library(dplyr)
library(ggplot2)
setwd("~/Downloads/teaching/R")
who_disease = read.csv("dc/who_disease.csv")
View(who_disease)

# simple bar chart of the number of observations 
# by region
ggplot(who_disease, aes(x=region)) +
  geom_bar()

# scatter plot of the year by cases for a region
who_disease %>%
  filter(region == "AMR") %>% 
  ggplot(aes(x=year, y=cases)) +
  geom_point(alpha=0.5)


# Number of cases obsereved 
# for a given region for different disease
who_disease %>%
  filter(region == "AMR") %>% 
  ggplot(aes(x=year, y=cases, color=disease)) +
  geom_point(alpha=0.5)

df = data.frame(value = c(10, 23, 15, 18),
                group = paste0("G", 1:4))
print(df)

# pie chart as a stacked bar chart that has been 'wrapped' around some central axis.
ggplot(df, aes(x="", y=value, fill=group)) +
  geom_col() # heights of bars to represent values

# Pie Chart
ggplot(df, aes(x="", y=value, fill=group)) +
  geom_col() + # heights of bars to represent values
  coord_polar(theta = "y") +
  theme_void()

a = c(5,7,2,9)
ifelse(a %% 2 == 0, "even", "odd")
# "odd"  "odd"  "even" "odd" 

# Compact to see that half of disease is from AFR
who_disease %>%
  mutate(
    region = ifelse(
      region %in% c("EUR", "AFR"),
      region, "Other"
    )
  ) %>%
  ggplot(aes(x="", fill = region)) +
  geom_bar(color="white") +
  coord_polar(theta = "y") +
  theme_void()

library(dplyr)
library(ggplot2)
library(waffle)

setwd("~/Downloads/teaching/R")
who_disease = read.csv("dc/who_disease.csv")
View(who_disease)

# Bar Chart of country code and cases
# for SEAR region
who_disease %>%
  filter(region == "SEAR") %>%
  ggplot(aes(x=countryCode, y=cases)) +
  geom_col()

# fill bar with disease
who_disease %>%
  filter(region == "SEAR") %>%
  ggplot(aes(x=countryCode, y=cases, fill=disease)) +
  geom_col()

# stacks bars and constant height
who_disease %>%
  filter(region == "SEAR") %>%
  ggplot(aes(x=countryCode, y=cases, fill=disease)) +
  geom_col(position="fill")

# stack bar 'measles', 'mumps', other with year
disease_counts <- who_disease %>%
  mutate(disease = ifelse(
    disease %in% c('measles', 'mumps'), 
    disease, 
    'other')) %>%
  group_by(disease, year) %>% # year to the grouping
  summarise(total_cases = sum(cases))

print(disease_counts)

ggplot(disease_counts, 
       aes(x=year,
           y = total_cases, 
           fill = disease)) +
  geom_col(position="fill") # bars full height


# create factors
# rearrange factor level as in order as
# "measles", "other", "mumps"
disease_counts <- who_disease %>%
  mutate(
    disease = ifelse(disease %in% c('measles', 'mumps'), disease, 'other') %>% 
      factor(levels = c("measles", "other", "mumps")) # change factor levels to desired ordering
  ) %>%
  group_by(disease, year) %>%
  summarise(total_cases = sum(cases)) 
# plot
ggplot(disease_counts, aes(x = year, y = total_cases, fill = disease)) +
  geom_col(position = 'fill')


# Filter later than 1999
disease_counts <- who_disease %>%
	filter(year >= 1999) %>% 
	mutate(disease = ifelse( disease %in% c('measles', 'mumps'), 
                          disease, 
                          'other')) %>%
	group_by(disease, region) %>%    # Add region column to grouping
	summarise(total_cases = sum(cases))

# Set aesthetics so disease is the stacking variable, 
# region is the x-axis and counts are the y
ggplot(disease_counts, aes(x=region, 
                           y=total_cases, 
                           fill=disease)) +
	geom_col(position = "fill")

# Bar Chart
library(dplyr)
library(ggplot2)
setwd("~/Downloads/teaching/R")
who_disease = read.csv("dc/who_disease.csv")

# Total cases in each disease
ggplot(who_disease) +
  geom_col(aes(x=disease, y=cases))

# Bar chart should be used to represent meaning quantity
# Bar should be for stacking
# e.g. money spent on different activities in a project

# geom_col() when height is encoded in data

# Number of cases for disease in India in 1980
who_disease %>%
  filter((year == 1980) & (country=="India")) %>%
  ggplot(aes(x=disease, y=cases)) +
  geom_col()

who_disease %>%
  filter(year == 1980, country=="India") %>%
  ggplot(aes(x=disease, y=cases)) +
  geom_col()

# geom_bar need only x-axis
# who_disease observations for large cases
who_disease %>%
  # filter data to observations of greater than 1,000 cases
  filter(cases > 1000) %>%
  # map the x-axis to the region column
  ggplot(aes(x=region)) +
  # add a geom_bar call
  geom_bar()

# Single number associated with each category of data
# Count, average, rate

# Point Chart
#library(dplyr)
library(tidyverse)
library(ggplot2)
library(forcats)
setwd("~/Downloads/teaching/R")
who_disease = read.csv("dc/who_disease.csv")

interesting_countries = c(
  "NGA", "SDN", "FRA", "NPL", "MYS",
  "TZA", "YEM", "UKR", "BGD", "VNM"
)

who_subset = who_disease %>%
  filter(
    countryCode %in% interesting_countries,
    disease == "measles",
    year %in% c(2006, 2016)
  ) %>%
  mutate(year = paste0("cases_", year)) %>%
  spread(year, cases)#library(tidyverse) key,value to cols

View(who_subset)

who_subset %>%
  ggplot(aes(y=country, x=log10(cases_2016)) ) +
  geom_point()


who_subset %>%
  mutate(logFoldChange = log2(cases_2016/cases_2006)) %>%
  ggplot(aes(
    x = logFoldChange,
    y = reorder(country, logFoldChange) 
  )) +
  geom_point()