def leat_ai_raw(schema, train, test, s_option, nt, lift, z_beta):
cov_c45 = 0.0
cov_leat = 0.0
data = np.vstack((train,test))
base_prob = dt.laplace_smoothing(data)
obj_prob = lift * base_prob
pred = np.zeros(len(data))
alpha_list = [-1.0, -0.75, -0.5, -0.25, 0.0, 0.25, 0.5, 1.0, 1.5, 1.75, 2.0,2.25, 2.5, 2.75, 3.0]
# base tree
output = []
nt = 1
for alpha in alpha_list:
tree = dt.create_decision_tree(data, schema, alpha, -1,
True, obj_prob, z_beta)
pred_new = dt.apply_rules(data, schema, tree)
pred_added = pred + pred_new
cov_new = float(np.sum(pred_added > 0))/len(data)
cov_orig = float(np.sum(pred > 0))/len(data)
if cov_new > cov_orig:
pred = pred_added
output.append([nt,cov_new])
nt = nt + 1
print nt, cov_new
return output
def leat(schema, train, test, s_option, nt, lift, z_beta):
cov_c45 = 0.0
cov_leat = 0.0
data = np.vstack((train,test))
base_prob = dt.laplace_smoothing(data)
obj_prob = lift * base_prob
pred_a = np.zeros(len(data))
pred_c = np.zeros(len(data))
bag_cnt = 0
alpha_list = [-1.0, -0.75, -0.5,-0.25, 0.0, 0.25, 0.5, 1.5, 1.75, 2.0,2.25, 2.5, 2.75, 3.0]
while True:
# bagging
newdata = sampling(data, s_option)
# base tree
tree = dt.create_decision_tree(newdata, schema, 1.0, -1,
True, obj_prob, z_beta)
pred = dt.apply_rules(data, schema, tree)
pred_c = pred_c + pred
pred_a = pred_a + pred
for alpha in alpha_list:
tree = dt.create_decision_tree(newdata, schema, alpha, -1,
True, obj_prob, z_beta)
pred = dt.apply_rules(data, schema, tree)
pred_a = pred_a + pred
bag_cnt = bag_cnt + 1
if bag_cnt > nt:
break
cov_c45 = float(np.sum(pred_c > 0))/len(data)
cov_leat = float(np.sum(pred_a > 0))/len(data)
return cov_c45, cov_leat