In case you're confused - challenge1 testing vs training data

[patrickmuston1]

EY Challenge 1 references two .csv files: challenge1_train.csv (129 rows) and challenge1_test.csv (5000 rows).
The catch is that challenge1_train.csv lists the linescans that are available, while challenge1_test.csv lists the coordinate pairs that are required to be evaluated by your model for testing.

You will notice that challenge1_test.csv contains a "label" column. There are five distinct labels here. These are the five linescans which you will be tested on, with 1000 coordinate pairs listed in each, for a total of 5000 rows.