def main_with_validation(fileName, preproc=False, evalFunc = Util.brierScore):
trainX, trainY, testX, testY = Util.readData(fileName, preproc)
clf = GEVCanReg()
regs = np.logspace(-3, 3, 7)
xis = np.linspace(-1., 1.6, 14)
bestScore, bestXi, bestReg = 1e10, None, None
for xi in xis:
clf.setXi(xi)
print("Current xi = ", xi)
score, reg = Util.crossValidate(clf, trainX, trainY, \
evalFunc, 5, "Regular", regs)
if score < bestScore:
bestScore, bestXi, bestReg = score, xi, reg
print("bestScore, bestXi, bestReg = ", bestScore, bestXi, bestReg)
clf.setXi(bestXi)
clf.setRegular(bestReg)
clf.fit(trainX, trainY)
testScore = evalFunc(clf.predict(testX), testY)
with open("log/GEV_final_log.txt", 'a') as f:
log = ','.join([dt.now().strftime("%Y/%m/%d %H:%M"), str(fileName), \
str(bestReg), str(bestXi), str(preproc), \
evalFunc.__name__, str(bestScore), str(testScore)])
f.write(log + '\n')
def main_label(fileName, reg, xi, preproc=False, evalFunc = Util.f1):
data = np.loadtxt(fname=fileName, delimiter=",")
scoreList = []
clf = GEVCanReg()
clf.setRegular(reg)
clf.setXi(xi)
k = 10
for _ in range(k):
trainX, trainY, testX, testY = Util.readData(data, preproc)
clf.fit(trainX, trainY)
s = evalFunc(Util.probToLabel(clf.predict(testX)), testY)
print("score = ", s)
scoreList.append(s)
print("mean score = ", sum(scoreList)/k)
def main_prob(fileName, reg, xi, preproc=False, evalFunc = Util.brierScore):
data = np.loadtxt(fname=fileName, delimiter=",")
scoreList = []
clf = GEVCanReg()
clf.setRegular(reg)
clf.setXi(xi)
k = 10
for _ in range(k):
trainX, trainY, testX, testY = Util.readData(data, preproc)
clf.fit(trainX, trainY)
s = evalFunc(clf.predict(testX), testY)
print("score = ", s)
scoreList.append(s)
score = sum(scoreList)/k
print("mean score = ", score)
with open("log/GEV_test_log.txt", 'a') as f:
log = ','.join([dt.now().strftime("%Y/%m/%d %H:%M"), str(fileName), \
str(preproc), evalFunc.__name__, str(score)])
f.write(log + '\n')
