class _BaggingRegressorImpl:
def __init__(
self,
base_estimator=None,
n_estimators=10,
*,
max_samples=1.0,
max_features=1.0,
bootstrap=True,
bootstrap_features=False,
oob_score=False,
warm_start=False,
n_jobs=None,
random_state=None,
verbose=0,
):
estimator_impl = base_estimator
self._hyperparams = {
"base_estimator": estimator_impl,
"n_estimators": n_estimators,
"max_samples": max_samples,
"max_features": max_features,
"bootstrap": bootstrap,
"bootstrap_features": bootstrap_features,
"oob_score": oob_score,
"warm_start": warm_start,
"n_jobs": n_jobs,
"random_state": random_state,
"verbose": verbose,
}
self._wrapped_model = SKLModel(**self._hyperparams)
self._hyperparams["base_estimator"] = base_estimator
def get_params(self, deep=True):
out = self._wrapped_model.get_params(deep=deep)
# we want to return the lale operator, not the underlying impl
out["base_estimator"] = self._hyperparams["base_estimator"]
return out
def fit(self, X, y, sample_weight=None):
if isinstance(X, pd.DataFrame):
feature_transformer = FunctionTransformer(
func=lambda X_prime: pd.DataFrame(X_prime, columns=X.columns),
inverse_func=None,
check_inverse=False,
)
self._hyperparams["base_estimator"] = (
feature_transformer >> self._hyperparams["base_estimator"]
)
self._wrapped_model = SKLModel(**self._hyperparams)
self._wrapped_model.fit(X, y, sample_weight)
return self
def predict(self, X):
return self._wrapped_model.predict(X)
def score(self, X, y, sample_weight=None):
return self._wrapped_model.score(X, y, sample_weight)
def test_parameters(self):
""" Testing parameters of Model class. """
#1.)
#create instance of PLS model using Model class & creating instance
# using SKlearn libary, comparing if the parameters of both instances are equal
pls_parameters = {"n_components": 20, "scale": False, "max_iter": 200}
model = Model(algorithm="PlsRegression", parameters=pls_parameters)
pls_model = PLSRegression(n_components=20, scale="svd", max_iter=200)
for k, v in model.model.get_params().items():
self.assertIn(k, list(pls_model.get_params()))
#2.)
rf_parameters = {"n_estimators": 200, "max_depth": 50,"min_samples_split": 10}
model = Model(algorithm="RandomForest", parameters=rf_parameters)
rf_model = RandomForestRegressor(n_estimators=200, max_depth=50, min_samples_split=10)
for k, v in model.model.get_params().items():
self.assertIn(k, list(rf_model.get_params()))
#3.)
knn_parameters = {"n_neighbors": 10, "weights": "distance", "algorithm": "ball_tree"}
model = Model(algorithm="KNN", parameters=knn_parameters)
knn_model = KNeighborsRegressor(n_neighbors=10, weights='distance', algorithm="kd_tree")
for k, v in model.model.get_params().items():
self.assertIn(k, list(knn_model.get_params()))
#4.)
svr_parameters = {"kernel": "poly", "degree": 5, "coef0": 1}
model = Model(algorithm="SVR",parameters=svr_parameters)
svr_model = SVR(kernel='poly', degree=5, coef0=1)
for k, v in model.model.get_params().items():
self.assertIn(k, list(svr_model.get_params()))
#5.)
ada_parameters = {"n_estimators": 150, "learning_rate": 1.2, "loss": "square"}
model = Model(algorithm="AdaBoost", parameters=ada_parameters)
ada_model = AdaBoostRegressor(n_estimators=150, learning_rate=1.2, loss="square")
for k, v in model.model.get_params().items():
self.assertIn(k, list(ada_model.get_params()))
#6.)
bagging_parameters = {"n_estimators": 50, "max_samples": 1.5, "max_features": 2}
model = Model(algorithm="Bagging", parameters=bagging_parameters)
bagging_model = BaggingRegressor(n_estimators=50, max_samples=1.5, max_features="square")
for k, v in model.model.get_params().items():
self.assertIn(k, list(bagging_model.get_params()))
#7.)
lasso_parameters = {"alpha": 1.5, "max_iter": 500, "tol": 0.004}
model = Model(algorithm="lasso", parameters=lasso_parameters)
lasso_model = Lasso(alpha=1.5, max_iter=500, tol=0.004)
for k, v in model.model.get_params().items():
self.assertIn(k, list(lasso_model.get_params()))
f"{mean_absolute_error(target_test, target_predicted):.2f} k$")
# %% [markdown]
# Now, create a `RandomizedSearchCV` instance using the previous model and
# tune the important parameters of the bagging regressor. Find the best
# parameters and check if you are able to find a set of parameters that
# improve the default regressor still using the mean absolute error as a
# metric.
# ```{tip}
# You can list the bagging regressor's parameters using the `get_params`
# method.
# ```
# %%
for param in bagging.get_params().keys():
print(param)
# %%
from scipy.stats import randint
from sklearn.model_selection import RandomizedSearchCV
param_grid = {
"n_estimators": randint(10, 30),
"max_samples": [0.5, 0.8, 1.0],
"max_features": [0.5, 0.8, 1.0],
"base_estimator__max_depth": randint(3, 10),
}
search = RandomizedSearchCV(bagging,
param_grid,
n_iter=20,
class EnsembleModel(BaseEstimator, TransformerMixin):
"""
Class used to construct ensemble models with a particular number and type of weak learner (base model). The
ensemble model is compatible with most scikit-learn regressor models and KerasRegressor models
Args:
model: (str), string name denoting the name of the model type to use as the base model
n_estimators: (int), the number of base models to include in the ensemble
kwargs: keyword arguments for the base model parameter names and values
Methods:
fit: method that fits the model parameters to the provided training data
Args:
X: (pd.DataFrame), dataframe of X features
y: (pd.Series), series of y target data
Returns:
fitted model
predict: method that evaluates model on new data to give predictions
Args:
X: (pd.DataFrame), dataframe of X features
as_frame: (bool), whether to return data as pandas dataframe (else numpy array)
Returns:
series or array of predicted values
get_params: method to output key model parameters
Args:
deep: (bool), determines the extent of information returned, default True
Returns:
information on model parameters
"""
def __init__(self, model, n_estimators, **kwargs):
super(EnsembleModel, self).__init__()
try:
model = dict(sklearn.utils.all_estimators())[model](**kwargs)
except:
print(
'Could not find designated model type in scikit-learn model library. Note the other supported model'
'type is the keras.wrappers.scikit_learn.KerasRegressor model')
self.n_estimators = n_estimators
self.model = BaggingRegressor(base_estimator=model,
n_estimators=self.n_estimators)
self.base_estimator_ = model.__class__.__name__
def fit(self, X, y):
return self.model.fit(X, y)
def predict(self, X, as_frame=True):
if as_frame == True:
return pd.DataFrame(self.model.predict(X),
columns=['y_pred']).squeeze()
else:
return self.model.predict(X).ravel()
def get_params(self, deep=True):
return self.model.get_params(deep)
