The goal of animals is to provide a small dataset for text classification and regression tasks.
You can install the package with:
# install.packages("devtools")
devtools::install_github("EmilHvitfeldt/animals")
This package will most likely never be put on CRAN.
library(animals)
library(tibble)
glimpse(animals)
#> Rows: 610
#> Columns: 48
#> $ text <chr> "Aardvark Classification and Evolution\nAar…
#> $ colour <chr> "Brown, grey, yellow", "Fawn, Red, Blue, Gr…
#> $ lifespan <chr> "23 years", NA, "10 - 20 years", NA, NA, "6…
#> $ weight <chr> "60kg - 80kg (130lbs - 180lbs)", NA, "3kg -…
#> $ kingdom <chr> "Animalia", NA, "Animalia", NA, NA, "Animal…
#> $ class <chr> "Mammalia", NA, "Aves", NA, NA, "Mammalia",…
#> $ phylum <chr> "Chordata", NA, "Chordata", NA, NA, "Chorda…
#> $ diet <chr> "Omnivore", NA, "Carnivore", NA, NA, "Herbi…
#> $ conservation_status <chr> "Least Concern", NA, "Least Concern", NA, N…
#> $ order <chr> "Tubulidentata", NA, "Sphenisciformes", NA,…
#> $ scientific_name <chr> "Orycteropus afer", NA, "Pygoscelis adeliae…
#> $ skin_type <chr> "Hair", NA, "Feathers", NA, NA, "Leather", …
#> $ habitat <chr> "Sandy and clay soil", NA, "Antarctic land …
#> $ predators <chr> "Lions, Leopards, Hyenas", NA, "Leopard Sea…
#> $ family <chr> "Orycteropodidae", NA, "Spheniscidae", NA, …
#> $ lifestyle <chr> "Nocturnal", NA, "Diurnal", NA, NA, "Diurna…
#> $ average_litter_size <chr> "1", "6", NA, "3", "7", "1", "3", NA, "1", …
#> $ genus <chr> "Orycteropus", NA, "Pygoscelis", NA, NA, "L…
#> $ top_speed <chr> "40kph (25mph)", NA, "72kph (45mph)", NA, N…
#> $ favourite_food <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ main_prey <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ type <chr> NA, "Shorthair", NA, "Terrier", "Hound", NA…
#> $ common_name <chr> "Aardvark", "Abyssinian", "Adelie Penguin",…
#> $ group <chr> "Mammal", "Cat", "Bird", "Dog", "Dog", "Mam…
#> $ size <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ distinctive_features <chr> NA, "Silky fur and almond shaped eyes", NA,…
#> $ size_l <chr> "1.05m - 2.20m (3.4ft - 7.3ft)", NA, NA, NA…
#> $ origin <chr> NA, "Egypt", NA, "Germany", "Afghanistan", …
#> $ special_features <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
#> $ location <chr> "Sub-Saharan Africa", NA, "Coastal Antarcti…
#> $ number_of_species <chr> "18", NA, "1", NA, NA, "1", "1", "1", "1", …
#> $ average_clutch_size <chr> NA, NA, "2", NA, NA, NA, NA, NA, NA, NA, "2…
#> $ size_h <chr> NA, NA, "40cm - 75cm (16in - 30in)", NA, NA…
#> $ group_behaviour <chr> "Solitary", NA, "Colony", NA, NA, "Herd", "…
#> $ fun_fact <chr> "Can move up to 2ft of soil in just 15 seco…
#> $ age_of_sexual_maturity <chr> "2 years", NA, "2 - 3 years", NA, NA, "11 -…
#> $ name_of_young <chr> "Cub", NA, "Chicks", NA, NA, "Calf", "Pup",…
#> $ prey <chr> "Termites, Ants", NA, "Krill, Fish, Squid",…
#> $ estimated_population_size <chr> "Unknown", NA, "5 million", NA, NA, "300,00…
#> $ biggest_threat <chr> "Habitat loss", NA, "Rapid ice melt", NA, N…
#> $ average_lifespan <chr> NA, "15 years", NA, "12 years", "14 years",…
#> $ most_distinctive_feature <chr> "Long, sticky tongue and rabbit-like ears",…
#> $ other_name_s <chr> "Antbear, Earth Pig", NA, NA, NA, NA, "Afri…
#> $ gestation_period <chr> "7 months", NA, NA, NA, NA, "20 - 24 months…
#> $ age_of_weaning <chr> "3 months", NA, NA, NA, NA, "6 - 18 months"…
#> $ average_weight <chr> NA, "4.5kg (10lbs)", NA, "3.6kg (8lbs)", "2…
#> $ temperament <chr> NA, "Intelligent and curious", NA, "Alert a…
#> $ wingspan <chr> NA, NA, "35cm - 70cm (14in - 27.5in)", NA, …