python - 值错误 : Unknown label type: 'unknown' in sklearn

Question

我收到此错误 - “ValueError:未知标签类型:'unknown'”

我已经在网上搜索但无法摆脱这个错误，顺便说一句，我是 python 的新手:)

我的数据有 5 行 22 列，最后一列是标签 (True,False)

dataset = pandas.read_csv(path)  #Dataframe created

数据看起来像这样:

dataset.head()



loc     v(g)    ev(g)   iv(g)   n   v   l   d   i   e   ...     lOCode  lOComment   lOBlank     locCodeAndComment   uniq_Op     uniq_Opnd   total_Op    total_Opnd  branchCount     defects
0   1.0     1.0     1.0     1.0     1.0     1.00    1.0     1.0     1.00    1.00    ...     1   1   1   1   1.0     1.0     1.0     1.0     1.0     True
1   1.1     1.4     1.4     1.4     1.3     1.30    1.3     1.3     1.30    1.30    ...     2   2   2   1   1.2     1.2     1.2     1.2     1.4     False
2   2.0     1.0     1.0     1.0     1.0     0.00    0.0     0.0     0.00    0.00    ...     0   0   1   0   1.0     0.0     1.0     0.0     1.0     False
3   2.0     1.0     1.0     1.0     1.0     0.00    0.0     0.0     0.00    0.00    ...     0   0   1   0   1.0     0.0     1.0     0.0     1.0     False
4   3.0     1.0     1.0     1.0     22.0    85.95   0.2     5.0     17.19   429.76  ...     1   0   3   0   10.0    5.0     17.0    5.0     1.0     False

5 rows × 22 columns

其余代码:

array = dataset.values
X = array[:,0:21]  # Row=ALL, Col=1 to 21 (index=0to20)
Y = array[:,21]  # Row=ALL, Col=22nd (index=21)
X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=0.20, random_state=0) #80% Training data , 20% Test data

kfold = model_selection.KFold(n_splits=10, random_state=0)
cv_results = []

我在以下行收到错误:

cv_results = model_selection.cross_val_score(SVC(), X_train, Y_train, cv=kfold, scoring='accuracy')

详细错误:

ValueError                                Traceback (most recent call last)
<ipython-input-31-e1234a2bbe9b> in <module>()
----> 1 cv_results = model_selection.cross_val_score(SVC(), X_train, Y_train, cv=kfold, scoring='accuracy')

C:\Program Files\Anaconda2\lib\site-packages\sklearn\model_selection\_validation.pyc in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
    138                                               train, test, verbose, None,
    139                                               fit_params)
--> 140                       for train, test in cv_iter)
    141     return np.array(scores)[:, 0]
    142 

C:\Program Files\Anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.pyc in __call__(self, iterable)
    756             # was dispatched. In particular this covers the edge
    757             # case of Parallel used with an exhausted iterator.
--> 758             while self.dispatch_one_batch(iterator):
    759                 self._iterating = True
    760             else:

C:\Program Files\Anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.pyc in dispatch_one_batch(self, iterator)
    606                 return False
    607             else:
--> 608                 self._dispatch(tasks)
    609                 return True
    610 

C:\Program Files\Anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.pyc in _dispatch(self, batch)
    569         dispatch_timestamp = time.time()
    570         cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571         job = self._backend.apply_async(batch, callback=cb)
    572         self._jobs.append(job)
    573 

C:\Program Files\Anaconda2\lib\site-packages\sklearn\externals\joblib\_parallel_backends.pyc in apply_async(self, func, callback)
    107     def apply_async(self, func, callback=None):
    108         """Schedule a func to be run"""
--> 109         result = ImmediateResult(func)
    110         if callback:
    111             callback(result)

C:\Program Files\Anaconda2\lib\site-packages\sklearn\externals\joblib\_parallel_backends.pyc in __init__(self, batch)
    324         # Don't delay the application, to avoid keeping the input
    325         # arguments in memory
--> 326         self.results = batch()
    327 
    328     def get(self):

C:\Program Files\Anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.pyc 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):

C:\Program Files\Anaconda2\lib\site-packages\sklearn\model_selection\_validation.pyc 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)
    236             estimator.fit(X_train, **fit_params)
    237         else:
--> 238             estimator.fit(X_train, y_train, **fit_params)
    239 
    240     except Exception as e:

C:\Program Files\Anaconda2\lib\site-packages\sklearn\svm\base.pyc in fit(self, X, y, sample_weight)
    150 
    151         X, y = check_X_y(X, y, dtype=np.float64, order='C', accept_sparse='csr')
--> 152         y = self._validate_targets(y)
    153 
    154         sample_weight = np.asarray([]

C:\Program Files\Anaconda2\lib\site-packages\sklearn\svm\base.pyc in _validate_targets(self, y)
    518     def _validate_targets(self, y):
    519         y_ = column_or_1d(y, warn=True)
--> 520         check_classification_targets(y)
    521         cls, y = np.unique(y_, return_inverse=True)
    522         self.class_weight_ = compute_class_weight(self.class_weight, cls, y_)

C:\Program Files\Anaconda2\lib\site-packages\sklearn\utils\multiclass.pyc in check_classification_targets(y)
    170     if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
    171             'multilabel-indicator', 'multilabel-sequences']:
--> 172         raise ValueError("Unknown label type: %r" % y_type)
    173 
    174 

ValueError: Unknown label type: 'unknown'

Answer 1

第 1 部分

---

您得到的错误与您使用的 y 变量有关。

您需要将 TRUE/FALSE 转换为 0/1 以便 Y 变量包含 0s 和 1s。这应该可以修复错误。

来自文档 see here :

y : 类似数组，形状 (n_samples,)
目标值(分类中的类标签，回归中的实数)

---

第 2 部分

---

接下来，您应该使用交叉验证将数据自动拆分为 X_train,X_test 和 y_train, y_test 或 train_test_split 函数然后手动做这样的事情:

clf = SVC()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
...

另一方面，如果您想将交叉验证与KFold一起使用，只需使用:

kfold = model_selection.KFold(n_splits=10, random_state=0)

cv_results = model_selection.cross_val_score(SVC(), X, Y, cv=kfold, scoring='accuracy')

这将自动创建 X_train、X_test 和 y_train、y_test，它会给你cv_results。