我正在尝试根据这篇教程http://danielhnyk.cz/creating-your-own-estimator-scikit-learn/创建一个自定义转换器,用于Python sklearn流水线。
目前我的自定义类/转换器如下:
class SelectBestPercFeats(BaseEstimator, TransformerMixin):
def __init__(self, model=RandomForestRegressor(), percent=0.8,
random_state=52):
self.model = model
self.percent = percent
self.random_state = random_state
def fit(self, X, y, **fit_params):
"""
Find features with best predictive power for the model, and
have cumulative importance value less than self.percent
"""
# Check parameters
if not isinstance(self.percent, float):
print("SelectBestPercFeats.percent is not a float, it should be...")
elif not isinstance(self.random_state, int):
print("SelectBestPercFeats.random_state is not a int, it should be...")
# If checks are good proceed with fitting...
else:
try:
self.model.fit(X, y)
except:
print("Error fitting model inside SelectBestPercFeats object")
return self
# Get feature importance
try:
feat_imp = list(self.model.feature_importances_)
feat_imp_cum = pd.Series(feat_imp, index=X.columns) \
.sort_values(ascending=False).cumsum()
# Get features whose cumulative importance is <= `percent`
n_feats = len(feat_imp_cum[feat_imp_cum <= self.percent].index) + 1
self.bestcolumns_ = list(feat_imp_cum.index)[:n_feats]
except:
print ("ERROR: SelectBestPercFeats can only be used with models with"\
" .feature_importances_ parameter")
return self
def transform(self, X, y=None, **fit_params):
"""
Filter out only the important features (based on percent threshold)
for the model supplied.
:param X: Dataframe with features to be down selected
"""
if self.bestcolumns_ is None:
print("Must call fit function on SelectBestPercFeats object before transforming")
else:
return X[self.bestcolumns_]
我将把这个类整合到一个sklearn管道中,操作方法如下:
# Define feature selection and model pipeline components
rf_simp = RandomForestRegressor(criterion='mse', n_jobs=-1,
n_estimators=600)
bestfeat = SelectBestPercFeats(rf_simp, feat_perc)
rf = RandomForestRegressor(n_jobs=-1,
criterion='mse',
n_estimators=200,
max_features=0.4,
)
# Build Pipeline
master_model = Pipeline([('feat_sel', bestfeat), ('rf', rf)])
# define GridSearchCV parameter space to search,
# only listing one parameter to simplify troubleshooting
param_grid = {
'feat_select__percent': [0.8],
}
# Fit pipeline model
grid = GridSearchCV(master_model, cv=3, n_jobs=-1,
param_grid=param_grid)
# Search grid using CV, and get the best estimator
grid.fit(X_train, y_train)
每当我运行最后一行代码(
grid.fit(X_train, y_train)
)时,会出现以下 “PicklingError” 错误。有人可以看出我的代码中出了什么问题吗?编辑: 或者,我的Python设置有问题……可能我缺少一个包或类似的东西吗?我刚刚检查了一下,可以成功导入
pickle
追踪(Traceback)信息如下:``` Traceback (most recent call last): File "", line 5, in grid.fit(X_train, y_train) File "C:\Users\jjaaae\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\model_selection\_search.py", line 945, in fit return self._fit(X, y, groups, ParameterGrid(self.param_grid)) File "C:\Users\jjaaae\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\model_selection\_search.py", line 564, in _fit for parameters in parameter_iterable File "C:\Users\jjaaae\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\externals\joblib\parallel.py", line 768, in __call__ self.retrieve() File "C:\Users\jjaaae\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\externals\joblib\parallel.py", line 719, in retrieve raise exception File "C:\Users\jjaaae\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\externals\joblib\parallel.py", line 682, in retrieve self._output.extend(job.get(timeout=self.timeout)) File "C:\Users\jjaaae\AppData\Local\Programs\Python\Python36\lib\multiprocessing\pool.py", line 608, in get raise self._value _pickle.PicklingError: Can't pickle : attribute lookup SelectBestPercFeats on builtins failed ```
from transformation import SelectBestPercFeats
。这解决了pickling错误。 - Jed