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
|
import csv
import io
import os
import requests
import shutil
import zipfile
from pathlib import Path
from lxml import etree
from db import with_connection, dbengine
import pandas as pd
def request_payload(payload):
r = requests.post('https://www.markit.com/export.jsp', params=payload)
res = []
path = os.path.join(os.environ['BASE_DIR'], "Tranche_data", "RED_reports")
if 'Delta' in payload['report']:
path = os.path.join(path, "Deltas")
with zipfile.ZipFile(io.BytesIO(r.content)) as z:
for f in z.namelist():
if f.endswith("xml"):
z.extract(f, path=path)
res.append(f)
return res
def download_report(report):
version = 10 if 'Entity' in report else 9
payload = {'user': 'GuillaumeHorel',
'password': 'password',
'version': version,
'report': report}
if report in ['CredIndexAnnex', 'CredIndexAnnexSplit']:
for family in ['CDX', 'ITRAXX-EUROPE']:
payload.update({'family': family})
yield request_payload(payload)
else:
yield request_payload(payload)
@with_connection('serenitasdb')
def update_redcodes(conn, fname):
with open(os.path.join(os.environ['BASE_DIR'], "Tranche_data", "RED_reports", fname)) as fh:
et = etree.parse(fh)
data_version = []
data_maturity = []
for index in et.iter('index'):
temp = {c.tag: c.text for c in index if c.tag not in ['terms', 'paymentfrequency']}
data_version.append(temp)
for term in index.iter('term'):
d = {'redindexcode': temp['redindexcode']}
d.update({c.tag: c.text for c in term})
data_maturity.append(d)
df_maturity = pd.DataFrame(data_maturity)
df_version = pd.DataFrame(data_version)
df_version['activeversion'] = df_version['activeversion'].map({'Y': True, None: False})
df_maturity.tenor = df_maturity['tenor'].map(lambda s: s.lower() + 'r')
df_maturity.coupon = (pd.to_numeric(df_maturity.coupon) * 10000).astype(int)
serenitas_engine = dbengine('serenitasdb')
df_version.to_sql("index_version_markit", serenitas_engine, index=False, if_exists='append')
df_maturity.to_sql("index_maturity_markit", serenitas_engine, index=False, if_exists='append')
def update_redindices(fname):
basedir = Path(os.environ['BASE_DIR']) / "Tranche_data"
with open(basedir / "RED_reports" / fname) as fh:
e = etree.parse(fh)
root = e.getroot()
headers = ['referenceentity', 'redentitycode', 'role', 'redpaircode', 'jurisdiction',
'tier', 'pairiscurrent', 'pairvalidto', 'pairvalidfrom', 'ticker',
'ispreferred', 'isdatransactiontype', 'docclause', 'recorddate',
'publiccomments', 'weight']
for c in root.findall('index'):
names = [c.find(tag).text for tag in ['indexsubfamily', 'series', 'version']]
with open( basedir / "RED_indices" / "{0}.{1}.V{2}.csv".format(*names), "w") as fh2:
csvwriter = csv.DictWriter(fh2, fieldnames=headers)
csvwriter.writeheader()
data = []
for constituent in c.findall('.//originalconstituent'):
data.append({l.tag: l.text for l in constituent})
data = sorted(data, key=lambda x: x['referenceentity'])
csvwriter.writerows(data)
if __name__ == "__main__":
fname = next(download_report("REDIndexCodes"))
update_redcodes(fname[0])
# for f in download_report("CredIndexAnnex"):
# update_redindices(f[0])
# report_list = ['REDEntity', 'REDObligation', 'REDObligationPreferred']
# for report in report_list:
# download_report(report)
# report_list = ['REDEntityDelta', 'REDObligationDelta']
# for report in report_list:
# fname = download_report(report)
|
