尝试运行以下代码时出现问题。这是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),
])
尝试运行时出现错误：
housing_prepared = full_pipeline.fit_transform(housing)
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是导致这个错误的原因吗？
在得到这个错误之后，我试图找出原因，为此我逐一运行上述变换器：
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)
这些可以正确执行，除了我得到的结果是一个大小（16512,16）的numpy.ndarray，而housing_prepared = full_pipeline.fit_transform(housing)的预期结果应该是一个颠簸的。大小（16512,17）。 所以这是我的第二个问题为什么会造成差异？
Housing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。
提前谢谢。
答案 0 :(得分：0)
看起来sklearn以不同于您期望的方式识别数据类型。确保将数字标识为int。最简单的方法：使用“您的”发布编码的作者提供的数据。 Aurelien Geron Hands on Machine Learning
答案 1 :(得分：0)
我在阅读本书时遇到了这个问题。在尝试了一堆变通办法（我觉得这是浪费我的时间）之后，我放弃了并安装了scikit-learn v0.20 dev。下载方向盘here并使用pip安装它。这应该允许您使用旨在处理这些问题的CategoricalEncoder类。
答案 2 :(得分：0)
我遇到了同样的问题，这是由缩进问题引起的，这种问题不会总是引发错误（请参见https://stackoverflow.com/a/14046894/3665886）。
如果您直接从书中复制了代码，请确保代码已正确缩进。
答案 3 :(得分：0)
为什么这个错误？
答案：因为您使用的是LabelBinarizer（），它的响应变量为ideally suitable。
该怎么办？：您有一个few options：
如果您使用this data，则您有9个预测变量（8个数字和1个类别）。
CombinedAttributesAdder（）增加了3列，而LabelBinarizer（）增加了5列，因此它变成了17列
请记住， sklearn.pipeline.FeatureUnion连接多个转换器对象的结果
手动进行操作时，不会添加原始的“ ocean_proximity”变量。
让我们看看它的作用：
print("housing_shape: ", housing.shape)
num_attribs = list(housing_num)
cat_attribs = ["ocean_proximity"]
DFS=DataFrameSelector(num_attribs)
a1=DFS.fit_transform(housing)
print('Numerical variables_shape: ', a1.shape)
imputer=SimpleImputer(strategy='median')
a2=imputer.fit_transform(a1)
a2.shape
与a1.shape相同
CAA=CombinedAttributesAdder()
a3=CAA.fit_transform(a2)
SS=StandardScaler()
a4=SS.fit_transform(a3) # added 3 variables
print('Numerical variable shape after CAA: ', a4.shape, '\n')
DFS2=DataFrameSelector(cat_attribs)
b1=DFS2.fit_transform(housing)
print("Categorical variables_shape: ", b1.shape)
LB=LabelBinarizer()
b2=LB.fit_transform(b1) # instead of one column now we have 5 columns
print('categorical variable shape after LabelBinarization: ', b2.shape)
增加了4列
print(b2)
result=np.concatenate((a4,b2),axis=1)
print('final shape: ', result.shape, '\n') # Final shape
注意：转换后的列（a4的结果）和二值化列（b2的结果）尚未添加到原始数据框中。 为此，您需要将numpy数组b2转换为数据框
new_features = pd.DataFrame(a4)
new_features.shape
ocean_cat = ['<1H OCEAN', 'INLAND', 'NEAR OCEAN', 'NEAR BAY', 'ISLAND']
ocean_LabelBinarize = pd.DataFrame(b2, columns=[ocean_cat[i] for i in
range(len(ocean_cat))])
ocean_LabelBinarize
housing_prepared_new = pd.concat([new_features, ocean_LabelBinarize],
axis=1)
print('Shape of new data prepared by above steps',
housing_prepared_new.shape)
当我们使用管道时，它也保留原始（ocean_proximity）变量和新创建的二值化列