RamiKrispin

Notes about command lines functions from the "Data Science at the Command Line"

echo is a command that outputs the strings it is being passed as arguments

echo 'Hello World'
Hello World

RamiKrispin

#----------------------------------------
# Plotting the daily new confirmed cases
# China vs. rest of the world
#----------------------------------------
# Data: coronavirus dataset from the coronavirus package
# Using github version as it update the data on daily bases
#----------------------------------------
# Installing most recent version from Github
# must reset the R session after installation
# install.packages("devtools")

RamiKrispin

`%>%` <- magrittr::`%>%`

dates_seq <- seq.Date(from = as.Date("2018-11-24"), to = as.Date("2018-11-30"), by = "day")

df <- lapply(dates_seq, function(i){
  
  cmd <- paste("curl -X GET https://api.carbonintensity.org.uk/intensity/", i, 
               "T00:00Z/", i, 
               "T23:30Z | jq --raw-output '.data[] | [.from, .intensity.actual] | @tsv'", 
               sep = "")

RamiKrispin

library(coronavirus)
df <- coronavirus %>% 
  # dplyr::filter(date == max(date)) %>%
  dplyr::group_by(Country.Region, type) %>%
  dplyr::summarise(total = sum(cases)) %>%
  tidyr::pivot_wider(names_from =  type, 
                     values_from = total) %>%
  dplyr::arrange(-confirmed) %>%
  dplyr::ungroup() %>%
  dplyr::mutate(country = factor(Country.Region, levels = Country.Region))

RamiKrispin

province_vec <- coronavirus %>% 
  dplyr::filter(type == "confirmed", Country.Region == "Mainland China") %>%
  dplyr::group_by(Province.State) %>%
  dplyr::summarise(total = sum(cases, na.rm = TRUE)) %>%
  dplyr::arrange(-total) %>%
  dplyr::select(province = Province.State) 


coronavirus %>% 
  dplyr::filter(type == "confirmed", Country.Region == "Mainland China") %>%

RamiKrispin

#---------------- Plotting Daily Cumulative Cases of the Coronavirus----------------
# Installing the most update version of the coronavirus
# install.packages("devtools")
devtools::install_github("RamiKrispin/coronavirus")
data("coronavirus")


# Reformat and aggregate the data to daily by country and type of case
df_daily <- coronavirus %>% 
  dplyr::group_by(date, type) %>%

RamiKrispin

# Install the Github version (refreshed on a daily bases):

# install.packages("devtools")
devtools::install_github("RamiKrispin/coronavirus")

library(coronavirus)

data("covid_italy")

head(covid_italy)  

RamiKrispin

# Creating a tree-map plot for the total covid19 confirmed cases in Italy
#------------------------------------------------------------------------

# Required packages
library(covid19italy)
library(dplyr)
library(plotly)

# Check for updates
update_data()

RamiKrispin

library(plotly)
data(mtcars)

plot_ly(data = mtcars, x = ~ hp, y = ~ mpg)

plot_ly(x = ~ mtcars[,"hp"], y = mtcars[, "mpg"])

var1 <- "hp"
var2 <- "mpg"

RamiKrispin

#---------------------------------------------------------
# Creating a trajectory plot for covid19 confirmed cases
# Required packages - dplyr, tidyr, and plotly packages
# Data - coronavirus package
#---------------------------------------------------------

# To get the most update data use the Github version
#devtools::install_github("RamiKrispin/coronavirus")
library(coronavirus)
`%>%` <- magrittr::`%>%`