39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
import numpy as np
|
|
from AbstractTreeLearner import AbstractTreeLearner
|
|
|
|
|
|
class BagLearner(AbstractTreeLearner):
|
|
def __init__(self, learner, bags=9, boost=False, verbose=False, kwargs={}):
|
|
self.learner = learner
|
|
self.verbose = verbose
|
|
self.bags = bags
|
|
self.learners = [learner(**kwargs) for _ in range(bags)]
|
|
|
|
def get_bag(self, data_x, data_y):
|
|
num_items = int(data_x.shape[0] * 0.5) # 50% of samples
|
|
bag_x, bag_y = [], []
|
|
for _ in range(num_items):
|
|
i = np.random.randint(0, data_x.shape[0])
|
|
bag_x.append(data_x[i,:])
|
|
bag_y.append(data_y[i])
|
|
return np.array(bag_x), np.array(bag_y)
|
|
|
|
def addEvidence(self, data_x, data_y):
|
|
"""
|
|
@summary: Add training data to learner
|
|
@param dataX: X values of data to add
|
|
@param dataY: the Y training values
|
|
"""
|
|
for learner in self.learners:
|
|
x, y = self.get_bag(data_x, data_y)
|
|
learner.addEvidence(x, y)
|
|
|
|
def query(self, points):
|
|
"""
|
|
@summary: Estimate a set of test points given the model we built.
|
|
@param points: numpy array with each row corresponding to a query.
|
|
@returns the estimated values according to the saved model.
|
|
"""
|
|
return np.mean([l.query(points) for l in self.learners], axis=0)
|
|
|