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 | def getMongoDB(**context):
token = context.get("ti").xcom_pull(key="token")
# response_s01 = requests.get(
# url=f"{dRoW_api_end_url}/api/module/document-export/airflow/workflow/6597889461a8f490bf96667f?export_type=0",
# headers={
# "x-access-token": f"Bearer {token}",
# "ICWPxAccessKey": "nd@201907ICWP_[1AG:4UdI){n=b~"
# }
# )
response_s02 = requests.get(
url=f"{dRoW_api_end_url}/api/module/document-export/airflow/workflow/67340443f327df1969f416a1?export_type=0",
headers={
"x-access-token": f"Bearer {token}",
"ICWPxAccessKey": "nd@201907ICWP_[1AG:4UdI){n=b~"
}
)
# RISC_Data_01 = json.loads(response_s01.text)
RISC_Data_01 = None
RISC_Data_02 = json.loads(response_s02.text)
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
conn_string = ('postgres://' +
dbUserName + ':' +
dbUserPassword +
'@' + host + ':' + port +
'/' + database)
db = create_engine(conn_string)
conn = db.connect()
full_df = pd.DataFrame()
monthly_summary = {}
with conn:
if RISC_Data_01 is not None:
for entry in RISC_Data_01:
df_nested_list = json_normalize(entry['data'])
# List to hold object for each table
df_list = []
# Get total number of tables
total_tables = len([key for key, val in df_nested_list.items() if 'Table' in key])
# Inspection date
date_of_inspection = df_nested_list['Date of Inspection'][0]
if (date_of_inspection == None):
continue
# Contract title
contract_title = df_nested_list['Contract Title'][0]
# Process each table dynamically
for i in range(1, total_tables):
table_key = f"Table {i}"
if table_key not in df_nested_list:
continue
df_table = df_nested_list[table_key]
for record in df_table[0]:
item_no = list(record.values())[0].split(" ")[0]
group_key = list(record.keys())[0]
dict_record = {
'Date of Inspection': date_of_inspection,
'Month': date_of_inspection[:7],
'Contract Title': contract_title,
'Group No.': str(i),
'Group': group_key,
'Item No.': item_no,
'Description': record[group_key].replace(f"{item_no} ", ""),
'Template': 'S01_Daily Site Safety Inspection Checklist',
}
record.pop(list(record.keys())[0])
for k, v in record.items():
dict_record[k.replace(f'{i}. ', "")] = v
if 'Date completed' not in dict_record or 'Agreed date for completion' not in dict_record:
dict_record['On Time'] = None
elif not dict_record['Date completed'] or not dict_record['Agreed date for completion']:
dict_record['On Time'] = None
elif dict_record['Date completed'] <= dict_record['Agreed date for completion']:
dict_record['On Time'] = "On-Time"
else:
dict_record['On Time'] = "Late"
df_list.append(dict_record)
if date_of_inspection[:7] in monthly_summary:
monthly_summary[date_of_inspection[:7]]['items'] += 1
if dict_record['Safety Compliance'] == 'No':
monthly_summary[date_of_inspection[:7]]['concern'] += 1
else:
monthly_summary[date_of_inspection[:7]] = {
'items': 1,
'concern': 1 if dict_record['Safety Compliance'] == 'No' else 0
}
df_combined = pd.DataFrame(data=df_list)
# Append non-compliant records
if not full_df.empty and not df_combined.empty:
full_df = pd.concat([full_df, df_combined], ignore_index=True)
elif not df_combined.empty:
full_df = df_combined
if RISC_Data_02 is not None:
# weekly safety inspection
Mapping = {
"A2 Date Time of Inspection" : "Date of Inspection",
}
for entry in RISC_Data_02:
df_nested_list = json_normalize(entry['data'])
df_nested_list.rename(columns=Mapping, inplace=True)
# Mo remark: progress stopped here on 26 Feb 2026
# List to hold object for each table
df_list = []
# Get total number of tables
# total_tables = len([key for key, val in df_nested_list.items() if 'Table' in key])
# Inspection date
date_of_inspection = df_nested_list['Date of Inspection'][0]
if (date_of_inspection == None):
continue
# Contract title
# contract_title = df_nested_list['Contract Title'][0]
contract_title = 'Central Kowloon Route – Remaining Works'
# Process each table dynamically
# for i in range(1, total_tables):
# table_key = f"Table {i}"
# if table_key not in df_nested_list:
# continue
# df_table = df_nested_list[table_key]
# for record in df_table[0]:
# item_no = list(record.values())[0].split(" ")[0]
# group_key = list(record.keys())[0]
# dict_record = {
# 'Date of Inspection': date_of_inspection,
# 'Month': date_of_inspection[:7],
# 'Contract Title': contract_title,
# 'Group No.': str(i),
# 'Group': group_key,
# 'Item No.': item_no,
# 'Description': record[group_key].replace(f"{item_no} ", ""),
# 'Template': 'S02_Weekly Site Safety Inspection Checklist',
# }
# record.pop(list(record.keys())[0])
# for k, v in record.items():
# dict_record[k.replace(f'{i}. ', "")] = v
# if 'Date completed' not in dict_record or 'Agreed date for completion' not in dict_record:
# dict_record['On Time'] = None
# elif not dict_record['Date completed'] or not dict_record['Agreed date for completion']:
# dict_record['On Time'] = None
# elif dict_record['Date completed'] <= dict_record['Agreed date for completion']:
# dict_record['On Time'] = "On-Time"
# else:
# dict_record['On Time'] = "Late"
# df_list.append(dict_record)
# if date_of_inspection[:7] in monthly_summary:
# monthly_summary[date_of_inspection[:7]]['items'] += 1
# if dict_record['Safety Compliance'] == 'No':
# monthly_summary[date_of_inspection[:7]]['concern'] += 1
# else:
# monthly_summary[date_of_inspection[:7]] = {
# 'items': 1,
# 'concern': 1 if dict_record['Safety Compliance'] == 'No' else 0
# }
for field_name, value in df_nested_list.items():
if field_name == 'Follow-up Summary':
for sub_row in value[0]:
item_number = sub_row['Items'].split(" ")[0]
item_description = sub_row['Items'].replace(f"{item_number} ","")
dict_record = {
'Date of Inspection': date_of_inspection,
'Month': date_of_inspection[:7],
'Contract Title': contract_title,
'Group No.': None,
'Group': None,
'Item No.': item_number,
'Description': item_description,
'Template': '3.1 Weekly Safety Inspection',
'Safety Compliance': 'No' if 'Date Completed' not in sub_row else 'Yes',
# 'Safety Compliance': 'Yes' if 'Date Completed' in sub_row and sub_row['Date Completed'] else 'No',
'Location': None if 'Location' not in sub_row else sub_row['Location'],
'Date completed': None if 'Date Completed' not in sub_row else sub_row['Date Completed'],
'Agreed date for completion': None if 'Agreed Due Date for Completion' not in sub_row else sub_row['Agreed Due Date for Completion']
}
# 'Safety Compliance': 'No' if 'Safety Compliance' not in sub_row else sub_row['Safety Compliance'],
if dict_record['Agreed date for completion'] is None or dict_record['Date completed'] is None:
dict_record['On Time'] = None
elif dict_record['Date completed'] <= dict_record['Agreed date for completion']:
dict_record['On Time'] = 'On-Time'
else:
dict_record['On Time'] = 'Late'
df_list.append(dict_record)
if date_of_inspection[:7] in monthly_summary:
monthly_summary[date_of_inspection[:7]]['items'] += 1
if dict_record['Safety Compliance'] == 'No':
monthly_summary[date_of_inspection[:7]]['concern'] += 1
else:
monthly_summary[date_of_inspection[:7]] = {
'items': 1,
'concern': 1 if dict_record['Safety Compliance'] == 'No' else 0
}
df_combined = pd.DataFrame(data=df_list)
# Append non-compliant records
if not full_df.empty and not df_combined.empty:
full_df = pd.concat([full_df, df_combined], ignore_index=True)
elif not df_combined.empty:
full_df = df_combined
# Sort by date of inspection
# non_compliant_df = full_df[full_df['Safety Compliance'] == 'No']
non_compliant_df = full_df
non_compliant_df.sort_values(by=['Date of Inspection', 'Contract Title', 'Item No.'], inplace=True)
# Clean up column names for SQL
non_compliant_df.columns = non_compliant_df.columns.str.replace(' ', '_').str.replace(r'[().%]', '', regex=True).str.replace('/', '_')
# Retrieve only relevant columns
# final_df = non_compliant_df[['Date_of_Inspection', 'Month', 'Contract_Title', 'Template', 'Group_No', 'Group', 'Item_No', 'Description', 'Location', 'Safety_Compliance', 'Date_completed', 'Agreed_date_for_completion', 'On_Time']]
final_df = non_compliant_df[['Date_of_Inspection', 'Month', 'Contract_Title', 'Template', 'Group_No', 'Group', 'Item_No', 'Description', 'Location', 'Safety_Compliance', 'Date_completed', 'Agreed_date_for_completion', 'On_Time']]
# Write to SQL database
# parse_columns(final_df)
final_df.to_sql('safety_inspection_hy202308', con=conn, if_exists='replace', index=False)
# Create a summary df
summary_dict = []
for k, v in monthly_summary.items():
summary_dict.append({
'Month': k,
'Items': v['items'],
'Concerns': v['concern']
})
summary_df = pd.DataFrame(data=summary_dict)
# parse_columns(summary_df)
summary_df.to_sql('safety_inspection_summary_hy202308', con=conn, if_exists='replace', index=False)
|