def train(self, method=None, bins=None):
k = 10
kfolder = KFolder(self.D, k, normalize=True, shuffle=False)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.P = [], [], []
for i in range(k):
# Get data and labels at fold k
X,Y = kfolder.training(i)
# Get the testing data
Xi,Yi = kfolder.testing(i)
# Store the results
self.X_train.append(X), self.Y_train.append(Y)
# Calculate the prior
p = [float(len(Y[Y==0.0])) / float(len(Y))]
p.append(1.0-p[0])
# Calculate the parameters for our naive bayes classification
if method == 'gaussian':
mean, var = self.gaussian(X, Y)
self.X_test.append(Xi), self.Y_test.append(Yi), self.P.append((mean, var, p))
elif method == 'bernoulli':
mean, e0, e1 = self.bernoulli(X, Y)
self.X_test.append(Xi), self.Y_test.append(Yi), self.P.append((mean, e0, e1, p))
elif method == 'histogram':
if bins == 4:
histograms = self.hist4(X, Y)
elif bins == 9:
histograms = self.hist9(X, Y)
else:
print "Unsupported number of bins."
self.X_test.append(Xi), self.Y_test.append(Yi), self.P.append((histograms, p))
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)
def train(self, random=False):
k = 10
kfolder = KFolder(self.D, k, normalize=True, shuffle=False)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.P = [], [], []
for i in range(1):
# Get data and labels at fold k
X,Y = kfolder.training(i)
# Get the testing data
Xi,Yi = kfolder.testing(i)
# Solve for the vector of linear factors, W
return self.boost(X, Y, Xi, Yi, self.thresh(X), random=random)
def train(self, shared=True):
k = 10
kfolder = KFolder(self.D, k, normalize=False, shuffle=False)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.P = [], [], []
test_acc = np.zeros(k)
for i in range(k):
# Get data and labels at fold k
X,Y = kfolder.training(i)
# Get the testing data
Xi,Yi = kfolder.testing(i)
# Solve for the vector of linear factors, W
test_acc[i] = self.boost(X, Y, Xi, Yi, self.thresh(X))
print "Average test_acc:",test_acc.mean()
def train(self, random=False):
k = 10
kfolder = KFolder(self.D, k, normalize=True, shuffle=False)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.P = [], [], []
# set up top15
tot_top15 = np.zeros(57)
for i in range(k):
print "Fold:", i+1
# Get data and labels at fold k
X,Y = kfolder.training(i)
# Get the testing data
Xi,Yi = kfolder.testing(i)
# Solve for the vector of linear factors, W
round_top15 = self.boost(X, Y, Xi, Yi, self.thresh(X), random=random)
for f in round_top15:
tot_top15[f] += 1
return np.argsort(tot_top15)[-15:]
def train(self, shared=True):
k = 10
kfolder = KFolder(self.D, k, normalize=True, shuffle=True)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.P = [], [], []
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
u,cov,p = self.estimate(X, Y, shared)
# 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.P.append((u,cov,p))
def train(self, depth, bags):
k = 10
kfolder = KFolder(self.D, k, normalize=False)
self.T = []
# Get data and labels at fold k
self.X,self.Y = kfolder.training(0)
C = np.append(self.X,self.Y,axis=1)
n = len(C)
for i in range(bags):
print "Bag #", i+1
# Sample a bag
idx = np.random.randint(n, size=n)
Xi, Yi = C.T[:-1].T[idx], C.T[-1:].T[idx].ravel()
# Build the decision tree
dt = DecisionTree(Xi, Yi)
Ti = dt.build(depth)
self.T.append(Ti)
# Get the testing data
self.Xt,self.Yt = kfolder.testing(0)
def train(self):
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
rsolver = RegressionSolver(X, Y)
Wi = rsolver.solve()
# 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)
def train(self):
k = 10
kfolder = KFolder(self.D, k, normalize=False)
self.X_train, self.Y_train = [], []
self.X_test, self.Y_test, self.T = [], [], []
for i in range(1): # k
# Get data and labels at fold k
X, Y = kfolder.training(i)
# Build the decision tree
dt = DecisionTree(X, Y)
Ti = dt.build(6)
# 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.T.append(Ti)
data_file = "../data/spambase/spambase.data"
dmat = []
f = open(data_file, "r")
for line in f:
x = line.split(',')
x = [float(e) for e in x]
dmat.append(x)
data = np.array(dmat)
# k-folds
folds = 10
kfolder = KFolder(data, folds, standard=True, shuffle=False)
for i in range(1):
print "Fold:", i+1
# Get data and labels at fold k
X,Y = kfolder.training(i)
# Get the testing data
Xi,Yi = kfolder.testing(i)
# Run knn
H = wnn(X, Xi, Y, d=euclidean_distance, r=4.6)
c = np.sum(Yi.ravel()==H)
print "r=%f:" % 4.6, float(c)/float(len(Yi))
elif args.d == "d":
# Load data using specialized script
train_dataset = load_mnist(path="../data/mnist/", dataset="training")
test_dataset = load_mnist(path="../data/mnist/", dataset="testing")
# Take a fraction of the data to speed computation
train_images, train_labels = sample(train_dataset, 10000)
test_images, test_labels = sample(test_dataset, 1000)