def get_economic_event_ret_over_custom_event_day(self, data_frame_in, event_dates, name, event, start, end, lagged = False,
NYC_cutoff = 10):
time_series_filter = TimeSeriesFilter()
event_dates = time_series_filter.filter_time_series_by_date(start, end, event_dates)
data_frame = data_frame_in.copy(deep=True) # because we change the dates!
time_series_tz = TimeSeriesTimezone()
calendar = Calendar()
bday = CustomBusinessDay(weekmask='Mon Tue Wed Thu Fri')
event_dates_nyc = time_series_tz.convert_index_from_UTC_to_new_york_time(event_dates)
average_hour_nyc = numpy.average(event_dates_nyc.index.hour)
event_dates = calendar.floor_date(event_dates)
# realised is traditionally on later day eg. 3rd Jan realised ON is 2nd-3rd Jan realised
# so if Fed meeting is on 2nd Jan later, then we need realised labelled on 3rd (so minus a day)
# implied expires on next day eg. 3rd Jan implied ON is 3rd-4th Jan implied
# TODO smarter way of adjusting dates, as sometimes events can be before/after 10am NY cut
if (lagged and average_hour_nyc >= NYC_cutoff):
data_frame.index = data_frame.index - bday
elif (not lagged and average_hour_nyc < NYC_cutoff): # ie. implied
data_frame.index = data_frame.index + bday
# set as New York time and select only those ON vols at the 10am NY cut just before the event
data_frame_events = data_frame.ix[event_dates.index]
data_frame_events.columns = data_frame.columns.values + '-' + name + ' ' + event
return data_frame_events
def get_surprise_against_intraday_moves_over_event(
self,
data_frame_cross_orig,
cross,
event_fx,
event_name,
start,
end,
offset_list=[1, 5, 30, 60],
add_surprise=False,
surprise_field='survey-average'):
tsf = TimeSeriesFilter()
fields = [
'actual-release', 'survey-median', 'survey-average', 'survey-high',
'survey-low'
]
ef_time_frame = self.get_economic_event_date_time_fields(
fields, event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end,
ef_time_frame)
return self.get_surprise_against_intraday_moves_over_custom_event(
data_frame_cross_orig,
ef_time_frame,
cross,
event_fx,
event_name,
start,
end,
offset_list=offset_list,
add_surprise=add_surprise,
surprise_field=surprise_field)
def get_intraday_moves_over_event(self,
data_frame_rets,
cross,
event_fx,
event_name,
start,
end,
vol,
mins=3 * 60,
min_offset=0,
create_index=False,
resample=False,
freq='minutes'):
tsf = TimeSeriesFilter()
ef_time_frame = self.get_economic_event_date_time_dataframe(
event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end,
ef_time_frame)
return self.get_intraday_moves_over_custom_event(
data_frame_rets,
ef_time_frame,
vol,
mins=mins,
min_offset=min_offset,
create_index=create_index,
resample=resample,
freq=freq) #, start, end)
def compare_strategy_vs_benchmark(self, br, strategy_df, benchmark_df):
"""
compare_strategy_vs_benchmark - Compares the trading strategy we are backtesting against a benchmark
Parameters
----------
br : BacktestRequest
Parameters for backtest such as start and finish dates
strategy_df : pandas.DataFrame
Strategy time series
benchmark_df : pandas.DataFrame
Benchmark time series
"""
include_benchmark = False
calc_stats = False
if hasattr(br, 'include_benchmark'): include_benchmark = br.include_benchmark
if hasattr(br, 'calc_stats'): calc_stats = br.calc_stats
if include_benchmark:
tsd = TimeSeriesDesc()
cash_backtest = CashBacktest()
ts_filter = TimeSeriesFilter()
ts_calcs = TimeSeriesCalcs()
# align strategy time series with that of benchmark
strategy_df, benchmark_df = strategy_df.align(benchmark_df, join='left', axis = 0)
# if necessary apply vol target to benchmark (to make it comparable with strategy)
if hasattr(br, 'portfolio_vol_adjust'):
if br.portfolio_vol_adjust is True:
benchmark_df = cash_backtest.calculate_vol_adjusted_index_from_prices(benchmark_df, br = br)
# only calculate return statistics if this has been specified (note when different frequencies of data
# might underrepresent vol
if calc_stats:
benchmark_df = benchmark_df.fillna(method='ffill')
tsd.calculate_ret_stats_from_prices(benchmark_df, br.ann_factor)
benchmark_df.columns = tsd.summary()
# realign strategy & benchmark
strategy_benchmark_df = strategy_df.join(benchmark_df, how='inner')
strategy_benchmark_df = strategy_benchmark_df.fillna(method='ffill')
strategy_benchmark_df = ts_filter.filter_time_series_by_date(br.plot_start, br.finish_date, strategy_benchmark_df)
strategy_benchmark_df = ts_calcs.create_mult_index_from_prices(strategy_benchmark_df)
self._benchmark_pnl = benchmark_df
self._benchmark_tsd = tsd
return strategy_benchmark_df
return strategy_df
def get_intraday_moves_over_event(self, data_frame_rets, cross, event_fx, event_name, start, end, vol, mins = 3 * 60,
min_offset = 0, create_index = False, resample = False, freq = 'minutes'):
tsf = TimeSeriesFilter()
ef_time_frame = self.get_economic_event_date_time_dataframe(event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end, ef_time_frame)
return self.get_intraday_moves_over_custom_event(data_frame_rets, ef_time_frame,
vol, mins = mins, min_offset = min_offset,
create_index = create_index, resample = resample, freq = freq)#, start, end)
def get_surprise_against_intraday_moves_over_event(self, data_frame_cross_orig, cross, event_fx, event_name, start, end,
offset_list = [1, 5, 30, 60], add_surprise = False,
surprise_field = 'survey-average'):
tsf = TimeSeriesFilter()
fields = ['actual-release', 'survey-median', 'survey-average', 'survey-high', 'survey-low']
ef_time_frame = self.get_economic_event_date_time_fields(fields, event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end, ef_time_frame)
return self.get_surprise_against_intraday_moves_over_custom_event(data_frame_cross_orig, ef_time_frame, cross, event_fx, event_name, start, end,
offset_list = offset_list, add_surprise = add_surprise,
surprise_field = surprise_field)
def dump_indicators(self):
tsf = TimeSeriesFilter()
self.logger.info("About to write all indicators to CSV")
self.indicator.to_csv(self._csv_indicator_dump, date_format='%d/%m/%Y')
if (self._csv_econ_indicator_dump is not None):
self.logger.info("About to write economy based indicators to CSV")
self.indicator_econ.to_csv(self._csv_econ_indicator_dump, date_format='%d/%m/%Y')
self.logger.info("About to write final indicators to CSV")
# remove weekends and remove start of series
if (self._csv_final_indicator_dump is not None):
indicator_final_copy = tsf.filter_time_series_by_holidays(self.indicator_final, cal = 'WEEKDAY')
indicator_final_copy = tsf.filter_time_series_by_date(
start_date="01 Jan 2000", finish_date = None, data_frame=indicator_final_copy)
indicator_final_copy.to_csv(self._csv_final_indicator_dump, date_format='%d/%m/%Y')
def get_economic_event_ret_over_custom_event_day(self,
data_frame_in,
event_dates,
name,
event,
start,
end,
lagged=False,
NYC_cutoff=10):
time_series_filter = TimeSeriesFilter()
event_dates = time_series_filter.filter_time_series_by_date(
start, end, event_dates)
data_frame = data_frame_in.copy(
deep=True) # because we change the dates!
time_series_tz = TimeSeriesTimezone()
calendar = Calendar()
bday = CustomBusinessDay(weekmask='Mon Tue Wed Thu Fri')
event_dates_nyc = time_series_tz.convert_index_from_UTC_to_new_york_time(
event_dates)
average_hour_nyc = numpy.average(event_dates_nyc.index.hour)
event_dates = calendar.floor_date(event_dates)
# realised is traditionally on later day eg. 3rd Jan realised ON is 2nd-3rd Jan realised
# so if Fed meeting is on 2nd Jan later, then we need realised labelled on 3rd (so minus a day)
# implied expires on next day eg. 3rd Jan implied ON is 3rd-4th Jan implied
# TODO smarter way of adjusting dates, as sometimes events can be before/after 10am NY cut
if (lagged and average_hour_nyc >= NYC_cutoff):
data_frame.index = data_frame.index - bday
elif (not lagged and average_hour_nyc < NYC_cutoff): # ie. implied
data_frame.index = data_frame.index + bday
# set as New York time and select only those ON vols at the 10am NY cut just before the event
data_frame_events = data_frame.ix[event_dates.index]
data_frame_events.columns = data_frame.columns.values + '-' + name + ' ' + event
return data_frame_events
def dump_indicators(self):
tsf = TimeSeriesFilter()
self.logger.info("About to write all indicators to CSV")
self.indicator.to_csv(self._csv_indicator_dump, date_format='%d/%m/%Y')
if (self._csv_econ_indicator_dump is not None):
self.logger.info("About to write economy based indicators to CSV")
self.indicator_econ.to_csv(self._csv_econ_indicator_dump,
date_format='%d/%m/%Y')
self.logger.info("About to write final indicators to CSV")
# remove weekends and remove start of series
if (self._csv_final_indicator_dump is not None):
indicator_final_copy = tsf.filter_time_series_by_holidays(
self.indicator_final, cal='WEEKDAY')
indicator_final_copy = tsf.filter_time_series_by_date(
start_date="01 Jan 2000",
finish_date=None,
data_frame=indicator_final_copy)
indicator_final_copy.to_csv(self._csv_final_indicator_dump,
date_format='%d/%m/%Y')
def get_intraday_moves_over_custom_event(self, data_frame_rets, ef_time_frame, vol=False,
minute_start = 5, mins = 3 * 60, min_offset = 0 , create_index = False,
resample = False, freq = 'minutes'):
tsf = TimeSeriesFilter()
ef_time_frame = tsf.filter_time_series_by_date(data_frame_rets.index[0], data_frame_rets.index[-1], ef_time_frame)
ef_time = ef_time_frame.index
if freq == 'minutes':
ef_time_start = ef_time - timedelta(minutes = minute_start)
ef_time_end = ef_time + timedelta(minutes = mins)
ann_factor = 252 * 1440
elif freq == 'days':
ef_time = ef_time_frame.index.normalize()
ef_time_start = ef_time - timedelta(days = minute_start)
ef_time_end = ef_time + timedelta(days = mins)
ann_factor = 252
ords = range(-minute_start + min_offset, mins + min_offset)
# all data needs to be equally spaced
if resample:
tsf = TimeSeriesFilter()
# make sure time series is properly sampled at 1 min intervals
data_frame_rets = data_frame_rets.resample('1min')
data_frame_rets = data_frame_rets.fillna(value = 0)
data_frame_rets = tsf.remove_out_FX_out_of_hours(data_frame_rets)
data_frame_rets['Ind'] = numpy.nan
start_index = data_frame_rets.index.searchsorted(ef_time_start)
finish_index = data_frame_rets.index.searchsorted(ef_time_end)
# not all observation windows will be same length (eg. last one?)
# fill the indices which represent minutes
# TODO vectorise this!
for i in range(0, len(ef_time_frame.index)):
try:
data_frame_rets.ix[start_index[i]:finish_index[i], 'Ind'] = ords
except:
data_frame_rets.ix[start_index[i]:finish_index[i], 'Ind'] = ords[0:(finish_index[i] - start_index[i])]
# set the release dates
data_frame_rets.ix[start_index,'Rel'] = ef_time # set entry points
data_frame_rets.ix[finish_index + 1,'Rel'] = numpy.zeros(len(start_index)) # set exit points
data_frame_rets['Rel'] = data_frame_rets['Rel'].fillna(method = 'pad') # fill down signals
data_frame_rets = data_frame_rets[pandas.notnull(data_frame_rets['Ind'])] # get rid of other
data_frame = data_frame_rets.pivot(index='Ind',
columns='Rel', values=data_frame_rets.columns[0])
data_frame.index.names = [None]
if create_index:
tsc = TimeSeriesCalcs()
data_frame.ix[-minute_start + min_offset,:] = numpy.nan
data_frame = tsc.create_mult_index(data_frame)
else:
if vol is True:
# annualise (if vol)
data_frame = pandas.rolling_std(data_frame, window=5) * math.sqrt(ann_factor)
else:
data_frame = data_frame.cumsum()
return data_frame
class LightEventsFactory(EventStudy):
_econ_data_frame = None
# where your HDF5 file is stored with economic data MUST CHANGE!!
_hdf5_file_econ_file = "somefilnename.h5"
### manual offset for certain events where Bloomberg displays the wrong date (usually because of time differences)
_offset_events = {
'AUD-Australia Labor Force Employment Change SA.release-dt': 1
}
def __init__(self):
super(EventStudy, self).__init__()
self.config = ConfigManager()
self.logger = LoggerManager().getLogger(__name__)
self.time_series_filter = TimeSeriesFilter()
self.time_series_io = TimeSeriesIO()
if (LightEventsFactory._econ_data_frame is None):
self.load_economic_events()
return
def load_economic_events(self):
LightEventsFactory._econ_data_frame = self.time_series_io.read_time_series_cache_from_disk(
self._hdf5_file_econ_file)
def harvest_category(self, category_name):
cat = self.config.get_categories_from_tickers_selective_filter(
category_name)
for k in cat:
time_series_request = self.time_series_factory.populate_time_series_request(
k)
data_frame = self.time_series_factory.harvest_time_series(
time_series_request)
# TODO allow merge of multiple sources
return data_frame
def get_economic_events(self):
return LightEventsFactory._econ_data_frame
def dump_economic_events_csv(self, path):
LightEventsFactory._econ_data_frame.to_csv(path)
def get_economic_event_date_time(self, name, event=None, csv=None):
ticker = self.create_event_desciptor_field(name, event,
"release-date-time-full")
if csv is None:
data_frame = LightEventsFactory._econ_data_frame[ticker]
data_frame.index = LightEventsFactory._econ_data_frame[ticker]
else:
dateparse = lambda x: datetime.datetime.strptime(
x, '%d/%m/%Y %H:%M')
data_frame = pandas.read_csv(csv,
index_col=0,
parse_dates=True,
date_parser=dateparse)
data_frame = data_frame[pandas.notnull(data_frame.index)]
start_date = datetime.datetime.strptime("01-Jan-1971", "%d-%b-%Y")
self.time_series_filter.filter_time_series_by_date(
start_date, None, data_frame)
return data_frame
def get_economic_event_date_time_dataframe(self,
name,
event=None,
csv=None):
series = self.get_economic_event_date_time(name, event, csv)
data_frame = pandas.DataFrame(series.values, index=series.index)
data_frame.columns.name = self.create_event_desciptor_field(
name, event, "release-date-time-full")
return data_frame
def get_economic_event_date_time_fields(self, fields, name, event=None):
### acceptible fields
# actual-release
# survey-median
# survey-average
# survey-high
# survey-low
# survey-high
# number-observations
# release-dt
# release-date-time-full
# first-revision
# first-revision-date
ticker = []
# construct tickers of the form USD-US Employees on Nonfarm Payrolls Total MoM Net Change SA.actual-release
for i in range(0, len(fields)):
ticker.append(
self.create_event_desciptor_field(name, event, fields[i]))
# index on the release-dt field eg. 20101230 (we shall convert this later)
ticker_index = self.create_event_desciptor_field(
name, event, "release-dt")
######## grab event date/times
event_date_time = self.get_economic_event_date_time(name, event)
date_time_fore = event_date_time.index
# create dates for join later
date_time_dt = [
datetime.datetime(date_time_fore[x].year, date_time_fore[x].month,
date_time_fore[x].day)
for x in range(len(date_time_fore))
]
event_date_time_frame = pandas.DataFrame(event_date_time.index,
date_time_dt)
event_date_time_frame.index = date_time_dt
######## grab event date/fields
data_frame = LightEventsFactory._econ_data_frame[ticker]
data_frame.index = LightEventsFactory._econ_data_frame[ticker_index]
data_frame = data_frame[data_frame.index !=
0] # eliminate any 0 dates (artifact of Excel)
data_frame = data_frame[pandas.notnull(
data_frame.index)] # eliminate any NaN dates (artifact of Excel)
ind_dt = data_frame.index
# convert yyyymmdd format to datetime
data_frame.index = [
datetime.datetime(
int((ind_dt[x] - (ind_dt[x] % 10000)) / 10000),
int(((ind_dt[x] % 10000) - (ind_dt[x] % 100)) / 100),
int(ind_dt[x] % 100)) for x in range(len(ind_dt))
]
# HACK! certain events need an offset because BBG have invalid dates
if ticker_index in self._offset_events:
data_frame.index = data_frame.index + timedelta(
days=self._offset_events[ticker_index])
######## join together event dates/date-time/fields in one data frame
data_frame = event_date_time_frame.join(data_frame, how='inner')
data_frame.index = pandas.to_datetime(data_frame.index)
data_frame.index.name = ticker_index
return data_frame
def create_event_desciptor_field(self, name, event, field):
if event is None:
return name + "." + field
else:
return name + "-" + event + "." + field
def get_all_economic_events_date_time(self):
event_names = self.get_all_economic_events()
columns = ['event-name', 'release-date-time-full']
data_frame = pandas.DataFrame(data=numpy.zeros((0, len(columns))),
columns=columns)
for event in event_names:
event_times = self.get_economic_event_date_time(event)
for time in event_times:
data_frame.append(
{
'event-name': event,
'release-date-time-full': time
},
ignore_index=True)
return data_frame
def get_all_economic_events(self):
field_names = LightEventsFactory._econ_data_frame.columns.values
event_names = [x.split('.')[0] for x in field_names if '.Date' in x]
event_names_filtered = [x for x in event_names if len(x) > 4]
# sort list alphabetically (and remove any duplicates)
return list(set(event_names_filtered))
def get_economic_event_date(self, name, event=None):
return LightEventsFactory._econ_data_frame[
self.create_event_desciptor_field(name, event, ".release-dt")]
def get_economic_event_ret_over_custom_event_day(self,
data_frame_in,
name,
event,
start,
end,
lagged=False,
NYC_cutoff=10):
# get the times of events
event_dates = self.get_economic_event_date_time(name, event)
return super(LightEventsFactory,
self).get_economic_event_ret_over_custom_event_day(
data_frame_in,
event_dates,
name,
event,
start,
end,
lagged=lagged,
NYC_cutoff=NYC_cutoff)
def get_economic_event_vol_over_event_day(self,
vol_in,
name,
event,
start,
end,
realised=False):
return self.get_economic_event_ret_over_custom_event_day(
vol_in, name, event, start, end, lagged=realised)
# return super(EventsFactory, self).get_economic_event_ret_over_event_day(vol_in, name, event, start, end, lagged = realised)
def get_daily_moves_over_event(self):
# TODO
pass
# return only US events etc. by dates
def get_intraday_moves_over_event(self,
data_frame_rets,
cross,
event_fx,
event_name,
start,
end,
vol,
mins=3 * 60,
min_offset=0,
create_index=False,
resample=False,
freq='minutes'):
tsf = TimeSeriesFilter()
ef_time_frame = self.get_economic_event_date_time_dataframe(
event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end,
ef_time_frame)
return self.get_intraday_moves_over_custom_event(
data_frame_rets,
ef_time_frame,
vol,
mins=mins,
min_offset=min_offset,
create_index=create_index,
resample=resample,
freq=freq) #, start, end)
def get_surprise_against_intraday_moves_over_event(
self,
data_frame_cross_orig,
cross,
event_fx,
event_name,
start,
end,
offset_list=[1, 5, 30, 60],
add_surprise=False,
surprise_field='survey-average'):
tsf = TimeSeriesFilter()
fields = [
'actual-release', 'survey-median', 'survey-average', 'survey-high',
'survey-low'
]
ef_time_frame = self.get_economic_event_date_time_fields(
fields, event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end,
ef_time_frame)
return self.get_surprise_against_intraday_moves_over_custom_event(
data_frame_cross_orig,
ef_time_frame,
cross,
event_fx,
event_name,
start,
end,
offset_list=offset_list,
add_surprise=add_surprise,
surprise_field=surprise_field)
data_source = 'bloomberg', # use Bloomberg as data source
tickers = ['NFP'],
fields = ['release-date-time-full'], # which fields to download
vendor_tickers = ['NFP TCH Index'], # ticker (Bloomberg)
vendor_fields = ['ECO_FUTURE_RELEASE_DATE_LIST'], # which Bloomberg fields to download
cache_algo = 'internet_load_return') # how to return data
ltsf = LightTimeSeriesFactory()
ts_filter = TimeSeriesFilter()
df_event_times = ltsf.harvest_time_series(time_series_request)
utc_time = pytz.utc
df_event_times = pandas.DataFrame(index = df_event_times['NFP.release-date-time-full'])
df_event_times.index = df_event_times.index.tz_localize(utc_time) # work in UTC time
df_event_times = ts_filter.filter_time_series_by_date(start_date, finish_date, df_event_times)
# get last NFP time
start_date = df_event_times.index[-1] - timedelta(minutes=1)
finish_date = start_date + timedelta(minutes=4)
tickers = ['EURUSD', 'JPYUSD', 'GBPUSD']
vendor_tickers = ['EURUSD BGN Curncy', 'USDJPY BGN Curncy', 'GBPUSD BGN Curncy']
# Bloomberg will give tick data which is downsampled within the LightTimeSeriesFactory class
time_series_request = TimeSeriesRequest(
start_date = start_date, # start date
finish_date = finish_date, # finish date
freq = 'second', # second data
data_source = 'bloomberg', # use Bloomberg as data source
tickers = tickers, # ticker (Thalesians)
data_source = 'bloomberg', # use Bloomberg as data source
tickers = ['NFP'],
fields = ['release-date-time-full'], # which fields to download
vendor_tickers = ['NFP TCH Index'], # ticker (Bloomberg)
vendor_fields = ['ECO_FUTURE_RELEASE_DATE_LIST'], # which Bloomberg fields to download
cache_algo = 'internet_load_return') # how to return data
ltsf = LightTimeSeriesFactory()
ts_filter = TimeSeriesFilter()
df_event_times = ltsf.harvest_time_series(time_series_request)
utc_time = pytz.utc
df_event_times = pandas.DataFrame(index = df_event_times['NFP.release-date-time-full'])
df_event_times.index = df_event_times.index.tz_localize(utc_time) # work in UTC time
df_event_times = ts_filter.filter_time_series_by_date(start_date, finish_date, df_event_times)
# get last NFP time
start_date = df_event_times.index[-1] - timedelta(minutes=1)
finish_date = start_date + timedelta(minutes=4)
tickers = ['EURUSD', 'JPYUSD', 'GBPUSD']
vendor_tickers = ['EURUSD BGN Curncy', 'USDJPY BGN Curncy', 'GBPUSD BGN Curncy']
# Bloomberg will give tick data which is downsampled within the LightTimeSeriesFactory class
time_series_request = TimeSeriesRequest(
start_date = start_date, # start date
finish_date = finish_date, # finish date
freq = 'second', # second data
data_source = 'bloomberg', # use Bloomberg as data source
tickers = tickers, # ticker (Thalesians)
class LightEventsFactory(EventStudy):
_econ_data_frame = None
# where your HDF5 file is stored with economic data MUST CHANGE!!
_hdf5_file_econ_file = "somefilnename.h5"
### manual offset for certain events where Bloomberg displays the wrong date (usually because of time differences)
_offset_events = {'AUD-Australia Labor Force Employment Change SA.release-dt' : 1}
def __init__(self):
super(EventStudy, self).__init__()
self.config = ConfigManager()
self.logger = LoggerManager().getLogger(__name__)
self.time_series_filter = TimeSeriesFilter()
self.time_series_io = TimeSeriesIO()
if (LightEventsFactory._econ_data_frame is None):
self.load_economic_events()
return
def load_economic_events(self):
LightEventsFactory._econ_data_frame = self.time_series_io.read_time_series_cache_from_disk(self._hdf5_file_econ_file)
def harvest_category(self, category_name):
cat = self.config.get_categories_from_tickers_selective_filter(category_name)
for k in cat:
time_series_request = self.time_series_factory.populate_time_series_request(k)
data_frame = self.time_series_factory.harvest_time_series(time_series_request)
# TODO allow merge of multiple sources
return data_frame
def get_economic_events(self):
return LightEventsFactory._econ_data_frame
def dump_economic_events_csv(self, path):
LightEventsFactory._econ_data_frame.to_csv(path)
def get_economic_event_date_time(self, name, event = None, csv = None):
ticker = self.create_event_desciptor_field(name, event, "release-date-time-full")
if csv is None:
data_frame = LightEventsFactory._econ_data_frame[ticker]
data_frame.index = LightEventsFactory._econ_data_frame[ticker]
else:
dateparse = lambda x: datetime.datetime.strptime(x, '%d/%m/%Y %H:%M')
data_frame = pandas.read_csv(csv, index_col=0, parse_dates = True, date_parser=dateparse)
data_frame = data_frame[pandas.notnull(data_frame.index)]
start_date = datetime.datetime.strptime("01-Jan-1971", "%d-%b-%Y")
self.time_series_filter.filter_time_series_by_date(start_date, None, data_frame)
return data_frame
def get_economic_event_date_time_dataframe(self, name, event = None, csv = None):
series = self.get_economic_event_date_time(name, event, csv)
data_frame = pandas.DataFrame(series.values, index=series.index)
data_frame.columns.name = self.create_event_desciptor_field(name, event, "release-date-time-full")
return data_frame
def get_economic_event_date_time_fields(self, fields, name, event = None):
### acceptible fields
# actual-release
# survey-median
# survey-average
# survey-high
# survey-low
# survey-high
# number-observations
# release-dt
# release-date-time-full
# first-revision
# first-revision-date
ticker = []
# construct tickers of the form USD-US Employees on Nonfarm Payrolls Total MoM Net Change SA.actual-release
for i in range(0, len(fields)):
ticker.append(self.create_event_desciptor_field(name, event, fields[i]))
# index on the release-dt field eg. 20101230 (we shall convert this later)
ticker_index = self.create_event_desciptor_field(name, event, "release-dt")
######## grab event date/times
event_date_time = self.get_economic_event_date_time(name, event)
date_time_fore = event_date_time.index
# create dates for join later
date_time_dt = [datetime.datetime(
date_time_fore[x].year,
date_time_fore[x].month,
date_time_fore[x].day)
for x in range(len(date_time_fore))]
event_date_time_frame = pandas.DataFrame(event_date_time.index, date_time_dt)
event_date_time_frame.index = date_time_dt
######## grab event date/fields
data_frame = LightEventsFactory._econ_data_frame[ticker]
data_frame.index = LightEventsFactory._econ_data_frame[ticker_index]
data_frame = data_frame[data_frame.index != 0] # eliminate any 0 dates (artifact of Excel)
data_frame = data_frame[pandas.notnull(data_frame.index)] # eliminate any NaN dates (artifact of Excel)
ind_dt = data_frame.index
# convert yyyymmdd format to datetime
data_frame.index = [datetime.datetime(
int((ind_dt[x] - (ind_dt[x] % 10000))/10000),
int(((ind_dt[x] % 10000) - (ind_dt[x] % 100))/100),
int(ind_dt[x] % 100)) for x in range(len(ind_dt))]
# HACK! certain events need an offset because BBG have invalid dates
if ticker_index in self._offset_events:
data_frame.index = data_frame.index + timedelta(days=self._offset_events[ticker_index])
######## join together event dates/date-time/fields in one data frame
data_frame = event_date_time_frame.join(data_frame, how='inner')
data_frame.index = pandas.to_datetime(data_frame.index)
data_frame.index.name = ticker_index
return data_frame
def create_event_desciptor_field(self, name, event, field):
if event is None:
return name + "." + field
else:
return name + "-" + event + "." + field
def get_all_economic_events_date_time(self):
event_names = self.get_all_economic_events()
columns = ['event-name', 'release-date-time-full']
data_frame = pandas.DataFrame(data=numpy.zeros((0,len(columns))), columns=columns)
for event in event_names:
event_times = self.get_economic_event_date_time(event)
for time in event_times:
data_frame.append({'event-name':event, 'release-date-time-full':time}, ignore_index=True)
return data_frame
def get_all_economic_events(self):
field_names = LightEventsFactory._econ_data_frame.columns.values
event_names = [x.split('.')[0] for x in field_names if '.Date' in x]
event_names_filtered = [x for x in event_names if len(x) > 4]
# sort list alphabetically (and remove any duplicates)
return list(set(event_names_filtered))
def get_economic_event_date(self, name, event = None):
return LightEventsFactory._econ_data_frame[
self.create_event_desciptor_field(name, event, ".release-dt")]
def get_economic_event_ret_over_custom_event_day(self, data_frame_in, name, event, start, end, lagged = False,
NYC_cutoff = 10):
# get the times of events
event_dates = self.get_economic_event_date_time(name, event)
return super(LightEventsFactory, self).get_economic_event_ret_over_custom_event_day(data_frame_in, event_dates, name, event, start, end,
lagged = lagged, NYC_cutoff = NYC_cutoff)
def get_economic_event_vol_over_event_day(self, vol_in, name, event, start, end, realised = False):
return self.get_economic_event_ret_over_custom_event_day(vol_in, name, event, start, end,
lagged = realised)
# return super(EventsFactory, self).get_economic_event_ret_over_event_day(vol_in, name, event, start, end, lagged = realised)
def get_daily_moves_over_event(self):
# TODO
pass
# return only US events etc. by dates
def get_intraday_moves_over_event(self, data_frame_rets, cross, event_fx, event_name, start, end, vol, mins = 3 * 60,
min_offset = 0, create_index = False, resample = False, freq = 'minutes'):
tsf = TimeSeriesFilter()
ef_time_frame = self.get_economic_event_date_time_dataframe(event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end, ef_time_frame)
return self.get_intraday_moves_over_custom_event(data_frame_rets, ef_time_frame,
vol, mins = mins, min_offset = min_offset,
create_index = create_index, resample = resample, freq = freq)#, start, end)
def get_surprise_against_intraday_moves_over_event(self, data_frame_cross_orig, cross, event_fx, event_name, start, end,
offset_list = [1, 5, 30, 60], add_surprise = False,
surprise_field = 'survey-average'):
tsf = TimeSeriesFilter()
fields = ['actual-release', 'survey-median', 'survey-average', 'survey-high', 'survey-low']
ef_time_frame = self.get_economic_event_date_time_fields(fields, event_fx, event_name)
ef_time_frame = tsf.filter_time_series_by_date(start, end, ef_time_frame)
return self.get_surprise_against_intraday_moves_over_custom_event(data_frame_cross_orig, ef_time_frame, cross, event_fx, event_name, start, end,
offset_list = offset_list, add_surprise = add_surprise,
surprise_field = surprise_field)
def get_intraday_moves_over_custom_event(self,
data_frame_rets,
ef_time_frame,
vol=False,
minute_start=5,
mins=3 * 60,
min_offset=0,
create_index=False,
resample=False,
freq='minutes'):
tsf = TimeSeriesFilter()
ef_time_frame = tsf.filter_time_series_by_date(
data_frame_rets.index[0], data_frame_rets.index[-1], ef_time_frame)
ef_time = ef_time_frame.index
if freq == 'minutes':
ef_time_start = ef_time - timedelta(minutes=minute_start)
ef_time_end = ef_time + timedelta(minutes=mins)
ann_factor = 252 * 1440
elif freq == 'days':
ef_time = ef_time_frame.index.normalize()
ef_time_start = ef_time - timedelta(days=minute_start)
ef_time_end = ef_time + timedelta(days=mins)
ann_factor = 252
ords = range(-minute_start + min_offset, mins + min_offset)
# all data needs to be equally spaced
if resample:
tsf = TimeSeriesFilter()
# make sure time series is properly sampled at 1 min intervals
data_frame_rets = data_frame_rets.resample('1min')
data_frame_rets = data_frame_rets.fillna(value=0)
data_frame_rets = tsf.remove_out_FX_out_of_hours(data_frame_rets)
data_frame_rets['Ind'] = numpy.nan
start_index = data_frame_rets.index.searchsorted(ef_time_start)
finish_index = data_frame_rets.index.searchsorted(ef_time_end)
# not all observation windows will be same length (eg. last one?)
# fill the indices which represent minutes
# TODO vectorise this!
for i in range(0, len(ef_time_frame.index)):
try:
data_frame_rets.ix[start_index[i]:finish_index[i],
'Ind'] = ords
except:
data_frame_rets.ix[start_index[i]:finish_index[i],
'Ind'] = ords[0:(finish_index[i] -
start_index[i])]
# set the release dates
data_frame_rets.ix[start_index, 'Rel'] = ef_time # set entry points
data_frame_rets.ix[finish_index + 1, 'Rel'] = numpy.zeros(
len(start_index)) # set exit points
data_frame_rets['Rel'] = data_frame_rets['Rel'].fillna(
method='pad') # fill down signals
data_frame_rets = data_frame_rets[pandas.notnull(
data_frame_rets['Ind'])] # get rid of other
data_frame = data_frame_rets.pivot(index='Ind',
columns='Rel',
values=data_frame_rets.columns[0])
data_frame.index.names = [None]
if create_index:
tsc = TimeSeriesCalcs()
data_frame.ix[-minute_start + min_offset, :] = numpy.nan
data_frame = tsc.create_mult_index(data_frame)
else:
if vol is True:
# annualise (if vol)
data_frame = pandas.rolling_std(
data_frame, window=5) * math.sqrt(ann_factor)
else:
data_frame = data_frame.cumsum()
return data_frame
