compare_models() function in pycaret "Unused keyword parameter: n_jobs during cuML estimator initialization" error

Question

I'm encountering issues while attempting to run a regression problem with hyperparameter tuning using Google Colab with GPU enabled. I've outlined the steps I've taken and the problem I'm facing.

Here are the steps I followed:

1. Enabled GPU on Google Colab.
2. Installed the pycaret library with the command !pip install pycaret[full] and restarted session afterwards.
3. Checked the installed version using import pycaret and print(pycaret.__version__) , which returned version 3.2.0.
4. Used pycaret.show_versions() to display system and library information (included at the end).
5. Checked the CUDA version with !nvcc --version, confirming version 11.8.
6. Installed cuML using !pip install --extra-index-url=https://pypi.nvidia.com cuml-cu11 and restarted session afterwards.
7. Checked cuML version with import cumland print(cuml.__version__), which returned version 23.10.00.

After loading data with pandas, I attempted to set up a regression model using:

from pycaret.regression import *

s = setup(data, target=target_column, session_id=109, preprocess=True, use_gpu=True,
           pca=True, normalize=True, polynomial_features=False, feature_selection=False,
           pca_components=0.95, normalize_method="zscore", fold=5, train_size=0.8)
best = compare_models(sort="MSE")

However, during the process, I encountered warnings and errors, such as:

[LightGBM] [Warning] There are no meaningful features which satisfy the provided configuration. Decreasing Dataset parameters min_data_in_bin or min_data_in_leaf and re-constructing Dataset might resolve this warning.
[LightGBM] [Info] This is the GPU trainer!!
[LightGBM] [Info] Total Bins 0
[LightGBM] [Info] Number of data points in the train set: 2, number of used features: 0
[LightGBM] [Warning] Using sparse features with CUDA is currently not supported.

Subsequently, the session crashes and restarts automatically with the message:

[I] [14:06:56.249093] Unused keyword parameter: n_jobs during cuML estimator initialization

pycaret.show_versions()has the following output:

System:
    python: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]
executable: /usr/bin/python3
   machine: Linux-5.15.120+-x86_64-with-glibc2.35

PyCaret required dependencies:
                 pip: 23.1.2
          setuptools: 67.7.2
             pycaret: 3.2.0
             IPython: 7.34.0
          ipywidgets: 7.7.1
                tqdm: 4.66.1
               numpy: 1.23.5
              pandas: 1.5.3
              jinja2: 3.1.2
               scipy: 1.10.1
              joblib: 1.3.2
             sklearn: 1.2.2
                pyod: 1.1.1
            imblearn: 0.10.1
   category_encoders: 2.6.3
            lightgbm: 4.1.0
               numba: 0.57.1
            requests: 2.31.0
          matplotlib: 3.6.0
          scikitplot: 0.3.7
         yellowbrick: 1.5
              plotly: 5.15.0
    plotly-resampler: Not installed
             kaleido: 0.2.1
           schemdraw: 0.15
         statsmodels: 0.14.0
              sktime: 0.21.1
               tbats: 1.1.3
            pmdarima: 2.0.4
              psutil: 5.9.5
          markupsafe: 2.1.3
             pickle5: Not installed
         cloudpickle: 2.2.1
         deprecation: 2.1.0
              xxhash: 3.4.1
           wurlitzer: 3.0.3

PyCaret optional dependencies:
                shap: 0.43.0
           interpret: 0.4.4
                umap: 0.5.4
     ydata_profiling: 4.6.0
  explainerdashboard: 0.4.3
             autoviz: Not installed
           fairlearn: 0.7.0
          deepchecks: Not installed
             xgboost: 2.0.1
            catboost: 1.2.2
              kmodes: 0.12.2
             mlxtend: 0.22.0
       statsforecast: 1.5.0
        tune_sklearn: 0.5.0
                 ray: 2.8.0
            hyperopt: 0.2.7
              optuna: 3.4.0
               skopt: 0.9.0
              mlflow: 1.30.1
              gradio: 3.50.2
             fastapi: 0.104.1
             uvicorn: 0.24.0.post1
              m2cgen: 0.10.0
           evidently: 0.2.8
               fugue: 0.8.6
           streamlit: Not installed
             prophet: 1.1.5

I have followed various instructions from GitHub and Stack Overflow but haven't been able to resolve this issue. I need to run this code on Colab due to the resource-intensive nature of hyperparameter tuning.

What might be causing this problem and how can I solve it?