heamy之stacking和blending实例

1、stacking实例

from heamy.dataset import Dataset
from heamy.estimator import Regressor, Classifier
from heamy.pipeline import ModelsPipeline
from sklearn import cross_validation
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error
#加载数据集
from sklearn.datasets import load_boston
data = load_boston()
X, y = data['data'], data['target']
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=, random_state=)
#创建数据集
dataset = Dataset(X_train,y_train,X_test)
#创建RF模型和LR模型
model_rf = Regressor(dataset=dataset, estimator=RandomForestRegressor, parameters={'n_estimators': },name='rf')
model_lr = Regressor(dataset=dataset, estimator=LinearRegression, parameters={'normalize': True},name='lr')
# Stack两个模型
# Returns new dataset with out-of-fold predictions
pipeline = ModelsPipeline(model_rf,model_lr)
stack_ds = pipeline.stack(k=,seed=)
#第二层使用lr模型stack
stacker = Regressor(dataset=stack_ds, estimator=LinearRegression)
results = stacker.predict()
# 使用10折交叉验证结果
results10 = stacker.validate(k=,scorer=mean_absolute_error)
           

2、blending实例

from heamy.dataset import Dataset
from heamy.estimator import Regressor, Classifier
from heamy.pipeline import ModelsPipeline
from sklearn import cross_validation
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error
#加载数据集
from sklearn.datasets import load_boston
data = load_boston()
X, y = data['data'], data['target']
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=, random_state=)
#创建数据集
dataset = Dataset(X_train,y_train,X_test)
#创建RF模型和LR模型
model_rf = Regressor(dataset=dataset, estimator=RandomForestRegressor, parameters={'n_estimators': },name='rf')
model_lr = Regressor(dataset=dataset, estimator=LinearRegression, parameters={'normalize': True},name='lr')
# Blending两个模型
# Returns new dataset with out-of-fold predictions
pipeline = ModelsPipeline(model_rf,model_lr)
stack_ds = pipeline.blend(proportion=,seed=)
#第二层使用lr模型stack
stacker = Regressor(dataset=stack_ds, estimator=LinearRegression)
results = stacker.predict()
# 使用10折交叉验证结果
results10 = stacker.validate(k=,scorer=mean_absolute_error)
           

3、权重加权平均

from heamy.dataset import Dataset
from heamy.estimator import Regressor, Classifier
from heamy.pipeline import ModelsPipeline
from sklearn import cross_validation
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error
from sklearn.neighbors import KNeighborsRegressor
data = load_boston()
X, y = data['data'], data['target']
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=, random_state=)
#创建数据集
dataset = Dataset(X_train,y_train,X_test)

model_rf = Regressor(dataset=dataset, estimator=RandomForestRegressor, parameters={'n_estimators': },name='rf')
model_lr = Regressor(dataset=dataset, estimator=LinearRegression, parameters={'normalize': True},name='lr')
model_knn = Regressor(dataset=dataset, estimator=KNeighborsRegressor, parameters={'n_neighbors': },name='knn')

pipeline = ModelsPipeline(model_rf,model_lr,model_knn)

weights = pipeline.find_weights(mean_absolute_error)
result = pipeline.weight(weights)
           

4、简单取平均或自定义

#取平均
# get predictions for test 
result = pipeline.mean().execute()
# or Validate 
_ = pipeline.mean().validate(mean_absolute_error,)
#自定义
result = pipeline.apply(lambda x: np.max(x,axis=)).execute()
           

参考文献：

1、http://heamy.readthedocs.io/en/latest/estimator.html

2、https://github.com/rushter/heamy/blob/master/examples/walkthrough.ipynb