当我试图运行下面的代码时遇到了一个问题。这是一个关于住房价格的机器学习问题。
from sklearn.pipeline import FeatureUnion
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.base import BaseEstimator,TransformerMixin
num_attributes=list(housing_num)
cat_attributes=['ocean_proximity']
rooms_ix, bedrooms_ix, population_ix, household_ix = 3, 4, 5, 6
class DataFrameSelector(BaseEstimator,TransformerMixin):
def __init__(self,attribute_names):
self.attribute_names=attribute_names
def fit(self,X,y=None):
return self
def transform(self,X,y=None):
return X[self.attribute_names].values
class CombinedAttributesAdder(BaseEstimator, TransformerMixin):
def __init__(self, add_bedrooms_per_room = True): # no *args or **kargs
self.add_bedrooms_per_room = add_bedrooms_per_room
def fit(self, X,y=None):
return self # nothing else to do
def transform(self, X,y=None):
rooms_per_household = X[:, rooms_ix] / X[:, household_ix]
population_per_household = X[:, population_ix] / X[:, household_ix]
if self.add_bedrooms_per_room:
bedrooms_per_room = X[:, bedrooms_ix] / X[:, rooms_ix]
return np.c_[X, rooms_per_household, population_per_household, bedrooms_per_room]
else:
return np.c_[X, rooms_per_household, population_per_household]
num_pipeline=Pipeline([
('selector',DataFrameSelector(num_attributes)),
('imputer',Imputer(strategy="median")),
('attribs_adder',CombinedAttributesAdder()),
('std_scalar',StandardScaler()),
])
cat_pipeline=Pipeline([
('selector',DataFrameSelector(cat_attributes)),
('label_binarizer',LabelBinarizer()),
])
full_pipeline=FeatureUnion(transformer_list=[
("num_pipeline",num_pipeline),
("cat_pipeline",cat_pipeline),
])
当我试图运行时，出现了错误。
housing_prepared = full_pipeline.fit_transform(housing)
然后错误显示为：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-141-acd0fd68117b> in <module>()
----> 1 housing_prepared = full_pipeline.fit_transform(housing)
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/pipeline.pyc in fit_transform(self, X, y, **fit_params)
744 delayed(_fit_transform_one)(trans, weight, X, y,
745 **fit_params)
--> 746 for name, trans, weight in self._iter())
747
748 if not result:
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
777 # was dispatched. In particular this covers the edge
778 # case of Parallel used with an exhausted iterator.
--> 779 while self.dispatch_one_batch(iterator):
780 self._iterating = True
781 else:
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
586 dispatch_timestamp = time.time()
587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588 job = self._backend.apply_async(batch, callback=cb)
589 self._jobs.append(job)
590
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in apply_async(self, func, callback)
109 def apply_async(self, func, callback=None):
110 """Schedule a func to be run"""
--> 111 result = ImmediateResult(func)
112 if callback:
113 callback(result)
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in __init__(self, batch)
330 # Don't delay the application, to avoid keeping the input
331 # arguments in memory
--> 332 self.results = batch()
333
334 def get(self):
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/pipeline.pyc in _fit_transform_one(transformer, weight, X, y, **fit_params)
587 **fit_params):
588 if hasattr(transformer, 'fit_transform'):
--> 589 res = transformer.fit_transform(X, y, **fit_params)
590 else:
591 res = transformer.fit(X, y, **fit_params).transform(X)
/Users/nieguangtao/ml/env_1/lib/python2.7/site-packages/sklearn/pipeline.pyc in fit_transform(self, X, y, **fit_params)
290 Xt, fit_params = self._fit(X, y, **fit_params)
291 if hasattr(last_step, 'fit_transform'):
--> 292 return last_step.fit_transform(Xt, y, **fit_params)
293 elif last_step is None:
294 return Xt
TypeError: fit_transform() takes exactly 2 arguments (3 given)
所以... 我的第一个问题n是什么原因导致这个bug？
得到这个bug后，我试图找出原因，所以我把上面的变换器一个个运行成这样。
DFS=DataFrameSelector(num_attributes)
a1=DFS.fit_transform(housing)
imputer=Imputer(strategy='median')
a2=imputer.fit_transform(a1)
CAA=CombinedAttributesAdder()
a3=CAA.fit_transform(a2)
SS=StandardScaler()
a4=SS.fit_transform(a3)
DFS2=DataFrameSelector(cat_attributes)
b1=DFS2.fit_transform(housing)
LB=LabelBinarizer()
b2=LB.fit_transform(b1)
result=np.concatenate((a4,b2),axis=1)
这些都能正确执行，除了... 结果 我得到的是一个大小为(16512, 16)的numpy.ndarray，而预期结果是 housing_prepared = full_pipeline.fit_transform(housing) 应该是一个大小为(16512,17)的bumpy.ndarray。所以这是我的第二个问题，为什么会造成这种差异？
房屋是一个大小为(16512,9)的DataFrame，只有1个分类特征和8个数字特征。
先谢谢你。
看起来sklearn识别数据类型的方式比你预期的要好。确保数字被识别为int。最简单的方法。使用 "你 "发布的编码的作者提供的数据。Aurelien Geron 手上的机器学习
我在看这本书的时候就遇到了这个问题。在尝试了一系列的解决方法后（我觉得这是在浪费我的时间），我放弃了，安装了scikit-learn v0.20开发版。下载轮子 此处 并使用pip进行安装。这应该允许你使用为处理这些问题而设计的CategoricalEncoder类。
我也遇到了同样的问题，它是由一个缩进问题引起的，这个问题并不总是抛出一个错误（见 https:/stackoverflow.coma140468943665886。).
如果你直接从书中复制代码，请确保代码正确缩进。