felixm/ML4T
1
0
Fork 0
Code Releases Activity

Resolve split_value issue in DTLearner and pass all tests.

Browse Source
This commit is contained in:
Felix Martin 2020-09-25 10:27:15 -04:00
parent 7007bc7514
commit bd19b4fb18
3 changed files with 21 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
assess_learners/BagLearner.py
View File

@ -1,18 +1,14 @@
import numpy as np
from AbstractTreeLearner import AbstractTreeLearner
class BagLearner(object):
def __init__(self, learner, bags=20, boost=False, verbose=False, **kwargs):
class BagLearner(AbstractTreeLearner):
def __init__(self, learner, bags=9, boost=False, verbose=False, kwargs={}):
self.learner = learner
self.bags = bags
self.boost = boost
self.verbose = verbose
self.kwargs = kwargs
self.bags = bags
self.learners = [learner(**kwargs) for _ in range(bags)]
def author(self):
return 'felixm' # replace tb34 with your Georgia Tech username
def get_bag(self, data_x, data_y):
num_items = int(data_x.shape[0] * 0.5) # 50% of samples
bag_x, bag_y = [], []
@ -22,7 +18,6 @@ class BagLearner(object):
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
@ -36,10 +31,8 @@ class BagLearner(object):
def query(self, points):
"""
@summary: Estimate a set of test points given the model we built.
@param points: should be a numpy array with each row corresponding to a specific query.
@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)
if __name__=="__main__":
print("the secret clue is 'zzyzx'")

20
assess_learners/DTLearner.py
View File

@ -8,9 +8,6 @@ class DTLearner(AbstractTreeLearner):
self.leaf_size = leaf_size
self.verbose = verbose
def author(self):
return 'felixm' # replace tb34 with your Georgia Tech username
def get_correlations(self, xs, y):
""" Return a list of sorted 2-tuples where the first element
is the correlation and the second element is the index. Sorted by
@ -25,14 +22,23 @@ class DTLearner(AbstractTreeLearner):
return correlations
def get_i_and_split_value(self, xs, y):
# If all elements are true we would get one sub-tree with zero
# elements, but we need at least one element in both trees. We avoid
# zero-trees in two steps. First we take the average between the median
# value and a smaller value an use that as the new split value. If that
# doesn't work (when all values are the same) we choose the X with the
# next smaller correlation. We assert that not all values are
# smaller/equal to the split value at the end.
for _, i in self.get_correlations(xs, y):
split_value = np.median(xs[:,i])
select = xs[:, i] <= split_value
# If all elements are true we would get one sub-tree with zero
# elements, but we need at least one element. Therefore, we only
# choose the index if not all elements are true. If they are we go
# to the next smaller correlation.
if select.all():
for value in xs[:, i]:
if value < split_value:
split_value = (value + split_value) / 2.0
select = xs[:, i] <= split_value
if not select.all():
break
assert(not select.all())
return i, split_value

13
assess_learners/testlearner.py
View File

@ -48,12 +48,6 @@ if __name__=="__main__":
trainY = data[:train_rows,-1]
testX = data[train_rows:,0:-1]
testY = data[train_rows:,-1]
# trainX = data[:, 0:-1]
# trainY = data[:, -1]
# testX = data[:, 0:-1]
# testY = data[:, -1]
print(f"{testX.shape}")
print(f"{testY.shape}")
@ -85,8 +79,7 @@ if __name__=="__main__":
# test_learner(lrl.LinRegLearner)
test_learner(dtl.DTLearner, leaf_size=1)
test_learner(rtl.RTLearner)
test_learner(rtl.RTLearner, leaf_size=5)
# test_learner(bgl.BagLearner, learner=dtl.DTLearner, bags=20)
# learner = isl.InsaneLearner()
# test_learner(rtl.RTLearner, leaf_size=6)
test_learner(bgl.BagLearner, learner=dtl.DTLearner, bags=20, kwargs = {'leaf_size': 5})
test_learner(isl.InsaneLearner)