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
|
import pandas as pd
import pdb
import re
import os
import pdb
os.chdir("quotes")
for f in os.listdir("."):
with open(os.path.abspath(f), "rb") as fh:
flag = False
masterdf = {}
for line in fh:
line = line.decode('utf-8', 'ignore')
line = line.rstrip()
m = re.search("(IG|HY)24 5y SWAPTION UPDATE - Ref\D+(.+)$", line)
if m:
indextype = m.groups()[0]
if indextype=='HY':
refprice, refspread = map(float,
re.match("([\S]+)\s+\(([^)]+)\)", m.groups()[1]).groups())
else:
refspread = float(m.groups()[1])
continue
if line.startswith("At"):
quotedate = pd.to_datetime(line[4:])
continue
if line.startswith("Expiry"):
m = re.match("Expiry (\d{2}\w{3}\d{2}) \((?:([\S]+) )?([\S]+)\)", line)
if m:
date, fwprice, fwspread = m.groups()
date = pd.datetime.strptime(date, '%d%b%y')
continue
if line.startswith("Stk"):
flag = True
r = []
continue
if flag:
if line:
vals = re.sub(" +", " ", line).split(" ")
if indextype=='HY':
vals.pop(2)
vals.pop(9)
else:
vals.pop(1)
vals.pop(8)
r.append(vals)
continue
else:
if indextype=='HY':
cols = ['Stk', 'Sprd', 'Pay', 'Delta', 'Rec', 'Vol',
'VolChg', 'VolBpd', 'Tail']
else:
cols = ['Stk', 'Pay', 'Delta', 'Rec', 'Vol',
'VolChg', 'VolBpd', 'Tail']
df = pd.DataFrame.from_records(r, columns = cols)
df['refspread'] = refspread
if indextype=='HY':
df['refprice'] = refprice
df[['PayBid', 'PayOffer']] = df.Pay.str.split('/', expand=True)
df[['RecBid', 'RecOffer']] = df.Rec.str.split('/', expand=True)
df.drop(['Pay', 'Rec'], axis=1, inplace=True)
df = df.convert_objects(convert_numeric=True)
df.set_index('Stk', inplace=True)
masterdf[date]=df
flag = False
r = []
continue
masterdf = pd.concat(masterdf)
pdb.set_trace()
|