R covid 19 data analytics projects

 R covid 19 data analytics projects

R covid 19 data analytics projects part 2

 

# install packages "reader" , "ggplot2" , "dplyr"

install.packages("readr")

install.packages("ggplot2")

install.packages("dplyr")

# Load the readr, ggplot2, and dplyr packages

library(readr)

library(ggplot2)

library(dplyr)

# Read datasets/confirmed_cases_worldwide.csv into confirmed_cases_worldwide

confirmed_cases_worldwide <-read_csv("confirmed_cases_worldwide.csv")

# See the result

confirmed_cases_worldwide

#  Confirmed cases throughout the world

# Draw a line plot of cumulative cases vs. date

# Label the y-axis

ggplot(data=confirmed_cases_worldwide,aes(date,cum_cases))+

  geom_line() +

  ylab("Cumulative confirmed cases") 

 #  China compared to the rest of the world

confirmed_cases_china_vs_world <- read_csv("confirmed_cases_china_vs_world.csv")

# See the result

glimpse(confirmed_cases_china_vs_world)

# Draw a line plot of cumulative cases vs. date, grouped and colored by is_china

# Define aesthetics within the line geom

plt_cum_confirmed_cases_china_vs_world <- ggplot(confirmed_cases_china_vs_world) +

  geom_line(aes(date, cum_cases,  color = is_china)) +

  ylab("Cumulative confirmed cases")

# See the plot

plt_cum_confirmed_cases_china_vs_world

# Let's annotate!

who_events <- tribble(

  ~ date, ~ event,

  "2020-01-30", "Global health\nemergency declared",

  "2020-03-11", "Pandemic\ndeclared",

  "2020-02-13", "China reporting\nchange"

) %>%

  mutate(date = as.Date(date))

# Using who_events, add vertical dashed lines with an xintercept at date

# and text at date, labeled by event, and at 100000 on the y-axis

plt_cum_confirmed_cases_china_vs_world +

  geom_vline(aes(xintercept = date), data = who_events, linetype = "dashed")  +

   geom_text(aes(date, label = event), data = who_events, y = 60000 ) 

#  Adding a trend line to China

# Filter for China, from Feb 15

china_after_feb15 <- confirmed_cases_china_vs_world %>%

  filter(is_china == "China", date >= "2020-02-15")

# Using china_after_feb15, draw a line plot cum_cases vs. date

# Add a smooth trend line using linear regression, no error bars

ggplot(china_after_feb15, aes(date, cum_cases)) +

  geom_line() +

  geom_smooth(method = "lm", se = FALSE) +

  ylab("Cumulative confirmed cases")