def train(self, l, method='normal'):
k = 10
kfolder = KFolder(self.D, k, normalize=True)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.W = [], [], []
for i in range(k):
# Get data and labels at fold k
X,Y = kfolder.training(i)
# Solve for the vector of linear factors, W
if method == 'normal':
rsolver = RegressionSolver(X, Y)
Wi = rsolver.solve(l)
elif method == 'descent':
gd = GradientDescent(X, Y)
Wi = gd.linreg_stoch2()
elif method == 'logistic':
gd = GradientDescent(X, Y)
Wi = gd.logreg_stoch()
# Get the testing data
Xi,Yi = kfolder.testing(i)
# Store the results
self.X_train.append(X), self.Y_train.append(Y)
self.X_test.append(Xi), self.Y_test.append(Yi), self.W.append(Wi)
from polluted import PollutedSpambase
from evaluator import Evaluator
from descent import GradientDescent
if __name__=="__main__":
# Get data
dataset = PollutedSpambase()
train_data, train_labels = dataset.training()
test_data, test_labels = dataset.testing()
# Do Logistic Regression
gd = GradientDescent(train_data, train_labels)
# 200,000 iterations gives ~85% acc
W = gd.logreg_stoch(it=200001)
# Evaluate solution
evaluator = Evaluator([test_data], [test_labels], [W])
evaluator.accuracy()