def __init__(self, pca=False):
dataset = PollutedSpambase()
self.train_data, self.train_labels = dataset.training()
self.test_data, self.test_labels = dataset.testing()
if pca:
pca = PCA(n_components=100)
pca.fit(self.train_data)
# Project PCA onto testing data
#print self.train_data.shape, self.test_data.shape
self.train_data = pca.transform(self.train_data)
self.test_data = pca.transform(self.test_data)
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()