Skip to content

Error running the example notebook  #1

@HadiKutabi

Description

@HadiKutabi

Hello,

Im trying to run the code in "dswizard/scripts/example.ipynb".

I'm getting an error right after I run:

master = Master(
    ds=ds,
    working_directory=os.path.join(log_dir, str(task)),
    n_workers=2,
    model='/home/jovyan/dswizard/assets/rf_complete.pkl',
    wallclock_limit=wallclock_limit,
    cutoff=cutoff
)
pipeline, run_history, ensemble = master.optimize()

Error:

/home/hadi/Desktop/diwizard/venv/bin/python /home/hadi/Desktop/diwizard/1_optimize.py 
/home/hadi/Desktop/diwizard/venv/lib/python3.8/site-packages/dswizard/optimizers/config_generators/__init__.py:9: UserWarning: SMAC not installed
  warnings.warn("SMAC not installed")
2023-01-29 13:25:03,555 INFO     root            MainThread Processing task 146606
2023-01-29 13:25:03,621 INFO     openml.config   MainThread No config file found at /home/hadi/.config/openml/config, using default configuration.
2023-01-29 13:25:03,677 INFO     openml.datasets.dataset MainThread pickle load data higgs
2023-01-29 13:25:03,718 DEBUG    Meta-Features   MainThread Calculating MF
2023-01-29 13:25:07,741 DEBUG    Meta-Features   MainThread Calculating MF
2023-01-29 13:25:09,500 INFO     Structure       Thread-5   Loading transfer model from rf_complete.pkl
2023-01-29 13:25:10,298 INFO     Worker          MainThread Running on hadi with pid 32166
2023-01-29 13:25:10,299 INFO     Worker          MainThread Running on hadi with pid 32166
2023-01-29 13:25:10,321 INFO     Master          MainThread starting run at 2023-01-29 13:25:10. Configuration:
	wallclock_limit: 60
	cutoff: 10
	pre_sample: False
2023-01-29 13:25:10,321 DEBUG    Dispatcher      MainThread Waiting for all workers to finish current work. 0 / 2 busy...
2023-01-29 13:25:10,321 INFO     Master          MainThread Starting repetition 0
2023-01-29 13:25:10,370 DEBUG    Dispatcher      MainThread Processing job (0, 0, None)
2023-01-29 13:25:10,397 DEBUG    Structure       NoDaemonPoolWorker-4 	Selecting Root
2023-01-29 13:25:10,413 DEBUG    Structure       NoDaemonPoolWorker-4 	Expanding with dswizard.components.feature_preprocessing.variance_threshold.VarianceThresholdComponent. Option 1/10
2023-01-29 13:25:10,433 INFO     Worker          NoDaemonPoolWorker-4 start transforming job (0, 0, '0_variance_threshold')
2023-01-29 13:25:10,621 DEBUG    Meta-Features   NoDaemonPoolWorker-4 Calculating MF
2023-01-29 13:25:11,358 DEBUG    Dispatcher      MainThread Processing job (0, 1, None)
2023-01-29 13:25:11,388 DEBUG    Structure       NoDaemonPoolWorker-5 	Selecting Root
2023-01-29 13:25:11,401 DEBUG    Structure       NoDaemonPoolWorker-5 	Expanding with dswizard.components.data_preprocessing.standard_scaler.StandardScalerComponent. Option 2/10
2023-01-29 13:25:11,421 INFO     Worker          NoDaemonPoolWorker-5 start transforming job (0, 1, '0_standard_scaler')
2023-01-29 13:25:11,559 DEBUG    Meta-Features   NoDaemonPoolWorker-5 Calculating MF
2023-01-29 13:25:12,323 DEBUG    Dispatcher      MainThread waiting for next worker to be available
2023-01-29 13:25:14,938 ERROR    Dispatcher      MainThread Unhandled exception during job processing: Unknown Distance Metric: wminkowski
Traceback (most recent call last):
  File "/home/hadi/Desktop/diwizard/venv/lib/python3.8/site-packages/dswizard/core/dispatcher.py", line 100, in _process_job
    cs = self.structure_generator.fill_candidate(job.cs, job.ds, cutoff=job.cutoff, worker=worker)
  File "<string>", line 2, in fill_candidate
  File "/usr/lib/python3.8/multiprocessing/managers.py", line 850, in _callmethod
    raise convert_to_error(kind, result)
ValueError: Unknown Distance Metric: wminkowski
2023-01-29 13:25:14,944 DEBUG    Master          Thread-3   Structure callback (0, 0, None)
2023-01-29 13:25:14,944 WARNING  Master          Thread-3   Encountered job without a structure. Using simple best-practice pipeline.
2023-01-29 13:25:14,947 CRITICAL Master          Thread-3   Encountered unhandled exception Unknown Distance Metric: wminkowski. This should never happen!
Traceback (most recent call last):
  File "/home/hadi/Desktop/diwizard/venv/lib/python3.8/site-packages/dswizard/core/master.py", line 388, in _structure_callback
    cs = FixedStructure(steps=[('ohe', OneHotEncoderComponent()),
  File "/home/hadi/Desktop/diwizard/venv/lib/python3.8/site-packages/dswizard/optimizers/structure_generators/fixed.py", line 20, in fill_candidate
    key = self.cfg_cache.get_config_key(configspace=task.get_hyperparameter_search_space(),
  File "<string>", line 2, in get_config_key
  File "/usr/lib/python3.8/multiprocessing/managers.py", line 850, in _callmethod
    raise convert_to_error(kind, result)
ValueError: Unknown Distance Metric: wminkowski
2023-01-29 13:25:14,982 DEBUG    Dispatcher      MainThread Processing job (0, 2, None)
2023-01-29 13:25:15,024 DEBUG    Structure       NoDaemonPoolWorker-4 	Selecting Root
2023-01-29 13:25:15,034 DEBUG    Structure       NoDaemonPoolWorker-4 	Expanding with dswizard.components.data_preprocessing.knn_imputer.KNNImputerComponent. Option 3/10
2023-01-29 13:25:15,054 INFO     Worker          NoDaemonPoolWorker-4 start transforming job (0, 2, '0_knn_imputer')
2023-01-29 13:25:15,388 DEBUG    Meta-Features   NoDaemonPoolWorker-4 Calculating MF
2023-01-29 13:25:15,949 DEBUG    Dispatcher      MainThread waiting for next worker to be available
2023-01-29 13:25:16,029 ERROR    Dispatcher      MainThread Unhandled exception during job processing: Unknown Distance Metric: wminkowski

Can somebody assist me in understanding what is happening?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions