Data Visualization

d <- read.csv(file.choose(), header = T)
read.csv(file = './data/abc.csv')

install.packages('xlsx')
library(xlsx)

tmp <- read.xlsx(file.choose(), sheetIndex = 1, header = T)
tmp <- read.xlsx(file = './data/abc.xlsx')

library(datasets)
data(package = 'datasets')

library(ggplot2)
data(package = 'ggplot2')

tmp <- swiss
tmp <- diamonds
tmp <- read.csv("https://data.nber.org/cps-basic2/csv/cpsb202302.csv")

library(WDI)
ind <- WDIsearch('Total reserves')
d <- WDI(indicator = 'FI.RES.TOTL.MO', country = c('VNM'), extra = T)
tmp <- d %>% select(year,FI.RES.TOTL.MO)
tmp <- na.omit(tmp)
names(tmp) <- c('year','DuTru')

library(tidyverse)
library(scales)
tmp <- diamonds
tmp %>% ggplot(aes(x = cut)) +
    geom_bar() +
    labs(x = 'Loại', y = 'Số lượng')

tmp <- diamonds
tmp %>% ggplot(aes(x = cut)) +
    geom_bar() +
    labs(x = 'Loại', y = 'Số lượng') +
    coord_flip()

tmp %>% group_by(cut) %>% summarise(n = n()) %>%
  ggplot(aes(cut,n)) +
    geom_col(fill='green') +
    geom_text(aes(label = n),vjust = 2, color = 'red') +
    labs(x = 'Loại', y = 'Số lượng')

tmp %>% group_by(cut) %>% summarise(n = n()) %>%
  ggplot(aes(cut,n)) +
    geom_col(fill='green') +
    geom_text(aes(label = percent(n/length(tmp$carat))),vjust = 2, color = 'red') +
    labs(x = 'Loại', y = 'Số lượng')

tmp %>% group_by(cut,color) %>% summarise(n=n()) %>%
  ggplot(aes(x = cut,y = n)) +
    geom_col(position = 'dodge') +
    facet_wrap(~color) +
    labs(x = 'Loại', y = 'Số lượng')

tmp %>% group_by(cut,color) %>% summarise(n=n()) %>%
  ggplot(aes(x = cut,y = n)) +
    geom_col(position = 'dodge') +
    facet_wrap(~color) +
    geom_text(aes(label = n),vjust = 2, color = 'green') +
    labs(x = 'Loại', y = 'Số lượng')

tmp <- diamonds
tmp %>% group_by(cut) %>% summarise(m= mean(carat)) %>%
  ggplot(aes(x = cut,y = m)) +
    geom_col(position = 'dodge') +
    geom_text(aes(label = round(m,2)), vjust = 2, color = 'green') +
    labs(x = 'Màu', y = 'Mean')

tmp <- diamonds
tmp %>% group_by(cut,color) %>% summarise(m = mean(price)) %>%
  ggplot(aes(x = cut,y = m)) +
    geom_col(position = 'dodge') +
    facet_wrap(~color) +
    geom_text(aes(label = round(m))) +
    labs(x = 'cut', y = 'Số lượng')

tmp <- diamonds
tmp <- tmp %>% group_by(cut, color) %>% summarise(n = n())
tmp %>% ggplot(aes(x = cut, y = n)) +
  geom_col(data = tmp %>% filter(color == 'D'), fill = 'red') +
  geom_col(data = tmp %>% filter(color == 'J'), fill = 'blue')

tmp <- diamonds 
tmp <- tmp %>% mutate(caratC = cut(carat,5, label = c('rất nhỏ', 'nhỏ','vừa','lớn','rất lớn')))
tmp %>% ggplot(aes(x = caratC)) +
  geom_bar(fill = 'red')

tmp <- diamonds
tmp %>% ggplot(aes(x = price)) +
  geom_histogram(binwidth = 500, fill = 'blue', color = 'red')

tmp <- diamonds
tmp %>% ggplot(aes(x = price, fill = color)) +
  geom_histogram(binwidth = 500)

tmp <- diamonds
tmp %>% ggplot(aes(x = price)) +
  geom_histogram(binwidth = 500, fill = 'blue', color = 'red') +
  facet_wrap(~color)

tmp <- diamonds
tmp %>% ggplot(aes(x = price)) +
  geom_histogram(data = tmp %>% filter(color == 'G'), binwidth = 500, fill = 'red') +
  geom_histogram(data = tmp %>% filter(color == 'J'), binwidth = 500, fill = 'green')

tmp <- diamonds
tmp %>% ggplot(aes(x = price)) +
  geom_density(fill = 'red')

tmp <- diamonds
tmp %>% ggplot(aes(x = price, fill = cut)) +
  geom_density()

tmp <- diamonds
tmp %>% ggplot(aes(x = price)) +
  geom_density(fill = 'green') +
  facet_wrap(~cut)

tmp <- diamonds
tmp %>% group_by(color) %>% summarise(n = n()) %>%
  ggplot(aes(x = '', y = n,fill = color)) +
    geom_col() +
    geom_text(aes(label = n),position = position_stack(vjust = 1))

tmp <- diamonds
tmp %>% group_by(color) %>% summarise(n = n()) %>%
  ggplot(aes(x = '', y = n,fill = color)) +
    geom_col() +
    coord_polar('y')

tmp <- diamonds
tmp %>% group_by(color) %>% summarise(n = n()) %>%
  ggplot(aes(x = '', y = n,fill = color)) +
    geom_col(color = 'black') +
    coord_polar('y') +
    geom_text(aes(x = 1.3, label = n),position = position_stack(vjust = .5)) +
    theme_void()

tmp <- diamonds
tmp <- tmp %>% filter(cut == 'Good' )
tmp %>% group_by(color) %>% summarise(n = n()) %>%
  ggplot(aes(x = '', y = n,fill = color)) +
    geom_col(color = 'black', width = 1) +
    coord_polar('y') +
    geom_text(aes(x = 1.3, label = n),position = position_stack(vjust = .5)) +
    theme_void()

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length)) +
  geom_point() +
  xlab('Độ dài đài hoa') + 
  ylab('Độ dài của cánh hoa')

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
  geom_point()

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length, shape = Species)) +
  geom_point()

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length, size = Species)) +
  geom_point()

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length, alpha = Species)) +
  geom_point()

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length)) +
  geom_point(color = 'red') +
  geom_smooth(method = 'lm', color = 'green')

tmp <- iris
tmp %>% ggplot(aes(x = Sepal.Length, y = Petal.Length)) +
  geom_point(color = 'red') +
  geom_smooth(method = 'lm', color = 'green') +
  facet_wrap(~Species)

library(googledrive)
library(tidyverse)
library(gganimate)
library(magick)

pa <- 'https://drive.google.com/file/d/1Jc14iMyezkp0IARQdEPe03HbHh6NCiZA/view?usp=sharing'
id <- as_id(pa)
pa <- paste0('https://docs.google.com/uc?id=',id,'&export=download')
d <- read.csv(pa, header = T)
tmp <- d %>% filter(Country %in% c('Vietnam','Thailand','Malaysia', 'Cambodia', 'Laos'))
tmp <- tmp %>% select(Country,Population,Year)
tmp <- tmp %>% rename(country = Country ,pop = Population, year = Year)
tmp %>% ggplot(aes(x = year, y = pop, color = country)) +
  geom_line() +
  geom_point(size=2) +
  transition_reveal(year, keep_last = F)

myfun <- function(xvar) { 1/(1 + exp(-xvar + 10))}

curve(myfun(x), from = -4, to = 6, col = 'red')

myfun1 <- function(x,a = 1.2){exp(x - a)/(1 + exp(x - a))}

curve(myfun1(x), from = -5, to = 5, col = "blue")
curve(1/x^2,from = .2,to = 6, add = T, col= "red")

qplot(x,y,...,data,facets = NULL,geom = "auto",stat = deprecated(),position = )

qplot(color, data = diamonds, geom = 'bar', weight = carat)+ scale_y_continuous("carat")

qplot(carat, data = diamonds, facets = color ~., geom = "histogram", binwidth = 0.1)

qplot(x = carat, y = price, data = diamonds, color = cut)

qplot(carat, data = diamonds, geom = "histogram", binwidth = 0.05)

qplot(carat, data = diamonds, geom = "density")

qplot(color, data = diamonds, geom = "bar", weight = carat) + scale_y_continuous("carat")