A Beginner's Struggle with ROCKET Model Prediction

[14294302]

Dear author,

I am a newcomer to machine learning, and I followed the tutorial in 'tutorial_nbs/02_ROCKET_a_new_SOTA_classifier.ipynb' to run the ROCKET model, achieving excellent results. However, I am unsure of how to make predictions using 'learn' because the 'Xtrain' and 'Ytrain' in this tutorial seem different from my previous training data. Could you please provide more detailed instructions on how to use the ROCKET model for predicting 'Xtrain'? Thank you.

[MOREDataset]

I couldn't understand the problem but there are multiple tutorials about how to use different models for prediction.

…

On Thu, Sep 7, 2023, 10:05 AM 14294302 ***@***.***> wrote: Dear author, I am a newcomer to machine learning, and I followed the tutorial in 'tutorial_nbs/02_ROCKET_a_new_SOTA_classifier.ipynb' to run the ROCKET model, achieving excellent results. However, I am unsure of how to make predictions using 'learn' because the 'Xtrain' and 'Ytrain' in this tutorial seem different from my previous training data. Could you please provide more detailed instructions on how to use the ROCKET model for predicting 'Xtrain'? Thank you. — Reply to this email directly, view it on GitHub <#834>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ADK3KUAYXAIHPU3WPHDTOH3XZHPFNANCNFSM6AAAAAA4PBSTWM> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[14294302]

In 02_ROCKET_a_new_SOTA_classifier I use the follow code in it

f_mean = X_train.mean(axis=0, keepdims=True)
f_std = X_train.std(axis=0, keepdims=True) + eps
X_train_norm = (X_train - f_mean) / f_std
X_valid_norm = (X_valid - f_mean) / f_std
...
classifier.fit(X_train_norm, y_train)
preds = classifier.predict(X_valid_norm)

it tell me :
XGBoostError: [18:44:43] C:\buildkite-agent\builds\buildkite-windows-cpu-autoscaling-group-i-0fdc6d574b9c0d168-1\xgboost\xgboost-ci-windows\src\c_api\c_api_utils.h:167: Invalid missing value: null

then I use the code in previous tutorial:
probas, _, preds = learn.get_X_preds(X)

it tell me:
RuntimeError: mat1 and mat2 shapes cannot be multiplied (64x10005 and 20000x5)