DAG: nd201907_survey

schedule: 55 4,10,16,22 * * *


nd201907_survey

Toggle wrap
  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
try:

    from datetime import timedelta
    from airflow import DAG
    
    from airflow.operators.python_operator import PythonOperator
    from airflow.operators.http_operator import SimpleHttpOperator
    from datetime import datetime
    from pandas.io.json import json_normalize
    from airflow.operators.postgres_operator import PostgresOperator

    import pandas as pd
    import json
    import requests
    import numpy as np

    import psycopg2
    from sqlalchemy import create_engine
    #print("All Dag moudules are sucessfully imported")

except Exception as e:
    print("Error {} ".format(e))

dRoW_api_end_url = "https://uat2.drow.cloud"

def getDrowToken(**context):
    # response = SimpleHttpOperator(
    #     task_id="getDrowToken",
    #     http_conn_id="getDrowToken",
    #     endpoint="https://uat2.drow.cloud/api/auth/authenticate", 
    #     method="POST",
    #     data={
    #     "username": "icwp2@drow.cloud",
    #     "password": "dGVzdDAxQHRlc3QuY29t"
    #     },
    #     xcom_push=True,
    # )

    response = requests.post(
    url=f"{dRoW_api_end_url}/api/auth/authenticate",
    data={
    "username": "icwp2@drow.cloud",
    "password": "dGVzdDAxQHRlc3QuY29t"
    }
    ).json()
    context["ti"].xcom_push(key="token", value=response['token'])
    # return 'DLLM{}'.format(response)
    
def letter_to_number(input_string):
    # Check if the input format is correct
    if len(input_string) == 2 and input_string[0] == '-' and input_string[1].isalpha():
        # Remove the dash and convert the letter to uppercase
        letter = input_string[1].upper()
        # Calculate the position in the alphabet (A=1, B=2, ..., Z=26)
        return ord(letter) - ord('A') + 2
    else:
        # Return 0 if the format is not correct
        return 1


def getMongoDB(**context):
    token = context.get("ti").xcom_pull(key="token")
    response = requests.get(
    url=f"{dRoW_api_end_url}/api/module/nd201907/document-data?from=1665845580212&documentId=5fbe2095b52b8f7ffa7b5ff4",
    headers={
    "x-access-token": f"Bearer {token}",
    "ICWPxAccessKey": "nd@201907ICWP_[1AG:4UdI){n=b~"
    }
    )
    #print('got_data')
    RISC_Data = json.loads(response.text)
    Mapping= {"A10 - Request Submission Date Time" : "a10_request_submission_date_time", 
    "B01 - Request Received Date Time" : "b01_request_received_date_time",
    "A05 - Proposed Survey Check Date Time" : "a05_proposed_inspection_or_survey_date_time",
    'C02 - Survey Checked on Date Time' : 'c02_inspect_or_survey_on_date_time',
    "E01 - Received on behalf of Contractor on Date Time" : "e01_received_on_behalf_of_contractor_on_date_time",
    'A01a - Request No. Revision': "a01a_request_no_revision",
    "A01 - Request No.": "a01_request_no",
    "C12 Time Pass to Senior or Contractor" : 'c12_time_pass_to_senior_or_contractor',
    "D01 - Countersigned on Date Time" : 'd01_countersigned_on_date_time',
    'C03 - Approval given?' : "c03_approval_given",
    "A01b - Work Category" : "a01b_work_category",
    "A03 - Location of Work": "a03_location_of_work"
    }
    #print('start transform')
    host                  = 'drowdatewarehouse.crlwwhgepgi7.ap-east-1.rds.amazonaws.com'  

        # User name of the database server
    dbUserName            = 'dRowAdmin'  

    # Password for the database user
    dbUserPassword        = 'drowsuper'  

    # Name of the database 
    database              = 'drowDateWareHouse'

    # Character set
    charSet               = "utf8mb4"  

    port                  = "5432"

    # #cursor Type
    # cusrsorType            = pymysql.cursors.DictCursor



    #create_engine('mysql+mysqldb://root:password@localhost:3306/mydbname', echo = False)
    conn_string = ('postgres://' +
                           dbUserName + ':' + 
                           dbUserPassword +
                           '@' + host + ':' + port +
                           '/' + database)

    # df = context.get("ti").xcom_pull(key="InsertData")
    # print(df)
    # conn_string = 'postgres://user:password@host/data1'
    
    db = create_engine(conn_string)
    conn = db.connect()
    #print('db connected')
    with conn as conn:
        df = pd.DataFrame()
        for x in RISC_Data:
            #print(x)
            df_nested_list = json_normalize(x['data'])
            #print('process 1')
            df2 = df_nested_list.reindex(columns=Mapping.keys())
            df2["request_no"] = df2["A01 - Request No."].astype(str) + df2["A01a - Request No. Revision"]

            # if(not df2["C02 - Survey Checked on Date Time"].isnull().bool() and not df2["A10 - Request Submission Date Time"].isnull().bool() and ((df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]') < df2["A10 - Request Submission Date Time"].astype('datetime64[ns]')).bool())):
            #     #print((df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]') < df2["A10 - Request Submission Date Time"].astype('datetime64[ns]')))
            # else:
            #     #print((df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]') < df2["A10 - Request Submission Date Time"].astype('datetime64[ns]')))

            if (not df2["C02 - Survey Checked on Date Time"].isnull().bool() and (not df2["A10 - Request Submission Date Time"].isnull().bool()) and (df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]') < df2["A10 - Request Submission Date Time"].astype('datetime64[ns]')).bool()):
                df2['nc_report'] = True
            else:
                df2['nc_report'] = False

            if (not df2["C02 - Survey Checked on Date Time"].isnull().bool() and not df2["A10 - Request Submission Date Time"].isnull().bool() and (((df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]') - df2["A10 - Request Submission Date Time"].astype('datetime64[ns]'))) < pd.Timedelta(24, unit='h')).bool()):
                df2['urgent_report'] = True
            else:
                df2['urgent_report'] = False

            if (not df2['E01 - Received on behalf of Contractor on Date Time'].isnull().bool() and not df2['A10 - Request Submission Date Time'].isnull().bool()):
                df2['elapsed_time'] = (((df2['E01 - Received on behalf of Contractor on Date Time'].astype('datetime64[ns]') - 
                df2['A10 - Request Submission Date Time'].astype('datetime64[ns]'))/ np.timedelta64(1, 'h'))/24).round(2)
                if df2['elapsed_time'].isnull().bool() or df2['elapsed_time'].lt(0).bool():
                    df2['elapsed_time'] = 0
            else:
                df2['elapsed_time'] = 0
            
            if (not df2["C02 - Survey Checked on Date Time"].isnull().bool() and not df2["D01 - Countersigned on Date Time"].isnull().bool() and (((df2["D01 - Countersigned on Date Time"].astype('datetime64[ns]') - df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]')))>= pd.Timedelta(24, unit='h')).bool()):
                df2['overdue_report'] = True
            else:
                df2['overdue_report'] = False
            
            if (not df2["C02 - Survey Checked on Date Time"].isnull().bool() and not df2["C12 Time Pass to Senior or Contractor"].isnull().bool() and (((df2["C12 Time Pass to Senior or Contractor"].astype('datetime64[ns]') - df2["C02 - Survey Checked on Date Time"].astype('datetime64[ns]')))>= pd.Timedelta(24, unit='h')).bool()):
                df2['delayed_approval_report'] = True
            else:
                df2['delayed_approval_report'] = False

            if ((df2['A01a - Request No. Revision']=="-A").bool()):
                df2['fail_in_first_inspection'] = True
            else:
                df2['fail_in_first_inspection'] = False
                
            if not((df2['A01a - Request No. Revision']).isnull().all()):
                df2['no_of_rev'] = df2['A01a - Request No. Revision'].apply(letter_to_number)
            else:
                df2['no_of_rev'] = 1
            
            if (not df2["C12 Time Pass to Senior or Contractor"].isnull().bool() and not df2["C02 - Survey Checked on Date Time"].isnull().bool() and not df2["E01 - Received on behalf of Contractor on Date Time"].isnull().bool()):
                df2['complete_incomplete_outstanding_report'] = 'complete'
            elif ((df2["C12 Time Pass to Senior or Contractor"].isnull().bool() or df2["E01 - Received on behalf of Contractor on Date Time"].isnull().bool()) and not df2["C02 - Survey Checked on Date Time"].isnull().bool()):
                df2['complete_incomplete_outstanding_report'] = 'in-complete'
            elif ((not df2["C12 Time Pass to Senior or Contractor"].isnull().bool() or df2["E01 - Received on behalf of Contractor on Date Time"].isnull().bool()) and df2["C02 - Survey Checked on Date Time"].isnull().bool()):
                df2['complete_incomplete_outstanding_report'] = 'outstanding'
            else:
                df2['complete_incomplete_outstanding_report'] = 'outstanding'
            

            #print('process 2')
            df2.rename(columns=Mapping, inplace=True)
            # df2.to_sql('table_temp', engine, if_exists='replace')
            # context["ti"].xcom_push(key="InsertData", value=df2)
            #print('loading into DB')
            # our dataframe
            # data = {'Name': ['Tom', 'dick', 'harry'],
            #         'Age': [22, 21, 24]}

            # # Create DataFrame
            # df = pd.DataFrame(data)
            # conn = psycopg2.connect(conn_string
            #                         )
            # conn.autocommit = True
            # cursor = conn.cursor()
            df = df.append(df2)
        df.to_sql('nd201907_risc', con=conn, if_exists='append', index= False)
    
    # sql1 = '''select * from ND201907_RISC_Data;'''
    # cursor.execute(sql1)
    # for i in cursor.fetchall():
    #     print(1,i)
    
    # conn.commit()
    # conn.close()
    print("success")

    # context["ti"].xcom_push(key="dataResponse", value=response.text)

# def reformData(**context):
    # dataResponse = context.get("ti").xcom_pull(key="dataResponse")
    # RISC_Data = json.loads(dataResponse)
    # Mapping= {"A10 - Request Submission Date Time" : "a10_request_submission_date_time", 
    # 'C02 - Survey Checked on Date Time' : 'c02_inspect_on_date_time',
    # # 'C02 - Survey Checked on Date Time' : 'Inspection/Survey Inspection date',
    # "E01 - Received on behalf of Contractor on Date Time" : "e01_received_on_behalf_of_contractor_on_date_time",
    # 'A01a - Request No. Revision': "a01a_request_no_revision",
    # "A01 - Request No.": "a01_request_no",
    # "C12 Time Pass to Senior or Contractor" : 'c12_time_pass_to_senior_or_contractor',
    # "D01 - Countersigned on Date Time" : 'd01_countersigned_on_date_time',
    # 'C03 - Approval given?' : "c03_approval_given",
    # "A01b - Work Category" : "a01b_work_category"
    # # 'C12 Time Pass to Senior or Contractor' : 'Sign time by manager'
    # }
    # # df = pd.DataFrame.from_dict([RISC_Data['data'],RISC_Data['data']])
    # # print(df)
    # df_nested_list = json_normalize(
    # RISC_Data['data']
    # )
    # print (df_nested_list)
    # df2 = df_nested_list.reindex(columns=Mapping.keys())
    # df2["request_no"] = df2["A01 - Request No."].astype(str) + df2["A01a - Request No. Revision"]
    # print (df2)
    # df2.rename(columns=Mapping, inplace=True)
    # # df2.to_sql('table_temp', engine, if_exists='replace')
    # context["ti"].xcom_push(key="InsertData", value=df2)
    # insert_data_sql_query = """

    # """
    # return "Done"

# def insertData(**context):

    # Create a connection object

    # Host of the MySQL database server (or ip)


# id SERIAL
create_table_sql_query = """ 
    CREATE TABLE IF NOT EXISTS nd201907_risc (
    a10_request_submission_date_time TIMESTAMP, 
    b01_request_received_date_time TIMESTAMP,
    c02_inspect_or_survey_on_date_time TIMESTAMP,
    a05_proposed_inspection_or_survey_date_time TIMESTAMP,
    e01_received_on_behalf_of_contractor_on_date_time TIMESTAMP,
    a01a_request_no_revision VARCHAR (50),
    a01_request_no VARCHAR (50),
    c12_time_pass_to_senior_or_contractor TIMESTAMP,
    d01_countersigned_on_date_time TIMESTAMP,
    c03_approval_given VARCHAR (50),
    request_no VARCHAR (50),
    a01b_work_category VARCHAR (50),
    nc_report BOOLEAN,
    urgent_report BOOLEAN,
    elapsed_time NUMERIC(10,2),
    overdue_report BOOLEAN,
    delayed_approval_report BOOLEAN,
    fail_in_first_inspection BOOLEAN,
    complete_incomplete_outstanding_report VARCHAR(50),
    a03_location_of_work VARCHAR(50),
    no_of_rev NUMERIC(3,0)
    );
    """

# create_table_sql_query = """ 
#     CREATE TABLE IF NOT EXISTS nd201907_risc (id INT NOT NULL, 
#     a10_request_submission_date_time TIMESTAMP, 
#     c02_inspect_on_date_time TIMESTAMP,
#     e01_received_on_behalf_of_contractor_on_date_time TIMESTAMP,
#     a01a_request_no_revision VARCHAR (50),
#     a01_request_no VARCHAR (50),
#     c12_time_pass_to_senior_or_contractor TIMESTAMP,
#     d01_countersigned_on_date_time TIMESTAMP,
#     c03_approval_given VARCHAR (50),
#     request_no VARCHAR (50),
#     a01b_work_category VARCHAR (50)
#     );
#     """

# */2 * * * * Execute every two minute 
with DAG(
        dag_id="nd201907_survey",
        schedule_interval="55 4,10,16,22 * * *",
        default_args={
            "owner": "airflow",
            "retries": 1,
            "retry_delay": timedelta(minutes=5),
            "start_date": datetime(2023, 1, 17)
        },
        catchup=False) as f:
    
    getMongoDB = PythonOperator(
        task_id="getMongoDB",
        python_callable=getMongoDB,
        op_kwargs={"name": "Dylan"},
        provide_context=True,
    )

    # reformData = PythonOperator(
    #     task_id="reformData",
    #     python_callable=reformData,
    #     provide_context=True,
    #     # op_kwargs={"name": "Dylan"}
    # )

    getDrowToken = PythonOperator(
        task_id="getDrowToken",
        python_callable=getDrowToken,
        provide_context=True,
        # op_kwargs={"name": "Dylan"}
    )

    # insertData = PythonOperator(
    #     task_id="insetDateToPG",
    #     python_callable=insertData,
    #     provide_context=True,
    #     # op_kwargs={"name": "Dylan"}
    # )

    create_table = PostgresOperator(
        sql = create_table_sql_query,
        task_id = "create_table_task",
        postgres_conn_id = "postgres_rds",
    )

    # insert_data = PostgresOperator(
    #     sql = insert_data_sql_query,
    #     task_id = "insertData_sql_query_task",
    #     postgres_conn_id = "postgres_rds",
    # )



# getDrowToken >> getMongoDB >> reformData >> create_table
# create_table >> getDrowToken >> getMongoDB >> reformData >> insertData
# getDrowToken >> getMongoDB >> reformData >> insertData
create_table >> getDrowToken >> getMongoDB