업데이트 'keris.ipynb/PrefixSpan_20210925.py'

keris.ipynb/PrefixSpan_20210925.py

@@ -4,28 +4,6 @@
 # In[1]:
 
 
-import os
-import array
-import math
-import pickle
-# import joblib
-import sys
-import argparse
-import pandas as pd
-import numpy as np
-import matplotlib.pyplot as plt
-from datetime import datetime
-from pprint import pprint
-import ssl
-from elasticsearch.connection import create_ssl_context
-from elasticsearch import Elasticsearch
-from elasticsearch import helpers
-import urllib3
-
-
-# In[3]:
-
-
 import pandas as pd
 import numpy as np
 from mlxtend.preprocessing import TransactionEncoder
@@ -33,103 +11,6 @@ from mlxtend.frequent_patterns import association_rules, fpgrowth
 from prefixspan import PrefixSpan
 
 
-# In[4]:
-
-
-ssl_context = create_ssl_context()
-ssl_context.check_hostname = False
-ssl_context.verify_mode = ssl.CERT_NONE
-
-
-# In[12]:
-
-
-es = Elasticsearch(hosts=[{'host': '223.194.92.152', 'port': 9200}], scheme="http",verify_certs=False, timeout=300, ssl_context=ssl_context, http_auth=("elasticsearch", "hadoop2019@!@#$"))
-urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-
-
-# In[347]:
-
-
-######## 2020, 1 year ########
-######## There are no MTM data in 2018, 2019 ########
-
-body = {
-         "size" : 10000,
-         "query": {
-                 "range":{
-                    "TW_COLLECT_DT":{
-                        "gte":"2020-01-01T00:00:00.625+09:00",
-                        "lte":"2020-12-31T00:00:00.625+09:00" ################
-                    }
-                }
-                 },
-    "sort":[{
-        "_id":"asc"
-    }]
-}
-        
-res = es.search(index = 'ts_data_accident-2020', body=body)
-data = res['hits']['hits']
-nxt=res["hit"]["hit"][-1]["sort"][0]
-total = res['hits']['total']
-
-# print(total)
-
-accident = []
-for da in data:
-    att_type = da['_source']
-    # att_type["POL_NM"]=att_type["SCEN_INFOS"][0]["POL_NM"]
-    accident.append(att_type)
-
-# df = pd.DataFrame(accident,dtype=str)
-df_10000 = pd.DataFrame(accident)
-
-print(df_10000.head())
-
-
-# In[ ]:
-
-
-######## 2020, 1 year ########
-######## There are no MTM data in 2018, 2019 ########
-
-body = {
-         "size" : 10000,
-         "search_after":[nxt],
-         "query": {
-                 "range":{
-                    "TW_COLLECT_DT":{
-                        "gte":"2020-01-01T00:00:00.625+09:00",
-                        "lte":"2020-12-31T00:00:00.625+09:00" ################
-                    }
-                }
-                 },
-    "sort":[{
-        "_id":"asc"
-    }]
-}
-        
-res = es.search(index = 'ts_data_accident-2020', body=body)
-data = res['hits']['hits']
-nxt=res["hit"]["hit"][-1]["sort"][0]
-total = res['hits']['total']
-
-# print(total)
-
-accident = []
-for da in data:
-    att_type = da['_source']
-    # att_type["POL_NM"]=att_type["SCEN_INFOS"][0]["POL_NM"]
-    accident.append(att_type)
-
-# df = pd.DataFrame(accident,dtype=str)
-df_20000 = pd.DataFrame(accident)
-
-print(df_20000.head())
-
-
-# In[348]:
 
 
 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()