尝试使用Sci-Kit Learn和Tensorflow完成动手ML的第2章中的项目时，在构建模型之前尝试通过管道运行数据时遇到类型错误。
我不断收到TypeError告诉我fit_transform（）接受2个位置参数，但给出了3个。不确定我做错了什么，因为我会尽我最大的努力进行练习。请告知，让我知道，或者在我尝试遵循产生错误的最小代码量时，是否需要更多信息。感谢您可能提供的见解。
代码如下
#Load the Data
import os
import tarfile
from six.moves import urllib
download_root = "https://raw.githubusercontent.com/ageron/handson-ml/master/"
housing_path = os.path.join('datasets', 'housing')
housing_url = download_root + "datasets/housing/housing.tgz"
def fetch_housing_data(housing_url=housing_url, housing_path = housing_path):
if not os.path.isdir(housing_path):
os.makedirs(housing_path)
tgz_path = os.path.join(housing_path, 'housing.tgz')
urllib.request.urlretrieve(housing_url, tgz_path)
housing_tgz = tarfile.open(tgz_path)
housing_tgz.extractall(path=housing_path)
housing_tgz.close()
# Pipeline Build
from sklearn.preprocessing import Imputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, LabelBinarizer
from sklearn.base import BaseEstimator, TransformerMixin
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):
return x[self.attribute_names].values
from sklearn.base import BaseEstimator, TransformerMixin
rooms_ix, bedrooms_ix, population_ix, household_ix = 3, 4, 5, 6
class CombinedAttributesAdder(BaseEstimator, TransformerMixin):
def __init__(self, add_bedrooms_per_room=True):
self.add_bedrooms_per_room = add_bedrooms_per_room
def fit(self, X, y=None):
return self
def transform(self, X, y=None):
rooms_per_house = X[:, rooms_ix] / X[:, household_ix]
pop_per_house = 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_house, pop_per_house,
bedrooms_per_room]
else:
return np.c_[X, rooms_per_house, pop_per_house]
num_attribs = list(house_num)
cat_attribs = ['ocean_proximity']
num_pipeline = Pipeline([
('selector', DataFrameSelector(num_attribs)),
('imputer', Imputer(strategy='median')),
('attribs_adder', CombinedAttributesAdder()),
('std_scaler', StandardScaler())
])
cat_pipeline = Pipeline([
('selector', DataFrameSelector(cat_attribs)),
('label_binarizer', LabelBinarizer())
])
from sklearn.compose import ColumnTransformer
full_pipeline = ColumnTransformer([
('num_pipeline', num_pipeline, num_attribs),
('cat_pipeline', cat_pipeline, cat_attribs),
])
Type Error encountered is as follows
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-50-925e65d2e69a> in <module>
----> 1 house_prep = full_pipeline.fit_transform(house)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in fit_transform(self, X, y)
474 self._validate_remainder(X)
475
--> 476 result = self._fit_transform(X, y, _fit_transform_one)
477
478 if not result:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in _fit_transform(self, X, y, func, fitted)
418 message=self._log_message(name, idx, len(transformers)))
419 for idx, (name, trans, column, weight) in enumerate(
--> 420 self._iter(fitted=fitted, replace_strings=True), 1))
421 except ValueError as e:
422 if "Expected 2D array, got 1D array instead" in str(e):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
922 self._iterating = self._original_iterator is not None
923
--> 924 while self.dispatch_one_batch(iterator):
925 pass
926
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
714 with self._lock:
715 job_idx = len(self._jobs)
--> 716 job = self._backend.apply_async(batch, callback=cb)
717 # A job can complete so quickly than its callback is
718 # called before we get here, causing self._jobs to
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback)
180 def apply_async(self, func, callback=None):
181 """Schedule a func to be run"""
--> 182 result = ImmediateResult(func)
183 if callback:
184 callback(result)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch)
547 # Don't delay the application, to avoid keeping the input
548 # arguments in memory
--> 549 self.results = batch()
550
551 def get(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
714 with _print_elapsed_time(message_clsname, message):
715 if hasattr(transformer, 'fit_transform'):
--> 716 res = transformer.fit_transform(X, y, **fit_params)
717 else:
718 res = transformer.fit(X, y, **fit_params).transform(X)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py in fit_transform(self, X, y, **fit_params)
391 return Xt
392 if hasattr(last_step, 'fit_transform'):
--> 393 return last_step.fit_transform(Xt, y, **fit_params)
394 else:
395 return last_step.fit(Xt, y, **fit_params).transform(Xt)
TypeError: fit_transform() takes 2 positional arguments but 3 were given