def main():
X = [["home/away", "top25", "media"], ['home', 'out', '1-nbc'],
['home', 'in', '1-nbc'], ['away', 'out', '2-espn'],
['away', 'out', '3-fox'], ['home', 'out', '1-nbc'],
['away', 'out', '4-abc']]
Y = ["win", "lose", "win", "win", "win", "win"]
pyC45.train(X, Y, "Q1c45.xml")
def c45(X_train, y_train, X_test, y_test):
pyC45.train(X_train, y_train, "DecisionTree.xml")
# test the C45 decision tree
answer = []
testing_obs = []
for index, row in y_test.iteritems():
# testing_obs.append(row[:-1].tolist())
answer.append(str(row))
prediction = pyC45.predict("DecisionTree.xml", X_test)
return answer, prediction
def trainandpredict(self, trainX, trainY, testX, testY):
startTime = datetime.now()
pyC45.train(trainX, trainY, "DecisionTree.xml")
start_time = datetime.now()
# test the C45 decision tree
answer = []
testing_obs = []
for index, row in testY.iteritems():
answer.append(str(row))
startTime = datetime.now()
prediction = pyC45.predict("DecisionTree.xml", testX)
predictionTime = datetime.now()
dt = datetime.now() - start_time
ms = (dt.days * 24 * 60 * 60 + dt.seconds) * 1000 + dt.microseconds / 1000.0
print ('Time taken by this algo in millisec:' + str(ms))
return answer, prediction
def main():
X = [["Opponent", "Home/Away", "AP Top 25", "Media"],
['Texas', 'Home', 'Out',
'1-NBC'], ['Virginia', 'Away', 'Out', '4-ABC'],
['GeorgiaTech', 'Home', 'In', '1-NBC'],
['UMass', 'Home', 'Out', '1-NBC'], ['Clemson', 'Away', 'In', '4-ABC'],
['Navy', 'Home', 'Out', '1-NBC'], ['USC', 'Home', 'In', '1-NBC'],
['Temple', 'Away', 'Out', '4-ABC'], ['PITT', 'Away', 'Out', '4-ABC'],
['WakeForest', 'Home', 'Out', '1-NBC'],
['BostonCollege', 'Away', 'Out', '1-NBC'],
['Stanford', 'Away', 'In',
'3-FOX'], ['Texas', 'Away', 'Out', '4-ABC'],
['Nevada', 'Home', 'Out', '1-NBC'],
['MichiganState', 'Home', 'Out', '1-NBC'],
['Duke', 'Home', 'Out',
'1-NBC'], ['Syracuse', 'Home', 'Out', '2-ESPN'],
['NorthCarolinaState', 'Away', 'Out', '4-ABC'],
['Stanford', 'Home', 'In', '1-NBC'],
['MiamiFlorida', 'Home', 'Out', '1-NBC'],
['Navy', 'Home', 'Out', '5-CBS'], ['Army', 'Home', 'Out', '1-NBC'],
['VirginiaTech', 'Home', 'In', '1-NBC'],
['USC', 'Away', 'In', '4-ABC']]
Y = [
"Win", "Win", "Win", "Win", "Lose", "Win", "Win", "Win", "Win", "Win",
"Win", "Lose", "Lose", "Win", "Lose", "Lose", "Win", "Lose", "Lose",
"Win", "Lose", "Win", "Lose", "Lose"
]
pyC45.train(X, Y, "T5c45.xml")
testing = [
["Temple", "Home", "Out", "1-NBC"],
# ["Georgia", "Home", "In", "1-NBC"],
["BostonCollege", "Away", "Out", "2-ESPN"],
["MichiganState", "Away", "Out", "3-FOX"],
# ["MiamiOhio", "Home", "Out", "1-NBC"],
# ["NorthCarolina", "Away", "Out", "4-ABC"],
["USC", "Home", "In", "1-NBC"],
["NorthCarolinaState", "Home", "Out", "1-NBC"],
["WakeForest", "Home", "Out", "1-NBC"],
["MiamiFlorida", "Away", "In", "4-ABC"],
["Navy", "Home", "Out", "1-NBC"],
["Stanford", "Away", "In", "4-ABC"]
]
def main():
X = [["outlook", "temperature", "humidity", "windy"],
['sunny', 'hot', 'high', 'false'], ['sunny', 'hot', 'high', 'true'],
['overcast', 'hot', 'high', 'false'],
['rainy', 'mild', 'high', 'false'],
['rainy', 'cool', 'normal', 'false'],
['rainy', 'cool', 'normal', 'true'],
['overcast', 'cool', 'normal', 'true'],
['sunny', 'mild', 'high', 'false'],
['sunny', 'cool', 'normal', 'false'],
['rainy', 'mild', 'normal', 'false'],
['sunny', 'mild', 'normal', 'true'],
['overcast', 'mild', 'high', 'true'],
['overcast', 'hot', 'normal', 'false'],
['rainy', 'mild', 'high', 'true']]
Y = [
"No", "No", "Yes", "Yes", "Yes", "No", "Yes", "No", "Yes", "Yes",
"Yes", "Yes", "Yes", "No"
]
pyC45.train(X, Y, "Q2c45.xml")
import pyC45, csv
if __name__ == "__main__":
#train a C45 decision tree and save the tree as an XML file
reader = csv.reader(file('./data/training_set.csv'))
training_obs = []
training_cat = []
for line in reader:
training_obs.append(line[:-1])
training_cat.append(line[-1])
pyC45.train(training_obs, training_cat, "DecisionTree.xml")
#test the C45 decision tree
reader = csv.reader(file('./data/training_set.csv'))
answer = []
testing_obs = []
for line in reader:
testing_obs.append(line[:-1])
answer.append(line[-1])
answer.pop(0)
prediction = pyC45.predict("DecisionTree.xml", testing_obs)
err = 0
for i in range(len(answer)):
if not answer[i] == prediction[i]:
err = err + 1
print "error rate=", round(float(err) / len(prediction) * 100, 2), "%"
import pyC45
import csv
if __name__ == "__main__":
#train a C45 decision tree and save the tree as an XML open
reader = csv.reader(
open(
'C:/Users/Luiz Felipe/Documents/TCC/assistenteX/plugin/data/training_set.csv'
))
training_obs = []
training_cat = []
for line in reader:
training_obs.append(line[:-1])
training_cat.append(line[-1])
pyC45.train(
training_obs, training_cat,
"C:/Users/Luiz Felipe/Documents/TCC/assistenteX/plugin/dataDecisionTree.xml"
)
#test the C45 decision tree
reader = csv.reader(
open(
'C:/Users/Luiz Felipe/Documents/TCC/assistenteX/plugin/data/training_set.csv'
))
answer = []
testing_obs = []
for line in reader:
testing_obs.append(line[:-1])
answer.append(line[-1])
answer.pop(0)
prediction = pyC45.predict(
import pyC45,csv
if __name__=="__main__":
#train a C45 decision tree and save the tree as an XML file
reader = csv.reader(file('./data/training_set.csv'))
training_obs=[]
training_cat=[]
for line in reader:
training_obs.append(line[:-1])
training_cat.append(line[-1])
pyC45.train(training_obs,training_cat,"DecisionTree.xml")
#test the C45 decision tree
reader = csv.reader(file('./data/training_set.csv'))
answer=[]
testing_obs=[]
for line in reader:
testing_obs.append(line[:-1])
answer.append(line[-1])
answer.pop(0)
prediction=pyC45.predict("DecisionTree.xml",testing_obs)
err=0
for i in range(len(answer)):
if not answer[i]==prediction[i]:
err=err+1
print "error rate=",round(float(err)/len(prediction)*100,2),"%"