Import data
# excel file
data <- read_excel("../00_data/myData.xlsx")
data
## # A tibble: 1,430 × 4
## country food_category consumption co2_emmission
## <chr> <chr> <dbl> <dbl>
## 1 Argentina Pork 10.5 37.2
## 2 Argentina Poultry 38.7 41.5
## 3 Argentina Beef 55.5 1712
## 4 Argentina Lamb & Goat 1.56 54.6
## 5 Argentina Fish 4.36 6.96
## 6 Argentina Eggs 11.4 10.5
## 7 Argentina Milk - inc. cheese 195. 278.
## 8 Argentina Wheat and Wheat Products 103. 19.7
## 9 Argentina Rice 8.77 11.2
## 10 Argentina Soybeans 0 0
## # ℹ 1,420 more rows
Apply the following dplyr verbs to your data
Filter rows
filter(data, country == "Japan")
## # A tibble: 11 × 4
## country food_category consumption co2_emmission
## <chr> <chr> <dbl> <dbl>
## 1 Japan Pork 20.6 73.0
## 2 Japan Poultry 19.4 20.9
## 3 Japan Beef 9.15 282.
## 4 Japan Lamb & Goat 0.14 4.9
## 5 Japan Fish 31.1 49.7
## 6 Japan Eggs 19.2 17.6
## 7 Japan Milk - inc. cheese 72.1 103.
## 8 Japan Wheat and Wheat Products 45.0 8.59
## 9 Japan Rice 59.8 76.6
## 10 Japan Soybeans 7.34 3.3
## 11 Japan Nuts inc. Peanut Butter 2.59 4.58
Arrange rows
arrange(data, consumption)
## # A tibble: 1,430 × 4
## country food_category consumption co2_emmission
## <chr> <chr> <dbl> <dbl>
## 1 Argentina Soybeans 0 0
## 2 Albania Soybeans 0 0
## 3 Kuwait Pork 0 0
## 4 Armenia Soybeans 0 0
## 5 Venezuela Soybeans 0 0
## 6 Croatia Soybeans 0 0
## 7 Paraguay Soybeans 0 0
## 8 Ecuador Soybeans 0 0
## 9 Serbia Soybeans 0 0
## 10 United Arab Emirates Pork 0 0
## # ℹ 1,420 more rows
Select columns
select(data, country, co2_emmission)
## # A tibble: 1,430 × 2
## country co2_emmission
## <chr> <dbl>
## 1 Argentina 37.2
## 2 Argentina 41.5
## 3 Argentina 1712
## 4 Argentina 54.6
## 5 Argentina 6.96
## 6 Argentina 10.5
## 7 Argentina 278.
## 8 Argentina 19.7
## 9 Argentina 11.2
## 10 Argentina 0
## # ℹ 1,420 more rows
Add columns
# Approximate amount of kg of CO2 emitted per kg of food consumed
mutate(data,
kg = co2_emmission / consumption)
## # A tibble: 1,430 × 5
## country food_category consumption co2_emmission kg
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Argentina Pork 10.5 37.2 3.54
## 2 Argentina Poultry 38.7 41.5 1.07
## 3 Argentina Beef 55.5 1712 30.9
## 4 Argentina Lamb & Goat 1.56 54.6 35.0
## 5 Argentina Fish 4.36 6.96 1.60
## 6 Argentina Eggs 11.4 10.5 0.918
## 7 Argentina Milk - inc. cheese 195. 278. 1.42
## 8 Argentina Wheat and Wheat Products 103. 19.7 0.191
## 9 Argentina Rice 8.77 11.2 1.28
## 10 Argentina Soybeans 0 0 NaN
## # ℹ 1,420 more rows
Summarize by groups
data %>%
#group by food_category
group_by(food_category) %>%
#Calculate average consumption
summarise(avg_consumption = mean(consumption, na.rm = TRUE)) %>%
ungroup()
## # A tibble: 11 × 2
## food_category avg_consumption
## <chr> <dbl>
## 1 Beef 12.1
## 2 Eggs 8.16
## 3 Fish 17.3
## 4 Lamb & Goat 2.60
## 5 Milk - inc. cheese 126.
## 6 Nuts inc. Peanut Butter 4.14
## 7 Pork 16.1
## 8 Poultry 21.2
## 9 Rice 29.4
## 10 Soybeans 0.861
## 11 Wheat and Wheat Products 71.5