x = []
y = []
for i in range(len(dataset)):
y.append(float(dataset[i][len(dataset[0]) - 1]))
t = []
for j in range(len(dataset[0]) - 1):
t.append(float(dataset[i][j]))
x.append(t)
df1 = pd.read_csv('ex2data1test.csv', delimiter=',')
dataset1 = np.array(df1).tolist()
xt = []
yt = []
for i in range(len(dataset1)):
yt.append(float(dataset1[i][len(dataset1[0]) - 1]))
t = []
for j in range(len(dataset1[0]) - 1):
t.append(float(dataset1[i][j]))
xt.append(t)
from RF import RF
rf = RF(B=5, Bagging=True)
rf.train(x, y)
yPredict = rf.predict(xt)
count = 0
for i in range(len(yPredict)):
if yPredict[i] == yt[i]:
count += 1
print(count / float(len(yt)))
def bagging(N):
#training data
xRF = RFData.x
y = RFData.y
#testing data
xtRF = RFData.xt
yt = RFData.yt
xKNN = knnData.main()[0] #training X
xtKNN = knnData.main()[2] #test X
countYPredict = []
for i in range(len(yt)):
countYPredict.append(0)
for k in range(N): # number of bootstrapping
x_RF = []
y_RF = []
x_KNN = []
y_KNN = []
# bootstrapping
for i in range(int(len(xRF) * 0.6)):
r = randint(0, len(xRF) - 1)
tRF = []
for j in range(len(xRF[0]) - 1):
tRF.append(xRF[r][j])
# for RF, data duplicates are not allowed
if tRF not in x_RF:
x_RF.append(tRF)
y_RF.append(y[r])
x_KNN.append(xKNN[r])
y_KNN.append(y[r])
# RF
start = time.time()
rf = RF(B=TreeNum, Bagging=isBagging)
rf.train(x_RF, y_RF)
pred = rf.predict(xtRF)
end = time.time()
count = 0
for i in range(len(pred)):
if pred[i] == yt[i]:
count += 1
print("RF, trial #" + str(k + 1) + ": ")
print('\taccuracy: ' + str(round(count / float(len(yt)) * 100, 2)) +
'%')
print('\ttraining time: ' + str(round(end - start, 1)) + ' seconds')
for i in range(len(pred)):
countYPredict[i] = countYPredict[i] + pred[i]
# KNN
start = time.time()
pred = knn.main(x_KNN, y_KNN, xtKNN, kInKnn)
end = time.time()
count = 0
for i in range(len(pred)):
if pred[i] == yt[i]:
count += 1
print("KNN, trial #" + str(k + 1) + ": ")
print('\taccuracy: ' + str(round(count / float(len(yt)) * 100, 2)) +
'%')
print('\ttraining time: ' + str(round(end - start, 1)) + ' seconds')
for i in range(len(pred)):
countYPredict[i] = countYPredict[i] + pred[i]
finalPredict = []
for i in range(len(yt)):
if countYPredict[i] >= N:
finalPredict.append(1)
else:
finalPredict.append(0)
count = 0
for i in range(len(finalPredict)):
if finalPredict[i] == yt[i]:
count += 1
print()
print('After combining the classifiers by bagging: ')
print('\taccuracy: ' + str(round(count / float(len(yt)) * 100, 2)) + '%')
y = []
for i in range(len(dataset)):
y.append(float(dataset[i][len(dataset[0])-1]))
t = []
for j in range(len(dataset[0])-1):
t.append(float(dataset[i][j]))
x.append(t)
df1 = pd.read_csv('ex2data1test.csv', delimiter=',')
dataset1 = np.array(df1).tolist()
xt = []
yt = []
for i in range(len(dataset1)):
yt.append(float(dataset1[i][len(dataset1[0])-1]))
t = []
for j in range(len(dataset1[0])-1):
t.append(float(dataset1[i][j]))
xt.append(t)
from RF import RF
rf = RF(B=5, Bagging = True)
rf.train(x, y)
yPredict = rf.predict(xt)
count = 0
for i in range(len(yPredict)):
if yPredict[i] == yt[i]:
count +=1
print(count/float(len(yt)))
def bagging(N):
# training data
xRF = RFData.x
y = RFData.y
# testing data
xtRF = RFData.xt
yt = RFData.yt
xKNN = knnData.main()[0] # training X
xtKNN = knnData.main()[2] # test X
countYPredict = []
for i in range(len(yt)):
countYPredict.append(0)
for k in range(N): # number of bootstrapping
x_RF = []
y_RF = []
x_KNN = []
y_KNN = []
# bootstrapping
for i in range(int(len(xRF) * 0.6)):
r = randint(0, len(xRF) - 1)
tRF = []
for j in range(len(xRF[0]) - 1):
tRF.append(xRF[r][j])
# for RF, data duplicates are not allowed
if tRF not in x_RF:
x_RF.append(tRF)
y_RF.append(y[r])
x_KNN.append(xKNN[r])
y_KNN.append(y[r])
# RF
start = time.time()
rf = RF(B=TreeNum, Bagging=isBagging)
rf.train(x_RF, y_RF)
pred = rf.predict(xtRF)
end = time.time()
count = 0
for i in range(len(pred)):
if pred[i] == yt[i]:
count += 1
print("RF, trial #" + str(k + 1) + ": ")
print("\taccuracy: " + str(round(count / float(len(yt)) * 100, 2)) + "%")
print("\ttraining time: " + str(round(end - start, 1)) + " seconds")
for i in range(len(pred)):
countYPredict[i] = countYPredict[i] + pred[i]
# KNN
start = time.time()
pred = knn.main(x_KNN, y_KNN, xtKNN, kInKnn)
end = time.time()
count = 0
for i in range(len(pred)):
if pred[i] == yt[i]:
count += 1
print("KNN, trial #" + str(k + 1) + ": ")
print("\taccuracy: " + str(round(count / float(len(yt)) * 100, 2)) + "%")
print("\ttraining time: " + str(round(end - start, 1)) + " seconds")
for i in range(len(pred)):
countYPredict[i] = countYPredict[i] + pred[i]
finalPredict = []
for i in range(len(yt)):
if countYPredict[i] >= N:
finalPredict.append(1)
else:
finalPredict.append(0)
count = 0
for i in range(len(finalPredict)):
if finalPredict[i] == yt[i]:
count += 1
print()
print("After combining the classifiers by bagging: ")
print("\taccuracy: " + str(round(count / float(len(yt)) * 100, 2)) + "%")
