eta = 0.001
iters, sErr = 200, np.Infinity
TrEnt = []
TeEnt = []
for i in range(iters):
# np.random.shuffle(X)
for obs in range(Xtr.shape[0]):
o0, y = Xtr[obs, :], float(Ytr[obs])
o1 = L1.feed(o0)
o2 = float(L2.feed(o1))
dCost_do2 = L2.costFuncDeriv(y, o2)
delta2 = dCost_do2 * L2.deriv_out(o2)
# here eta*delta applies to the last column of
# the resulting hstack, i.e. the bias
L2.w += -eta * delta2 * np.hstack((o1, L2.biasVal))
delta1 = delta2 * L1.deriv_out(o1)
L1.w += -eta * delta1.reshape(-1, 1) * np.hstack((o0, L1.biasVal))
_tr = L2.costFunc(Ytr, L2.score(Xtr, L1))
_te = L2.costFunc(Yte, L2.score(Xte, L1))
train_err = float(sum(_tr))
test_err = float(sum(_te))
sErr0 = sErr
sErr = test_err
if (sErr - sErr0) / sErr0 > 1e-6 and i > 50:
