我正在尝试使用一些自定义转换器优化 scikit-learn 管道中的超参数，但我不断收到错误消息:
from sklearn.model_selection import TimeSeriesSplit
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
class RollingMeanTransform(BaseEstimator, TransformerMixin):
def __init__(self, col, window=3):
self._window = window
self._col = col
def fit(self, X, y=None):
return self
def transform(self, X):
df = X.copy()
df['{}_rolling_mean'.format(self._col)] = df[self._col].shift(1).rolling(self._window).mean().fillna(0.0)
return df
class TimeEncoding(BaseEstimator, TransformerMixin):
def __init__(self, col, drop_original=True):
self._col = col
self._drop_original = drop_original
def fit(self, X, y=None):
return self
def transform(self, X):
X = X.copy()
unique_vals = float(len(X[self._col].unique()))
X['sin_{}'.format(self._col)] = np.sin(2 * np.pi * X[self._col] / unique_vals)
X['cos_{}'.format(self._col)] = np.cos(2 * np.pi * X[self._col] / unique_vals)
if self._drop_original:
X.drop([self._col], axis=1, inplace=True, errors='ignore')
return X
huber = HuberRegressor()
huber_max_iter = [100, 200, 500, 1000]
huber_alpha = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1.0, 10, 100]
huber_epsilon = [1.15, 1.25, 1.35, 1.5]
huber_grid = {'clf__alpha':huber_alpha,
'clf__epsilon':huber_epsilon,
'clf__max_iter':huber_max_iter,
}
regression_pipeline = Pipeline([('encoding', TimeEncoding('my_col')),
('mean', RollingMeanTransform('my_other_col')),
('select', Treshold()),
('scale', Scale()),
('clf', huber)
])
我试着用它来拟合:
grid = GridSearchCV(regression_pipeline, huber_grid, cv=TimeSeriesSplit(n_splits=5))
grid.fit(X_train, y_train)
但我得到以下异常:
ValueError Traceback (most recent call last)
<ipython-input-14-3949096c802a> in <module>()
----> 1 grid.fit(X_train, y_train)
~/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
637 error_score=self.error_score)
638 for parameters, (train, test) in product(candidate_params,
--> 639 cv.split(X, y, groups)))
640
641 # if one choose to see train score, "out" will contain train score info
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py 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:
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py 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
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py 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)
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py 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):
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py 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):
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~/anaconda3/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, error_score)
456 estimator.fit(X_train, **fit_params)
457 else:
--> 458 estimator.fit(X_train, y_train, **fit_params)
459
460 except Exception as e:
~/anaconda3/lib/python3.6/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
246 This estimator
247 """
--> 248 Xt, fit_params = self._fit(X, y, **fit_params)
249 if self._final_estimator is not None:
250 self._final_estimator.fit(Xt, y, **fit_params)
~/anaconda3/lib/python3.6/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
211 Xt, fitted_transformer = fit_transform_one_cached(
212 cloned_transformer, None, Xt, y,
--> 213 **fit_params_steps[name])
214 # Replace the transformer of the step with the fitted
215 # transformer. This is necessary when loading the transformer
~/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/memory.py in __call__(self, *args, **kwargs)
360
361 def __call__(self, *args, **kwargs):
--> 362 return self.func(*args, **kwargs)
363
364 def call_and_shelve(self, *args, **kwargs):
~/anaconda3/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, weight, X, y, **fit_params)
579 **fit_params):
580 if hasattr(transformer, 'fit_transform'):
--> 581 res = transformer.fit_transform(X, y, **fit_params)
582 else:
583 res = transformer.fit(X, y, **fit_params).transform(X)
~/anaconda3/lib/python3.6/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
518 else:
519 # fit method of arity 2 (supervised transformation)
--> 520 return self.fit(X, y, **fit_params).transform(X)
521
522
~/my_project/my_model.py in transform(self, X)
126 def transform(self, X):
127 X = X.copy()
--> 128 unique_vals = float(len(X[self._col].unique()))
129 X['sin_{}'.format(self._col)] = np.sin(2 * np.pi * X[self._col] / unique_vals)
130 X['cos_{}'.format(self._col)] = np.cos(2 * np.pi * X[self._col] / unique_vals)
~/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in __getitem__(self, key)
2137 return self._getitem_multilevel(key)
2138 else:
-> 2139 return self._getitem_column(key)
2140
2141 def _getitem_column(self, key):
~/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in _getitem_column(self, key)
2144 # get column
2145 if self.columns.is_unique:
-> 2146 return self._get_item_cache(key)
2147
2148 # duplicate columns & possible reduce dimensionality
~/anaconda3/lib/python3.6/site-packages/pandas/core/generic.py in _get_item_cache(self, item)
1840 res = cache.get(item)
1841 if res is None:
-> 1842 values = self._data.get(item)
1843 res = self._box_item_values(item, values)
1844 cache[item] = res
~/anaconda3/lib/python3.6/site-packages/pandas/core/internals.py in get(self, item, fastpath)
3850 loc = indexer.item()
3851 else:
-> 3852 raise ValueError("cannot label index with a null key")
3853
3854 return self.iget(loc, fastpath=fastpath)
ValueError: cannot label index with a null key
我不知道发生了什么，也不知道如何解决。如果我移除变压器，它就可以工作，但我的管道中需要它。
如果我将管道更改为
regression_pipeline = Pipeline([('mean', RollingMeanTransform('my_other_col')),
('encoding', TimeEncoding('my_col')),
('select', Treshold()),
('scale', Scale()),
('clf', huber)
])
我得到了同样的错误，但这次调用了 mean 转换器。
完整的代码示例:
from sklearn.linear_model import HuberRegressor
from sklearn.model_selection import TimeSeriesSplit
from sklearn.model_selection import GridSearchCV
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
import pandas as pd
import numpy as np
class RollingMeanTransform(BaseEstimator, TransformerMixin):
def __init__(self, col, window=3):
self._window = window
self._col = col
def fit(self, X, y=None):
return self
def transform(self, X):
df = X.copy()
df['{}_rolling_mean'.format(self._col)] = df[self._col].shift(1).rolling(self._window).mean().fillna(0.0)
return df
class TimeEncoding(BaseEstimator, TransformerMixin):
def __init__(self, col, drop_original=True):
self._col = col
self._drop_original = drop_original
def fit(self, X, y=None):
return self
def transform(self, X):
X = X.copy()
unique_vals = float(len(X[self._col].unique()))
X['sin_{}'.format(self._col)] = np.sin(2 * np.pi * X[self._col] / unique_vals)
X['cos_{}'.format(self._col)] = np.cos(2 * np.pi * X[self._col] / unique_vals)
if self._drop_original:
X.drop([self._col], axis=1, inplace=True, errors='ignore')
return X
class Treshold(BaseEstimator, TransformerMixin):
# note: Threshold which removes features with constant value
# and preserves the input data as data frame
def __init__(self):
self.to_keep = list()
def fit(self, X, y=None):
self.to_keep = list()
self.colname_original = X.columns
for i, col in enumerate(X):
if len(np.unique(X.values[:, i])) >= 2:
self.to_keep.append(col)
return self
def transform(self, X, copy=None):
return X[self.to_keep]
class Scale(BaseEstimator, TransformerMixin):
# note: scaler which keeps the input data as data frame
# and does not scale binary features
def __init__(self, copy=True, with_mean=True, with_std=True):
self.scaler = StandardScaler(copy, with_mean, with_std)
self.bin_vars_index = list()
self.cont_vars_index = list()
self.colnames_original = list()
def fit(self, X, y=None):
self.bin_vars_index = list()
self.cont_vars_index = list()
self.colnames_original = list()
self.colnames_original = X.columns
for i in range(X.shape[1]):
if len(np.unique(X.values[:, i])) <= 2:
self.bin_vars_index.append(i)
else:
self.cont_vars_index.append(i)
self.scaler.fit(X.values[:, self.cont_vars_index])
return self
def transform(self, X, copy=None):
X_tail = self.scaler.transform(X.values[:, self.cont_vars_index], copy)
res = np.concatenate((X.values[:, self.bin_vars_index], X_tail), axis=1)
colnames_res = np.array(
list(self.colnames_original[self.bin_vars_index]) + list(self.colnames_original[self.cont_vars_index]))
assert len(colnames_res) == len(self.colnames_original)
res = pd.DataFrame(data=res, columns=colnames_res)
return res[[str(el) for el in self.colnames_original]].set_index(X.index)
huber = HuberRegressor()
huber_max_iter = [100, 200, 500, 1000]
huber_alpha = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1.0, 10, 100]
huber_epsilon = [1.15, 1.25, 1.35, 1.5]
huber_grid = {'clf__alpha':huber_alpha,
'clf__epsilon':huber_epsilon,
'clf__max_iter':huber_max_iter,
}
regression_pipeline = Pipeline([('encoding', TimeEncoding('my_col')),
('mean', RollingMeanTransform('my_other_col')),
('select', Treshold()),
('scale', Scale()),
('clf', huber)
])
grid = GridSearchCV(regression_pipeline, huber_grid, cv=TimeSeriesSplit(n_splits=5))
X = pd.DataFrame(np.random.randint(low=0, high=10, size=(20, 2)), columns=['my_col', 'my_other_col'])
y = pd.Series(np.random.randint(low=0, high=10, size=(20,)))
grid.fit(X, y)
最佳答案
您会看到 GridSearchCV(以及 scikit-learn 中的大多数交叉验证实用程序)克隆提供的数据以执行网格搜索。
在这样做时，他们将使用 get_params() and set_params()您继承的 BaseEstimator 类。现在 get_params() 将从您声明的 __init__() 方法获取参数。
init_signature = signature(init)
# Consider the constructor parameters excluding 'self'
parameters = [p for p in init_signature.parameters.values()
if p.name != 'self' and p.kind != p.VAR_KEYWORD]
...
...
现在要获取值，使用]( https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/base.py#L228 ):
for key in self._get_param_names():
value = getattr(self, key, None)
所以这将给出的参数是:
col = None
drop_original = None
不是您使用的带有 前导下划线 的那些。两者的值都是 None，因为您的对象没有任何具有这些名称的属性。
现在这些无值参数将用于实例化克隆对象in clone() :
...
new_object = klass(**new_object_params)
...
...
然后这些 None 值将设置为您的 _col 和 _drop_original。这就是错误的根源。
这件事已记录在the deleloper guidelines in scikit中:
The arguments accepted by init should all be keyword arguments with a default value. In other words, a user should be able to instantiate an estimator without passing any arguments to it. The arguments should all correspond to hyperparameters describing the model or the optimisation problem the estimator tries to solve.
In addition, every keyword argument accepted by init should correspond to an attribute on the instance. Scikit-learn relies on this to find the relevant attributes to set on an estimator when doing model selection.
因此，建议的解决方法是从参数名称中删除前导下划线(以便 __init__ 和 self 中的名称应该相同):
class TimeEncoding(BaseEstimator, TransformerMixin):
# Changed the names from _col to col
def __init__(self, col, drop_original=True):
self.col = col
self.drop_original = drop_original
def transform(self, X):
X = X.copy()
# Updated the names to be used
unique_vals = float(len(X[self.col].unique()))
X['sin_{}'.format(self.col)] = np.sin(2 * np.pi * X[self.col] / unique_vals)
X['cos_{}'.format(self.col)] = np.cos(2 * np.pi * X[self.col] / unique_vals)
if self.drop_original:
X.drop([self.col], axis=1, inplace=True, errors='ignore')
return X
现在对所有自定义估算器执行此操作。
现在，如果您在使用属性的前导下划线方面有一些限制(可能尝试将它们设为私有(private)或类似的东西)，您的第二个选择是覆盖 set_params() 方法以显式设置参数。
关于python - 自定义转换器和 GridSearch - 管道中的 ValueError，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/50523930/