15345172
## 15   Oceania 1962   6641759
## 16    Africa 1967   6447875
## 17  Americas 1967  19229865
## 18      Asia 1967  57747361
## 19    Europe 1967  16039299
## 20   Oceania 1967   7300207
## 21    Africa 1972   7305376
## 22  Americas 1972  21175368
## 23      Asia 1972  65180977
## 24    Europe 1972  16687835
## 25   Oceania 1972   8053050
## 26    Africa 1977   8328097
## 27  Americas 1977  23122708
## 28      Asia 1977  72257987
## 29    Europe 1977  17238818
## 30   Oceania 1977   8619500
## 31    Africa 1982   9602857
## 32  Americas 1982  25211637
## 33      Asia 1982  79095018
## 34    Europe 1982  17708897
## 35   Oceania 1982   9197425
## 36    Africa 1987  11054502
## 37  Americas 1987  27310159
## 38      Asia 1987  87006690
## 39    Europe 1987  18103139
## 40   Oceania 1987   9787208
## 41    Africa 1992  12674645
## 42  Americas 1992  29570964
## 43      Asia 1992  94948248
## 44    Europe 1992  18604760
## 45   Oceania 1992  10459826
## 46    Africa 1997  14304480
## 47  Americas 1997  31876016
## 48      Asia 1997 102523803
## 49    Europe 1997  18964805
## 50   Oceania 1997  11120715
## 51    Africa 2002  16033152
## 52  Americas 2002  33990910
## 53      Asia 2002 109145521
## 54    Europe 2002  19274129
## 55   Oceania 2002  11727415
## 56    Africa 2007  17875763
## 57  Americas 2007  33538464
## 58      Asia 2007 115513752
## 59    Europe 2007  19536618
## 60   Oceania 2007  12274974

Median population by continent and year

aggregate(pop ~ continent + year,
          data = country_df, FUN = median)

##    continent year      pop
## 1     Africa 1952  2668125
## 2   Americas 1952  3146381
## 3       Asia 1952  7982342
## 4     Europe 1952  7199787
## 5    Oceania 1952  5343003
## 6     Africa 1957  2885791
## 7   Americas 1957  3507701
## 8       Asia 1957  9128546
## 9     Europe 1957  7507528
## 10   Oceania 1957  5970988
## 11    Africa 1962  3145210
## 12  Americas 1962  3880130
## 13      Asia 1962 10267083
## 14    Europe 1962  7814503
## 15   Oceania 1962  6641759
## 16    Africa 1967  3473693
## 17  Americas 1967  4318137
## 18      Asia 1967 11261690
## 19    Europe 1967  8140724
## 20   Oceania 1967  7300207
## 21    Africa 1972  3945595
## 22  Americas 1972  4698301
## 23      Asia 1972 12412593
## 24    Europe 1972  8444744
## 25   Oceania 1972  8053050
## 26    Africa 1977  4522666
## 27  Americas 1977  5302800
## 28      Asia 1977 13933198
## 29    Europe 1977  8741695
## 30   Oceania 1977  8619500
## 31    Africa 1982  5668229
## 32  Americas 1982  5968349
## 33      Asia 1982 14441916
## 34    Europe 1982  8962461
## 35   Oceania 1982  9197425
## 36    Africa 1987  6635612
## 37  Americas 1987  6655297
## 38      Asia 1987 16495304
## 39    Europe 1987  9101371
## 40   Oceania 1987  9787208
## 41    Africa 1992  7140389
## 42  Americas 1992  7351181
## 43      Asia 1992 17861905
## 44    Europe 1992  9272632
## 45   Oceania 1992 10459826
## 46    Africa 1997  7805423
## 47  Americas 1997  7992357
## 48      Asia 1997 21229759
## 49    Europe 1997  9527017
## 50   Oceania 1997 11120715
## 51    Africa 2002  8821779
## 52  Americas 2002  8650322
## 53      Asia 2002 22662365
## 54    Europe 2002  9518744
## 55   Oceania 2002 11727415
## 56    Africa 2007 10093311
## 57  Americas 2007  9119152
## 58      Asia 2007 24821286
## 59    Europe 2007  9493598
## 60   Oceania 2007 12274974