diff options
Diffstat (limited to 'python/parse_emails.py')
| -rw-r--r-- | python/parse_emails.py | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/python/parse_emails.py b/python/parse_emails.py index 7b58a856..997681a5 100644 --- a/python/parse_emails.py +++ b/python/parse_emails.py @@ -140,7 +140,7 @@ def parse_ms(fh, indextype): return option_stack subject_BAML = re.compile("(?:Fwd:){0,2}(?:BAML )?(\w{2})([0-9]{1,2})\s") -subject_MS = re.compile("\$\$ MS CDX OPTIONS: (IG|HY)(\d{2})[^\d]*(\d.(?:\.\d*)?)") +subject_MS = re.compile("\$\$ MS CDX OPTIONS: (IG|HY)(\d{2})[^\d]*(\d+(?:\.\d*)?)") def parse_email(email_path): with email_path.open("rt") as fh: @@ -156,7 +156,7 @@ def parse_email(email_path): if m: indextype, series, ref = m.groups() series = int(series) - ref = float(series) + ref = float(ref) quotedate = parse_quotedate(fh, date_received) option_stack = parse_ms(fh, indextype) fwd_index = pd.DataFrame({'quotedate': quotedate, @@ -186,9 +186,11 @@ if __name__=="__main__": emails = [f for f in Path("../../data/swaptions").iterdir() if f.is_file()] swaption_stack = {} index_data = pd.DataFrame() - with open(".pickle", "rb") as fh: - already_uploaded = pickle.load(fh) - #already_uploaded = set() + try: + with open(".pickle", "rb") as fh: + already_uploaded = pickle.load(fh) + except FileNotFoundError: + already_uploaded = set() for f in emails: if f.name in already_uploaded: continue |