def problem_1b(n=500):
# change n for two size of datasets
algorithmList = [
'Perceptron', 'Perceptron with margin', 'Winnow', 'Winnow with margin',
'AdaGrad'
]
t = Trainer()
d = t.data_generator(l=10,
m=100,
n=n,
number_of_instances=50000,
noise=False)
x, y = d['x'], d['y']
D1_x, D1_y, D2_x, D2_y = d['D1_x'], d['D1_y'], d['D2_x'], d['D2_y']
initDict = initDictGenerator(n=t.n)
for algorithm in algorithmList:
algorithmInit = initDict[algorithm]
learningRateList = algorithmInit['learning rate']
marginList = algorithmInit['margin']
t.learning(algorithm, D1_x, D1_y, initDict=initDict, times=20)
for lr in learningRateList:
for mg in marginList:
err_rate = t.error_estimate(t.D2_x, t.D2_y, lr, mg)
mistake = t.mistakeCount(lr, mg)
print(
'LR: {0: >6s}, MG: {1: >6s}, ER: {2: >6s}, Mis: {3: >6s}'.
format(str(lr), str(mg), str(err_rate), str(mistake)))
def problem_3_tuning():
algorithmList = [
'Perceptron', 'Perceptron with margin', 'Winnow', 'Winnow with margin',
'AdaGrad'
]
for m in [100, 500, 1000]:
print()
d = problem_3_dataLoader(m, 'train')
x, y = d['x'], d['y']
D1_x, D1_y, D2_x, D2_y = d['D1_x'], d['D1_y'], d['D2_x'], d['D2_y']
t = Trainer()
t.set_param(l=10, m=m, n=x.shape[1], number_of_instances=x.shape[0])
initDict = initDictGenerator(n=t.n)
for algorithm in algorithmList:
algorithmInit = initDict[algorithm]
learningRateList = algorithmInit['learning rate']
marginList = algorithmInit['margin']
t.learning(algorithm, D1_x, D1_y, initDict=initDict, times=20)
for lr in learningRateList:
for mg in marginList:
err_rate = t.error_estimate(D2_x, D2_y, lr, mg)
mistake = t.mistakeCount(lr, mg)
print(
'LR: {0: >6s}, MG: {1: >6s}, ER: {2: >6s}, Mis: {3: >6s}'
.format(str(lr), str(mg), str(err_rate), str(mistake)))
def problem_3_train_and_evaluate():
algorithmList = [
'Perceptron', 'Perceptron with margin', 'Winnow', 'Winnow with margin',
'AdaGrad'
]
bestParaList = {
100: [(1, 0), (0.005, 1), (1.1, 0), (1.1, 0.3), (1.5, 1)],
500: [(1, 0), (1.5, 1), (1.1, 0), (1.1, 0.3), (1.5, 1)],
1000: [(1, 0), (0.25, 1), (1.1, 0), (1.1, 0.3), (0.25, 1)]
}
for m in [100, 500, 1000]:
print()
#plt.figure()
d = problem_3_dataLoader(m)
x, y = d['x'], d['y']
d = problem_3_dataLoader(m, 'test')
xtest, ytest = d['x'], d['y']
t = Trainer()
t.set_param(l=10, m=m, n=x.shape[1], number_of_instances=x.shape[0])
initDict = initDictGenerator(n=t.n)
#color = 'rgb'
for idx in range(len(algorithmList)):
algorithm = algorithmList[idx]
algorithmInit = initDict[algorithm]
if m in bestParaList:
lr, mg = bestParaList[m][idx]
else:
lr, mg = bestParaList[500][idx]
algorithmInit['learning rate'] = [lr]
algorithmInit['margin'] = [mg]
t.learning(algorithm,
x,
y,
initDict={algorithm: algorithmInit},
times=20)
err_rate = t.error_estimate(xtest, ytest, lr, mg)
print('LR: {0: >6s}, MG: {1: >6s}, ER: {2: >6s}'.format(
str(lr), str(mg), str(err_rate)))