def CART(dataset, a=12, b=1, c=2):
dataset = normalize(dataset)
mre_list = []
sa_list = []
for train, test in KFold_df(dataset, 3):
train_input = train.iloc[:, :-1]
train_actual_effort = train.iloc[:, -1]
test_input = test.iloc[:, :-1]
test_actual_effort = test.iloc[:, -1]
# max_depth: [1:12], min_samples_leaf: [1:12], min_samples_split: [2:21]
model = DecisionTreeRegressor(max_depth=a,
min_samples_leaf=b,
min_samples_split=c)
model.fit(train_input, train_actual_effort)
test_predict_effort = model.predict(test_input)
test_predict_Y = test_predict_effort
test_actual_Y = test_actual_effort.values
mre_list.append(mre_calc(test_predict_Y,
test_actual_Y)) ######### for MRE
sa_list.append(sa_calc(test_predict_Y,
test_actual_Y)) ######### for SA
mre_mean = np.mean(mre_list) ######### for MRE
sa_mean = np.mean(sa_list) ######### for SA
return mre_mean ######### for MRE
def cart_builder(a, b, c):
model = DecisionTreeRegressor(max_depth=a,
min_samples_leaf=b,
min_samples_split=c)
model.fit(train_input, train_actual_effort)
test_predict_effort = model.predict(test_input)
test_predict_Y = test_predict_effort
test_actual_Y = test_actual_effort.values
# mre_list.append(mre_calc(test_predict_Y, test_actual_Y))
# sa_list.append(sa_calc(test_predict_Y, test_actual_Y))
if metrics == 0:
return mre_calc(test_predict_Y,
test_actual_Y) ############# MRE
elif metrics == 1:
return sa_calc(test_predict_Y, test_actual_Y) ############# SA
def RF(dataset, max_depth=3):
dataset = normalize(dataset)
mre_list = []
sa_list = []
for train, test in KFold_df(dataset, 3):
train_input = train.iloc[:, :-1]
train_actual_effort = train.iloc[:, -1]
test_input = test.iloc[:, :-1]
test_actual_effort = test.iloc[:, -1]
model = RandomForestRegressor(max_depth)
model.fit(train_input, train_actual_effort)
test_predict_effort = model.predict(test_input)
test_predict_Y = test_predict_effort
test_actual_Y = test_actual_effort.values
mre_list.append(mre_calc(test_predict_Y,
test_actual_Y)) ######### for MRE
sa_list.append(sa_calc(test_predict_Y,
test_actual_Y)) ######### for SA
return mre_list, sa_list
def SVM(dataset):
dataset = normalize(dataset)
mre_list = []
sa_list = []
for train, test in KFold_df(dataset, 3):
train_input = train.iloc[:, :-1]
train_actual_effort = train.iloc[:, -1]
test_input = test.iloc[:, :-1]
test_actual_effort = test.iloc[:, -1]
model = svm.SVR(gamma='scale')
model.fit(train_input, train_actual_effort)
test_predict_effort = model.predict(test_input)
test_predict_Y = test_predict_effort
test_actual_Y = test_actual_effort.values
mre_list.append(mre_calc(test_predict_Y,
test_actual_Y)) ######### for MRE
sa_list.append(sa_calc(test_predict_Y,
test_actual_Y)) ######### for SA
return mre_list, sa_list
def KNN(dataset, n_neighbors=3):
dataset = normalize(dataset)
mre_list = []
sa_list = []
for train, test in KFold_df(dataset, 3):
train_input = train.iloc[:, :-1]
train_actual_effort = train.iloc[:, -1]
test_input = test.iloc[:, :-1]
test_actual_effort = test.iloc[:, -1]
model = neighbors.KNeighborsRegressor(n_neighbors)
model.fit(train_input, train_actual_effort)
test_predict_effort = model.predict(test_input)
test_predict_Y = test_predict_effort
test_actual_Y = test_actual_effort.values
mre_list.append(mre_calc(test_predict_Y,
test_actual_Y)) ######### for MRE
sa_list.append(sa_calc(test_predict_Y,
test_actual_Y)) ######### for SA
return mre_list, sa_list
def flash(metrics, train_input, train_actual_effort, test_input, test_actual_effort, pop_size):
def convert(index):
a = int(index / 240 + 1)
b = int(index % 240 / 20 + 1)
c = int(index % 20 + 2)
return a, b, c
all_case = set(range(0, 2880))
modeling_pool = random.sample(all_case, pop_size)
List_X = []
List_Y = []
for i in range(len(modeling_pool)):
temp = convert(modeling_pool[i])
List_X.append(temp)
model = DecisionTreeRegressor(max_depth=temp[0], min_samples_leaf=temp[1], min_samples_split=temp[2])
model.fit(train_input, train_actual_effort)
test_predict_effort = model.predict(test_input)
test_predict_Y = test_predict_effort
test_actual_Y = test_actual_effort.values
if metrics == 0:
List_Y.append(mre_calc(test_predict_Y, test_actual_Y)) ######### for MRE flash
elif metrics == 1:
List_Y.append(sa_calc(test_predict_Y, test_actual_Y)) ######### for SA flash
remain_pool = all_case - set(modeling_pool)
test_list = []
for i in list(remain_pool):
test_list.append(convert(i))
upper_model = DecisionTreeRegressor()
life = 20
if metrics == 0:
while len(List_X) < 201 and life > 0: # eval_number
upper_model.fit(List_X, List_Y)
candidate = random.sample(test_list, 1)
test_list.remove(candidate[0])
candi_pred_value = upper_model.predict(candidate)
if candi_pred_value < np.median(List_Y): ######### for MRE flash
List_X.append(candidate[0])
candi_config = candidate[0]
candi_model = DecisionTreeRegressor(max_depth=candi_config[0], min_samples_leaf=candi_config[1],
min_samples_split=candi_config[2])
candi_model.fit(train_input, train_actual_effort)
candi_pred_Y = candi_model.predict(test_input)
candi_actual_Y = test_actual_effort.values
List_Y.append(mre_calc(candi_pred_Y, candi_actual_Y)) ######### for MRE flash
else:
life -= 1
return np.min(List_Y) ########## min for MRE
elif metrics == 1:
while len(List_X) < 201 and life > 0: # eval_number
upper_model.fit(List_X, List_Y)
candidate = random.sample(test_list, 1)
test_list.remove(candidate[0])
candi_pred_value = upper_model.predict(candidate)
if candi_pred_value > np.median(List_Y): ######### for SA flash
List_X.append(candidate[0])
candi_config = candidate[0]
candi_model = DecisionTreeRegressor(max_depth=candi_config[0], min_samples_leaf=candi_config[1],
min_samples_split=candi_config[2])
candi_model.fit(train_input, train_actual_effort)
candi_pred_Y = candi_model.predict(test_input)
candi_actual_Y = test_actual_effort.values
List_Y.append(sa_calc(candi_pred_Y, candi_actual_Y)) ######### for SA flash
else:
life -= 1
return np.max(List_Y) ########## min for SA