The training dataset includes two files. 

The train_label.csv file contains columns Recipe_ID and Cuisine. Recipe_ID is the ID of the recipe and Cuisine is the name of the regional cuisine to which the recipe belongs. Recipe_ID and Cuisine have one-to-one mapping. 

The train_features.csv file contains columns Recipe_ID, Ingredient_ID, state, quantity, unit. Here Recipe_ID is the ID of the recipe and rest of the columns contain detailed information of the ingredients used in this recipe. Recipe_ID and other columns have one-to-many mappings. 

Test dataset includes test_features.csv file which contains the following columns: Recipe_ID, Ingredient_ID, state, quantity, unit. Here Recipe_ID is the ID of the recipe and rest of the columns contain detailed information of the ingredients used in this recipe. Recipe_ID and other columns have one-to-many mappings.
 
You are expected to generate a submission file with two columns: Recipe_ID and Cuisine. Here Recipe_ID should have all the unique values of recipe IDs in test dataset and Cuisine should have the predicted regional cuisine of the corresponding recipe.

## Data Source
This dataset is part of the Complex Systems Laboratory's (IIIT-Delhi) Computational Gastronomy repository. URL: https://cosylab.iiitd.edu.in/