from imblearn.over_sampling import SMOTE
from metrics_list import metric_list
path = "High_IR_Data_cross_folder"
dirs = os.listdir(path) #Get files in the folder
First_line = True
for Dir in dirs:
print("Data Set Name: ", Dir)
dir_path = path + "/" + Dir
files = os.listdir(dir_path) # Get files in the folder
methods = ["xGBoost", "SMOTE", "SMOTE-SMOTE"]
for m in methods:
Num_Cross_Folders = 5
ml_record = metric_list(np.array([1]), np.array([1]),
Num_Cross_Folders)
i = 0
for file in files:
name = dir_path + '/' + file
r = np.load(name)
Positive_Features_train = r["P_F_tr"]
Num_Positive_train = Positive_Features_train.shape[0]
Positive_Labels_train = np.linspace(1, 1, Num_Positive_train)
Positive_Features_test = r["P_F_te"]
Num_Positive_test = Positive_Features_test.shape[0]
Positive_Labels_test = np.linspace(1, 1, Num_Positive_test)
Negative_Features_train = r["N_F_tr"]
Num_Negative_train = Negative_Features_train.shape[0]
dirs = os.listdir(path) #Get files in the folder
for Dir in dirs:
print("Data Set Name: ", Dir)
dir_path = path + "/" + Dir
files = os.listdir(dir_path) # Get files in the folder
f_i = 0
par_a = []
par_b = []
Num_Gamma = 100
gamma = np.logspace(-4, 2, Num_Gamma)
Num_C = 100
C = np.logspace(-2, 4, Num_C)
Num_Cross_Folders = 3
ml_record = metric_list(gamma, C, Num_Cross_Folders)
'''
max_depth = np.arange(3,10,1) # best = 3
min_child_weight = np.arange(1,6,1) # best = 1
gamma = np.arange(0,1,0.1) # best = 0.0
subsample = np.arange(0.5,1,0.1) # best = 0.5
colsample_bytree = np.arange(0.5,1,0.1) # best = 0.6
reg_alpha = np.logspace(-5, 5, 10) # best = 0.002
learning_rate = np.logspace(-2, 0, 10) # best = 0.215
'''
Num_Cross_Folders = 3
ml_record = metric_list(gamma, C, Num_Cross_Folders)
i = 0
for file in files: