# Metric
The evaluation metric for this competition is [Accuracy]( https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification) – the number of correct predictions divided by the number of all predictions.

# Submission format
You should submit a csv file with the same number of rows + header row as in test.csv file. For every row in the test data, submission files should contain two columns: ``id`` (representing the id of the museum object) and ``type`` (representing the **type** of the object). Example format:

``id, type``

``2652198, foto``

``3851731, kiri``

``Etc.``

In the example above, we say that object with id **2652198** has a type **foto**. All unique types are described in ``unique_types.csv`` (read more under data section).