Here is the full error:

`---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[33], line 2
      1 gnb = GaussianNB()
----> 2 cv = cross_val_score(gnb,X_train,y_train,cv=5, error_score = 'raise')
      3 print(cv)
      4 print(cv.mean())

File /opt/conda/lib/python3.10/site-packages/sklearn/model_selection/_validation.py:515, in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, error_score)
    512 # To ensure multimetric format is not supported
    513 scorer = check_scoring(estimator, scoring=scoring)
--> 515 cv_results = cross_validate(
    516     estimator=estimator,
    517     X=X,
    518     y=y,
    519     groups=groups,
    520     scoring={"score": scorer},
    521     cv=cv,
    522     n_jobs=n_jobs,
    523     verbose=verbose,
    524     fit_params=fit_params,
    525     pre_dispatch=pre_dispatch,
    526     error_score=error_score,
    527 )
    528 return cv_results["test_score"]

File /opt/conda/lib/python3.10/site-packages/sklearn/model_selection/_validation.py:266, in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
    263 # We clone the estimator to make sure that all the folds are
    264 # independent, and that it is pickle-able.
    265 parallel = Parallel(n_jobs=n_jobs, verbose=verbose, pre_dispatch=pre_dispatch)
--> 266 results = parallel(
    267     delayed(_fit_and_score)(
    268         clone(estimator),
    269         X,
    270         y,
    271         scorers,
    272         train,
    273         test,
    274         verbose,
    275         None,
    276         fit_params,
    277         return_train_score=return_train_score,
    278         return_times=True,
    279         return_estimator=return_estimator,
    280         error_score=error_score,
    281     )
    282     for train, test in cv.split(X, y, groups)
    283 )
    285 _warn_or_raise_about_fit_failures(results, error_score)
    287 # For callabe scoring, the return type is only know after calling. If the
    288 # return type is a dictionary, the error scores can now be inserted with
    289 # the correct key.

File /opt/conda/lib/python3.10/site-packages/sklearn/utils/parallel.py:63, in Parallel.__call__(self, iterable)
     58 config = get_config()
     59 iterable_with_config = (
     60     (_with_config(delayed_func, config), args, kwargs)
     61     for delayed_func, args, kwargs in iterable
     62 )
---> 63 return super().__call__(iterable_with_config)

File /opt/conda/lib/python3.10/site-packages/joblib/parallel.py:1918, in Parallel.__call__(self, iterable)
   1916     output = self._get_sequential_output(iterable)
   1917     next(output)
-> 1918     return output if self.return_generator else list(output)
   1920 # Let's create an ID that uniquely identifies the current call. If the
   1921 # call is interrupted early and that the same instance is immediately
   1922 # re-used, this id will be used to prevent workers that were
   1923 # concurrently finalizing a task from the previous call to run the
   1924 # callback.
   1925 with self._lock:

File /opt/conda/lib/python3.10/site-packages/joblib/parallel.py:1847, in Parallel._get_sequential_output(self, iterable)
   1845 self.n_dispatched_batches += 1
   1846 self.n_dispatched_tasks += 1
-> 1847 res = func(*args, **kwargs)
   1848 self.n_completed_tasks += 1
   1849 self.print_progress()

File /opt/conda/lib/python3.10/site-packages/sklearn/utils/parallel.py:123, in _FuncWrapper.__call__(self, *args, **kwargs)
    121     config = {}
    122 with config_context(**config):
--> 123     return self.function(*args, **kwargs)

File /opt/conda/lib/python3.10/site-packages/sklearn/model_selection/_validation.py:686, 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, return_estimator, split_progress, candidate_progress, error_score)
    684         estimator.fit(X_train, **fit_params)
    685     else:
--> 686         estimator.fit(X_train, y_train, **fit_params)
    688 except Exception:
    689     # Note fit time as time until error
    690     fit_time = time.time() - start_time

File /opt/conda/lib/python3.10/site-packages/sklearn/naive_bayes.py:267, in GaussianNB.fit(self, X, y, sample_weight)
    265 self._validate_params()
    266 y = self._validate_data(y=y)
--> 267 return self._partial_fit(
    268     X, y, np.unique(y), _refit=True, sample_weight=sample_weight
    269 )

File /opt/conda/lib/python3.10/site-packages/sklearn/naive_bayes.py:427, in GaussianNB._partial_fit(self, X, y, classes, _refit, sample_weight)
    424 if _refit:
    425     self.classes_ = None
--> 427 first_call = _check_partial_fit_first_call(self, classes)
    428 X, y = self._validate_data(X, y, reset=first_call)
    429 if sample_weight is not None:

File /opt/conda/lib/python3.10/site-packages/sklearn/utils/multiclass.py:420, in _check_partial_fit_first_call(clf, classes)
    413             raise ValueError(
    414                 "`classes=%r` is not the same as on last call "
    415                 "to partial_fit, was: %r" % (classes, clf.classes_)
    416             )
    418     else:
    419         # This is the first call to partial_fit
--> 420         clf.classes_ = unique_labels(classes)
    421         return True
    423 # classes is None and clf.classes_ has already previously been set:
    424 # nothing to do

File /opt/conda/lib/python3.10/site-packages/sklearn/utils/multiclass.py:107, in unique_labels(*ys)
    105 _unique_labels = _FN_UNIQUE_LABELS.get(label_type, None)
    106 if not _unique_labels:
--> 107     raise ValueError("Unknown label type: %s" % repr(ys))
    109 if is_array_api:
    110     # array_api does not allow for mixed dtypes
    111     unique_ys = xp.concat([_unique_labels(y) for y in ys])

ValueError: Unknown label type: (array([0.0, 1.0], dtype=object),)`

I am trying to implement cross-validation in the Spaceship Titanic Project on Kaggle, you can find my full notebook here. I have not been able to get the cross-validation function to run. I have been fiddling with it for hours, and I have not been able to find the solution.

I followed Ken Jee’s Titanic Project Example to complete my own Titanic Prediction submission. In this code, the cross-validation function can successfully run, and I tried to re-purpose this to the Spaceship Titanic project.

Please let me know if you need any other details. I am quite new to Machine Learning, so I thank you in advance for your patience.

I’ve tried getting rid of null values, verified that the data types for my training and test lists are the same, and I’ve tried mapping categorical variables to numerical variables.