def CART_DE(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]
# max_depth: [1:12], min_samples_leaf: [1:12], min_samples_split: [2:21]
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))
return mre_calc(test_predict_Y, test_actual_Y) ############# MRE
# return sa_calc(test_predict_Y, test_actual_Y) ############# SA
output = de(cart_builder,
bounds=[(1, 12), (0.00001, 0.5), (0.00001, 1)])
mre_list.append(output) ############# MRE
# sa_list.append(output) ############# SA
return mre_list ############# MRE
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_FLASH(dataset, metrics):
dataset = normalize(dataset)
score_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]
output = flash(metrics, train_input, train_actual_effort, test_input,
test_actual_effort, 10)
score_list.append(output)
return score_list
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 cart_classifier(dataset):
dataset = normalize(dataset)
detail_report = []
for train, test in KFold_df(dataset, 3):
train_input = train.iloc[:, :-1]
train_actual_output = train.iloc[:, -1]
test_input = test.iloc[:, :-1]
test_actual_output = test.iloc[:, -1]
model = DecisionTreeClassifier()
# model = GaussianNB()
# model = RandomForestClassifier()
# model = SVC(gamma='scale')
# model = KNeighborsClassifier()
model.fit(train_input, train_actual_output)
test_predict_output = model.predict(test_input)
test_actual_output = test_actual_output.values
# print(test_actual_output, "???")
# print(test_predict_output, "!!!")
detail_report = classification_report(test_actual_output, test_predict_output,
target_names=['Unarchived', 'Archived'])
return detail_report
