Coffee Data Exploration

Understanding coffee production and consumption across the world.
tidytuesday
Author

Ted Laderas

Published

July 8, 2020

What was your dataset?

Load your dataset in with the function below. The input is the date the dataset was issued. You should be able to get this from the tt_available() function.

coffee <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-07-07/coffee_ratings.csv')
Rows: 1339 Columns: 43
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (24): species, owner, country_of_origin, farm_name, lot_number, mill, ic...
dbl (19): total_cup_points, number_of_bags, aroma, flavor, aftertaste, acidi...

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

What was your question?

Given your inital exploration of the data, what was the question you wanted to answer?

Does processing method affect overall coffee rating?

Initial Skim of Data

skimr::skim(coffee)
Data summary
Name coffee
Number of rows 1339
Number of columns 43
_______________________
Column type frequency:
character 24
numeric 19
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
species 0 1.00 7 7 0 2 0
owner 7 0.99 3 50 0 315 0
country_of_origin 1 1.00 4 28 0 36 0
farm_name 359 0.73 1 73 0 571 0
lot_number 1063 0.21 1 71 0 227 0
mill 315 0.76 1 77 0 460 0
ico_number 151 0.89 1 40 0 847 0
company 209 0.84 3 73 0 281 0
altitude 226 0.83 1 41 0 396 0
region 59 0.96 2 76 0 356 0
producer 231 0.83 1 100 0 691 0
bag_weight 0 1.00 1 8 0 56 0
in_country_partner 0 1.00 7 85 0 27 0
harvest_year 47 0.96 3 24 0 46 0
grading_date 0 1.00 13 20 0 567 0
owner_1 7 0.99 3 50 0 319 0
variety 226 0.83 4 21 0 29 0
processing_method 170 0.87 5 25 0 5 0
color 218 0.84 4 12 0 4 0
expiration 0 1.00 13 20 0 566 0
certification_body 0 1.00 7 85 0 26 0
certification_address 0 1.00 40 40 0 32 0
certification_contact 0 1.00 40 40 0 29 0
unit_of_measurement 0 1.00 1 2 0 2 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
total_cup_points 0 1.00 82.09 3.50 0 81.08 82.50 83.67 90.58 ▁▁▁▁▇
number_of_bags 0 1.00 154.18 129.99 0 14.00 175.00 275.00 1062.00 ▇▇▁▁▁
aroma 0 1.00 7.57 0.38 0 7.42 7.58 7.75 8.75 ▁▁▁▁▇
flavor 0 1.00 7.52 0.40 0 7.33 7.58 7.75 8.83 ▁▁▁▁▇
aftertaste 0 1.00 7.40 0.40 0 7.25 7.42 7.58 8.67 ▁▁▁▁▇
acidity 0 1.00 7.54 0.38 0 7.33 7.58 7.75 8.75 ▁▁▁▁▇
body 0 1.00 7.52 0.37 0 7.33 7.50 7.67 8.58 ▁▁▁▁▇
balance 0 1.00 7.52 0.41 0 7.33 7.50 7.75 8.75 ▁▁▁▁▇
uniformity 0 1.00 9.83 0.55 0 10.00 10.00 10.00 10.00 ▁▁▁▁▇
clean_cup 0 1.00 9.84 0.76 0 10.00 10.00 10.00 10.00 ▁▁▁▁▇
sweetness 0 1.00 9.86 0.62 0 10.00 10.00 10.00 10.00 ▁▁▁▁▇
cupper_points 0 1.00 7.50 0.47 0 7.25 7.50 7.75 10.00 ▁▁▁▇▁
moisture 0 1.00 0.09 0.05 0 0.09 0.11 0.12 0.28 ▃▇▅▁▁
category_one_defects 0 1.00 0.48 2.55 0 0.00 0.00 0.00 63.00 ▇▁▁▁▁
quakers 1 1.00 0.17 0.83 0 0.00 0.00 0.00 11.00 ▇▁▁▁▁
category_two_defects 0 1.00 3.56 5.31 0 0.00 2.00 4.00 55.00 ▇▁▁▁▁
altitude_low_meters 230 0.83 1750.71 8669.44 1 1100.00 1310.64 1600.00 190164.00 ▇▁▁▁▁
altitude_high_meters 230 0.83 1799.35 8668.81 1 1100.00 1350.00 1650.00 190164.00 ▇▁▁▁▁
altitude_mean_meters 230 0.83 1775.03 8668.63 1 1100.00 1310.64 1600.00 190164.00 ▇▁▁▁▁

Total Number of Samples Per Country

coffee %>%
  janitor::tabyl(country_of_origin) %>%
  arrange(desc(n)) %>%
  gt::gt()
country_of_origin n percent valid_percent
Mexico 236 0.176250934 0.1763826607
Colombia 183 0.136669156 0.1367713004
Guatemala 181 0.135175504 0.1352765321
Brazil 132 0.098581031 0.0986547085
Taiwan 75 0.056011949 0.0560538117
United States (Hawaii) 73 0.054518297 0.0545590433
Honduras 53 0.039581777 0.0396113602
Costa Rica 51 0.038088125 0.0381165919
Ethiopia 44 0.032860344 0.0328849028
Tanzania, United Republic Of 40 0.029873040 0.0298953662
Uganda 36 0.026885736 0.0269058296
Thailand 32 0.023898432 0.0239162930
Nicaragua 26 0.019417476 0.0194319880
Kenya 25 0.018670650 0.0186846039
El Salvador 21 0.015683346 0.0156950673
Indonesia 20 0.014936520 0.0149476831
China 16 0.011949216 0.0119581465
India 14 0.010455564 0.0104633782
Malawi 11 0.008215086 0.0082212257
Peru 10 0.007468260 0.0074738416
United States 10 0.007468260 0.0074738416
Myanmar 8 0.005974608 0.0059790732
Vietnam 8 0.005974608 0.0059790732
Haiti 6 0.004480956 0.0044843049
Philippines 5 0.003734130 0.0037369208
Panama 4 0.002987304 0.0029895366
United States (Puerto Rico) 4 0.002987304 0.0029895366
Ecuador 3 0.002240478 0.0022421525
Laos 3 0.002240478 0.0022421525
Burundi 2 0.001493652 0.0014947683
Cote d?Ivoire 1 0.000746826 0.0007473842
Japan 1 0.000746826 0.0007473842
Mauritius 1 0.000746826 0.0007473842
Papua New Guinea 1 0.000746826 0.0007473842
Rwanda 1 0.000746826 0.0007473842
Zambia 1 0.000746826 0.0007473842
NA 1 0.000746826 NA

Distribution of total_cup_points versus processing_method

ggplot(coffee) + 
  aes(y=total_cup_points, x=processing_method, fill=processing_method) +
  geom_boxplot() +
  theme(axis.text.x = element_text(angle=90, hjust = 1)) +
  coord_flip() 

Counts of Country of Origin versus Processing Method

coffee %>%
  mutate(country_of_origin= fct_rev(country_of_origin)) %>%
  ggplot() +
  aes(y=country_of_origin, x=processing_method, 
      color=processing_method) +
  geom_count() +
  theme(axis.text.x = element_text(angle=90))

Here’s a sortable table of the above table

library(reactable)
coffee %>%
  janitor::tabyl(country_of_origin, processing_method) %>%
  reactable::reactable()

Sorted Heatmap of scores by total_cup_points

coffee %>% mutate(sample_id = rownames(coffee)) %>%
  select(sample_id, country_of_origin, total_cup_points, aroma, flavor, acidity, body, balance, uniformity, clean_cup, sweetness, cupper_points)%>%
  pivot_longer(cols = c(aroma, flavor, acidity, body, balance, uniformity, clean_cup, sweetness, cupper_points), names_to="type", values_to="score") %>%
  mutate(sample_id = fct_reorder(sample_id, total_cup_points)) %>%
  ggplot() +
  aes(y=sample_id, x=type, fill=score) +
    geom_tile()

Bi-clustered Heatmap of Scores

library(heatmaply)
Loading required package: plotly

Attaching package: 'plotly'
The following object is masked from 'package:ggplot2':

    last_plot
The following object is masked from 'package:stats':

    filter
The following object is masked from 'package:graphics':

    layout
Loading required package: viridis
Loading required package: viridisLite

======================
Welcome to heatmaply version 1.2.1

Type citation('heatmaply') for how to cite the package.
Type ?heatmaply for the main documentation.

The github page is: https://github.com/talgalili/heatmaply/
Please submit your suggestions and bug-reports at: https://github.com/talgalili/heatmaply/issues
Or contact: <tal.galili@gmail.com>
======================
coffee %>% mutate(sample_id = rownames(coffee)) %>%
  select(aroma, flavor, acidity, body, balance, uniformity, clean_cup, sweetness, cupper_points) %>% heatmaply()
Warning in doTryCatch(return(expr), name, parentenv, handler): unable to load shared object '/Library/Frameworks/R.framework/Resources/modules//R_X11.so':
  dlopen(/Library/Frameworks/R.framework/Resources/modules//R_X11.so, 0x0006): Library not loaded: '/opt/X11/lib/libSM.6.dylib'
  Referenced from: '/Library/Frameworks/R.framework/Versions/4.1-arm64/Resources/modules/R_X11.so'
  Reason: tried: '/opt/X11/lib/libSM.6.dylib' (no such file), '/Library/Frameworks/R.framework/Resources/lib/libSM.6.dylib' (no such file), '/Library/Java/JavaVirtualMachines/zulu-11.jdk/Contents/Home/lib/server/libSM.6.dylib' (no such file)
Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.
`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.
`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.
`guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.