Joining Data

Code for Quiz 6, more dplyr and our first interactive chart using echarts4r

Steps 1-6

  1. Load the R packages we will use
library(tidyverse)
library(echarts4r)
library(hrbrthemes)
  1. Read the data in the files drug_cos_csv, health_cos_csv in to R and assign to the variable drug_cos and health_cos , respectively
drug_cos <- read.csv("https://estanny.com/static/week6/drug_cos.csv")
health_cos <- read.csv("https://estanny.com/static/week6/health_cos.csv")
  1. use glimpse to get a glimpse of the data
drug_cos %>% glimpse()

Rows: 104
Columns: 9
$ ticker       <chr> "ZTS", "ZTS", "ZTS", "ZTS", "ZTS", "ZTS", "ZTS"~
$ name         <chr> "Zoetis Inc", "Zoetis Inc", "Zoetis Inc", "Zoet~
$ location     <chr> "New Jersey; U.S.A", "New Jersey; U.S.A", "New ~
$ ebitdamargin <dbl> 0.149, 0.217, 0.222, 0.238, 0.182, 0.335, 0.366~
$ grossmargin  <dbl> 0.610, 0.640, 0.634, 0.641, 0.635, 0.659, 0.666~
$ netmargin    <dbl> 0.058, 0.101, 0.111, 0.122, 0.071, 0.168, 0.163~
$ ros          <dbl> 0.101, 0.171, 0.176, 0.195, 0.140, 0.286, 0.321~
$ roe          <dbl> 0.069, 0.113, 0.612, 0.465, 0.285, 0.587, 0.488~
$ year         <int> 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018,~
health_cos %>% glimpse()

Rows: 464
Columns: 11
$ ticker      <chr> "ZTS", "ZTS", "ZTS", "ZTS", "ZTS", "ZTS", "ZTS",~
$ name        <chr> "Zoetis Inc", "Zoetis Inc", "Zoetis Inc", "Zoeti~
$ revenue     <dbl> 4233000000, 4336000000, 4561000000, 4785000000, ~
$ gp          <dbl> 2581000000, 2773000000, 2892000000, 3068000000, ~
$ rnd         <dbl> 427000000, 409000000, 399000000, 396000000, 3640~
$ netincome   <dbl> 245000000, 436000000, 504000000, 583000000, 3390~
$ assets      <dbl> 5711000000, 6262000000, 6558000000, 6588000000, ~
$ liabilities <dbl> 1975000000, 2221000000, 5596000000, 5251000000, ~
$ marketcap   <dbl> NA, NA, 16345223371, 21572007994, 23860348635, 2~
$ year        <int> 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, ~
$ industry    <chr> "Drug Manufacturers - Specialty & Generic", "Dru~
  1. Which variables are the same in both data sets
names_drug <- drug_cos %>% names()
names_health <- health_cos %>% names()
intersect(names_drug, names_health)

[1] "ticker" "name"   "year"
  1. Which variables are the same in both data sets
names_drug <- drug_cos %>% names()
names_health <- health_cos %>% names()
intersect(names_drug, names_health)

[1] "ticker" "name"   "year"
  1. Select subset of variables to work with For drug_cos select (in this order): ticker, year, grossmargin Extract observations for 2018 Assign output to drug_subset For health_cos select (in this order ticker, year, revenue, gp, industrial Extract observations for 2018 Assign output to health_subset
drug_subset <- drug_cos %>%
  select(ticker, year, grossmargin) %>% 
  filter(year == 2018)