Pranav Prajapati

Thanks for assigning the issue, I'll start working on it

@shivance thanks for the notebook but I think the notebook shares the pre-training approach of `ELECTRA` while I'm trying to implement the backbone of `ELECTRA` which is similar to `BERT`...

I have the test `test_neural_forecast_with_auto_freq` failing too locally with the error `FAILED sktime/forecasting/tests/test_neuralforecast.py::test_neural_forecast_with_auto_freq[NeuralForecastLSTM] - ValueError: Invalid frequency: YE-DEC, failed to parse with error message: ValueError("for Period, please use 'Y-DEC' instead...

> I have the test `test_neural_forecast_with_auto_freq` failing too locally with the error `FAILED sktime/forecasting/tests/test_neuralforecast.py::test_neural_forecast_with_auto_freq[NeuralForecastLSTM] - ValueError: Invalid frequency: YE-DEC, failed to parse with error message: ValueError("for Period, please use 'Y-DEC'...

The issue seems to be arising due to monkeylearn returning different JSON outputs for different monkeylearn classifiers. I'm unable to check all the classifiers on my free trial monkeylearn account

I'm unable to create a API key for monkeylearn to debug the code, I tried using my different gmail accounts. If you have a API key you can send it...

Hello I'm interested to work on this, quick question where can I save the trained model ?? as pytorch tabular will require training on data before prediction

Wait why is this issue open if it's already implemented , Ohk this was your fork. I will try working on this

updating the default config didn't worked for me I tried doing same mentioned above by @elephaint, accessing the dictionary keys and updating the values for `AutoLSTM`. Opening an issue regarding...

gotcha, why are docs of neuralforecast ahead of actual package. Cause I was. trying to implement this parameter after reading the docs