我有一个包含分类和数值特征的数据集，我想对其应用一些转换，然后使用 XGBClassifier 进行分类。
数据集链接: https://www.kaggle.com/blastchar/telco-customer-churn
由于数值和分类特征的转换不同，我使用了 sklearn_pandas 及其 DataFrameMapper。
为了对分类特征进行独热编码，我想使用 DictVectorizer。但要使用 DictVectorizer，我首先需要将数据框转换为字典，我尝试使用自定义转换器 Dictifier 来完成这个操作。
当我运行管道时，我得到了错误 ‘builtin_function_or_method’ 对象不可迭代。有人知道可能导致这个错误的原因吗？
错误跟踪
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py:542: FutureWarning: 从版本 0.22 开始，拟合期间的错误将默认导致交叉验证得分为 NaN。使用 error_score='raise' 如果你想要引发异常，或者使用 error_score=np.nan 来采用版本 0.22 的行为。
FutureWarning)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-187-96272018fb87> in <module>()
53
54 # 执行交叉验证
---> 55 cross_val_scores = cross_val_score(pipeline, X, y, scoring="roc_auc", cv=3)
/opt/conda/lib/python3.6/site-packages/sklearn_pandas/cross_validation.py in cross_val_score(model, X, *args, **kwargs)
19 warnings.warn(DEPRECATION_MSG, DeprecationWarning)
20 X = DataWrapper(X)
---> 21 return sk_cross_val_score(model, X, *args, **kwargs)
22
23
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, error_score)
400 fit_params=fit_params,
401 pre_dispatch=pre_dispatch,
--> 402 error_score=error_score)
403 return cv_results['test_score']
404
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
238 return_times=True, return_estimator=return_estimator,
239 error_score=error_score)
--> 240 for train, test in cv.split(X, y, groups))
241
242 zipped_scores = list(zip(*scores))
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
979 # remaining jobs.
980 self._iterating = False
--> 981 if self.dispatch_one_batch(iterator):
982 self._iterating = self._original_iterator is not None
983
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
821 return False
822 else:
--> 823 self._dispatch(tasks)
824 return True
825
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
778 with self._lock:
779 job_idx = len(self._jobs)
--> 780 job = self._backend.apply_async(batch, callback=cb)
781 # A job can complete so quickly than its callback is
782 # called before we get here, causing self._jobs to
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
181 def apply_async(self, func, callback=None):
182 """Schedule a func to be run"""
--> 183 result = ImmediateResult(func)
184 if callback:
185 callback(result)
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
541 # Don't delay the application, to avoid keeping the input
542 # arguments in memory
--> 543 self.results = batch()
544
545 def get(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, error_score)
526 estimator.fit(X_train, **fit_params)
527 else:
--> 528 estimator.fit(X_train, y_train, **fit_params)
529
530 except Exception as e:
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
263 This estimator
264 """
--> 265 Xt, fit_params = self._fit(X, y, **fit_params)
266 if self._final_estimator is not None:
267 self._final_estimator.fit(Xt, y, **fit_params)
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
228 Xt, fitted_transformer = fit_transform_one_cached(
229 cloned_transformer, Xt, y, None,
--> 230 **fit_params_steps[name])
231 # Replace the transformer of the step with the fitted
232 # transformer. This is necessary when loading the transformer
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/memory.py in __call__(self, *args, **kwargs)
320
321 def __call__(self, *args, **kwargs):
--> 322 return self.func(*args, **kwargs)
323
324 def call_and_shelve(self, *args, **kwargs):
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, **fit_params)
612 def _fit_transform_one(transformer, X, y, weight, **fit_params):
613 if hasattr(transformer, 'fit_transform'):
--> 614 res = transformer.fit_transform(X, y, **fit_params)
615 else:
616 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
790 delayed(_fit_transform_one)(trans, X, y, weight,
791 **fit_params)
--> 792 for name, trans, weight in self._iter())
793
794 if not result:
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
979 # remaining jobs.
980 self._iterating = False
--> 981 if self.dispatch_one_batch(iterator):
982 self._iterating = self._original_iterator is not None
983
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
821 return False
822 else:
--> 823 self._dispatch(tasks)
824 return True
825
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
778 with self._lock:
779 job_idx = len(self._jobs)
--> 780 job = self._backend.apply_async(batch, callback=cb)
781 # A job can complete so quickly than its callback is
782 # called before we get here, causing self._jobs to
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
181 def apply_async(self, func, callback=None):
182 """Schedule a func to be run"""
--> 183 result = ImmediateResult(func)
184 if callback:
185 callback(result)
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
541 # Don't delay the application, to avoid keeping the input
542 # arguments in memory
--> 543 self.results = batch()
544
545 def get(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, **fit_params)
612 def _fit_transform_one(transformer, X, y, weight, **fit_params):
613 if hasattr(transformer, 'fit_transform'):
--> 614 res = transformer.fit_transform(X, y, **fit_params)
615 else:
616 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.6/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
460 else:
461 # fit method of arity 2 (supervised transformation)
--> 462 return self.fit(X, y, **fit_params).transform(X)
463
464
/opt/conda/lib/python3.6/site-packages/sklearn_pandas/dataframe_mapper.py in transform(self, X)
342 stacked,
343 columns=self.transformed_names_,
--> 344 index=index)
345 # preserve types
346 for col, dtype in zip(self.transformed_names_, dtypes):
/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
377 else:
378 mgr = self._init_ndarray(data, index, columns, dtype=dtype,
--> 379 copy=copy)
380 elif isinstance(data, (list, types.GeneratorType)):
381 if isinstance(data, types.GeneratorType):
/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in _init_ndarray(self, values, index, columns, dtype, copy)
525 raise_with_traceback(e)
526
--> 527 index, columns = _get_axes(*values.shape)
528 values = values.T
529
/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in _get_axes(N, K, index, columns)
482 index = com._default_index(N)
483 else:
--> 484 index = _ensure_index(index)
485
486 if columns is None:
/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py in _ensure_index(index_like, copy)
4972 index_like = copy(index_like)
4973
-> 4974 return Index(index_like)
4975
4976
/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py in __new__(cls, data, dtype, copy, name, fastpath, tupleize_cols, **kwargs)
449 data, names=name or kwargs.get('names'))
450 # other iterable of some kind
--> 451 subarr = com._asarray_tuplesafe(data, dtype=object)
452 return Index(subarr, dtype=dtype, copy=copy, name=name, **kwargs)
453
/opt/conda/lib/python3.6/site-packages/pandas/core/common.py in _asarray_tuplesafe(values, dtype)
303
304 if not (isinstance(values, (list, tuple)) or hasattr(values, '__array__')):
--> 305 values = list(values)
306 elif isinstance(values, Index):
307 return values.values
TypeError: 'builtin_function_or_method' 对象不可迭代回答：
这看起来像是 sklearn_pandas.cross_val_score 中的一个错误。
sklearn_pandas 会将你提供的数据框包装在一个 DataWrapper 对象中，如源代码所示：
def cross_val_score(model, X, *args, **kwargs):
warnings.warn(DEPRECATION_MSG, DeprecationWarning)
X = DataWrapper(X)
return sk_cross_val_score(model, X, *args, **kwargs)这显然是为了处理旧版本的 sklearn.cross_validation.cross_val_score，因为它对 pandas DataFrame 的处理不够好。DataWrapper 在划分为训练和测试集时会返回一个 list 实例。
但是在 DataframeMapper 的 transform() 过程中，它没有被正确处理，如源代码所示
if self.df_out:
# 如果没有删除行，则保留原始索引，
# 否则使用新的整数索引
no_rows_dropped = len(X) == len(stacked)
if no_rows_dropped:
index = X.index # <== 这是错误的来源
else:
index = None在这里，X 不是一个 DataFrame，而是一个列表对象，因此 index 不是一个列表，而是 pandas 的实际索引，而是列表的函数，因此你得到了这个错误。
但由于较新的 sklearn cross_val_score 可以正确处理 DataFrame，你不需要使用其他导入。
将其从：
from sklearn_pandas import cross_val_score改为：
from sklearn.model_selection import cross_val_score这样你就不会再得到那个错误了。
但是，在代码的更深处，你会得到另一个关于的错误：
AttributeError: 'numpy.ndarray' 对象没有属性 'to_dict'这是因为你将两个 DataFrameMapper 对象包装在一个 FeatureUnion 中，通过这样做：
num_cat_union = FeatureUnion([("num_mapper", num_transf_mapper),
("cat_mapper", cat_transf_mapper)])然后这样做：
pipeline = Pipeline([("featureunion", num_cat_union),
("dictifier", Dictifier()),
("vectorizer", DictVectorizer(sort=False)),
("clf", xgb.XGBClassifier(max_depth=3))])你的 Dictifier 期望传递给它一个 DataFrame，以便它可以调用 to_dict()，但管道中的前一步 FeatureUnion 不会保留 DataFrame，它会将其转换为 numpy 数组。
一般来说，DataFrameMapper 和 FeatureUnion 不能很好地一起工作。我建议你完全删除 FeatureUnion，而是将你的两个 DataFrameMapper 对象 合并为一个对象。这将有效地实现你想要 FeatureUnion 实现的功能。
像这样做：
transformers = []
# 仅在此处组合你的两个操作
transformers.extend([([num_col], [Imputer(strategy="median"),
StandardScaler()]) for num_col in num_cols])
transformers.extend([(cat_col , [CategoricalImputer()]) for cat_col in cat_cols])
num_cat_union = DataFrameMapper(transformers,
input_df=True,
df_out=True)
# 你的其他代码......