-
Notifications
You must be signed in to change notification settings - Fork 2
/
graph.py
128 lines (112 loc) · 3.74 KB
/
graph.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
import csv
import time
import numpy as np
class Node(object):
def __init__(self, data, acc=-1, des='', parent=None):
self.data = data
if acc == '':
self.acc = 0
else:
self.acc = float(acc)
self.children = []
self.parent = parent
self.des = des
def __str__(self, level=0):
ret = "\t"*level+repr(self.data)+"\n"
for child in self.children:
ret += child.__str__(level+1)
return ret
def print(self):
print(self.data)
for child in self.children:
child.print()
pass
return
def add_child(self, data, acc, des):
child = Node(data, acc, des)
self.children.append(child)
return self
def add_parent_child(self, parent, data, acc, des):
if parent == '':
return None
if self.data == parent:
return self.add_child(data, acc, des)
for child in self.children:
child.add_parent_child(parent, data, acc, des)
pass
return None
def search(self, data):
if self.data == data:
return self
for child in self.children:
childSearch = child.search(data)
if childSearch != None:
return childSearch
pass
return None
def findMax(self):
if len(self.children) == 0:
return self
Acc = []
for child in self.children:
Acc.append(child.findMax())
Acc.append(self)
maxIndex = 0
for i, a in enumerate(Acc):
if Acc[maxIndex].acc <= Acc[i].acc:
maxIndex = i
pass
return Acc[maxIndex]
def pprint_tree(node, file=None, _prefix="", _last=True):
print(_prefix, "|- " if _last else "|- ", node.data + ": " + str(node.des) + " - " + str(node.acc), ' (RUNNING)' if (node.acc == 0 and node.data != 'PLANNED') else '', sep="", file=file)
_prefix += " " if _last else "| "
child_count = len(node.children)
for i, child in enumerate(node.children):
_last = i == (child_count - 1)
pprint_tree(child, file, _prefix, _last)
def getData():
IDS = []
PARENTS = []
DATA = {}
with open('D:/Predictive-Text/experiments/predictiveTrump/experiments.csv') as csvfile:
reader = csv.reader(csvfile)
for i, row in enumerate(reader):
if i == 0:
IDS = row[2:]
if row[1] == 'Parent':
PARENTS = row[2:]
if row[0] == 'Test Results':
testAcc = row[2:]
DATA['testAcc'] = testAcc
if row[1] == 'Short':
ShortDes = row[2:]
DATA['ShortDes'] = ShortDes
print(ShortDes)
return IDS, PARENTS, DATA
def buildForest():
forest = []
IDS, PARENTS, DATA = getData()
# Find roots
for i, id in enumerate(IDS):
if(PARENTS[i] == ''):
root = Node(id, DATA['testAcc'][i], DATA['ShortDes'][i])
forest.append(root)
pass
# Insert parent/child pairs
for i, id in enumerate(IDS):
for tree in forest:
tree.add_parent_child(PARENTS[i], id, DATA['testAcc'][i], DATA['ShortDes'][i])
pass
pass
return forest
forest = buildForest()
for tree in forest:
pprint_tree(tree)
BestModel = forest[0].findMax()
print("\n Best Model: " + BestModel.data + " - " + str(BestModel.acc))
with open('D:/Predictive-Text/experiments/predictiveTrump/Summary.txt', 'w') as out:
timestr = time.strftime("%Y%m%d-%H%M%S\n")
print(timestr, file=out)
for tree in forest:
pprint_tree(tree, file=out)
print("\n Best Model: " + BestModel.data + " - " + str(BestModel.acc), file=out)