File descriptions
train.csv
- the training set
Contains an
id
variable for a product, the features(variables)
x_1, ..., x_100
describing the products, each line/row being a single product. The class variable
y
contains the product class 1, 2, ..., 9. The classes and features have been anonymized to avoid advantages of background knowledge.
test.csv
- the test set
Contains an
id
variable for a product, the features(variables)
x_1, ..., x_100
describing products, each line being a single product, similarly to the training set. Does not have the class variable
y
, which needs to be predicted for each product.