尝试使用 MinMaxScaler() 缩放数据帧 (X_train)抛出 ValueError : array shape = (0,) 最少需要 1

如何解决尝试使用 MinMaxScaler() 缩放数据帧 (X_train)抛出 ValueError : array shape = (0,) 最少需要 1

为了预处理我的数据，我试图转换一个二元分类器。所有部分单独工作正常，但当放入函数时，值错误：Found array with 0 sample (s) (shape = (0,)) while a minimum of 1 is required.

OneHotEncoding 后的 X_train 数据：

0   0.66    759.5   318.5   220.50  3.5 2   0.40    3   1.0 0.0 0.0 0.0
1   0.76    661.5   416.5   122.50  7.0 3   0.10    1   0.0 1.0 0.0 0.0
2   0.66    759.5   318.5   220.50  3.5 3   0.10    1   0.0 1.0 0.0 0.0
3   0.74    686.0   245.0   220.50  3.5 5   0.10    4   0.0 0.0 0.0 1.0
4   0.64    784.0   343.0   220.50  3.5 2   0.40    4   1.0 0.0 0.0 0.0
... ... ... ... ... ... ... ... ... ... ... ... ...
609 0.98    514.5   294.0   110.25  7.0 4   0.40    2   0.0 0.0 1.0 0.0
610 0.90    563.5   318.5   122.50  7.0 3   0.10    1   0.0 1.0 0.0 0.0
611 0.82    612.5   318.5   147.00  7.0 4   0.25    2   0.0 0.0 1.0 0.0
612 0.71    710.5   269.5   220.50  3.5 5   0.10    1   0.0 0.0 0.0 1.0
613 0.64    784.0   343.0   220.50  3.5 2   0.25    5   1.0 0.0 0.0 0.0

我尝试使用的功能

def feature_engineering(data):
    data = data[(np.nan_to_num(np.abs(stats.zscore(data,nan_policy='omit')),0) < 3).all(axis=1)]
    data = data[(np.nan_to_num(np.abs(stats.zscore(data,0) > 3).all(axis=1)]
    csc = OneHotEncoder(handle_unknown='ignore').fit_transform(data[['orientation']])
    ob = pd.DataFrame(data=csc.toarray(),columns=["o1","o2","o3","o4"])
    ob = csc.reshape((ob,614*12))
    data = pd.concat([data,ob],axis = 1)
    scaler = MinMaxScaler(feature_range=(0,1))
    X_train = scaler.fit_transform(data)


data = pd.DataFrame(feature_engineering(X_train))
X_eval = pd.DataFrame(feature_engineering(X_eval))

回溯错误

-------------------------------------------------- ------------------------- 
ValueError                                 Traceback (most recent call last)
 <ipython-input-51-d0f1271d1165> in <module> 
     11  
     12  # 
- -> 13  data = pd . DataFrame ( feature_engineering ( X_train ) ) 
     14 X_eval = pd . DataFrame ( feature_engineering ( X_eval ) )

<ipython-input-51-d0f1271d1165> in feature_engineering (data) 
      3      data = data [ ( np . nan_to_num ( np . abs ( stats . zscore ( data,nan_policy = ' omit ' ) ),0 )  <  3 ) . all ( axis = 1 ) ] 
      4      data = data [ ( np .nan_to_num ( np . abs ( stats . zscore ( data,0 )  >  3 ) . all ( axis = 1 ) ] 
----> 5      csc = OneHotEncoder ( handle_unknown = 'ignore' ) . fit_transform ( data [ [ 'orientation' ] ] ) 
      6      ob= pd . DataFrame ( data = csc . Toarray ( ),columns = [ "o1","o4" ] ) 
      7      ob = csc . reshape ( ( ob,614 * 12 ) )

~ \ anaconda3 \ lib \ site-packages \ sklearn \ preprocessing \ _encoders.py in fit_transform (self,X,y) 
    408          "" "
     409          self . _validate_keywords ( ) 
-> 410 return super ( ) . fit_transform ( X,y )     411     412 def transform ( self,X ) :         
 
     

~ \ anaconda3 \ lib \ site-packages \ sklearn \ base.py in fit_transform (self,y,** fit_params) 
    688          if y is  None : 
    689              # fit method of arity 1 (unsupervised transformation) 
-> 690 return self . fit ( X,** fit_params ) . transform ( X )     691 else :     692 # fit method of arity 2 (supervised transformation)              
         
             

~ \ anaconda3 \ lib \ site-packages \ sklearn \ preprocessing \ _encoders.py in fit (self,y) 
    383          "" "
     384          self . _validate_keywords ( ) 
-> 385          self . _fit ( X,handle_unknown = self . handle_unknown ) 
    386          self . drop_idx_ = self . _compute_drop_idx ( ) 
    387          return self

~ \ anaconda3 \ lib \ site-packages \ sklearn \ preprocessing \ _encoders.py in _fit (self,handle_unknown) 
     72  
     73      def _fit ( self,handle_unknown = 'error' ) : 
---> 74          X_list,n_samples,n_features = self . _check_X ( X ) 
     75  
     76          if self . categories ! =  'auto' :

~ \ anaconda3 \ lib \ site-packages \ sklearn \ preprocessing \ _encoders.py in _check_X (self,X) 
     58          for i in range ( n_features ) : 
     59              Xi = self . _get_feature ( X,feature_idx = i ) 
---> 60              Xi = check_array (Xi,ensure_2d = False,dtype = None,61                               force_all_finite = needs_validation)
      62              X_columns . append ( Xi )

~ \ anaconda3 \ lib \ site-packages \ sklearn \ utils \ validation.py in inner_f (* args,** kwargs) 
     70                            FutureWarning)
      71          kwargs . update ( { k : arg for k,arg in zip ( sig . parameters,args ) } ) 
---> 72 return f ( ** kwargs )      73 return inner_f
      74         
      

~ \ anaconda3 \ lib \ site-packages \ sklearn \ utils \ validation.py in check_array (array,accept_sparse,accept_large_sparse,-dtype,order,copy,force_all_finite,ensure_2d,allow_nd,ensure_min_samples,ensure_min_features,estimator) 
    648          N_SAMPLES = _num_samples ( array ) 
    649          if n_samples < ensure_min_samples : 
-> 650              raise ValueError ("Found array with% d sample (s) (shape =% s) while a"
     651                               "minimum of% d is required% s." 
    652                               % (n_samples,array.shape,ValueError : Found array with 0 sample (s) (shape = (0,)) while a minimum of 1 is required.

X_train['orientation']:

0 2
1 3
2 3
3 5
4 2
      ..
609 4
610 3
611 4
612 5