def adaboost_predict (A, H, I, x, t):
n=x.shape[0]
out = np.zeros(n)
for i in range(t):
out += A[i] * ds.stump_predict(x[:,I[i]], H[i])
return np.sign(out);
def adaboost_find_t (A, H, I, x, y):
n=x.shape[0]
out = np.zeros(n)
t=len(A)
HE = []
for i in range(t):
out += A[i] * ds.stump_predict(x[:,I[i]], H[i])
HE.append( (np.sign(out) * y < 0).sum() / float(n) )
idx = np.argmin(HE)
return HE, idx + 1
def adaboost_find_t (A, H, I, x, y):
n=x.shape[0]
out = np.zeros(n)
t=len(A)
HE = []
for i in range(t):
out += A[i] * ds.stump_predict(x[:,I[i]], H[i])
HE.append( (np.sign(out) * y < 0).sum() / float(n) )
idx = min(enumerate(HE), key=operator.itemgetter(1))[0]
return HE, idx
def adaboost_train (x, y, T):
cf = x.shape[1]
n = y.shape[0]
weights = ones(n)/n
H = []
A = []
I = []
TE = []
for t in range(T):
pplus = sum(weights * (y > 0))
# Let's train on all the features and find the one that works the best
decisionVariables = []
score = []
we = []
for idx in range(cf):
f = x[:,idx]
# train the stump
(dv, err) = ds.stump_fit(f, y, weights, pplus)
we.append( err )
decisionVariables.append(dv)
# score the classifiers on all features for this round
score.append(abs(.5-err))
print "Round: ", t, str(datetime.now())
# choose the one feature we'll use for this round's classifier
I.append(np.argmax(score))
H.append(decisionVariables[I[t]])
eps = we[I[t]]
# calculate our alpha
A.append(.5 * math.log((1-eps)/eps))
# update the weights
numerators = weights * np.exp( -A[t] * y * ds.stump_predict(x[:,I[t]], H[t]) )
Z = numerators.sum()
weights = numerators / Z
# Calculate the overall training errors
y_hat = adaboost_predict(A,H,I,x, len(A))
TE.append((y_hat * y < 0).sum() / float(n))
return A, H, I, TE
