PrefixSpan/keris.ipynb/PrefixSpan_20210925_edit.py

#!/usr/bin/env python
# coding: utf-8

# <p>NTM(유해트래픽 탐지장비)</p>
# <p>MTM(악성파일 탐지장비)</p>

# In[1]:


#!/usr/bin/env python
# coding: utf-8

import pandas as pd
import numpy as np
from mlxtend.preprocessing import TransactionEncoder
from mlxtend.frequent_patterns import association_rules, fpgrowth
from prefixspan import PrefixSpan

# load ts_data_accident-2020_sample.csv
# to prevent dtypewarning, set low_memory=False
df = pd.read_csv('ts_data_accident-2020_sample.csv', low_memory=False)
df=df[['RISK_V2','INST_NM','DRULE_ATT_TYPE_CODE1','TW_ATT_IP','TW_ATT_PORT','TW_DMG_IP','TW_DMG_PORT','ACCD_DMG_PROTO_NM','TW_ATT_CT_NM','ACCD_FIND_MTD_CODE','DRULE_NM']].dropna()
len(df) #len(df) : 10000, load successful

##################### NTM section #####################
NTM_df=df[df['ACCD_FIND_MTD_CODE']==1] #* edit'1' to 1
len(NTM_df)
#* NTM_df.head()

# Pick out it in order to get the asset, risk, intent, black IP out
RISK_V2=NTM_df['RISK_V2']

RISK_V2_FILTERED=RISK_V2.dropna()
print(RISK_V2.size)
print(RISK_V2_FILTERED.size)

#* 추가 : 기존 filter_assets_value 사용시 값을 인식하지 못하는 문제 발생 -> RISK_V2를 별도의 df로 수정
import json
from pandas import json_normalize
risk_df = pd.DataFrame()
for newVal in RISK_V2_FILTERED:
    newVal = newVal.replace("'", "\"")
    newVal_str = json.loads(newVal)
    newVal_df = json_normalize(newVal_str) 
    risk_df = pd.concat([risk_df,newVal_df],ignore_index=True) 
    
risk_df_col = risk_df.columns.values.tolist()

# In[352]:
asset_val = []
intent_val=[]
source_val=[]
def filter_assets_value(risk):
    for i in range(len(risk)):
        risks=[]
        intents=[]
        sources=[]
        try:
            for key in risk_df_col:
                if 'ASSETS_VAL_' in key and risk.iloc[i][key]:
                    risk_key_desc = 'RISK_V2.' + key + '=' + get_asset_desc(key)
                    risks.append(risk_key_desc)
                if 'INTENT_VAL_' in key and risk.iloc[i][key]:
                    intent_key_desc = 'RISK_V2.' + key + '=' + get_intent_desc(key)
                    intents.append(intent_key_desc)
                if 'SOURCE_VAL_' in key and risk.iloc[i][key]:
                    source_key_desc='RISK_V2.' + key + '=' + get_source_desc(key)
                    sources.append(source_key_desc)
        except:
            print(risk)
            print(type(risk))
        finally:
            asset_val.append(risks)
            intent_val.append(intents)
            source_val.append(sources)
    
    
# modified
def get_asset_desc(asset_field):
    if asset_field == 'ASSETS_VAL_1':
        return '공인-전체IP대역(유선)'
    elif asset_field == 'ASSETS_VAL_2':
        return '공인-전체IP대역(무선)'
    elif asset_field == 'ASSETS_VAL_3':
        return '공인-WEB서버'
    elif asset_field == 'ASSETS_VAL_4':
        return '공인-내부응용서버'
    elif asset_field == 'ASSETS_VAL_5':
        return '공인-DB서버'
    elif asset_field == 'ASSETS_VAL_6':
        return '공인-패치서버'
    elif asset_field == 'ASSETS_VAL_7':
        return '공인-네트워크'
    elif asset_field == 'ASSETS_VAL_8':
        return '공인-보안'
    elif asset_field == 'ASSETS_VAL_9':
        return '공인-업무용PC'
    elif asset_field == 'ASSETS_VAL_10':
        return '공인-비업무용PC'
    elif asset_field == 'ASSETS_VAL_11':
        return '공인-기타'
    elif asset_field == 'ASSETS_VAL_12':
        return '사설-전체IP대역(유선)'
    elif asset_field == 'ASSETS_VAL_13':
        return '사설-전체IP대역(무선)'
    elif asset_field == 'ASSETS_VAL_14':
        return '사설-WEB서버'
    elif asset_field == 'ASSETS_VAL_15':
        return '사설-내부응용서버'
    elif asset_field == 'ASSETS_VAL_16':
        return '사설-DB서버'
    elif asset_field == 'ASSETS_VAL_17':
        return '사설-패치서버'
    elif asset_field == 'ASSETS_VAL_18':
        return '사설-네트워크'
    elif asset_field == 'ASSETS_VAL_19':
        return '사설-보안'
    elif asset_field == 'ASSETS_VAL_20':
        return '사설-업무용PC'
    elif asset_field == 'ASSETS_VAL_21':
        return '사설-비업무용PC'
    elif asset_field == 'ASSETS_VAL_22':
        return '사설-기타'
    else:
        return ''



# modified
def filter_intent(intent):
    intents=[]
    for intent_key in intent:
        if 'INTENT_VAL_' in intent_key and intent[intent_key]:
            intent_key_desc = 'RISK_V2.' + intent_key + '=' + get_intent_desc(intent_key)
            intents.append(intent_key_desc)
    return intents


# In[356]:


def get_intent_desc(intent_field):
    if intent_field == 'INTENT_VAL_1':
        return '파괴'
    elif intent_field == 'INTENT_VAL_2':
        return '유출'
    elif intent_field == 'INTENT_VAL_3':
        return '지연'
    elif intent_field == 'INTENT_VAL_4':
        return '잠복'
    elif intent_field == 'INTENT_VAL_5':
        return '단순침입'
    elif intent_field == 'INTENT_VAL_6':
        return 'MD5'
    elif intent_field == 'INTENT_VAL_0':
        return 'Default'
    else:
        return ''


# In[358]:


# modified
def filter_source(source):
    sources=[]
    for source_key in source:
        if 'SOURCE_VAL_' in source_key and source[source_key]:
            source_key_desc='RISK_V2.' + source_key + '=' + get_source_desc(source_key)
            sources.append(source_key_desc)
    return sources


# In[359]:


def get_source_desc(source_field):
    if source_field=='SOURCE_VAL_1':
        return '북한IP'
    if source_field=='SOURCE_VAL_3':
        return 'ECSC Black IP'
    else:
        return ''



# In[2]:


filter_assets_value(risk_df)
#뒤에 isna()를 통해 na값을 0으로 바꿔주는 작업을 하므로, 값이 비어있는 경우 [] 대신 비워두기
# New assets column
NTM_df['ASSETS_VAL']= asset_val
NTM_df['ASSETS_VAL']=NTM_df['ASSETS_VAL'].astype(str)
NTM_df['ASSETS_VAL']=NTM_df['ASSETS_VAL'].str.replace('[','', regex=False)
NTM_df['ASSETS_VAL']=NTM_df['ASSETS_VAL'].str.replace(']','', regex=False)
NTM_df[:1]
# New column of intent value
NTM_df['INTENT_VAL']=intent_val
NTM_df['INTENT_VAL']=NTM_df['INTENT_VAL'].astype(str)
NTM_df['INTENT_VAL']=NTM_df['INTENT_VAL'].str.replace('[','',regex=False)
NTM_df['INTENT_VAL']=NTM_df['INTENT_VAL'].str.replace(']','',regex=False)
NTM_df[:1]
# New column of SOURCE_VAL value
NTM_df['SOURCE_VAL']=source_val
NTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].astype(str)
NTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].str.replace('[','',regex=False)
NTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].str.replace(']','',regex=False)
NTM_df[:5]

# In[361]:
NTM_df.drop(columns=['RISK_V2'], inplace=True)
NTM_df.columns


# In[3]:


#data frame의 i번째 row를 list로 저장하여 itertools.combinations로 모든 조합 만들 예정
#TW_ATT_IP와 TW_DMG_IP의 값이 같은 경우 어떤 값과의 관계인지 알 수 없으므로 데이터 가공
NTM_df['TW_ATT_IP']="TW_ATT_IP="+NTM_df['TW_ATT_IP'].astype(str)
NTM_df['TW_ATT_PORT']="TW_ATT_PORT="+NTM_df['TW_ATT_PORT'].astype(str)
NTM_df['TW_DMG_IP']="TW_DMG_IP="+NTM_df['TW_DMG_IP'].astype(str)
NTM_df['TW_DMG_PORT']="TW_DMG_PORT="+NTM_df['TW_DMG_PORT'].astype(str)


# In[4]:


##################### 여기서부터 진행하시면 됩니다. #####################
##################### 아래 12개 아이템(12. 장비 ACCD_FIND_MTD_CODE 제외)에 대해서 모든 아이템 조합에 알고리즘 적용하기#####################

# It should be 13 columns in total

# 1. 기관 INST_NM
# 2. 공격 DRULE_ATT_TYPE_CODE1
# 3. 자산 ASSETS_VAL
# 4. 위협공격ip TW_ATT_IP
# 5. 위협공격port TW_ATT_PORT
# 6. 위협피해ip TW_DMG_IP
# 7. 위협피해port TW_DMG_PORT
# 8. 위협피해프로토콜 ACCD_DMG_PROTO_NM
# 9. 공격국가 TW_ATT_CT_NM
# 10. 의도(7개) INTENT_VAL
# 11. IP/URL 가중치 SOURCE_VAL
# 12. 장비 ACCD_FIND_MTD_CODE
# 13. 탐지규칙명 DRULE_NM


# In[363]:
NTM_df.isna().sum()


# Change the Nan to zero
NTM_df['ACCD_DMG_PROTO_NM']=NTM_df['ACCD_DMG_PROTO_NM'].replace(np.nan,'')
NTM_df['INST_NM']=NTM_df['INST_NM'].replace(np.nan,'')
NTM_df['DRULE_ATT_TYPE_CODE1']=NTM_df['DRULE_ATT_TYPE_CODE1'].replace(np.nan,'')
NTM_df['TW_ATT_IP']=NTM_df['TW_ATT_IP'].replace(np.nan,0)
NTM_df['TW_ATT_PORT']=NTM_df['TW_ATT_PORT'].replace(np.nan,0)
NTM_df['TW_DMG_IP']=NTM_df['TW_DMG_IP'].replace(np.nan,0)
NTM_df['TW_DMG_PORT']=NTM_df['TW_DMG_PORT'].replace(np.nan,0)
NTM_df['TW_ATT_CT_NM']=NTM_df['TW_ATT_CT_NM'].replace(np.nan,'')
NTM_df['ASSETS_VAL']=NTM_df['ASSETS_VAL'].replace(np.nan,0)
NTM_df['INTENT_VAL']=NTM_df['INTENT_VAL'].replace(np.nan,0)
NTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].replace(np.nan,0)
NTM_df['DRULE_NM']=NTM_df['DRULE_NM'].replace(np.nan,'')


# Check NaN out again
NTM_df.isna().sum()


# In[5]:


# NTM_df의 col을 list로 저장. itertools.combinations로 가능한 시나리오 모두 추출

# ACCD_FIND_MTD_CODE col 지우기
NTM_df.drop(columns=['ACCD_FIND_MTD_CODE'], inplace=True)


# In[6]:


# 12의 아이템 중 2개의 조합으로 만들어질 수 있는 모든 시나리오의 갯수 파악
import itertools
item_n=[]
for i in range(2,7):
    temp = itertools.combinations(NTM_df.columns.tolist(), i)
    item_n.append(list(temp))

#12C4부터 495개의 데이터를 저장하는데에 소요되는 시간이 너무 커서 단순 반복문 사용은 적합하지 않음.
for i in range(len(item_n)):
    print("12C" + str(i+2)+" = "+str(len(item_n[i])))


# In[7]:


from prefixspan import PrefixSpan

# arr를 매개변수로 받아 n개의 아이템의 조합 반환
def get_combination(arr, n):
    combination_n = list(itertools.combinations(arr.columns.tolist(),n))
    com_list=[]
    # row i 의 (1,2),(1,3)... 이런식으로 하니까 시간 너무 오래걸림
    # (1,2) 조합에 대한 row i, row i+1, row i+2... 이렇게 바꿈
    for m in range(len(combination_n[n-2])):
        for i in range(len(arr)):
            tmp_list=[]
            temp_df = arr.iloc[i]
            for col in combination_n[m]:
                tmp_list.append(temp_df[col])
            com_list.append(tmp_list)
    return com_list

def get_prefixspan(n, load_list, save_list, save_df):
    save_list = PrefixSpan(load_list)
    #n개 아이템 조합으로 이루어졌는데 n보다 작은 갯수의 아이템으로 이루어진 prefixspan 결과 값 나옴 
    # 방지하기 위해 prefixspan의 결과값에는 'n개의 아이템의 값'이 다 들어가도록 filter 설정
    save_list = save_list.frequent(1,filter = lambda patt, matches:len(patt)>n)
    save_df = pd.DataFrame(save_list)
    save_df.rename(columns={0:'Frequency',1:'Cause'},inplace=True)
    save_df = save_df.sort_values(by=['Frequency'],ascending=False,ignore_index=True)
    save_df = get_effect(save_df)
    return save_df

def get_effect(edit_df):
    #Make the new column for filling the Effect
    edit_df['Effect']=np.nan
     #Change the order of columns
    edit_df=edit_df[['Cause','Effect','Frequency']]
    for i in range(len(edit_df)):
        drules=['Attack','DDOS','HACK','MAIL','Malwr','WEB']
        loc_value = edit_df.loc[i]
        for item in loc_value['Cause']:
            for drule in drules:
                if item == drule:
                    edit_df.loc[i,'Effect'] = item
    return edit_df


# In[8]:


# 1. 두 아이템의 조합
item_of_two = get_combination(NTM_df,2)
prefix_two=[]
prefix_two_df = pd.DataFrame()
prefix_of_two = get_prefixspan(1, item_of_two, prefix_two, prefix_two_df)
prefix_of_two.to_csv('prefix_of_two.csv',sep=',')


# In[9]:


# 2. 세 아이템의 조합
item_of_three = get_combination(NTM_df, 3)
prefix_three_tmp=[]
prefix_three_df = pd.DataFrame()
prefix_of_three = get_prefixspan(2, item_of_three, prefix_three_tmp, prefix_three_df)
prefix_of_three


# In[ ]:





# In[10]:


# 3. 네 아이템의 조합
item_of_four = get_combination(NTM_df, 4)
prefix_four_tmp=[]
prefix_four_df = pd.DataFrame()
prefix_of_four = get_prefixspan(3, item_of_four, prefix_four_tmp, prefix_four_df)


# In[11]:


# 4. 다섯 아이템의 조합
item_of_five = get_combination(NTM_df, 5)
prefix_five_tmp=[]
prefix_five_df = pd.DataFrame()
prefix_of_five = get_prefixspan(4, item_of_five, prefix_five_tmp, prefix_five_df)
prefix_of_five


# In[12]:


# 5. 여섯 아이템의 조합
item_of_six = get_combination(NTM_df, 6)
prefix_six_tmp=[]
prefix_six_df = pd.DataFrame()
prefix_of_six = get_prefixspan(5, item_of_six, prefix_six_tmp, prefix_six_df)
prefix_of_six
##################### NTM section End #####################


# In[13]:


##################### MTM section #####################
# Same goes for the MTM section

# In[375]:


MTM_df=df[df['ACCD_FIND_MTD_CODE']==2]
len(MTM_df)


# In[376]:


# Pick out it in order to get the asset, risk, intent, black IP out
RISK_V2_MTM=MTM_df['RISK_V2']

RISK_V2_FILTERED_MTM=RISK_V2_MTM.dropna()
print(RISK_V2_MTM.size)
print(RISK_V2_FILTERED_MTM.size)

risk_df_MTM = pd.DataFrame()
for newVal_MTM in RISK_V2_FILTERED_MTM:
    newVal_MTM = newVal_MTM.replace("'", "\"")
    newVal_MTM_str = json.loads(newVal_MTM)
    newVal_df_MTM = json_normalize(newVal_MTM_str) 
    risk_df_MTM = pd.concat([risk_df_MTM,newVal_df_MTM],ignore_index=True) 
    
risk_df_col_MTM = risk_df_MTM.columns.values.tolist()

# In[377]:


asset_val_MTM = []
intent_val_MTM=[]
source_val_MTM=[]

def filter_assets_value_MTM(risk):
    for i in range(len(risk)):
        risks=[]
        intents=[]
        sources=[]
        try:
            for key in risk_df_col:
                if 'ASSETS_VAL_' in key and risk.iloc[i][key]:
                    risk_key_desc = 'RISK_V2.' + key + '=' + get_asset_desc(key)
                    risks.append(risk_key_desc)
                if 'INTENT_VAL_' in key and risk.iloc[i][key]:
                    intent_key_desc = 'RISK_V2.' + key + '=' + get_intent_desc(key)
                    intents.append(intent_key_desc)
                if 'SOURCE_VAL_' in key and risk.iloc[i][key]:
                    source_key_desc='RISK_V2.' + key + '=' + get_source_desc(key)
                    sources.append(source_key_desc)
        except:
            print(risk)
            print(type(risk))
        finally:
            asset_val_MTM.append(risks)
            intent_val_MTM.append(intents)
            source_val_MTM.append(sources)

# In[378]:

# modified
def get_asset_desc_MTM(asset_field):
    if asset_field == 'ASSETS_VAL_1':
        return '공인-전체IP대역(유선)'
    elif asset_field == 'ASSETS_VAL_2':
        return '공인-전체IP대역(무선)'
    elif asset_field == 'ASSETS_VAL_3':
        return '공인-WEB서버'
    elif asset_field == 'ASSETS_VAL_4':
        return '공인-내부응용서버'
    elif asset_field == 'ASSETS_VAL_5':
        return '공인-DB서버'
    elif asset_field == 'ASSETS_VAL_6':
        return '공인-패치서버'
    elif asset_field == 'ASSETS_VAL_7':
        return '공인-네트워크'
    elif asset_field == 'ASSETS_VAL_8':
        return '공인-보안'
    elif asset_field == 'ASSETS_VAL_9':
        return '공인-업무용PC'
    elif asset_field == 'ASSETS_VAL_10':
        return '공인-비업무용PC'
    elif asset_field == 'ASSETS_VAL_11':
        return '공인-기타'
    elif asset_field == 'ASSETS_VAL_12':
        return '사설-전체IP대역(유선)'
    elif asset_field == 'ASSETS_VAL_13':
        return '사설-전체IP대역(무선)'
    elif asset_field == 'ASSETS_VAL_14':
        return '사설-WEB서버'
    elif asset_field == 'ASSETS_VAL_15':
        return '사설-내부응용서버'
    elif asset_field == 'ASSETS_VAL_16':
        return '사설-DB서버'
    elif asset_field == 'ASSETS_VAL_17':
        return '사설-패치서버'
    elif asset_field == 'ASSETS_VAL_18':
        return '사설-네트워크'
    elif asset_field == 'ASSETS_VAL_19':
        return '사설-보안'
    elif asset_field == 'ASSETS_VAL_20':
        return '사설-업무용PC'
    elif asset_field == 'ASSETS_VAL_21':
        return '사설-비업무용PC'
    elif asset_field == 'ASSETS_VAL_22':
        return '사설-기타'
    else:
        return ''


# In[381]:


# modified
def filter_intent_MTM(intent):
    intents=[]
    for intent_key in intent:
        if 'INTENT_VAL_' in intent_key and intent[intent_key]:
            intent_key_desc = 'RISK_V2.' + intent_key + '=' + get_intent_desc(intent_key)
            intents.append(intent_key_desc)
    return intents


# In[382]:


def get_intent_desc_MTM(intent_field):
    if intent_field == 'INTENT_VAL_1':
        return '파괴'
    elif intent_field == 'INTENT_VAL_2':
        return '유출'
    elif intent_field == 'INTENT_VAL_3':
        return '지연'
    elif intent_field == 'INTENT_VAL_4':
        return '잠복'
    elif intent_field == 'INTENT_VAL_5':
        return '단순침입'
    elif intent_field == 'INTENT_VAL_6':
        return 'MD5'
    elif intent_field == 'INTENT_VAL_0':
        return 'Default'
    else:
        return ''



# In[384]:


# modified
def filter_source_MTM(source):
    sources=[]
    for source_key in source:
        if 'SOURCE_VAL_' in source_key and source[source_key]:
            source_key_desc='RISK_V2.' + source_key + '=' + get_source_desc(source_key)
            sources.append(source_key_desc)
    return sources


# In[385]:


def get_source_desc_MTM(source_field):
    if source_field=='SOURCE_VAL_1':
        return '북한IP'
    if source_field=='SOURCE_VAL_3':
        return 'ECSC Black IP'
    else:
        return ''


# In[386]:

filter_assets_value(risk_df_MTM)
#뒤에 isna()를 통해 na값을 0으로 바꿔주는 작업을 하므로, 값이 비어있는 경우 [] 대신 비워두기
# New assets column
MTM_df['ASSETS_VAL']= asset_val_MTM
MTM_df['ASSETS_VAL']=MTM_df['ASSETS_VAL'].astype(str)
MTM_df['ASSETS_VAL']=MTM_df['ASSETS_VAL'].str.replace('[','', regex=False)
MTM_df['ASSETS_VAL']=MTM_df['ASSETS_VAL'].str.replace(']','', regex=False)
MTM_df[:1]
# New column of intent value
MTM_df['INTENT_VAL']=intent_val_MTM
MTM_df['INTENT_VAL']=MTM_df['INTENT_VAL'].astype(str)
MTM_df['INTENT_VAL']=MTM_df['INTENT_VAL'].str.replace('[','',regex=False)
MTM_df['INTENT_VAL']=MTM_df['INTENT_VAL'].str.replace(']','',regex=False)
MTM_df[:1]
# New column of SOURCE_VAL value
MTM_df['SOURCE_VAL']=source_val_NTN
MTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].astype(str)
MTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].str.replace('[','',regex=False)
MTM_df['SOURCE_VAL']=NTM_df['SOURCE_VAL'].str.replace(']','',regex=False)
MTM_df[:5]

# In[361]:
MTM_df.drop(columns=['RISK_V2'], inplace=True)
MTM_df.columns


# In[388]:


MTM_df.isna().sum()


# In[389]:


# Change the Nan to zero
MTM_df['ACCD_DMG_PROTO_NM']=MTM_df['ACCD_DMG_PROTO_NM'].replace(np.nan,'')
MTM_df['INST_NM']=MTM_df['INST_NM'].replace(np.nan,'')
MTM_df['DRULE_ATT_TYPE_CODE1']=MTM_df['DRULE_ATT_TYPE_CODE1'].replace(np.nan,'')
MTM_df['TW_ATT_IP']=MTM_df['TW_ATT_IP'].replace(np.nan,0)
MTM_df['TW_ATT_PORT']=MTM_df['TW_ATT_PORT'].replace(np.nan,0)
MTM_df['TW_DMG_IP']=MTM_df['TW_DMG_IP'].replace(np.nan,0)
MTM_df['TW_DMG_PORT']=MTM_df['TW_DMG_PORT'].replace(np.nan,0)
MTM_df['TW_ATT_CT_NM']=MTM_df['TW_ATT_CT_NM'].replace(np.nan,'')
MTM_df['ASSETS_VAL']=MTM_df['ASSETS_VAL'].replace(np.nan,0)
MTM_df['INTENT_VAL']=MTM_df['INTENT_VAL'].replace(np.nan,0)
MTM_df['SOURCE_VAL']=MTM_df['SOURCE_VAL'].replace(np.nan,0)
MTM_df['DRULE_NM']=MTM_df['DRULE_NM'].replace(np.nan,'')


# In[390]:


# Check NaN out again
MTM_df.isna().sum()


# In[391]:

# ACCD_FIND_MTD_CODE col 지우기
MTM_df.drop(columns=['ACCD_FIND_MTD_CODE'], inplace=True)

# arr를 매개변수로 받아 n개의 아이템의 조합 반환
def get_combination_MTM(arr, n):
    combination_n = list(itertools.combinations(arr.columns.tolist(),n))
    com_list=[]
    # row i 의 (1,2),(1,3)... 이런식으로 하니까 시간 너무 오래걸림
    # (1,2) 조합에 대한 row i, row i+1, row i+2... 이렇게 바꿈
    for m in range(len(combination_n[n-2])):
        for i in range(len(arr)):
            tmp_list=[]
            temp_df = arr.iloc[i]
            for col in combination_n[m]:
                tmp_list.append(temp_df[col])
            com_list.append(tmp_list)
    return com_list

def get_prefixspan_MTM(n, load_list, save_list, save_df):
    save_list = PrefixSpan(load_list)
    #n개 아이템 조합으로 이루어졌는데 n보다 작은 갯수의 아이템으로 이루어진 prefixspan 결과 값 나옴 
    # 방지하기 위해 prefixspan의 결과값에는 'n개의 아이템의 값'이 다 들어가도록 filter 설정
    save_list = save_list.frequent(1,filter = lambda patt, matches:len(patt)>n)
    save_df = pd.DataFrame(save_list)
    save_df.rename(columns={0:'Frequency',1:'Cause'},inplace=True)
    save_df = save_df.sort_values(by=['Frequency'],ascending=False,ignore_index=True)
    save_df = get_effect(save_df)
    return save_df

def get_effect_MTM(edit_df):
    #Make the new column for filling the Effect
    edit_df['Effect']=np.nan
     #Change the order of columns
    edit_df=edit_df[['Cause','Effect','Frequency']]
    for i in range(len(edit_df)):
        drules=['Attack','DDOS','HACK','MAIL','Malwr','WEB']
        loc_value = edit_df.loc[i]
        for item in loc_value['Cause']:
            for drule in drules:
                if item == drule:
                    edit_df.loc[i,'Effect'] = item
    return edit_df

# 1. 두 아이템의 조합
item_of_two_MTM = get_combination(MTM_df,2)
prefix_two_MTM=[]
prefix_two_df_MTM = pd.DataFrame()
prefix_of_two_MTM = get_prefixspan(1, item_of_two_MTM, prefix_two_MTM, prefix_two_d_MTMf)
prefix_of_two_MTM

# 2. 세 아이템의 조합
item_of_three_MTM = get_combination(MTM_df, 3)
prefix_three_tmp_MTM=[]
prefix_three_df_MTM = pd.DataFrame()
prefix_of_three_MTM = get_prefixspan(2, item_of_three_MTM, prefix_three_tmp_MTM, prefix_three_df_MTM)
prefix_of_three_MTM

# 3. 네 아이템의 조합
item_of_four_MTM = get_combination(MTM_df, 4)
prefix_four_tmp_MTM=[]
prefix_four_df_MTM = pd.DataFrame()
prefix_of_four_MTM = get_prefixspan(3, item_of_four_MTM, prefix_four_tmp_MTM, prefix_four_df_MTM)

# 4. 다섯 아이템의 조합
item_of_five_MTM = get_combination(MTM_df, 5)
prefix_five_tmp_MTM=[]
prefix_five_df_MTM = pd.DataFrame()
prefix_of_five_MTM = get_prefixspan(4, item_of_five_MTM, prefix_five_tmp_MTM, prefix_five_df_MTM)
prefix_of_five_MTM

# 5. 여섯 아이템의 조합
item_of_six_MTM = get_combination(MTM_df, 6)
prefix_six_tmp_MTM=[]
prefix_six_df_MTM = pd.DataFrame()
prefix_of_six_MTM = get_prefixspan(5, item_of_six_MTM, prefix_six_tmp_MTM, prefix_six_df_MTM)
prefix_of_six_MTM

##################### MTM section End #####################


# In[ ]:





# In[ ]: