python - 无法在 svm 的 sklearn 上拟合我的模型

Question

我正在尝试使用 sklearn 进行情感分析。我已经加载了数据并创建了词向量化，用于分类，这里试图在 svm 模型上拟合 X 和 Y，但它通过了一个类型错误

您可以在下面看到我的代码和错误消息。

请让我知道此问题的解决方法。

提前致谢

from sklearn.model_selection import train_test_split

training, test= train_test_split(reviews, test_size=0.33, random_state=42)

train_x = [x.text for x in training]
train_y = [x.sentiment for x in training]

test_x = [x.text for x in test]
test_y = [x.sentiment for x in test]

train_X[0]
train_Y[0]

from sklearn.feature_extraction.text import CountVectorizer

vectorizer = CountVectorizer()
train_x_Vector = vectorizer.fit_transform(train_x)

test_x_vector = vectorizer.transform(test_x)

print(train_x[0])
print(train_x_Vector[0])

from sklearn import svm

clf_svm = svm.SVC(kernel='linear')

clf_svm.fit(train_x_Vector, train_y)

-----------------------------------------------------------------------
TypeError                                 
Traceback (most recent call last)
<ipython-input-283-1cb540dee78d> in <module>
      3 clf_svm = svm.SVC(kernel='linear')
      4 
----> 5 clf_svm.fit(test_x_vector, test_y)
      6 
      7 test_x[0]

/opt/anaconda3/lib/python3.7/site-packages/sklearn/svm/base.py in fit(self, X, y, sample_weight)
    145                          order='C', accept_sparse='csr',
    146                          accept_large_sparse=False)
--> 147         y = self._validate_targets(y)
    148 
    149         sample_weight = np.asarray([]

/opt/anaconda3/lib/python3.7/site-packages/sklearn/svm/base.py in _validate_targets(self, y)
    513     def _validate_targets(self, y):
    514         y_ = column_or_1d(y, warn=True)
--> 515         check_classification_targets(y)
    516         cls, y = np.unique(y_, return_inverse=True)
    517         self.class_weight_ = compute_class_weight(self.class_weight, cls, y_)

/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/multiclass.py in check_classification_targets(y)
    164     y : array-like
    165     """
--> 166     y_type = type_of_target(y)
    167     if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
    168                       'multilabel-indicator', 'multilabel-sequences']:

/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/multiclass.py in type_of_target(y)
    285         return 'continuous' + suffix
    286 
--> 287     if (len(np.unique(y)) > 2) or (y.ndim >= 2 and len(y[0]) > 1):
    288         return 'multiclass' + suffix  # [1, 2, 3] or [[1., 2., 3]] or [[1, 2]]
    289     else:

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

/opt/anaconda3/lib/python3.7/site-packages/numpy/lib/arraysetops.py in unique(ar, return_index, return_inverse, return_counts, axis)
    260     ar = np.asanyarray(ar)
    261     if axis is None:
--> 262         ret = _unique1d(ar, return_index, return_inverse, return_counts)
    263         return _unpack_tuple(ret)
    264 

/opt/anaconda3/lib/python3.7/site-packages/numpy/lib/arraysetops.py in _unique1d(ar, return_index, return_inverse, return_counts)
    308         aux = ar[perm]
    309     else:
--> 310         ar.sort()
    311         aux = ar
    312     mask = np.empty(aux.shape, dtype=np.bool_)

TypeError: '<' not supported between instances of 'NoneType' and 'str'

标签： pythontypeerrorsvmsentiment-analysissklearn-pandas