我有一个 scikit 学习管道来缩放数字特征和编码分类特征。在我尝试从 imblearn 实现RandomUnderSampler之前，它工作正常。我的目标是实施欠采样步骤，因为我的数据集非常不平衡 1:1000。
我确保使用 imblearn 中的 Pipeline 方法而不是 sklearn。下面是我尝试过的代码。
代码数据在没有欠采样方法的情况下工作（使用 sklearn 管道）。
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from imblearn.pipeline import make_pipeline as make_pipeline_imb
from imblearn.pipeline import Pipeline as Pipeline_imb
from sklearn.base import BaseEstimator, TransformerMixin
class TypeSelector(BaseEstimator, TransformerMixin):
def __init__(self, dtype):
self.dtype = dtype
def fit(self, X, y=None):
return self
def transform(self, X):
assert isinstance(X, pd.DataFrame)
return X.select_dtypes(include=[self.dtype])
transformer = Pipeline([
# Union numeric, categoricals and boolean
('features', FeatureUnion(n_jobs=1, transformer_list=[
# Select bolean features
('boolean', Pipeline([
('selector', TypeSelector('bool')),
])),
# Select and scale numericals
('numericals', Pipeline([
('selector', TypeSelector(np.number)),
('scaler', StandardScaler()),
])),
# Select and encode categoricals
('categoricals', Pipeline([
('selector', TypeSelector('category')),
('encoder', OneHotEncoder(handle_unknown='ignore')),
]))
])),
])
pipe = Pipeline([('prep', transformer),
('clf', RandomForestClassifier(n_estimators=500, class_weight='balanced'))
])
使用 undersampler 方法不起作用的代码（使用 imblearn 管道）。
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from imblearn.pipeline import make_pipeline as make_pipeline_imb
from imblearn.pipeline import Pipeline as Pipeline_imb
from sklearn.base import BaseEstimator, TransformerMixin
class TypeSelector(BaseEstimator, TransformerMixin):
def __init__(self, dtype):
self.dtype = dtype
def fit(self, X, y=None):
return self
def transform(self, X):
assert isinstance(X, pd.DataFrame)
return X.select_dtypes(include=[self.dtype])
transformer = Pipeline_imb([
# Union numeric, categoricals and boolean
('features', FeatureUnion(n_jobs=1, transformer_list=[
# Select bolean features
('boolean', Pipeline_imb([
('selector', TypeSelector('bool')),
])),
# Select and scale numericals
('numericals', Pipeline_imb([
('selector', TypeSelector(np.number)),
('scaler', StandardScaler()),
])),
# Select and encode categoricals
('categoricals', Pipeline_imb([
('selector', TypeSelector('category')),
('encoder', OneHotEncoder(handle_unknown='ignore')),
]))
])),
])
pipe = Pipeline_imb([
('sampler', RandomUnderSampler(0.1)),
('prep', transformer),
('clf', RandomForestClassifier(n_estimators=500, class_weight='balanced'))
])
这是我得到的错误：
/usr/local/lib/python3.6/dist-packages/sklearn/pipeline.py in __init__(self, steps, memory, verbose)
133 def __init__(self, steps, memory=None, verbose=False):
134 self.steps = steps
--> 135 self._validate_steps()
136 self.memory = memory
137 self.verbose = verbose
/usr/local/lib/python3.6/dist-packages/imblearn/pipeline.py in _validate_steps(self)
144 if isinstance(t, pipeline.Pipeline):
145 raise TypeError(
--> 146 "All intermediate steps of the chain should not be"
147 " Pipelines")
148
TypeError: All intermediate steps of the chain should not be Pipelines