Add my DT Learner to defeat_learners assignment
parent
db537d7043
commit
a662e302db
|
@ -1,64 +1,108 @@
|
||||||
"""
|
import numpy as np
|
||||||
A simple wrapper for linear regression. (c) 2015 Tucker Balch
|
|
||||||
Note, this is NOT a correct DTLearner; Replace with your own implementation.
|
|
||||||
Copyright 2018, Georgia Institute of Technology (Georgia Tech)
|
class DTLearner:
|
||||||
Atlanta, Georgia 30332
|
LEAF = -1
|
||||||
All Rights Reserved
|
NA = -1
|
||||||
|
|
||||||
Template code for CS 4646/7646
|
def __init__(self, leaf_size=1, verbose=False):
|
||||||
|
self.leaf_size = leaf_size
|
||||||
Georgia Tech asserts copyright ownership of this template and all derivative
|
self.verbose = verbose
|
||||||
works, including solutions to the projects assigned in this course. Students
|
|
||||||
and other users of this template code are advised not to share it with others
|
def author(self):
|
||||||
or to make it available on publicly viewable websites including repositories
|
return 'felixm' # replace tb34 with your Georgia Tech username
|
||||||
such as github and gitlab. This copyright statement should not be removed
|
|
||||||
or edited.
|
def create_node(self, factor, split_value, left, right):
|
||||||
|
return np.array([(factor, split_value, left, right), ],
|
||||||
We do grant permission to share solutions privately with non-students such
|
dtype='|i4, f4, i4, i4')
|
||||||
as potential employers. However, sharing with other current or future
|
|
||||||
students of CS 7646 is prohibited and subject to being investigated as a
|
def query_point(self, point):
|
||||||
GT honor code violation.
|
node_index = 0
|
||||||
|
while self.rel_tree[node_index][0] != self.LEAF:
|
||||||
-----do not edit anything above this line---
|
node = self.rel_tree[node_index]
|
||||||
|
split_factor = node[0]
|
||||||
Student Name: Tucker Balch (replace with your name)
|
split_value = node[1]
|
||||||
GT User ID: tb34 (replace with your User ID)
|
if point[split_factor] <= split_value:
|
||||||
GT ID: 900897987 (replace with your GT ID)
|
# Recurse into left sub-tree.
|
||||||
"""
|
node_index += node[2]
|
||||||
|
else:
|
||||||
import numpy as np
|
node_index += node[3]
|
||||||
import warnings
|
v = self.rel_tree[node_index][1]
|
||||||
|
return v
|
||||||
class DTLearner(object):
|
|
||||||
|
def query(self, points):
|
||||||
def __init__(self, leaf_size=1, verbose = False):
|
"""
|
||||||
warnings.warn("\n\n WARNING! THIS IS NOT A CORRECT DTLearner IMPLEMENTATION! REPLACE WITH YOUR OWN CODE\n")
|
@summary: Estimate a set of test points given the model we built.
|
||||||
pass # move along, these aren't the drones you're looking for
|
@param points: should be a numpy array with each row corresponding to a specific query.
|
||||||
|
@returns the estimated values according to the saved model.
|
||||||
def author(self):
|
"""
|
||||||
return 'tb34' # replace tb34 with your Georgia Tech username
|
def query_point(p): return self.query_point(p)
|
||||||
|
r = np.apply_along_axis(query_point, 1, points)
|
||||||
def addEvidence(self,dataX,dataY):
|
return r
|
||||||
"""
|
|
||||||
@summary: Add training data to learner
|
def build_tree(self, xs, y):
|
||||||
@param dataX: X values of data to add
|
"""
|
||||||
@param dataY: the Y training values
|
@summary: Build a decision tree from the training data.
|
||||||
"""
|
@param dataX: X values of data to add
|
||||||
|
@param dataY: the Y training values
|
||||||
# slap on 1s column so linear regression finds a constant term
|
"""
|
||||||
newdataX = np.ones([dataX.shape[0],dataX.shape[1]+1])
|
assert(xs.shape[0] == y.shape[0])
|
||||||
newdataX[:,0:dataX.shape[1]]=dataX
|
assert(xs.shape[0] > 0) # If this is 0 something went wrong.
|
||||||
|
|
||||||
# build and save the model
|
if xs.shape[0] <= self.leaf_size:
|
||||||
self.model_coefs, residuals, rank, s = np.linalg.lstsq(newdataX, dataY, rcond=None)
|
value = np.mean(y)
|
||||||
|
return self.create_node(self.LEAF, value, self.NA, self.NA)
|
||||||
def query(self,points):
|
|
||||||
"""
|
if np.all(y[0] == y):
|
||||||
@summary: Estimate a set of test points given the model we built.
|
return self.create_node(self.LEAF, y[0], self.NA, self.NA)
|
||||||
@param points: should be a numpy array with each row corresponding to a specific query.
|
|
||||||
@returns the estimated values according to the saved model.
|
i, split_value = self.get_i_and_split_value(xs, y)
|
||||||
"""
|
select_l = xs[:, i] <= split_value
|
||||||
return (self.model_coefs[:-1] * points).sum(axis = 1) + self.model_coefs[-1]
|
select_r = xs[:, i] > split_value
|
||||||
|
lt = self.build_tree(xs[select_l], y[select_l])
|
||||||
if __name__=="__main__":
|
rt = self.build_tree(xs[select_r], y[select_r])
|
||||||
print("the secret clue is 'zzyzx'")
|
root = self.create_node(i, split_value, 1, lt.shape[0] + 1)
|
||||||
|
root = np.concatenate([root, lt, rt])
|
||||||
|
return root
|
||||||
|
|
||||||
|
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
|
||||||
|
"""
|
||||||
|
self.rel_tree = self.build_tree(data_x, data_y)
|
||||||
|
|
||||||
|
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
|
||||||
|
highest correlation first. """
|
||||||
|
# a = np.argmax([abs(np.corrcoef(xs[:,i], y)[0, 1])
|
||||||
|
# for i in range(xs.shape[1])])
|
||||||
|
correlations = []
|
||||||
|
for i in range(xs.shape[1]):
|
||||||
|
c = abs(np.corrcoef(xs[:, i], y=y)[0, 1])
|
||||||
|
correlations.append((c, i))
|
||||||
|
correlations.sort(reverse=True)
|
||||||
|
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 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
|
||||||
|
|
Loading…
Reference in New Issue