def ada_boost_experiment():
examples = ID3.data_parsing(FILE_PATH_TRAIN, numeric_cols)
# hypothesis = AdaBoost.ada_boost(examples, 5, numeric_cols, missing_identifier)
# print(hypothesis)
iterations = 100
hypothesis = AdaBoost.ada_boost(examples, iterations, numeric_cols,
missing_identifier)
ada_results_train = AdaBoost.test_ada_boost_hypothesis(
hypothesis, FILE_PATH_TRAIN, numeric_cols, missing_identifier)
ada_results_test = AdaBoost.test_ada_boost_hypothesis(
hypothesis, FILE_PATH_TEST, numeric_cols, missing_identifier)
# for t in range(iterations):
# print("AdaBoost Training Set - t:", t, "results:", ada_results_train[t],
# "{0:.2%}".format(1-ada_results_train[t][0]/ada_results_train[t][1]))
# for t in range(iterations):
# print("AdaBoost Testing Set - t:", t, "results:", ada_results_test[t],
# "{0:.2%}".format(1-ada_results_test[t][0]/ada_results_test[t][1]))
# for t in range(iterations):
# tree_results = ID3.test_tree(hypothesis[t][0],FILE_PATH_TRAIN, numeric_cols, missing_identifier)
# print("Decision Tree Training Set - t:", t, "results:", tree_results,
# "{0:.2%}".format(1 - tree_results[0] / tree_results[1]))
# for t in range(iterations):
# tree_results = ID3.test_tree(hypothesis[t][0],FILE_PATH_TEST, numeric_cols, missing_identifier)
# print("Decision Tree Test Set - t:", t, "results:", tree_results,
# "{0:.2%}".format(1 - tree_results[0] / tree_results[1]))
ada_train = []
ada_test = []
dec_train = []
dec_test = []
for t in range(iterations):
ada_train.append(1 - ada_results_train[t][0] / ada_results_train[t][1])
ada_test.append(1 - ada_results_test[t][0] / ada_results_test[t][1])
tree_results = ID3.test_tree(hypothesis[t][0], FILE_PATH_TRAIN,
numeric_cols, missing_identifier)
dec_train.append(1 - tree_results[0] / tree_results[1])
tree_results = ID3.test_tree(hypothesis[t][0], FILE_PATH_TEST,
numeric_cols, missing_identifier)
dec_test.append(1 - tree_results[0] / tree_results[1])
ada_graph = [
tuple([ada_train, "AdaBoost Train"]),
tuple([ada_test, "AdaBoost Test"])
]
GraphUtility.graph(ada_graph, "AdaBoost Data", "Iterations", "Error")
tree_graph = [
tuple([dec_train, "Tree Train"]),
tuple([dec_test, "Tree Test"])
]
GraphUtility.graph(tree_graph, "Decision Tree Data", "Iterations", "Error")
def lms_experiment():
file_path_train = "/home/john/PycharmProjects/u1201441_Private_Repository/CS6350_Files/HW2/concrete/train.csv"
file_path_test = "/home/john/PycharmProjects/u1201441_Private_Repository/CS6350_Files/HW2/concrete/test.csv"
batch_size = -1 # -1 for full batch descent, or a batch size for stochastic descent.
iterations = 1000
learning_constant = 1
plot_iter = 1000
results = []
for t in range(plot_iter):
hypothesis = LeastMeanSquares.least_mean_squares(
file_path_train, batch_size, iterations, learning_constant)
if hypothesis[2]:
break
learning_constant = learning_constant / 2
r = hypothesis[0]
hypotheses = hypothesis[1]
for hyp in hypotheses:
results.append(LeastMeanSquares.test_lms(hyp, file_path_test))
print("Gradient Descent - r:", r, "Weight:", hypotheses[-1], "Losses:",
results)
batch_size = 1 # -1 for full batch descent, or a small batch size for stochastic descent.
results_stoch = []
for t in range(plot_iter):
hypothesis = LeastMeanSquares.least_mean_squares(
file_path_train, batch_size, iterations, learning_constant)
if hypothesis[2]:
break
learning_constant = learning_constant / 2
r = hypothesis[0]
hypotheses = hypothesis[1]
for hyp in hypotheses:
results_stoch.append(LeastMeanSquares.test_lms(hyp, file_path_test))
print("Stochastic Gradient Descent - r:", r, "Weight:", hypotheses[-1],
"Losses:", results_stoch)
lms_graph = [
tuple([results, "Descent"]),
tuple([results_stoch, "Stochastic Descent"])
]
GraphUtility.graph(lms_graph, "LMS_Test", "Loss",
"Gradient Descent Iterations")
def DegreeClassify(dataPath='../LinkAnalyticsData/UTK_problem/'):
""" Finds the distrbtion of the cummulative node and edge wights """
filenames=('Moria_2','Standelf_2')
attrs=('calls','texts','degree','secs')
for f in filenames:
# Reading in the Graph
MG = GU.readData(os.path.join(dataPath,f)+'.graph')
deg = nx.degree(MG)
def GetEdgeDistributions(dataPath='../LinkAnalyticsData/UTK_problem/'):
filenames=('Moria_1.graph','Standelf_1.graph')
attrs=('calls','texts','days','secs')
for f in filenames:
# Reading in the Graph
MG = GU.readData(os.path.join(dataPath,f))
# Distribution of each Attribute
for attr in attrs:
data = GU.GetAttr(MG,attr)
# Plotting
pyplot.hist(data,100)
pyplot.yscale('log')
pyplot.grid(True)
pyplot.ylabel("Frequency")
pyplot.xlabel(attr)
name = f.split('.')[0].split('_')[0]
title = name+" "+attr+" distribution"
pyplot.title(title)
pyplot.savefig(name+"_"+attr+"_distribution.png")
pyplot.clf()
def readData(filename='../LinkAnalyticsData/UTK_problem/Moria_1.graph'):
""" Creates a dataset for ANN training of the formated data supplied by filename """
""" Currently based on 4x2 inputs of days, calls, call duration, and texts """
""" Two 'classes' are implemented, either there or not """
numInputs = 2+4+2
alldata = ClassificationDataSet(numInputs,1,nb_classes=2)
MG = GU.readData(filename)
closeness = nx.closeness_centrality(MG)
degree = nx.degree(MG)
startTime = datetime.now()
# Computing the data
data = [[closeness[u],degree[u],\
edata['calls'],edata['secs'],edata['texts'],edata['days'],\
degree[v],closeness[v]] \
for u,v,edata in MG.edges(data=True)]
for d in data:
alldata.addSample(d,[1])
print "Converted to data in ",(datetime.now()-startTime)
return alldata
def GetDataDistributions(dataPath='../LinkAnalyticsData/UTK_problem/'):
filenames=('Moria_1.graph','Standelf_1.graph')
""" Finds the distrbtion of the cummulative node and edge wights """
attrs=('calls','texts','degree','secs')
for f in filenames:
# Reading in the Graph
MG = GU.readData(os.path.join(dataPath,f))
g = GU.ConvertToSingle(MG)
for attr in attrs:
x = list()
for n in g.nodes():
x.append(g.node[n][attr])
# Plotting the Data
largest = heapq.nlargest(3,x)
pyplot.figure()
pyplot.hist(x,bins=np.logspace(1,np.log2(largest[2]),25,base=2))
pyplot.ylabel("Frequency")
pyplot.xlabel(attr)
name = f.split('.')[0].split('_')[0]
title = name+" "+attr+" distribution"
pyplot.title(title)
pyplot.savefig(name+"_"+attr+"_cum_distribution.png")
def analyze(dirname,directory):
start = TimeUtility.start()
anu=an.Abbreviations()
rootNode = Node(dirname)
file_paths = [] # List which will store all of the full filepaths.
fileFxnDictionary = {}
fileImportDictionary = {}
fileClassDictionary = {}
callerFxnArgumentsDictionary={}
callerCalleeFxn={}
calleFxnArguments={}
fileFxnCount={}
fileImportCount={}
fileClassCount={}
uniqueImports=[]
callerCalleePath=[]
fxnGraph = nx.DiGraph()
fxnGraphFull=nx.DiGraph()
fxnList=[]
classList=[]
importList=[]
for root, directories, files in os.walk(directory): # Walk the tree.
for filename in files:
str=filename.__str__()
#print("root",root)
filepath=root.replace("\\","/") # Join the two strings in order to form the full filepath.
filepath=filepath+"/"+filename
#filepath = os.path.join(root, filename)
file_paths.append(filepath) # Add it to the list.
#module = importlib.import_module(filepath)
#my_class = getattr(module, 'MyClass')
#my_instance = my_class()
#dir()
# #print("filepath : ",filepath," members are :",dir(module(filepath)))
#print("filepath : ", filepath)
if(not filepath.endswith(".py")):
continue
localFileNode = Node(filepath.replace(directory,""), parent=rootNode)
file = open(filepath, "r+",encoding="utf8")
variable=[]
functionName=[]
className=[]
importModules=[]
isNextWordfxn=False
isNextWordclass=False
isNextWordImport=False
isNewWord=False
classChildren=False
fxnChildren=False
mainFxnNode=None
clsNode=None
for word in file.read().split():
if(stopWordsRemoval.isStopWord(word) or word.__len__()<=2):
continue
if(isNextWordclass):
if(word.__contains__("(")) :
className.append(word)
classChildren=True
clsNode = Node("class:" + word, parent=localFileNode)
isNextWordclass=False
#print(word)
elif(isNextWordfxn):
print("fxnname",word)
if("(" in word):
arg=word.split("(")[1]
word=word.split("(")[0]
functionName.append(word.lower())
isNextWordfxn=False
if(classChildren and (not fxnChildren)):
mainFxnNode = Node("Fxn:" + word, parent=clsNode)
elif(fxnChildren):
fxnNode = Node("Fxn:" + word, parent=mainFxnNode)
callerCalleeFxn.update({mainFxnNode.name,fxnChildren})
else:
fxnNode = Node("Fxn:" + word, parent=localFileNode)
fxnChildren = True
#print(word)
elif(isNextWordImport):
importModules.append(word)
isNextWordImport=False
importNode = Node("Import:" + word, parent=localFileNode)
#print(word)
if (word == "def"):
isNextWordfxn = True
isNewWord=True
fxnChildren = False
#print("true")
elif (word == "class"):
isNextWordclass = True
isNewWord=True
fxnChildren=False
elif (word == "import"):
isNextWordImport = True
isNewWord=True
elif (checkWordForValidFunction(word) and fxnChildren):
print("got new function lets see::::",word)
if(fxnChildren and mainFxnNode is not None):
fxnNode = Node("Fxn:" + word, parent=mainFxnNode)
callerCalleeFxn[mainFxnNode.name]=[word]
fxnGraph.add_edge(anu.get(su.sanitize(mainFxnNode.name)),anu.get(su.sanitize(word)))
fxnGraphFull.add_edge(su.sanitize(mainFxnNode.name),su.sanitize(word))
# print("File:",filepath,"Functions:",functionName)
#print("File:",filepath,"Classes:", className)
#print("File:",filepath,"Import:", importModules)
if(len(functionName) != 0):
fileFxnDictionary.update({filepath.replace(directory,""):set(functionName)})
fileFxnCount[filepath.replace(directory,"")]=len(set(functionName))
if (len(className) != 0):
fileClassDictionary.update({filepath.replace(directory,""): set(className)})
fileClassCount[filepath.replace(directory, "")]=len(set(className))
if (len(importModules) != 0):
fileImportDictionary.update({filepath.replace(directory,""): set(importModules)})
fileImportCount[filepath.replace(directory, "")]= len(set(importModules))
uniqueImports.append(importModules)
#print(len(fileFxnDictionary.values()))
workbook = xlsxwriter.Workbook(dirname+"data"+".xlsx")
workbook1 = xlsxwriter.Workbook(dirname+"function"+".xlsx")
workbook2=xlsxwriter.Workbook(dirname+"count"+".xlsx")
ExcelUtility.writeToExcel(callerCalleeFxn, "CallerCalleFxn", workbook1)
ExcelUtility.writeToExcel(anu.shortNames, "FxnAbbre.", workbook1)
ExcelUtility.writeToExcel(fileFxnDictionary,"functionInfo",workbook)
ExcelUtility.writeToExcel(fileClassDictionary, "classInfo",workbook)
ExcelUtility.writeToExcel(fileImportDictionary, "importInfo",workbook)
ExcelUtility.writeToExcelCount(fileFxnCount, "fxncount", workbook2)
ExcelUtility.writeToExcelCount(fileImportCount, "importcount", workbook2)
ExcelUtility.writeToExcelCount(fileClassCount, "classcount", workbook2)
dumpclean(callerCalleeFxn)
print("tree:")
PrintUtility.printTree(rootNode)
print("Unique Imports are:",len(uniqueImports))
gu.getAllPaths(fxnGraph,True,dirname)
gu.getAllPathsWithoutAbbreviations(fxnGraphFull,True,dirname)
#visualize tha paths and get all the optimized paths of nodes that is this
# function is calling this functioon and further on.. path1: f1 f2 f3 f4 f5 f6 f7
# the results will be saved in excel file as
filename=dirname+'pathsoptimized.xlsx'
all_paths=gu.getAllOptimizedPaths(fxnGraph, True,filename,dirname)
gu.getAllOptimizedPathsWithoutAbbreviations(fxnGraphFull,True,dirname+"pathsoptimizedNoAbbre.xlsx",dirname)
print("anu.counter:",anu.counter)
callerMatrix=ceu.encodeValues(all_paths,anu.counter,dirname)
pathMatrix=cs.getResultSimilarityMatrix(callerMatrix,dirname+"similarity.csv")
cluster.test(dirname,pathMatrix)
TimeUtility.end(start)
#caller=callerMatrix()
#caller.cleanInput(callerCalleeFxn)
#stopWordsRemoval.removeStopwords('dataold.xlsx')
#DeterMinePaths.determine(callerCalleeFxn)
PrintUtility.printTree(rootNode)
return rootNode,pathMatrix
def credit_experiment():
file_path = "/home/john/PycharmProjects/u1201441_Private_Repository/CS6350_Files/HW2/credit/default of credit card clients.csv"
numeric_cols = [0, 4, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22]
missing_identifier = None
training_data = []
test_data = []
data = ID3.data_parsing(file_path, numeric_cols)
LABEL_INDEX = len(data[0]) - 2
for instance in data:
if instance[LABEL_INDEX] == '1':
instance[LABEL_INDEX] = "yes"
else:
instance[LABEL_INDEX] = "no"
test_indices = random.sample(range(len(data)), len(data))
for i in test_indices:
if i < 6000:
test_data.append(data[i])
else:
training_data.append(data[i])
iterations = 100
decision_tree = ID3.build_decision_tree(
training_data,
max_depth=-1,
info_gain_type=1,
numeric_cols=numeric_cols,
missing_identifier=missing_identifier)
adaboost = AdaBoost.ada_boost(training_data,
iterations=iterations,
numeric_cols=numeric_cols,
missing_identifier=missing_identifier)
bagged_tree = BaggedTrees.bagged_trees(
training_data,
iterations=iterations,
sample_size=100,
numeric_cols=numeric_cols,
missing_identifier=missing_identifier)
forest = RandomForest.random_forest(training_data,
iterations=iterations,
sample_size=100,
numeric_cols=numeric_cols,
missing_identifier=missing_identifier,
feature_size=4)
# Decision Tree results
tree_results = ID3.test_tree(decision_tree, training_data, numeric_cols,
missing_identifier)
tree_train = 1 - tree_results[0] / tree_results[1]
tree_results = ID3.test_tree(decision_tree, test_data, numeric_cols,
missing_identifier)
tree_test = 1 - tree_results[0] / tree_results[1]
tree_train_ln = []
tree_test_ln = []
for t in range(iterations):
tree_train_ln.append(tree_train)
tree_test_ln.append(tree_test)
# AdaBoost results
ada_results_train = AdaBoost.test_ada_boost_hypothesis(
adaboost, training_data, numeric_cols, missing_identifier)
ada_results_test = AdaBoost.test_ada_boost_hypothesis(
adaboost, test_data, numeric_cols, missing_identifier)
ada_train = []
ada_test = []
for t in range(iterations):
ada_train.append(1 - ada_results_train[t][0] / ada_results_train[t][1])
ada_test.append(1 - ada_results_test[t][0] / ada_results_test[t][1])
ada_graph = [
tuple([ada_train, "AdaBoost Train"]),
tuple([ada_test, "AdaBoost Test"]),
tuple([tree_train_ln, "Tree Train"]),
tuple([tree_test_ln, "Tree Test"])
]
GraphUtility.graph(ada_graph, "AdaBoost Data", "Iterations", "Error")
# Bagging results
results_train = BaggedTrees.test_bagged_tree_hypothesis(
bagged_tree, training_data, numeric_cols, missing_identifier)
results_test = BaggedTrees.test_bagged_tree_hypothesis(
bagged_tree, test_data, numeric_cols, missing_identifier)
# Charts
bag_train = []
bag_test = []
for t in range(iterations):
bag_train.append(1 - results_train[t][0] / results_train[t][1])
bag_test.append(1 - results_test[t][0] / results_test[t][1])
bag_graph = [
tuple([bag_train, "Bagging Train"]),
tuple([bag_test, "Bagging Test"]),
tuple([tree_train_ln, "Tree Train"]),
tuple([tree_test_ln, "Tree Test"])
]
GraphUtility.graph(bag_graph, "Bagged Tree Data", "Num Trees", "Error")
# Forest Results
results_train = RandomForest.test_random_forest_hypothesis(
forest, training_data, numeric_cols, missing_identifier)
results_test = RandomForest.test_random_forest_hypothesis(
forest, test_data, numeric_cols, missing_identifier)
# Charts
forest_train = []
forest_test = []
for t in range(iterations):
forest_train.append(1 - results_train[t][0] / results_train[t][1])
forest_test.append(1 - results_test[t][0] / results_test[t][1])
forest_graph = [
tuple([forest_train, "Forest Train - " + str(2) + " features"]),
tuple([forest_test, "Forest Test - " + str(2) + " features"]),
tuple([tree_train_ln, "Tree Train"]),
tuple([tree_test_ln, "Tree Test"])
]
GraphUtility.graph(forest_graph, "Random Forest Data", "Num Trees",
"Error")
def random_forest_experiment():
examples = ID3.data_parsing(FILE_PATH_TRAIN, numeric_cols)
# hypothesis = AdaBoost.ada_boost(examples, 5, numeric_cols, missing_identifier)
# print(hypothesis)
LABEL_INDEX = len(examples[0]) - 2
iterations = 100
sample_size = int(len(examples) / 4)
for feature_size in [2, 4, 6]:
hypothesis = RandomForest.random_forest(examples, iterations,
sample_size, numeric_cols,
missing_identifier,
feature_size)
results_train = RandomForest.test_random_forest_hypothesis(
hypothesis, FILE_PATH_TRAIN, numeric_cols, missing_identifier)
results_test = RandomForest.test_random_forest_hypothesis(
hypothesis, FILE_PATH_TEST, numeric_cols, missing_identifier)
# Charts
forest_train = []
forest_test = []
for t in range(iterations):
# print("Random Forest -", "Feature Size:", feature_size, "t:", t, "results:", results[t], results[t][0]/results[t][1])
forest_train.append(1 - results_train[t][0] / results_train[t][1])
forest_test.append(1 - results_test[t][0] / results_test[t][1])
forest_graph = [
tuple([
forest_train,
"Forest Train - " + str(feature_size) + " features"
]),
tuple([
forest_test, "Forest Test - " + str(feature_size) + " features"
])
]
GraphUtility.graph(forest_graph, "Random Forest Data", "Num Trees",
"Error")
# Bias/Variance
iterations = 100
forest = []
trees = []
sample_size = 100
feature_size = 2
for t in range(iterations):
data = random.sample(examples, 1000)
forest.append(
RandomForest.random_forest(data, iterations, sample_size,
numeric_cols, missing_identifier,
feature_size))
trees.append(forest[t][0][0])
# Bias/Variance of individual trees.
labels = []
biases = []
variances = []
for instance in examples:
for tree in trees:
label = ID3.get_label(tree, instance, numeric_cols,
missing_identifier)
labels.append(1 if label == "yes" else -1)
if instance[LABEL_INDEX] == "yes":
true_label = 1
else:
true_label = -1
avg = numpy.average(labels)
biases.append((avg - true_label)**2)
variances.append(numpy.var(labels))
tree_bias = numpy.average(biases)
tree_variance = numpy.average(variances)
# Bias/Variance of bagged trees.
labels = []
biases = []
variances = []
for instance in examples:
for tree in forest:
label = RandomForest.get_label(tree, instance, numeric_cols,
missing_identifier)
labels.append(1 if label == "yes" else -1)
true_label = 1 if instance[LABEL_INDEX] == "yes" else -1
avg = numpy.average(labels)
biases.append((avg - true_label)**2)
variances.append(numpy.var(labels))
forest_bias = numpy.average(biases)
forest_variance = numpy.average(variances)
print("Tree Bias:", "{0:.3}".format(tree_bias), "Tree Variance:",
"{0:.3}".format(tree_variance))
print("Forest Bias:", "{0:.3}".format(forest_bias), "Forest Variance:",
"{0:.3}".format(forest_variance))
def bagged_trees_experiment():
examples = ID3.data_parsing(FILE_PATH_TRAIN, numeric_cols)
# hypothesis = AdaBoost.ada_boost(examples, 5, numeric_cols, missing_identifier)
# print(hypothesis)
LABEL_INDEX = len(examples[0]) - 2
iterations = 100
sample_size = int(len(examples) / 2)
hypothesis = BaggedTrees.bagged_trees(examples, iterations, sample_size,
numeric_cols, missing_identifier)
results_train = BaggedTrees.test_bagged_tree_hypothesis(
hypothesis, FILE_PATH_TRAIN, numeric_cols, missing_identifier)
results_test = BaggedTrees.test_bagged_tree_hypothesis(
hypothesis, FILE_PATH_TEST, numeric_cols, missing_identifier)
# for t in range(iterations):
# print("Bagged Tree Training Set - t:", t, "results:", results_train[t],
# "{0:.2%}".format(1-results_train[t][0]/results_train[t][1]))
# for t in range(iterations):
# print("Bagged Tree Test Set - t:", t, "results:", results_test[t],
# "{0:.2%}".format(1-results_test[t][0]/results_test[t][1]))
# Charts
bag_train = []
bag_test = []
for t in range(iterations):
bag_train.append(1 - results_train[t][0] / results_train[t][1])
bag_test.append(1 - results_test[t][0] / results_test[t][1])
bag_graph = [
tuple([bag_train, "Bagging Train"]),
tuple([bag_test, "Bagging Test"])
]
GraphUtility.graph(bag_graph, "Bagged Tree Data", "Num Trees", "Error")
# Bias/Variance calculations.
iterations = 100
bagged_trees = []
trees = []
sample_size = 100
for t in range(iterations):
data = random.sample(examples, 1000)
bagged_trees.append(
BaggedTrees.bagged_trees(data, iterations, sample_size,
numeric_cols, missing_identifier))
trees.append(bagged_trees[t][0][0])
# Bias/Variance of individual trees.
labels = []
biases = []
variances = []
for instance in examples:
for tree in trees:
label = ID3.get_label(tree, instance, numeric_cols,
missing_identifier)
labels.append(1 if label == "yes" else -1)
if instance[LABEL_INDEX] == "yes":
true_label = 1
else:
true_label = -1
avg = numpy.average(labels)
biases.append((avg - true_label)**2)
variances.append(numpy.var(labels))
tree_bias = numpy.average(biases)
tree_variance = numpy.average(variances)
# Bias/Variance of bagged trees.
labels = []
biases = []
variances = []
for instance in examples:
for tree in bagged_trees:
label = BaggedTrees.get_label(tree, instance, numeric_cols,
missing_identifier)
labels.append(1 if label == "yes" else -1)
true_label = 1 if instance[LABEL_INDEX] == "yes" else -1
avg = numpy.average(labels)
biases.append((avg - true_label)**2)
variances.append(numpy.var(labels))
bag_bias = numpy.average(biases)
bag_variance = numpy.average(variances)
print("Tree Bias:", "{0:.3}".format(tree_bias), "Tree Variance:",
"{0:.3}".format(tree_variance))
print("Bagged Bias:", "{0:.3}".format(bag_bias), "Bagged Variance:",
"{0:.3}".format(bag_variance))
import networkx as nx
import StringUtility as su
import AbbreviatedNamesUtility as AN
import GraphUtility as gu
import OneHotEncodingUtility as heu
fxnGraph = nx.DiGraph()
anu = AN.Abbreviations()
fxnGraph.add_edge(anu.get(su.sanitize("abc")), anu.get(su.sanitize("def")))
fxnGraph.add_edge(anu.get(su.sanitize("def")), anu.get(su.sanitize("ghj")))
fxnGraph.add_edge(anu.get(su.sanitize("asd")), anu.get(su.sanitize("dds")))
fxnGraph.add_edge(anu.get(su.sanitize("sas")), anu.get(su.sanitize("sada")))
fxnGraph.add_edge(anu.get(su.sanitize("sas")), anu.get(su.sanitize("asdx")))
gu.visualize_to_dot(fxnGraph, "test2.dot")
gu.visualize_to_png("test2.dot", "test2.png")
all_paths = gu.getAllPaths(fxnGraph, True)
#all_paths=gu.getAllOptimizedPaths(fxnGraph,True)
print("List size:", len(all_paths))
for sublist in all_paths:
print(sublist)
heu.getLabelEncoder(sublist)