- setup pipeline
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
num_pipeline = Pipeline([
(‘imputer’, Imputer(strategy=“median”)), #中值写入
(‘attribs_adder’, CombinedAttributesAdder()),#增加比例列
(‘std_scaler’, StandardScaler()),#标准化
])
housing_num_tr = num_pipeline.fit_transform(housing_num)
And a transformer to just select a subset of the Pandas DataFrame columns:
from sklearn.base import BaseEstimator, TransformerMixin
Create a class to select numerical or categorical columns
since Scikit-Learn doesn’t handle DataFrames yet
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
2. 建立总的pipeline*
num_attribs = list(housing_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)),
(‘cat_encoder’, CategoricalEncoder(encoding=“onehot-dense”)),
])
from sklearn.pipeline import FeatureUnion
full_pipeline = FeatureUnion(transformer_list=[
(“num_pipeline”, num_pipeline),
(“cat_pipeline”, cat_pipeline),
])
housing_prepared = full_pipeline.fit_transform(housing)
housing_prepared
