混淆矩阵可视化：仅支持使用字符串指定列的列。

Question

基于这篇文章： https://towardsdatascience.com/how-to-plot-a-confusion-matrix-from-ak-folm-ak-fold-cross-validation-b607317e9874 ，我想可视化数据集的混淆矩阵。但是我会收到以下错误消息：

AttributeError                            Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/sklearn/utils/__init__.py in _get_column_indices(X, key)
    408         try:
--> 409             all_columns = X.columns
    410         except AttributeError:

AttributeError: 'numpy.ndarray' object has no attribute 'columns'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
8 frames
<ipython-input-76-827f7c5dca49> in <module>()
      1 # call the functions
----> 2 actual_classes, predicted_classes, _ = cross_val_predict(best_grid, kf, X.to_numpy(), y.to_numpy())
      3 plot_confusion_matrix(actual_classes, predicted_classes, ['Rating_1', 'Rating_2', 'Rating_3', 'Rating_4', 'Rating_5'])

<ipython-input-68-f1bff3bd9ebf> in cross_val_predict(best_grid, kf, X, y)
     19         actual_classes = np.append(actual_classes, test_y)
     20 
---> 21         model_.fit(train_X, train_y)
     22         predicted_classes = np.append(predicted_classes, model_.predict(test_X))
     23 

/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
    388         """
    389         fit_params_steps = self._check_fit_params(**fit_params)
--> 390         Xt = self._fit(X, y, **fit_params_steps)
    391         with _print_elapsed_time("Pipeline", self._log_message(len(self.steps) - 1)):
    392             if self._final_estimator != "passthrough":

/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params_steps)
    353                 message_clsname="Pipeline",
    354                 message=self._log_message(step_idx),
--> 355                 **fit_params_steps[name],
    356             )
    357             # Replace the transformer of the step with the fitted

/usr/local/lib/python3.7/dist-packages/joblib/memory.py in __call__(self, *args, **kwargs)
    347 
    348     def __call__(self, *args, **kwargs):
--> 349         return self.func(*args, **kwargs)
    350 
    351     def call_and_shelve(self, *args, **kwargs):

/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
    891     with _print_elapsed_time(message_clsname, message):
    892         if hasattr(transformer, "fit_transform"):
--> 893             res = transformer.fit_transform(X, y, **fit_params)
    894         else:
    895             res = transformer.fit(X, y, **fit_params).transform(X)

/usr/local/lib/python3.7/dist-packages/sklearn/compose/_column_transformer.py in fit_transform(self, X, y)
    670         self._check_n_features(X, reset=True)
    671         self._validate_transformers()
--> 672         self._validate_column_callables(X)
    673         self._validate_remainder(X)
    674 

/usr/local/lib/python3.7/dist-packages/sklearn/compose/_column_transformer.py in _validate_column_callables(self, X)
    350                 columns = columns(X)
    351             all_columns.append(columns)
--> 352             transformer_to_input_indices[name] = _get_column_indices(X, columns)
    353 
    354         self._columns = all_columns

/usr/local/lib/python3.7/dist-packages/sklearn/utils/__init__.py in _get_column_indices(X, key)
    410         except AttributeError:
    411             raise ValueError(
--> 412                 "Specifying the columns using strings is only "
    413                 "supported for pandas DataFrames"
    414             )

ValueError: Specifying the columns using strings is only supported for pandas DataFrames

这是我的代码：

def cross_val_predict(best_grid, kf:KFold, X:np.array, y:np.array) -> Tuple[np.array, np.array, np.array]:

model_ = cp.deepcopy(best_grid)

no_classes = len(np.unique(y))

actual_classes = np.empty([0], dtype=int)
predicted_classes = np.empty([0], dtype=int)
predicted_proba = np.empty([0, no_classes]) 

for train_idx, test_idx in kf.split(X):

    train_X, train_y, test_X, test_y = X[train_idx], y[train_idx], X[test_idx], y[test_idx]

    actual_classes = np.append(actual_classes, test_y)

    model_.fit(train_X, train_y)
    predicted_classes = np.append(predicted_classes, model_.predict(test_X))

    try:
        predicted_proba = np.append(predicted_proba, model_.predict_proba(test_X), axis=0)
    except:
        predicted_proba = np.append(predicted_proba, np.zeros((len(test_X), no_classes), dtype=float), axis=0)

return actual_classes, predicted_classes, predicted_proba

# Visualise the Confusion Matrix
def plot_confusion_matrix(actual_classes : np.array, predicted_classes : np.array, sorted_labels : list):

    matrix = confusion_matrix(actual_classes, predicted_classes, labels=sorted_labels)
    
    plt.figure(figsize=(12.8,6))
    sns.heatmap(matrix, annot=True, xticklabels=sorted_labels, yticklabels=sorted_labels, cmap='Blues', fmt='g')
    plt.xlabel('Predicted'); plt.ylabel('Actual'); plt.title('Confusion Matrix Visualization')

    plt.show()

# call the functions
actual_classes, predicted_classes, _ = cross_val_predict(best_grid, kf, X.to_numpy(), y.to_numpy())
plot_confusion_matrix(actual_classes, predicted_classes, ['Rating_1', 'Rating_2', 'Rating_3', 'Rating_4', 'Rating_5'])

错误消息在我运行代码以调用函数之后出现。提前致谢。