类型错误：StructuredDataAdapter

如何解决类型错误：StructuredDataAdapter

谁能帮我解决上述错误？

### using trasnformers 
from sklearn.compose import ColumnTransformer
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import MinMaxScaler

column_trans = ColumnTransformer(
         [
          ('CompanyName_bow',TfidfVectorizer(),'CompanyName'),('state_category',OneHotEncoder(),['state']),('Termination_Reason_Desc_bow','Termination_Reason_Desc'),('TermType_category',['TermType'])
         ],remainder=MinMaxScaler()
        )
X = column_trans.fit_transform(X.head(100))

from sklearn.preprocessing import LabelEncoder
y = LabelEncoder().fit_transform(y.head(100))

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=5)

X_train.shape  #(80,92)
X_test.shape   #(20,92)
y_train.shape  #(80,)
X_train.todense()
matrix([[0.,0.,...,0.26921709,1.,0.        ],[0.,1.        ],0.46148896,0.        ]])

type(X_train)
--> scipy.sparse.csr.csr_matrix

print(y_train)
array([0,1,0])
 
type(y_train)
numpy.ndarray

# use autokeras to find a model for the sonar dataset
from numpy import asarray
from pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from autokeras import StructuredDataClassifier

print(X_train.shape,X_test.shape,y_train.shape,y_test.shape)
# define the search
search = StructuredDataClassifier(max_trials=15)
# perform the search
search.fit(x=(X_train),y=y_train,verbose=0)
# evaluate the model
loss,acc = search.evaluate(X_test,y_test,verbose=0)
print('Accuracy: %.3f' % acc)

错误

(80,92) (20,92) (80,) (20,)
INFO:tensorflow:Reloading Oracle from existing project .\structured_data_classifier\oracle.json
INFO:tensorflow:Reloading Tuner from .\structured_data_classifier\tuner0.json
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-106-94708e5d279d> in <module>
     10 search = StructuredDataClassifier(max_trials=15)
     11 # perform the search
---> 12 search.fit(x=(X_train),verbose=0)
     13 # evaluate the model
     14 loss,verbose=0)

~\anaconda3\lib\site-packages\autokeras\tasks\structured_data.py in fit(self,x,epochs,callbacks,validation_split,validation_data,**kwargs)
    313                 [keras.Model.fit](https://www.tensorflow.org/api_docs/python/tf/keras/Model#fit).
    314         """
--> 315         super().fit(
    316             x=x,317             y=y,~\anaconda3\lib\site-packages\autokeras\tasks\structured_data.py in fit(self,**kwargs)
    132         self.check_in_fit(x)
    133 
--> 134         super().fit(
    135             x=x,136             y=y,~\anaconda3\lib\site-packages\autokeras\auto_model.py in fit(self,batch_size,**kwargs)
    259             validation_split = 0
    260 
--> 261         dataset,validation_data = self._convert_to_dataset(
    262             x=x,y=y,validation_data=validation_data,batch_size=batch_size
    263         )

~\anaconda3\lib\site-packages\autokeras\auto_model.py in _convert_to_dataset(self,batch_size)
    373             x = dataset.map(lambda x,y: x)
    374             y = dataset.map(lambda x,y: y)
--> 375         x = self._adapt(x,self.inputs,batch_size)
    376         y = self._adapt(y,self._heads,batch_size)
    377         dataset = tf.data.Dataset.zip((x,y))

~\anaconda3\lib\site-packages\autokeras\auto_model.py in _adapt(self,dataset,hms,batch_size)
    287         adapted = []
    288         for source,hm in zip(sources,hms):
--> 289             source = hm.get_adapter().adapt(source,batch_size)
    290             adapted.append(source)
    291         if len(adapted) == 1:

~\anaconda3\lib\site-packages\autokeras\engine\adapter.py in adapt(self,batch_size)
     65             tf.data.Dataset. The converted dataset.
     66         """
---> 67         self.check(dataset)
     68         dataset = self.convert_to_dataset(dataset,batch_size)
     69         return dataset

~\anaconda3\lib\site-packages\autokeras\adapters\input_adapters.py in check(self,x)
     63     def check(self,x):
     64         if not isinstance(x,(pd.DataFrame,np.ndarray,tf.data.Dataset)):
---> 65             raise TypeError(
     66                 "Unsupported type {type} for "
     67                 "{name}.".format(type=type(x),name=self.__class__.__name__)

TypeError: Unsupported type <class 'scipy.sparse.csr.csr_matrix'> for StructuredDataAdapter.

解决方法

正如您在与此线程并行打开的 Github issue 中所注意到的，AutoKeras（当前）不支持稀疏矩阵，建议将它们转换为密集的 Numpy 数组。实际上，从 AutoKeras StructuredDataClassifier 的 documentation 来看，相应 x 方法中的训练数据 .fit 预计为：

字符串、numpy.ndarray、pandas.DataFrame 或 tensorflow.Dataset

而不是 SciPy 稀疏矩阵。

鉴于此处您的 X_train 非常小：

X_train.shape  
# (80,92)

您完全没有理由使用稀疏矩阵。尽管在这里您似乎试图将 X_train 转换为密集的，但您没有重新分配它，结果是它仍然是一个稀疏的；来自您自己的上述代码：

X_train.todense()
# ...
type(X_train)
# scipy.sparse.csr.csr_matrix

你需要做的只是将它重新分配给一个密集数组：

from scipy.sparse import csr_matrix
X_train = X_train.toarray()

这是一个使用虚拟数据的简短演示：

import numpy as np
from scipy.sparse import csr_matrix
X_train = csr_matrix((3,4),dtype=np.float)

type(X_train)
# scipy.sparse.csr.csr_matrix

# this will not work:
X_train.todense()
type(X_train)
# scipy.sparse.csr.csr_matrix # still sparse

# this will work:
X_train = X_train.toarray()
type(X_train)
# numpy.ndarray

您应该对 X_test 数据执行类似的过程（您的 y_train 和 y_test 似乎已经是密集的 Numpy 数组）。

,

可能的原因（由于上面粘贴的代码可读性低）可能是使用不同的数据集和保存的模型。我建议您在 overwrite=True 构造代码块中添加 BayesianOptimization。重新安装 TensorFlow 也可能有所帮助。