Answers for Quiz 6. More dplr with our first interactive chart using echarts4r.
drug_cos.csv
, health_cos.csv
in to R and assign to the variables drug_cos
and health_cos
, respectivelyRows: 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,~
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~
names_drug <- drug_cos %>% names()
names_health <- health_cos %>% names()
intersect(names_drug, names_health)
[1] "ticker" "name" "year"
drug_subset
join with columns in health_subset
# A tibble: 13 x 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~
drug_cos_subset
# A tibble: 8 x 9
ticker name location ebitdamargin grossmargin netmargin ros roe
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
1 MYL Myla~ United ~ 0.245 0.418 0.088 0.161 0.146
2 MYL Myla~ United ~ 0.244 0.428 0.094 0.163 0.184
3 MYL Myla~ United ~ 0.228 0.44 0.09 0.153 0.209
4 MYL Myla~ United ~ 0.242 0.457 0.12 0.169 0.283
5 MYL Myla~ United ~ 0.243 0.447 0.09 0.133 0.089
6 MYL Myla~ United ~ 0.19 0.424 0.043 0.052 0.044
7 MYL Myla~ United ~ 0.272 0.402 0.058 0.121 0.054
8 MYL Myla~ United ~ 0.258 0.35 0.031 0.074 0.028
# ... with 1 more variable: year <dbl>
combo_df
# A tibble: 8 x 17
ticker name location ebitdamargin grossmargin netmargin ros roe
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
1 MYL Myla~ United ~ 0.245 0.418 0.088 0.161 0.146
2 MYL Myla~ United ~ 0.244 0.428 0.094 0.163 0.184
3 MYL Myla~ United ~ 0.228 0.44 0.09 0.153 0.209
4 MYL Myla~ United ~ 0.242 0.457 0.12 0.169 0.283
5 MYL Myla~ United ~ 0.243 0.447 0.09 0.133 0.089
6 MYL Myla~ United ~ 0.19 0.424 0.043 0.052 0.044
7 MYL Myla~ United ~ 0.272 0.402 0.058 0.121 0.054
8 MYL Myla~ United ~ 0.258 0.35 0.031 0.074 0.028
# ... with 9 more variables: year <dbl>, revenue <dbl>, gp <dbl>,
# rnd <dbl>, netincome <dbl>, assets <dbl>, liabilities <dbl>,
# marketcap <dbl>, industry <chr>
co_name
co_location
co_industry
groupPut 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 Mylan NV is located in United Kingdom and is a member of the Drug Manufacturers - Specialty & Generic industry group.
combo_df
combo_df_subset
combo_df_subset
# A tibble: 8 x 6
year grossmargin netmargin revenue gp netincome
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 2011 0.418 0.088 6129825000 2563364000 536810000
2 2012 0.428 0.094 6796100000 2908300000 640900000
3 2013 0.44 0.09 6909100000 3040300000 623700000
4 2014 0.457 0.12 7719600000 3528000000 929400000
5 2015 0.447 0.09 9429300000 4216100000 847600000
6 2016 0.424 0.043 11076900000 4697000000 480000000
7 2017 0.402 0.058 11907700000 4783100000 696000000
8 2018 0.35 0.031 11433900000 4001600000 352500000
combo_df_subset %>%
mutate(grossmargin_check = gp / revenue,
close_enough = abs(grossmargin_check - grossmargin) < 0.001)
# A tibble: 8 x 8
year grossmargin netmargin revenue gp netincome
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 2011 0.418 0.088 6129825000 2563364000 536810000
2 2012 0.428 0.094 6796100000 2908300000 640900000
3 2013 0.44 0.09 6909100000 3040300000 623700000
4 2014 0.457 0.12 7719600000 3528000000 929400000
5 2015 0.447 0.09 9429300000 4216100000 847600000
6 2016 0.424 0.043 11076900000 4697000000 480000000
7 2017 0.402 0.058 11907700000 4783100000 696000000
8 2018 0.35 0.031 11433900000 4001600000 352500000
# ... with 2 more variables: grossmargin_check <dbl>,
# close_enough <lgl>
netmargin_check
to compare with the variable netmargin. They should be equal.close_enough
to check that the absolute value of the difference between netmargin_check
and netmargin is less than 0.001combo_df_subset %>%
mutate(netmargin_check = netincome / revenue,
close_enough = abs(netmargin_check - netmargin) < 0.001)
# A tibble: 8 x 8
year grossmargin netmargin revenue gp netincome netmargin_check
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 2011 0.418 0.088 6.13e 9 2.56e9 536810000 0.0876
2 2012 0.428 0.094 6.80e 9 2.91e9 640900000 0.0943
3 2013 0.44 0.09 6.91e 9 3.04e9 623700000 0.0903
4 2014 0.457 0.12 7.72e 9 3.53e9 929400000 0.120
5 2015 0.447 0.09 9.43e 9 4.22e9 847600000 0.0899
6 2016 0.424 0.043 1.11e10 4.70e9 480000000 0.0433
7 2017 0.402 0.058 1.19e10 4.78e9 696000000 0.0584
8 2018 0.35 0.031 1.14e10 4.00e9 352500000 0.0308
# ... with 1 more variable: close_enough <lgl>
health_cos %>%
group_by(industry) %>%
summarize(mean_netmargin_percent = mean(netincome / revenue) * 100, median_netmargin_percent = median(netincome / revenue) * 100, min_netmargin = min(netincome / revenue) * 100, max_netmargin = max(netincome / revenue) * 100)
# A tibble: 9 x 5
industry mean_netmargin_~ median_netmargi~ min_netmargin
<chr> <dbl> <dbl> <dbl>
1 Biotechnology -4.66 7.62 -197.
2 Diagnostics & Resea~ 13.1 12.3 0.399
3 Drug Manufacturers ~ 19.4 19.5 -34.9
4 Drug Manufacturers ~ 5.88 9.01 -76.0
5 Healthcare Plans 3.28 3.37 -0.305
6 Medical Care Facili~ 6.10 6.46 1.40
7 Medical Devices 12.4 14.3 -56.1
8 Medical Distribution 1.70 1.03 -0.102
9 Medical Instruments~ 12.3 14.0 -47.1
# ... with 1 more variable: max_netmargin <dbl>
mean netmargin for the industry Medical Distribution is 1.7%
median netmargin for the industry Medical Distribution is 1.03%
minimun netmargin for the industry Medical Distribution is -0.102%
maximum netmargin for the industry Medical Distribution is 4.51%
health_cos_subset
health_cos_subset
# A tibble: 8 x 11
ticker name revenue gp rnd netincome assets liabilities
<chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 AMGN Amgen I~ 1.56e10 1.29e10 3.17e9 3.68e9 4.89e10 29842000000
2 AMGN Amgen I~ 1.73e10 1.41e10 3.38e9 4.34e9 5.43e10 35238000000
3 AMGN Amgen I~ 1.87e10 1.53e10 4.08e9 5.08e9 6.61e10 44029000000
4 AMGN Amgen I~ 2.01e10 1.56e10 4.30e9 5.16e9 6.90e10 43231000000
5 AMGN Amgen I~ 2.17e10 1.74e10 4.07e9 6.94e9 7.14e10 43366000000
6 AMGN Amgen I~ 2.30e10 1.88e10 3.84e9 7.72e9 7.76e10 47751000000
7 AMGN Amgen I~ 2.28e10 1.88e10 3.56e9 1.98e9 8.00e10 54713000000
8 AMGN Amgen I~ 2.37e10 1.96e10 3.74e9 8.39e9 6.64e10 53916000000
# ... with 3 more variables: marketcap <dbl>, year <dbl>,
# industry <chr>
Run the code below
Assign the output to co_name
You can take output from your code and include it in your text.
In following chunk
co_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 Amgen Inc is a member of the Drug Manufacturers - General group.
df
Rows: 9
Columns: 2
$ industry <chr> "Biotechnology", "Diagnostics & Research", "Drug~
$ med_rnd_rev <dbl> 0.48317287, 0.05620271, 0.17451442, 0.06851879, ~
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()
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("vintage")