Compare commits
2 Commits
db537d7043
...
381670705b
| Author | SHA1 | Date | |
|---|---|---|---|
| 381670705b | |||
| a662e302db |
@ -1,64 +1,108 @@
|
||||
"""
|
||||
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)
|
||||
Atlanta, Georgia 30332
|
||||
All Rights Reserved
|
||||
|
||||
Template code for CS 4646/7646
|
||||
|
||||
Georgia Tech asserts copyright ownership of this template and all derivative
|
||||
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
|
||||
or to make it available on publicly viewable websites including repositories
|
||||
such as github and gitlab. This copyright statement should not be removed
|
||||
or edited.
|
||||
|
||||
We do grant permission to share solutions privately with non-students such
|
||||
as potential employers. However, sharing with other current or future
|
||||
students of CS 7646 is prohibited and subject to being investigated as a
|
||||
GT honor code violation.
|
||||
|
||||
-----do not edit anything above this line---
|
||||
|
||||
Student Name: Tucker Balch (replace with your name)
|
||||
GT User ID: tb34 (replace with your User ID)
|
||||
GT ID: 900897987 (replace with your GT ID)
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
import warnings
|
||||
|
||||
class DTLearner(object):
|
||||
|
||||
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")
|
||||
pass # move along, these aren't the drones you're looking for
|
||||
class DTLearner:
|
||||
LEAF = -1
|
||||
NA = -1
|
||||
|
||||
def __init__(self, leaf_size=1, verbose=False):
|
||||
self.leaf_size = leaf_size
|
||||
self.verbose = verbose
|
||||
|
||||
def author(self):
|
||||
return 'tb34' # replace tb34 with your Georgia Tech username
|
||||
return 'felixm' # replace tb34 with your Georgia Tech username
|
||||
|
||||
def addEvidence(self,dataX,dataY):
|
||||
"""
|
||||
@summary: Add training data to learner
|
||||
@param dataX: X values of data to add
|
||||
@param dataY: the Y training values
|
||||
"""
|
||||
def create_node(self, factor, split_value, left, right):
|
||||
return np.array([(factor, split_value, left, right), ],
|
||||
dtype='|i4, f4, i4, i4')
|
||||
|
||||
# slap on 1s column so linear regression finds a constant term
|
||||
newdataX = np.ones([dataX.shape[0],dataX.shape[1]+1])
|
||||
newdataX[:,0:dataX.shape[1]]=dataX
|
||||
def query_point(self, point):
|
||||
node_index = 0
|
||||
while self.rel_tree[node_index][0] != self.LEAF:
|
||||
node = self.rel_tree[node_index]
|
||||
split_factor = node[0]
|
||||
split_value = node[1]
|
||||
if point[split_factor] <= split_value:
|
||||
# Recurse into left sub-tree.
|
||||
node_index += node[2]
|
||||
else:
|
||||
node_index += node[3]
|
||||
v = self.rel_tree[node_index][1]
|
||||
return v
|
||||
|
||||
# build and save the model
|
||||
self.model_coefs, residuals, rank, s = np.linalg.lstsq(newdataX, dataY, rcond=None)
|
||||
|
||||
def query(self,points):
|
||||
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.
|
||||
@returns the estimated values according to the saved model.
|
||||
"""
|
||||
return (self.model_coefs[:-1] * points).sum(axis = 1) + self.model_coefs[-1]
|
||||
def query_point(p): return self.query_point(p)
|
||||
r = np.apply_along_axis(query_point, 1, points)
|
||||
return r
|
||||
|
||||
if __name__=="__main__":
|
||||
print("the secret clue is 'zzyzx'")
|
||||
def build_tree(self, xs, y):
|
||||
"""
|
||||
@summary: Build a decision tree from the training data.
|
||||
@param dataX: X values of data to add
|
||||
@param dataY: the Y training values
|
||||
"""
|
||||
assert(xs.shape[0] == y.shape[0])
|
||||
assert(xs.shape[0] > 0) # If this is 0 something went wrong.
|
||||
|
||||
if xs.shape[0] <= self.leaf_size:
|
||||
value = np.mean(y)
|
||||
return self.create_node(self.LEAF, value, self.NA, self.NA)
|
||||
|
||||
if np.all(y[0] == y):
|
||||
return self.create_node(self.LEAF, y[0], self.NA, self.NA)
|
||||
|
||||
i, split_value = self.get_i_and_split_value(xs, y)
|
||||
select_l = xs[:, i] <= split_value
|
||||
select_r = xs[:, i] > split_value
|
||||
lt = self.build_tree(xs[select_l], y[select_l])
|
||||
rt = self.build_tree(xs[select_r], y[select_r])
|
||||
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
|
||||
|
||||
@ -26,27 +26,63 @@ GT ID: 900897987 (replace with your GT ID)
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import math
|
||||
|
||||
# this function should return a dataset (X and Y) that will work
|
||||
# better for linear regression than decision trees
|
||||
|
||||
def best4LinReg(seed=1489683273):
|
||||
"""
|
||||
This function should return a dataset (X and Y) that will work better for
|
||||
linear regression than decision trees.
|
||||
|
||||
We make Y a simple linear combination of X. That will give the Linear
|
||||
Regression algorithm a very easy time (no RMSE at all) and beat the DT
|
||||
easily.
|
||||
"""
|
||||
np.random.seed(seed)
|
||||
X = np.zeros((100,2))
|
||||
Y = np.random.random(size = (100,))*200-100
|
||||
# Here's is an example of creating a Y from randomly generated
|
||||
# X with multiple columns
|
||||
# Y = X[:,0] + np.sin(X[:,1]) + X[:,2]**2 + X[:,3]**3
|
||||
X = np.random.random(size=(100, 2)) * 200 - 100
|
||||
Y = X[:, 0] * -2 + X[:, 1] * 3
|
||||
return X, Y
|
||||
|
||||
|
||||
def best4DT(seed=1489683273):
|
||||
"""
|
||||
This function should return a dataset that will work better for decision
|
||||
trees than linear regression.
|
||||
"""
|
||||
|
||||
# Z = np.append(X, Y.reshape(Y.shape[0], 1), 1)
|
||||
# pd.DataFrame(Z).to_csv("Z.csv", header=None, index=None)
|
||||
# np.random.seed(seed)
|
||||
# X = np.random.random(size=(100, 10))*1000-100
|
||||
# Y = np.random.random(size=(100,))*1000-100
|
||||
|
||||
np.random.seed(seed)
|
||||
X = np.zeros((100,2))
|
||||
Y = np.random.random(size = (100,))*200-100
|
||||
# X_1 = np.random.random(size=(100, 1))*200-100
|
||||
# X_2 = np.random.random(size=(100, 1))*200-100
|
||||
# X_3 = np.random.random(size=(100, 1))*200-100
|
||||
# X_4 = np.random.random(size=(100, 1))*200-100
|
||||
# X = np.concatenate([X_1, X_2, X_3, X_4], 1)
|
||||
|
||||
# XXX: I honestly don't know how to help the DTLearner, yet.
|
||||
|
||||
X_1 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
|
||||
X_2 = np.asarray([i for i in range(100, 1100, 10)]).reshape(100, 1)
|
||||
X_3 = np.asarray([i for i in range(200, 300)]).reshape(100, 1)
|
||||
X_4 = np.asarray([i for i in range(300, 400)]).reshape(100, 1)
|
||||
X_5 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
|
||||
X_6 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
|
||||
X_7 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
|
||||
X_8 = np.asarray([i for i in range(1, 101)]).reshape(100, 1)
|
||||
X = np.concatenate([X_1, X_2, X_3, X_4, X_5, X_6, X_7, X_8], 1)
|
||||
# Y = X[:, 0] * 2 + X[:, 1] * 3
|
||||
Y = np.random.random(size=(100,)) * 200 - 100
|
||||
return X, Y
|
||||
|
||||
def author():
|
||||
return 'tb34' #Change this to your user ID
|
||||
|
||||
if __name__=="__main__":
|
||||
def author():
|
||||
return 'felixm' # Change this to your user ID
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
print("they call me Tim.")
|
||||
|
||||
@ -28,10 +28,12 @@ import DTLearner as dt
|
||||
from gen_data import best4LinReg, best4DT
|
||||
|
||||
# compare two learners' rmse out of sample
|
||||
|
||||
|
||||
def compare_os_rmse(learner1, learner2, X, Y):
|
||||
|
||||
# compute how much of the data is training and testing
|
||||
train_rows = int(math.floor(0.6* X.shape[0]))
|
||||
train_rows = int(math.floor(0.6 * X.shape[0]))
|
||||
test_rows = X.shape[0] - train_rows
|
||||
|
||||
# separate out training and testing data
|
||||
@ -43,24 +45,25 @@ def compare_os_rmse(learner1, learner2, X, Y):
|
||||
testY = Y[test]
|
||||
|
||||
# train the learners
|
||||
learner1.addEvidence(trainX, trainY) # train it
|
||||
learner2.addEvidence(trainX, trainY) # train it
|
||||
learner1.addEvidence(trainX, trainY) # train it
|
||||
learner2.addEvidence(trainX, trainY) # train it
|
||||
|
||||
# evaluate learner1 out of sample
|
||||
predY = learner1.query(testX) # get the predictions
|
||||
predY = learner1.query(testX) # get the predictions
|
||||
rmse1 = math.sqrt(((testY - predY) ** 2).sum()/testY.shape[0])
|
||||
|
||||
# evaluate learner2 out of sample
|
||||
predY = learner2.query(testX) # get the predictions
|
||||
predY = learner2.query(testX) # get the predictions
|
||||
rmse2 = math.sqrt(((testY - predY) ** 2).sum()/testY.shape[0])
|
||||
|
||||
return rmse1, rmse2
|
||||
|
||||
|
||||
def test_code():
|
||||
|
||||
# create two learners and get data
|
||||
lrlearner = lrl.LinRegLearner(verbose = False)
|
||||
dtlearner = dt.DTLearner(verbose = False, leaf_size = 1)
|
||||
lrlearner = lrl.LinRegLearner(verbose=False)
|
||||
dtlearner = dt.DTLearner(verbose=False, leaf_size=1)
|
||||
X, Y = best4LinReg()
|
||||
|
||||
# compare the two learners
|
||||
@ -78,8 +81,8 @@ def test_code():
|
||||
print
|
||||
|
||||
# get data that is best for a random tree
|
||||
lrlearner = lrl.LinRegLearner(verbose = False)
|
||||
dtlearner = dt.DTLearner(verbose = False, leaf_size = 1)
|
||||
lrlearner = lrl.LinRegLearner(verbose=False)
|
||||
dtlearner = dt.DTLearner(verbose=False, leaf_size=1)
|
||||
X, Y = best4DT()
|
||||
|
||||
# compare the two learners
|
||||
@ -96,5 +99,6 @@ def test_code():
|
||||
print("DT >= 0.9 LR: fail")
|
||||
print
|
||||
|
||||
if __name__=="__main__":
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_code()
|
||||
|
||||
Loading…
Reference in New Issue
Block a user