Error when using GridSearchCV and RandomizedSearchCV - python-3.x

Question

When attempting to fit my training data using either GridSearchCV or RandomizedSearchCV, I keep getting the following error:
TypeError: no supported conversion for types: (dtype('O'), dtype('O'))
Here's a sample of the relevant code:
from xgboost.sklearn import XGBRegressor as XGR
from sklearn.model_selection import RandomizedSearchCV, GridSearchCV
xgbRegModel = XGR()
params = {'max_depth':[3, 6, 9], 'learning_rate':[.05, .1, .5], 'n_estimators': [50, 100, 200]}
rscv = RandomizedSearchCV(xgbRegModel, params)
rscv.fit(X, y)
rscv.best_model_
where X is a (39942, 112577) scipy.sparse.csr.csr_matrix and y is a (39942,) numpy.ndarray.
The dtypes are all either int64 or float64, and I've tried running it both with np.nan values and after filling the np.nan values with 0... (I thought that might be the problem, but no.)
Can anyone tell me what's going on here? It works just fine when I train the model without using GridSearchCV or RandomizedSearchCV.
Any ideas would be appreciated - thanks!
ps - the traceback for the error is really long, but here it is, if it helps..
TypeError Traceback (most recent call last)
<ipython-input-54-63d54d4cd03e> in <module>()
3 xgbRegModel = XGR()
4 rscv = RandomizedSearchCV(xgbRegModel, params)
----> 5 rscv.fit(X, y)
6 rscv.best_model_
~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
636 error_score=self.error_score)
637 for parameters, (train, test) in product(candidate_params,
--> 638 cv.split(X, y, groups)))
639
640 # if one choose to see train score, "out" will contain train score info
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
777 # was dispatched. In particular this covers the edge
778 # case of Parallel used with an exhausted iterator.
--> 779 while self.dispatch_one_batch(iterator):
780 self._iterating = True
781 else:
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in _dispatch(self, batch)
586 dispatch_timestamp = time.time()
587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588 job = self._backend.apply_async(batch, callback=cb)
589 self._jobs.append(job)
590
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in apply_async(self, func, callback)
109 def apply_async(self, func, callback=None):
110 """Schedule a func to be run"""
--> 111 result = ImmediateResult(func)
112 if callback:
113 callback(result)
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in __init__(self, batch)
330 # Don't delay the application, to avoid keeping the input
331 # arguments in memory
--> 332 self.results = batch()
333
334 def get(self):
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
425 start_time = time.time()
426
--> 427 X_train, y_train = _safe_split(estimator, X, y, train)
428 X_test, y_test = _safe_split(estimator, X, y, test, train)
429
~\Anaconda3\lib\site-packages\sklearn\utils\metaestimators.py in _safe_split(estimator, X, y, indices, train_indices)
198 X_subset = X[np.ix_(indices, train_indices)]
199 else:
--> 200 X_subset = safe_indexing(X, indices)
201
202 if y is not None:
~\Anaconda3\lib\site-packages\sklearn\utils\__init__.py in safe_indexing(X, indices)
160 return X.take(indices, axis=0)
161 else:
--> 162 return X[indices]
163 else:
164 return [X[idx] for idx in indices]
~\Anaconda3\lib\site-packages\scipy\sparse\csr.py in __getitem__(self, key)
315 if isintlike(col) or isinstance(col,slice):
316 P = extractor(row, self.shape[0]) # [[1,2],j] or [[1,2],1:2]
--> 317 extracted = P * self
318 if col == slice(None, None, None):
319 return extracted
~\Anaconda3\lib\site-packages\scipy\sparse\base.py in __mul__(self, other)
367 if self.shape[1] != other.shape[0]:
368 raise ValueError('dimension mismatch')
--> 369 return self._mul_sparse_matrix(other)
370
371 # If it's a list or whatever, treat it like a matrix
~\Anaconda3\lib\site-packages\scipy\sparse\compressed.py in _mul_sparse_matrix(self, other)
539 indptr = np.asarray(indptr, dtype=idx_dtype)
540 indices = np.empty(nnz, dtype=idx_dtype)
--> 541 data = np.empty(nnz, dtype=upcast(self.dtype, other.dtype))
542
543 fn = getattr(_sparsetools, self.format + '_matmat_pass2')
~\Anaconda3\lib\site-packages\scipy\sparse\sputils.py in upcast(*args)
49 return t
50
---> 51 raise TypeError('no supported conversion for types: %r' % (args,))
52
53
TypeError: no supported conversion for types: (dtype('O'), dtype('O'))

Answer 1

Thats because GridSearchCV doesn't support sparse matrices in the fit() method. Please have a look at the signature of fit method here:
Parameters:
X : array-like, shape = [n_samples, n_features]
As you see its written that only array-like inputs are supported.
As for why its working normally without grid search, thats because XGBRegressor supports sparse matrices.
The actual error arises when during cross_validation, the X is splitted into train and test which doesn't work for sparse matrices same way as normal arrays.
Also, make sure that for XGBRegressor the sparse matrix is of type CSC and not CSR as you have now, because it will give you wrong results. Its described here: https://github.com/dmlc/xgboost/issues/1238