if myForest.isTrained:
Xtest,yTest,XtestID = myForest.getDataFromFile(train_test_file)
finalPredictions = myForest.predict(Xtest)
myForest.writeToFile(XtestID,finalPredictions,'output.txt')
print("Accuracy is: " ,sum(finalPredictions==yTest)/len(yTest))
else:
print("Untrained model being tested")
#train train-data.txt adaboost_model.txt adaboost
#test test-data.txt adaboost_model.txt adaboost
if model == 'adaboost' :
if trainOrTest == 'train':
myBoost = AdaBoost(300,verbose = False)
TrainX,TrainY,TrainXID = myBoost.getDataFromFile(train_test_file)
myBoost.train(TrainX,TrainY)
pk.dump(myBoost,open(model_file,'wb'))
if trainOrTest == 'test':
try:
myBoost = pk.load(open(model_file,'rb'))
except:
print("output file has not been generated")
if myBoost.isTrained:
Xtest,yTest,XtestID = myBoost.getDataFromFile(train_test_file)
finalPredictions = myBoost.predict(Xtest)
myBoost.writeToFile(XtestID,finalPredictions,'output.txt')
print("Accuracy is: " ,sum(finalPredictions==yTest)/len(yTest))
else:
myForest.trainForest(TrainX, TrainY)
Xtest, yTest, XtestID = myForest.getDataFromFile('test-data.txt')
finalPredictions = myForest.predict(Xtest)
baggpropAccu.append(sum(finalPredictions == yTest) / len(yTest))
plt.plot(bagprop, baggpropAccu)
plt.xlabel("Variation Of Bagging Proportion")
plt.ylabel("Accuracy")
plt.title("Accuracy vs Bagging Proportion")
#########################Adaboost################################################
numTreeAccu = []
numTrees = list(range(5, 200, 5))
for numtree in numTrees:
myBoost = AdaBoost(nTrees=numtree)
TrainX, TrainY, TrainXID = myBoost.getDataFromFile('train-data.txt')
myBoost.train(TrainX, TrainY)
Xtest, yTest, XtestID = myBoost.getDataFromFile('test-data.txt')
finalPredictions = myBoost.predict(Xtest)
numTreeAccu.append(sum(finalPredictions == yTest) / len(yTest))
plt.plot(numTrees, numTreeAccu)
############################################################################
numTreeAccu = []
samples = []
for i in range(5000, 36000, 5000):
myBoost = AdaBoost(nTrees=200)
TrainX, TrainY, TrainXID = myBoost.getDataFromFile('train-data.txt')
