Python Impute using BayesianRidge() sklearn impute.IterativeImputer 回归估算分析值误差

Question

问题

使用 sklearn.impute.IterativeImputer 中的 interativeImputer，获得适合 BayesianRidge() 的回归模型，用于估算变量“Frontage”中的缺失数据。

在 interative_imputer_fit = interative_imputer.fit(data) 运行后，interative_imputer_fit.transform(X) 运行但调用函数 imputer_bay_ridge(data)，来自 interative_imputer 的 transform() 函数，例如 interative_imputer_fit.transform(X) 值错误错误。传入两个变量，Frontage 和 Area。但是只有 Frontage 在 numpy.array 里面。

使用 sklearn 的 Python 代码

from sklearn.experimental import enable_iterative_imputer
from sklearn.impute import IterativeImputer
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.linear_model import BayesianRidge

def imputer_bay_ridge(data):
    data_array = data.to_numpy()
    data_array.reshape(1, -1)
    interative_imputer = IterativeImputer(BayesianRidge())
    interative_imputer_fit = interative_imputer.fit(data_array)
    X = data['LotFrontage']
    data_imputed = interative_imputer_fit.transform(X)

  
train_data[['Frontage', 'Area']]    

调用函数

fit_tranformed_imputed = imputer_bay_ridge(train_data[['Frontage', 'Area']])

数据示例

train_data[['Frontage', 'Area']]   
    Frontage    Area
0   65.0    8450
1   80.0    9600
2   68.0    11250
3   60.0    9550
4   84.0    14260
... ... ...
1455    62.0    7917
1456    85.0    13175
1457    66.0    9042
1458    68.0    9717
1459    75.0    9937
1460 rows × 2 columns

错误

ValueError                                Traceback (most recent call last)
Cell In[243], line 1
----> 1 fit_tranformed_imputed = imputer_bay_ridge(train_data[['LotFrontage', 'LotArea']])

Cell In[242], line 12, in imputer_bay_ridge(data)
     10 interative_imputer_fit = interative_imputer.fit(data_array)
     11 X = data['LotFrontage']
---> 12 data_imputed = interative_imputer_fit.transform(X)

File ~/opt/anaconda3/lib/python3.9/site-packages/sklearn/impute/_iterative.py:724, in IterativeImputer.transform(self, X)
    707 """Impute all missing values in `X`.
    708 
    709 Note that this is stochastic, and that if `random_state` is not fixed,
   (...)
    720      The imputed input data.
    721 """
    722 check_is_fitted(self)
--> 724 X, Xt, mask_missing_values, complete_mask = self._initial_imputation(X)
    726 X_indicator = super()._transform_indicator(complete_mask)
    728 if self.n_iter_ == 0 or np.all(mask_missing_values):

File ~/opt/anaconda3/lib/python3.9/site-packages/sklearn/impute/_iterative.py:514, in IterativeImputer._initial_imputation(self, X, in_fit)
    511 else:
    512     force_all_finite = True
--> 514 X = self._validate_data(
    515     X,
    516     dtype=FLOAT_DTYPES,
    517     order="F",
    518     reset=in_fit,
    519     force_all_finite=force_all_finite,
    520 )
    521 _check_inputs_dtype(X, self.missing_values)
    523 X_missing_mask = _get_mask(X, self.missing_values)

File ~/opt/anaconda3/lib/python3.9/site-packages/sklearn/base.py:566, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, **check_params)
    564     raise ValueError("Validation should be done on X, y or both.")
    565 elif not no_val_X and no_val_y:
--> 566     X = check_array(X, **check_params)
    567     out = X
    568 elif no_val_X and not no_val_y:

File ~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/validation.py:769, 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)
    767     # If input is 1D raise error
    768     if array.ndim == 1:
--> 769         raise ValueError(
    770             "Expected 2D array, got 1D array instead:\narray={}.\n"
    771             "Reshape your data either using array.reshape(-1, 1) if "
    772             "your data has a single feature or array.reshape(1, -1) "
    773             "if it contains a single sample.".format(array)
    774         )
    776 # make sure we actually converted to numeric:
    777 if dtype_numeric and array.dtype.kind in "OUSV":

ValueError: Expected 2D array, got 1D array instead:
array=[65. 80. 68. ... 66. 68. 75.].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.