python - GridSearchCV - 类型错误 : an integer is required

Question

我正在尝试使用网格搜索为我的 SVM 找到最佳超参数。按以下方式执行时:

from sklearn.model_selection import GridSearchCV

param_grid = {'coef0': [10, 5, 0.5, 0.001], 'C': [100, 50, 1, 0.001]}
poly_svm_search = SVC(kernel="poly", degree="2")
grid_search = GridSearchCV(poly_svm_search, param_grid, cv=5, scoring='f1')

grid_search.fit(train_data, train_labels)

我收到此错误:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-72-dadf5782618c> in <module>
      8 
----> 9 grid_search.fit(train_data, train_labels)

~/.local/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
    720                 return results_container[0]
    721 
--> 722             self._run_search(evaluate_candidates)
    723 
    724         results = results_container[0]

~/.local/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
   1189     def _run_search(self, evaluate_candidates):
   1190         """Search all candidates in param_grid"""
-> 1191         evaluate_candidates(ParameterGrid(self.param_grid))
   1192 
   1193 

~/.local/lib/python3.6/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params)
    709                                for parameters, (train, test)
    710                                in product(candidate_params,
--> 711                                           cv.split(X, y, groups)))
    712 
    713                 all_candidate_params.extend(candidate_params)

~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
    981             # remaining jobs.
    982             self._iterating = False
--> 983             if self.dispatch_one_batch(iterator):
    984                 self._iterating = self._original_iterator is not None
    985 

~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
    823                 return False
    824             else:
--> 825                 self._dispatch(tasks)
    826                 return True
    827 

~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
    780         with self._lock:
    781             job_idx = len(self._jobs)
--> 782             job = self._backend.apply_async(batch, callback=cb)
    783             # A job can complete so quickly than its callback is
    784             # called before we get here, causing self._jobs to

~/.local/lib/python3.6/site-packages/sklearn/externals/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)

~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
    543         # Don't delay the application, to avoid keeping the input
    544         # arguments in memory
--> 545         self.results = batch()
    546 
    547     def get(self):

~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
    259         with parallel_backend(self._backend):
    260             return [func(*args, **kwargs)
--> 261                     for func, args, kwargs in self.items]
    262 
    263     def __len__(self):

~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
    259         with parallel_backend(self._backend):
    260             return [func(*args, **kwargs)
--> 261                     for func, args, kwargs in self.items]
    262 
    263     def __len__(self):

~/.local/lib/python3.6/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, return_estimator, error_score)
    526             estimator.fit(X_train, **fit_params)
    527         else:
--> 528             estimator.fit(X_train, y_train, **fit_params)
    529 
    530     except Exception as e:

~/.local/lib/python3.6/site-packages/sklearn/svm/base.py in fit(self, X, y, sample_weight)
    210 
    211         seed = rnd.randint(np.iinfo('i').max)
--> 212         fit(X, y, sample_weight, solver_type, kernel, random_seed=seed)
    213         # see comment on the other call to np.iinfo in this file
    214 

~/.local/lib/python3.6/site-packages/sklearn/svm/base.py in _sparse_fit(self, X, y, sample_weight, solver_type, kernel, random_seed)
    291                 sample_weight, self.nu, self.cache_size, self.epsilon,
    292                 int(self.shrinking), int(self.probability), self.max_iter,
--> 293                 random_seed)
    294 
    295         self._warn_from_fit_status()

sklearn/svm/libsvm_sparse.pyx in sklearn.svm.libsvm_sparse.libsvm_sparse_train()

TypeError: an integer is required

我的train_labels变量包含 bool 值列表，所以我有一个二元分类问题。 train_data是 <class'scipy.sparse.csr.csr_matrix'> ，基本上包含所有 scaled和One-Hot encoded特点。

我做错了什么？我很难找出问题所在。我提前感谢您提供的任何帮助；)。

Answer 1

当您使用此行初始化 SVC 时:

poly_svm_search = SVC(kernel="poly", degree="2")

您正在为 Degree 参数提供一个字符串，因为它周围有引号。但是according to the documentation , level 采用整数作为值。

degree : int, optional (default=3) Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels.

所以你需要这样做:

poly_svm_search = SVC(kernel="poly", degree=2)

请注意我在这里没有使用引号。