diff options
Diffstat (limited to 'python/index_data.py')
| -rw-r--r-- | python/index_data.py | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/python/index_data.py b/python/index_data.py index f04d7d4a..62cffeb2 100644 --- a/python/index_data.py +++ b/python/index_data.py @@ -1,5 +1,12 @@ from db import dbengine, dbconn from dates import bond_cal +import numpy as np + +from analytics.utils import roll_date, previous_twentieth +from pandas.tseries.offsets import BDay +from pyisda.curve import SpreadCurve, fill_curve +from multiprocessing import Pool +from yieldcurve import get_curve import datetime import pandas as pd @@ -119,3 +126,46 @@ def index_returns(df=None, index=None, series=None, tenor=None, from_date=None, groupby(level=['index', 'series', 'tenor'])['price_return']. transform(add_accrued)) return df + +def get_singlenames_quotes(indexname, date): + conn = dbconn('serenitasdb') + with conn.cursor() as c: + c.execute("SELECT * FROM curve_quotes(%s, %s)", vars=(indexname, date)) + return [r for r in c] + +def build_curve(r, today_date, yc, start_date, step_in_date, value_date, end_dates): + spread_curve = 1e-4 * np.array(r['spread_curve'][1:], dtype='float') + upfront_curve = 1e-2 * np.array(r['upfront_curve'][1:], dtype='float') + recovery_curve = np.array(r['recovery_curve'][1:], dtype='float') + try: + sc = SpreadCurve(today_date, yc, start_date, step_in_date, value_date, + end_dates, spread_curve, upfront_curve, recovery_curve, + ticker=r['cds_ticker']) + if len(sc) != end_dates.shape[0]: + sc = fill_curve(sc, end_dates) + except ValueError as e: + print(r[0], e) + return None + return sc + +def build_curves(quotes, args): + return [build_curve(q, *args) for q in quotes if q is not None] + +def build_curves_dist(quotes, args, workers=4): + ## about twice as fast as the non distributed version + ## non thread safe for some reason so need ProcessPool + with Pool(workers) as pool: + r = pool.starmap(build_curve, [(q, *args) for q in quotes], 30) + return r + +def get_singlenames_curves(index_type, series, trade_date): + end_dates = roll_date(trade_date, [1, 2, 3, 4, 5, 7, 10], nd_array=True) + sn_quotes = get_singlenames_quotes("{}{}".format(index_type.lower(), series), + trade_date.date()) + jp_yc = get_curve(trade_date) + start_date = previous_twentieth(trade_date) + step_in_date = trade_date + datetime.timedelta(days=1) + value_date = pd.Timestamp(trade_date) + 3* BDay() + args = (trade_date, jp_yc, start_date, step_in_date, value_date, end_dates) + curves = build_curves_dist(sn_quotes, args) + return curves, args |