User Tools

Site Tools


Difference between cookies, pastries and pizzas

Source of data

Food Network (, compiled by the user everest4ever on

Description of the dataset

From the online description: “I scraped 1931 recipes from the Food Network that contain the keywords cookies (my group of interest), pastry, or pizza (two control groups). Next I extracted the ingredient list and pooled similar ingredients together (e.g. salt, seasalt, Kosher salt), coming up with a total of 133 unique ingredients. I ended up with a 1931×133 matrix, where each row is one recipe, and each column is whether this recipe contains a certain ingredient (0 or 1).”

Ingredients contain 133 items, from almonds, anchovies, anise and apples to tomatoes, tortillas, vinegar, wine or zucchini.


Global (perhaps, given the variety of cooking recipes the Food Network website contains)

Environmental variables

Name of variable Description
type_of_food A factor with three levels: Cookies, Pastries vs Pizzas

Data for download

File name File type Description
cookies-pastry-pizza dataset (everest4ever).xlsx Excel file Contains Recipes × ingredients matrix, assignment of recipes to food type, and metadata
cookie_dataset_everest4ever_composition.txt tab-delimited txt format Recipes × ingredients matrix (1931 recipes in rows, 133 ingredients in columns)
cookie_dataset_everest4ever_type.txt tab-delimited txt format Type of food (a single column with 1931 rows, values: Cookies/Pastries'/Pizzas'')

Compositional and environmental data (for all species)

recipes.ingr <- read.delim ('', row.names = 1)
recipes.type <- read.delim ('', row.names = 1)


en/data/cookies-pastry-pizza.txt · Last modified: 2018/05/10 06:47 by David Zelený

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki