CODEWITHSUNDEEP
pandasnumpyscikit-learnmodelnumpy-ndarray
Mert Türkyılmaz
Mert Türkyılmaz

Reputation: 138

ValueError: object of too small depth for desired array,

When i run the code below yesterday, it was working. But when i run this code today, i got this error. I think this problem originates to revise my data but when i try with old data, it still give same error. (I'm not sure about, is it related with data's shape but i want to show it.) Can someone help me?

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 0)

print("Shape of x_train :", x_train.shape)
print("Shape of x_test :", x_test.shape)
print("Shape of y_train :", y_train.shape)
print("Shape of y_test :", y_test.shape)

Shape of x_train : (257763, 96)
Shape of x_test : (64441, 96)
Shape of y_train : (257763,)
Shape of y_test : (64441,)

from imblearn.ensemble import BalancedRandomForestClassifier 


model = BalancedRandomForestClassifier(n_estimators = 200, random_state = 0, max_depth=6)
model.fit(x_train, y_train)

Full Error is below;

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-9-7698c432c37d> in <module>
  7 
  8 model = BalancedRandomForestClassifier(n_estimators = 200, random_state = 
0, max_depth=6)
----> 9 model.fit(x_train, y_train)
 10 y_pred_rf = model.predict(x_test)
 11 

  /opt/anaconda/envs/env_python/lib/python3.6/site- 
  packages/imblearn/ensemble/_forest.py in fit(self, X, y, sample_weight)
  433                         s, t, self, X, y, sample_weight, i, 
  len(trees),
  434                         verbose=self.verbose, 
  class_weight=self.class_weight)
  --> 435                     for i, (s, t) in enumerate(zip(samplers, 
  trees)))
  436             samplers, trees = zip(*samplers_trees)
  437 

  /opt/anaconda/envs/env_python/lib/python3.6/site- 
  packages/joblib/parallel.py 
  in __call__(self, iterable)
  919             # remaining jobs.
  920             self._iterating = False
  --> 921             if self.dispatch_one_batch(iterator):
  922                 self._iterating = self._original_iterator is not None
  923 

  /opt/anaconda/envs/env_python/lib/python3.6/site- 
  packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
   757                 return False
   758             else:
   --> 759                 self._dispatch(tasks)
   760                 return True
   761 

   /opt/anaconda/envs/env_python/lib/python3.6/site- 
   packages/joblib/parallel.py in _dispatch(self, batch)
   714         with self._lock:
   715             job_idx = len(self._jobs)
   --> 716             job = self._backend.apply_async(batch, callback=cb)
   717             # A job can complete so quickly than its callback is
   718             # called before we get here, causing self._jobs to

   /opt/anaconda/envs/env_python/lib/python3.6/site- 
   packages/joblib/_parallel_backends.py in apply_async(self, func, 
   callback)
   180     def apply_async(self, func, callback=None):
   181         """Schedule a func to be run"""
   --> 182         result = ImmediateResult(func)
   183         if callback:
   184             callback(result)

   /opt/anaconda/envs/env_python/lib/python3.6/site- 
   packages/joblib/_parallel_backends.py in __init__(self, batch)
   547         # Don't delay the application, to avoid keeping the input
   548         # arguments in memory
   --> 549         self.results = batch()
   550 
   551     def get(self):

   /opt/anaconda/envs/env_python/lib/python3.6/site- 
   packages/joblib/parallel.py in __call__(self)
   223         with parallel_backend(self._backend, n_jobs=self._n_jobs):
   224             return [func(*args, **kwargs)
   --> 225                     for func, args, kwargs in self.items]
   226 
   227     def __len__(self):

   /opt/anaconda/envs/env_python/lib/python3.6/site- 
   packages/joblib/parallel.py in <listcomp>(.0)
   223         with parallel_backend(self._backend, n_jobs=self._n_jobs):
   224             return [func(*args, **kwargs)
   --> 225                     for func, args, kwargs in self.items]
   226 
   227     def __len__(self):

   /opt/anaconda/envs/env_python/lib/python3.6/site- 
   packages/imblearn/ensemble/_forest.py in 
   _local_parallel_build_trees(sampler, tree, forest, X, y, sample_weight, 
   tree_idx, n_trees, verbose, class_weight)
   43     tree = _parallel_build_trees(tree, forest, X_resampled, 
   y_resampled,
   44                                  sample_weight, tree_idx, n_trees,
   ---> 45                                  verbose=verbose, 
  class_weight=class_weight)
  46     return sampler, tree
  47 

  /opt/anaconda/envs/env_python/lib/python3.6/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)
  153         indices = _generate_sample_indices(tree.random_state, 
  n_samples,
  154                                            n_samples_bootstrap)
  --> 155         sample_counts = np.bincount(indices, minlength=n_samples)
  156         curr_sample_weight *= sample_counts
  157 

  <__array_function__ internals> in bincount(*args, **kwargs)

  ValueError: object of too small depth for desired array

Upvotes: 2

Views: 5050

Answers (2)

joel thomas
joel thomas

Reputation: 1

One small hack is to install the latest version of python in Jupyter notebook (For me installing 3.7.4 worked). For the older version of python, the error is still persistent.

I have the same issue. I installed Jupyter notebook on my computer and the python version on my notebook is 3.7.4. BalancedRandomForestClassifier works totally fine. However, When I'm trying to run it on an older version say python 3.6. I'm experiencing the same glitch mentioned above.

My created feature (BoW) is an array with two dimensions as well.

array([[0, 0, 0, ..., 0, 0, 0],
       [0, 0, 0, ..., 0, 0, 0],
       [0, 0, 0, ..., 0, 0, 0],
       ...,
       [0, 0, 0, ..., 0, 0, 0],
       [0, 0, 0, ..., 0, 0, 0],
       [0, 0, 0, ..., 0, 0, 0]])

Jupyter notebook on my machine

Jupyter notebook on my Google Colab

Upvotes: 0

hpaulj
hpaulj

Reputation: 231510

According to the traceback the error is raised by bincount. This reproduces it:

In [13]: np.bincount(0)                                                                          
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-13-65825aeaf27a> in <module>
----> 1 np.bincount(0)

<__array_function__ internals> in bincount(*args, **kwargs)

ValueError: object of too small depth for desired array
In [14]: np.bincount(np.arange(5))                                                               
Out[14]: array([1, 1, 1, 1, 1])

bincount works with a 1d array; it raises this error if given a scalar.

Now work you way back through to traceback to figure out what variable in your code is a scalar when it should be an array.

Upvotes: 2

Related Questions