def Bagging(trainSet, iteration, method='DecisionStump', caseNum=0):
# reading training data
N, L = trainSet.shape
# default caseNum is N
if (caseNum <= 0):
caseNum = N
if (method == 'LinearRegression'):
# bag is to record g(it) in each iteration
bag = np.zeros((iteration, L), float)
# dataSet is the for bootstrapping (resampling)
dataSet = np.zeros((N, L), float)
for it in range(iteration):
print("iteration No.", it + 1)
# booststrap dataSet
for case in range(caseNum):
idx = np.random.randint(caseNum)
dataSet[case, :] = trainSet[idx, :]
w = ML.LinearRegression(dataSet)
bag[it, :] = w[:]
y = ML.testLinearRegression(dataSet, w)
return bag
elif (method == 'DecisionStump'):
# bag is to record g(it) in each iteration
bag = np.zeros((iteration, 3), float)
# dataSet is the for bootstrapping (resampling)
dataSet = np.zeros((N, L), float)
for it in range(iteration):
print("iteration No.", it + 1)
# booststrap dataSet
for case in range(caseNum):
idx = np.random.randint(caseNum)
dataSet[case, :] = trainSet[idx, :]
stump = ML.DecisionStump(dataSet)
bag[it, :] = stump[:]
y = ML.testDecisionStump(dataSet, stump)
return bag
RUN
"""
import ML
import math
import time
import numpy as np
train = ML.csvRead('hw_train.csv')
#train=ML.csvRead('TrainData.csv')
test = ML.csvRead('hw_test.csv')
#test=ML.csvRead('TestData.csv')
N, L = train.shape
#print('DecisionStump')
stump = ML.DecisionStump(train)
y = ML.testDecisionStump(test, stump)
#tic=time.time()
#bag=ML.Bagging(train,30,'LinearRegression',)
#bag=ML.Bagging(train,30)
bag, aT = ML.AdaBoost_Stump(train, 1000)
#toc=time.time()
#print('Elapsed time is',toc-tic,'second')
# out-sample testing
N, L = test.shape
