Missing eras in tournament data

With the announcement of Validation data - 2 it was mentioned that test eras 854-899 were being replaced by val eras 197-206. However in the downloaded tournament data file test eras 853 and 900 are not present. Am I missing something here?

This is just a difference between the time it was announced vs the implementation by the time I finished testing and launched, you’re not missing anything

AttributeError Traceback (most recent call last)
in ()
1 # create a model and fit the training data (~30 sec to run)
2 model = sklearn.linear_model.LinearRegression()
----> 3 model.fit(training_features, training_data.target_kazutsugi)

/usr/local/lib/python3.6/dist-packages/pandas/core/generic.py in getattr(self, name)
5137 if self._info_axis._can_hold_identifiers_and_holds_name(name):
5138 return self[name]
-> 5139 return object.getattribute(self, name)
5141 def setattr(self, name: str, value) -> None:

AttributeError: ‘DataFrame’ object has no attribute ‘target_kazutsugi’

I think you’re behind on your announcements. The dataset this week has lost some test eras and added some validation eras. And we are using the new nomi target for scoring as of this round.

need more detail, please
i’m used https://colab.research.google.com/github/numerai/example-scripts/blob/master/making-your-first-submission-on-numerai.ipynb#scrollTo=WeAIJHaoW3VU

There is a new target:

So no more kazutsgui.

6 new validation eras have been added this week. At the same time, test eras 901-926 have been removed (they cover the same period).

Are you on rocketchat? See:

If you are just finding out about this now, I’m not sure what has to be adjusted in your pipeline, etc, but there are changes!