Steps 1-6

Load the R packages we will use.

library(tidyverse)
library(echarts4r) #install this package before using

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")

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         <dbl> 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        <dbl> 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, …
$ industry    <chr> "Drug Manufacturers - Specialty & Generic", "Dru…

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"

Select subset of variable 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, industry
- Extract observations for 2018
- Assign output to health_subset

drug_subset  <- drug_cos %>% 
  select(ticker, year, grossmargin) %>% 
  filter(year == 2018)
health_subset  <- health_cos  %>%
  select(ticker, year, revenue, gp, industry)  %>% 
  filter(year == 2018)

Keep all the rows and columns drug_subset join with columns in health_subset

drug_subset %>% left_join(health_subset)

# A tibble: 13 × 6
   ticker  year grossmargin     revenue          gp industry          
   <chr>  <dbl>       <dbl>       <dbl>       <dbl> <chr>             
 1 ZTS     2018       0.672  5825000000  3914000000 Drug Manufacturer…
 2 PRGO    2018       0.387  4731700000  1831500000 Drug Manufacturer…
 3 PFE     2018       0.79  53647000000 42399000000 Drug Manufacturer…
 4 MYL     2018       0.35  11433900000  4001600000 Drug Manufacturer…
 5 MRK     2018       0.681 42294000000 28785000000 Drug Manufacturer…
 6 LLY     2018       0.738 24555700000 18125700000 Drug Manufacturer…
 7 JNJ     2018       0.668 81581000000 54490000000 Drug Manufacturer…
 8 GILD    2018       0.781 22127000000 17274000000 Drug Manufacturer…
 9 BMY     2018       0.71  22561000000 16014000000 Drug Manufacturer…
10 BIIB    2018       0.865 13452900000 11636600000 Drug Manufacturer…
11 AMGN    2018       0.827 23747000000 19646000000 Drug Manufacturer…
12 AGN     2018       0.861 15787400000 13596000000 Drug Manufacturer…
13 ABBV    2018       0.764 32753000000 25035000000 Drug Manufacturer…

Question: join_ticker

Start with drug_cos
Extract observations for the ticker JNJ from drug_cos
Assign output to the variable drug_cos_subset

drug_cos_subset  <- drug_cos  %>% 
   filter(ticker == "JNJ")

Display drug_cos_subset

drug_cos_subset

# A tibble: 8 × 9
  ticker name  location ebitdamargin grossmargin netmargin   ros   roe
  <chr>  <chr> <chr>           <dbl>       <dbl>     <dbl> <dbl> <dbl>
1 JNJ    John… New Jer…        0.247       0.687     0.149 0.199 0.161
2 JNJ    John… New Jer…        0.272       0.678     0.161 0.218 0.173
3 JNJ    John… New Jer…        0.281       0.687     0.194 0.224 0.197
4 JNJ    John… New Jer…        0.336       0.694     0.22  0.284 0.217
5 JNJ    John… New Jer…        0.335       0.693     0.22  0.282 0.219
6 JNJ    John… New Jer…        0.338       0.697     0.23  0.286 0.229
7 JNJ    John… New Jer…        0.317       0.667     0.017 0.243 0.019
8 JNJ    John… New Jer…        0.318       0.668     0.188 0.233 0.244
# … with 1 more variable: year <dbl>

Use left_join to combine the rows and columns of drug_cos_subset with the columns of health_cos
Assign the output to combo_df

  combo_df <- drug_cos_subset  %>% 
  left_join(health_cos)

Display combo_df

combo_df

# A tibble: 8 × 17
  ticker name  location ebitdamargin grossmargin netmargin   ros   roe
  <chr>  <chr> <chr>           <dbl>       <dbl>     <dbl> <dbl> <dbl>
1 JNJ    John… New Jer…        0.247       0.687     0.149 0.199 0.161
2 JNJ    John… New Jer…        0.272       0.678     0.161 0.218 0.173
3 JNJ    John… New Jer…        0.281       0.687     0.194 0.224 0.197
4 JNJ    John… New Jer…        0.336       0.694     0.22  0.284 0.217
5 JNJ    John… New Jer…        0.335       0.693     0.22  0.282 0.219
6 JNJ    John… New Jer…        0.338       0.697     0.23  0.286 0.229
7 JNJ    John… New Jer…        0.317       0.667     0.017 0.243 0.019
8 JNJ    John… New Jer…        0.318       0.668     0.188 0.233 0.244
# … with 9 more variables: year <dbl>, revenue <dbl>, gp <dbl>,
#   rnd <dbl>, netincome <dbl>, assets <dbl>, liabilities <dbl>,
#   marketcap <dbl>, industry <chr>

Note: the variables ticker, name, location and industry are the same for all the observations

Assign the company name to co_name

co_name  <- combo_df  %>% 
  distinct(name) %>% 
  pull()

Assign the company came to co_location

co_location  <- combo_df  %>% 
  distinct(location) %>% 
  pull()

Assign the industry to co_industry group

co_industry  <- combo_df  %>% 
  distinct(industry) %>% 
  pull()

Put the r inline commands used in the blanks below. When you knit the document the results of the commands will be displayed in your text. The company Johnson & Johnson is located in New Jersey; U.S.A and is a member of the Drug Manufacturers - General group.

Start with combo_df
Select variables (in this order): year, grossmargin, netmargin, revenue, gp, netincome
Assign the output to combo_df_subset

combo_df_subset  <- combo_df  %>% 
  select( year,  grossmargin,  netmargin, 
   revenue,  gp,  netincome)

Display combo_df_subset

combo_df_subset

# A tibble: 8 × 6
   year grossmargin netmargin     revenue          gp   netincome
  <dbl>       <dbl>     <dbl>       <dbl>       <dbl>       <dbl>
1  2011       0.687     0.149 65030000000 44670000000  9672000000
2  2012       0.678     0.161 67224000000 45566000000 10853000000
3  2013       0.687     0.194 71312000000 48970000000 13831000000
4  2014       0.694     0.22  74331000000 51585000000 16323000000
5  2015       0.693     0.22  70074000000 48538000000 15409000000
6  2016       0.697     0.23  71890000000 50101000000 16540000000
7  2017       0.667     0.017 76450000000 51011000000  1300000000
8  2018       0.668     0.188 81581000000 54490000000 15297000000

Create the variable grossmargin_check to compare with the variable grossmargin. They should be equal. grossmargin_check = gp / revenue
Create the variable close_enough to check that the absolute value of the difference between grossmargin_check and grossmargin is less than 0.001

combo_df_subset  %>% 
  mutate(grossmargin_check =  gp/ revenue,
  close_enough = abs(grossmargin_check - grossmargin) < 0.001)

# A tibble: 8 × 8
   year grossmargin netmargin     revenue          gp   netincome
  <dbl>       <dbl>     <dbl>       <dbl>       <dbl>       <dbl>
1  2011       0.687     0.149 65030000000 44670000000  9672000000
2  2012       0.678     0.161 67224000000 45566000000 10853000000
3  2013       0.687     0.194 71312000000 48970000000 13831000000
4  2014       0.694     0.22  74331000000 51585000000 16323000000
5  2015       0.693     0.22  70074000000 48538000000 15409000000
6  2016       0.697     0.23  71890000000 50101000000 16540000000
7  2017       0.667     0.017 76450000000 51011000000  1300000000
8  2018       0.668     0.188 81581000000 54490000000 15297000000
# … with 2 more variables: grossmargin_check <dbl>,
#   close_enough <lgl>

Create the variable netmargin_check to compare with the variable netmargin. They should be equal.
Create the variable close_enough to check that the absolute value of the difference between netmargin_check and netmargin is less than 0.001

combo_df_subset %>% 
   mutate(netmargin_check =  netmargin /revenue,
  close_enough =  abs(netmargin_check - netmargin) < 0.001)

# A tibble: 8 × 8
   year grossmargin netmargin     revenue          gp   netincome
  <dbl>       <dbl>     <dbl>       <dbl>       <dbl>       <dbl>
1  2011       0.687     0.149 65030000000 44670000000  9672000000
2  2012       0.678     0.161 67224000000 45566000000 10853000000
3  2013       0.687     0.194 71312000000 48970000000 13831000000
4  2014       0.694     0.22  74331000000 51585000000 16323000000
5  2015       0.693     0.22  70074000000 48538000000 15409000000
6  2016       0.697     0.23  71890000000 50101000000 16540000000
7  2017       0.667     0.017 76450000000 51011000000  1300000000
8  2018       0.668     0.188 81581000000 54490000000 15297000000
# … with 2 more variables: netmargin_check <dbl>, close_enough <lgl>

Question: summarize_industry

Fill in the blanks
Fill in the blanks
Put the command you use in the Rchunks in the Rmd file for this quiz
Use the health_cos data
For each industry calculate
- mean_grossmargin_percent = mean(gp / revenue) * 100
- median_grossmargin_percent = median(gp / revenue) * 100
- min_grossmargin_percent = min(gp / revenue) * 100
- max_grossmargin_percent = max(gp / revenue) * 100

health_cos  %>% 
  group_by(industry)  %>% 
  summarize(mean_grossmargin_percent = mean(gp/revenue) * 100,
            median_grossmargin_percent = median(gp/revenue) *100,
            min_grossmargin_percent = min(gp/revenue) *100, 
            max_grossmargin_percent =max(gp/revenue) * 100)

# A tibble: 9 × 5
  industry          mean_grossmargi… median_grossmar… min_grossmargin…
  <chr>                        <dbl>            <dbl>            <dbl>
1 Biotechnology                 92.5            92.7             81.7 
2 Diagnostics & Re…             50.5            52.7             28.0 
3 Drug Manufacture…             75.4            76.4             36.8 
4 Drug Manufacture…             47.9            42.6             34.3 
5 Healthcare Plans              20.5            19.6             10.0 
6 Medical Care Fac…             55.9            37.4             28.1 
7 Medical Devices               70.8            72.0             53.2 
8 Medical Distribu…             10.4             5.38             2.49
9 Medical Instrume…             53.9            52.8             40.5 
# … with 1 more variable: max_grossmargin_percent <dbl>

mean_grossmargin_percent for the industry Medical Devices is 70.8%
median_grossmargin_percent for the industry Medical Devices is 72.0%
min_grossmargin_percent for the industry Medical Devices is 53.2%
max_grossmargin_percent for the industry Medical Devices is 84.7%

Question: inline_ticker

Fill in the blanks
Use the health_cos data
Extract observations for the ticker BMY from health_cos and assign to the variable health_cos_subset

health_cos_subset  <- health_cos  %>% 
  filter(ticker == "BMY")

Display health_cos_subset

health_cos_subset

# A tibble: 8 × 11
  ticker name     revenue      gp    rnd netincome  assets liabilities
  <chr>  <chr>      <dbl>   <dbl>  <dbl>     <dbl>   <dbl>       <dbl>
1 BMY    Bristol… 2.12e10 1.56e10 3.84e9    3.71e9 3.30e10 17103000000
2 BMY    Bristol… 1.76e10 1.30e10 3.90e9    1.96e9 3.59e10 22259000000
3 BMY    Bristol… 1.64e10 1.18e10 3.73e9    2.56e9 3.86e10 23356000000
4 BMY    Bristol… 1.59e10 1.19e10 4.53e9    2.00e9 3.37e10 18766000000
5 BMY    Bristol… 1.66e10 1.27e10 5.92e9    1.56e9 3.17e10 17324000000
6 BMY    Bristol… 1.94e10 1.45e10 5.01e9    4.46e9 3.37e10 17360000000
7 BMY    Bristol… 2.08e10 1.47e10 6.48e9    1.01e9 3.36e10 21704000000
8 BMY    Bristol… 2.26e10 1.60e10 6.34e9    4.92e9 3.50e10 20859000000
# … with 3 more variables: marketcap <dbl>, year <dbl>,
#   industry <chr>

In the console, type ?distinct. Go to the help pane to see what distinct does
In the console, type ?pull. Go to the help pane to see what pull does

Run the code below

health_cos_subset  %>% 
  distinct(name) %>%  
  pull(name)

[1] "Bristol Myers Squibb Co"

Assign the output to co_name

co_name  <- health_cos_subset  %>% 
  distinct(name) %>% 
  pull(name)

You can take output from your code and include it in your text.

The name of the company with ticker BMY is Bristol Myers Squibb Co

In following chuck

Assign the company’s industry group to the variable co_industry

co_industry  <- health_cos_subset  %>% 
  distinct(industry) %>% 
  pull(industry)

This is outside the R chunk. Put the r inline commands used in the blanks below. When you knit the document the results of the commands will be displayed in your text.

The company Bristol Myers Squibb Co is a member of the Drug Manufacturers - General group.

Steps 7-11

start with health_cos THEN
group_by industry THEN
calculate the median research and development expenditure as a percent of revenue by industry
assign the output to df

df <- health_cos  %>% 
  group_by(industry)  %>%
  summarize(med_rnd_rev = median(rnd/revenue))

Use glimpse to glimpse the data for the plots

df  %>% glimpse()

Rows: 9
Columns: 2
$ industry    <chr> "Biotechnology", "Diagnostics & Research", "Drug…
$ med_rnd_rev <dbl> 0.48317287, 0.05620271, 0.17451442, 0.06851879, …

9.Create a static bar chart

use ggplot to initialize the chart
data is df
the variable industry is mapped to the x-axis -reorder it based the value of med_rnd_rev
the variable med_rnd_rev is mapped to the y-axis
add a bar chart using geom_col
use scale_y_continuous to label the y-axis with percent
use coord_flip() to flip the coordinates
use labs to add title, subtitle and remove x and y-axes
use theme_classic() from the hrbrthemes package to improve the theme

ggplot(data = df, 
       mapping = aes(
         x = reorder(industry, med_rnd_rev ),
         y = med_rnd_rev
         )) +
  geom_col() + 
  scale_y_continuous(labels = scales::percent) +
  coord_flip() +
  labs(
    title = "Median R&D expenditures",
    subtitle = "by industry as a percent of revenue from 2011 to 2018",
    x = NULL, y = NULL) +
  theme_classic()

Save the previous plot to preview.png and add to the yaml chunk at the top

ggsave(filename = "preview.png", 
       path = here::here("_posts", "2022-03-07-joining-data"))

11.Create an interactive bar chart using the package echarts4r

start with the data df
use arrange to reorder med_rnd_rev
use e_charts to initialize a chart
- the variable industry is mapped to the x-axis
add a bar chart using e_bar with the values of med_rnd_rev
use e_flip_coords() to flip the coordinates
use e_title to add the title and the subtitle
use e_legend to remove the legends
use e_x_axis to change format of labels on x-axis to percent
use e_y_axis to remove labels on y-axis-
use e_theme to change the theme. Find more themes here

df  %>% 
  arrange(med_rnd_rev)  %>%
  e_charts(
    x = industry
    )  %>% 
  e_bar(
    serie = med_rnd_rev, 
    name = "median"
    )  %>%
  e_flip_coords()  %>% 
  e_tooltip()  %>% 
  e_title(
    text = "Median industry R&D expenditures", 
    subtext = "by industry as a percent of revenue from 2011 to 2018",
    left = "center") %>% 
  e_legend(FALSE) %>% 
  e_x_axis(
    formatter = e_axis_formatter("percent", digits = 0)
    )  %>%
  e_y_axis(
    show = FALSE
  )  %>% 
  e_theme("infographic")

Joining data

Steps 1-6

Question: join_ticker

Question: summarize_industry

Question: inline_ticker

Steps 7-11