def decisionTreeMain():
# ----- Import csv file -----
resource_package = 'resources'
filename = 'wine-quality-red.csv'
resource_path = os.path.join('training_data', filename)
filePath = pkg_resources.resource_filename(
resource_package,
resource_path) # Gets path of file from another package
lines = csv.reader(open(filePath, "rb"))
dataset = list(lines)
# ---- Prepare dataset for analysing ------
del dataset[0] # removes headers from dataset
dataset = datasetModule.normalizeDataset(dataset)
#datasetModule.postponeColumn(dataset, 2) # Shifts 'Survive' column to the last
#removeColumn(dataset, 3)
print(
'***** Splits random subsets in order to create a random forest *****')
subsets = datasetModule.randomSplit(dataset, 3)
datasetModule.printDataSet(subsets)
testSet = datasetModule.getTestSet(dataset, 11)
datasetModule.printDataSet(testSet)
# Delete balanced testSet from original dataset
dataset = [x for x in dataset if x not in testSet]
testRow = testSet[0]
# variousTrees = random_forest.createDecisionTrees(subsets, decision_tree.buildTreeWithMaxElementsInNode, minNodes = 100)
# for i in variousTrees:
# decision_tree.printtree(i)
#
# variousTreesPool = random_forest.createDecisionTreesPool(subsets, decision_tree.buildTreeWithMaxElementsInNode, processes = 5 ,minNodes = 100)
# for i in variousTreesPool:
# decision_tree.printtree(i)
variousTreesMultiprocessinng = random_forest.createDecisionTreesMultiprocessing(
subsets, decision_tree.buildTreeWithMaxElementsInNode, minNodes=100)
for i in variousTreesMultiprocessinng:
decision_tree.printtree(i)
classificationResult = random_forest.classifyForestMultiprocessing(
variousTreesMultiprocessinng, testRow)
print(classificationResult)
print("The final classification is: {}".format(
random_forest.getFinalResult(classificationResult)))
#tree = decision_tree.buildTreeWithHeigth(dataset, maxHeigth=5)
#decision_tree.printtree(tree)
print("Decided the next row:")
print(testRow)
def decisionTreeMain():
# ----- Import csv file -----
resource_package = 'resources'
filename = 'wine-quality-red.csv'
resource_path = os.path.join('training_data', filename)
filePath = pkg_resources.resource_filename(resource_package, resource_path) # Gets path of file from another package
lines = csv.reader(open(filePath, "rb"))
dataset = list(lines)
# ---- Prepare dataset for analysing ------
del dataset[0] # removes headers from dataset
dataset = datasetModule.normalizeDataset(dataset)
#datasetModule.postponeColumn(dataset, 2) # Shifts 'Survive' column to the last
#removeColumn(dataset, 3)
print('***** Splits random subsets in order to create a random forest *****')
subsets = datasetModule.randomSplit(dataset, 3)
datasetModule.printDataSet(subsets)
testSet = datasetModule.getTestSet(dataset,11)
datasetModule.printDataSet(testSet)
# Delete balanced testSet from original dataset
dataset = [x for x in dataset if x not in testSet]
testRow = testSet[0]
# variousTrees = random_forest.createDecisionTrees(subsets, decision_tree.buildTreeWithMaxElementsInNode, minNodes = 100)
# for i in variousTrees:
# decision_tree.printtree(i)
#
# variousTreesPool = random_forest.createDecisionTreesPool(subsets, decision_tree.buildTreeWithMaxElementsInNode, processes = 5 ,minNodes = 100)
# for i in variousTreesPool:
# decision_tree.printtree(i)
variousTreesMultiprocessinng = random_forest.createDecisionTreesMultiprocessing(subsets, decision_tree.buildTreeWithMaxElementsInNode, minNodes = 100)
for i in variousTreesMultiprocessinng:
decision_tree.printtree(i)
classificationResult = random_forest.classifyForestMultiprocessing(variousTreesMultiprocessinng, testRow)
print(classificationResult)
print("The final classification is: {}".format(random_forest.getFinalResult(classificationResult)))
#tree = decision_tree.buildTreeWithHeigth(dataset, maxHeigth=5)
#decision_tree.printtree(tree)
print("Decided the next row:")
print(testRow)
def maxElementsInNodeTest(columnToTestIndex=11, numberOfTrees=3, minNodes=15):
# ----- Import csv file -----
resource_package = 'resources'
filename = 'wine-color.csv'
resource_path = os.path.join('training_data', filename)
filePath = pkg_resources.resource_filename(
resource_package,
resource_path) # Gets path of file from another package
lines = csv.reader(open(filePath, "rb"))
dataset = list(lines)
# ---- Prepare dataset for analysing ------
del dataset[0] # removes headers from dataset
datasetModule.normalizeDataset(dataset)
# ----- Separates testSet from Dataset ------
testSet = datasetModule.getTestSet(dataset, columnToTestIndex, 10)
# Delete balanced testSet from original dataset
dataset = [x for x in dataset if x not in testSet]
#Split dataSet into different subsets in order to create decision trees
subsets = datasetModule.randomSplit(dataset, numberOfTrees)
# Creates random Forest
print "***** Creating random forest with {} min nodes({}) trees *****".format(
numberOfTrees, minNodes)
variousTreesMultiprocessinng = random_forest.createDecisionTreesMultiprocessing(
subsets,
decision_tree.buildTreeWithMaxElementsInNode,
minNodes=minNodes)
# Classify testSet against the forest
rightAnswersCount = 0
for testRow in testSet:
classificationResult = random_forest.classifyForestMultiprocessing(
variousTreesMultiprocessinng, testRow)
finalResult = random_forest.getFinalResult(classificationResult)
if finalResult == testRow[columnToTestIndex]:
rightAnswersCount += 1
print "evaluated correctly {} out of {} tests".format(
rightAnswersCount, len(testSet))
print
def maxElementsInNodeTest(columnToTestIndex=11, numberOfTrees=3, minNodes=15):
# ----- Import csv file -----
resource_package = 'resources'
filename = 'wine-color.csv'
resource_path = os.path.join('training_data', filename)
filePath = pkg_resources.resource_filename(resource_package,
resource_path) # Gets path of file from another package
lines = csv.reader(open(filePath, "rb"))
dataset = list(lines)
# ---- Prepare dataset for analysing ------
del dataset[0] # removes headers from dataset
datasetModule.normalizeDataset(dataset)
# ----- Separates testSet from Dataset ------
testSet = datasetModule.getTestSet(dataset, columnToTestIndex, 10)
# Delete balanced testSet from original dataset
dataset = [x for x in dataset if x not in testSet]
# Split dataSet into different subsets in order to create decision trees
subsets = datasetModule.randomSplit(dataset, numberOfTrees)
# Creates random Forest
print("***** Creating random forest with {} min nodes({}) trees *****".format(numberOfTrees, minNodes))
variousTreesMultiprocessinng = random_forest.createDecisionTreesMultiprocessing(subsets,
decision_tree.buildTreeWithMaxElementsInNode,
minNodes=minNodes)
# Classify testSet against the forest
rightAnswersCount = 0
for testRow in testSet:
classificationResult = random_forest.classifyForestMultiprocessing(variousTreesMultiprocessinng, testRow)
finalResult = random_forest.getFinalResult(classificationResult)
if finalResult == testRow[columnToTestIndex]:
rightAnswersCount += 1
print("evaluated correctly {} out of {} tests".format(rightAnswersCount, len(testSet)))
print()