Issue when running auto_forecast() or tune_test_forecast() with rf

[jroy12345]

Here is the error. Typically I can rerun the codeblock in my notebook and after 1-2 tries it will fix itself.

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_3112\911625238.py in <module>
      3     j.ingest_grid(model)
      4     j.cross_validate(dynamic_tuning=26)
----> 5     j.auto_forecast()
      6     j.save_summary_stats()
      7     print(model)

~\AppData\Roaming\Python\Python37\site-packages\scalecast\Forecaster.py in auto_forecast(self, call_me, dynamic_testing, test_only)

~\AppData\Roaming\Python\Python37\site-packages\scalecast\Forecaster.py in manual_forecast(self, call_me, dynamic_testing, test_only, **kwargs)

~\AppData\Roaming\Python\Python37\site-packages\scalecast\Forecaster.py in _forecast_sklearn(self, fcster, dynamic_testing, tune, Xvars, normalizer, test_only, **kwargs)

~\AppData\Roaming\Python\Python37\site-packages\scalecast\Forecaster.py in evaluate_model(scaler, regr, X, y, Xvars, fcst_horizon, future_xreg, dynamic_testing, true_forecast)

~\Anaconda3\envs\time\lib\site-packages\sklearn\ensemble\_forest.py in fit(self, X, y, sample_weight)
    465                     n_samples_bootstrap=n_samples_bootstrap,
    466                 )
--> 467                 for i, t in enumerate(trees)
    468             )
    469 

~\Anaconda3\envs\time\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
   1041             # remaining jobs.
   1042             self._iterating = False
-> 1043             if self.dispatch_one_batch(iterator):
   1044                 self._iterating = self._original_iterator is not None
   1045 

~\Anaconda3\envs\time\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
    859                 return False
    860             else:
--> 861                 self._dispatch(tasks)
    862                 return True
    863 

~\Anaconda3\envs\time\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
    777         with self._lock:
    778             job_idx = len(self._jobs)
--> 779             job = self._backend.apply_async(batch, callback=cb)
    780             # A job can complete so quickly than its callback is
    781             # called before we get here, causing self._jobs to

~\Anaconda3\envs\time\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback)
    206     def apply_async(self, func, callback=None):
    207         """Schedule a func to be run"""
--> 208         result = ImmediateResult(func)
    209         if callback:
    210             callback(result)

~\Anaconda3\envs\time\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch)
    570         # Don't delay the application, to avoid keeping the input
    571         # arguments in memory
--> 572         self.results = batch()
    573 
    574     def get(self):

~\Anaconda3\envs\time\lib\site-packages\joblib\parallel.py in __call__(self)
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
    262             return [func(*args, **kwargs)
--> 263                     for func, args, kwargs in self.items]
    264 
    265     def __reduce__(self):

~\Anaconda3\envs\time\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
    262             return [func(*args, **kwargs)
--> 263                     for func, args, kwargs in self.items]
    264 
    265     def __reduce__(self):

~\Anaconda3\envs\time\lib\site-packages\sklearn\utils\fixes.py in __call__(self, *args, **kwargs)
    214     def __call__(self, *args, **kwargs):
    215         with config_context(**self.config):
--> 216             return self.function(*args, **kwargs)
    217 
    218 

~\Anaconda3\envs\time\lib\site-packages\sklearn\ensemble\_forest.py in _parallel_build_trees(tree, forest, X, y, sample_weight, tree_idx, n_trees, verbose, class_weight, n_samples_bootstrap)
    171 
    172         indices = _generate_sample_indices(
--> 173             tree.random_state, n_samples, n_samples_bootstrap
    174         )
    175         sample_counts = np.bincount(indices, minlength=n_samples)

~\Anaconda3\envs\time\lib\site-packages\sklearn\ensemble\_forest.py in _generate_sample_indices(random_state, n_samples, n_samples_bootstrap)
    127 
    128     random_instance = check_random_state(random_state)
--> 129     sample_indices = random_instance.randint(0, n_samples, n_samples_bootstrap)
    130 
    131     return sample_indices

mtrand.pyx in numpy.random.mtrand.RandomState.randint()

_bounded_integers.pyx in numpy.random._bounded_integers._rand_int32()

TypeError: 'numpy.float64' object cannot be interpreted as an integer

[mikekeith52]

Could you please attach the grid you are using for the random forest model (or if it is the default grid, let me know), as well as the scikit-learn version you have installed?

[jroy12345]

rf default grid from GridGenerator.get_example_grids()

sklearn version '1.0.2'