def calculate_ret_stats(self, returns_df, ann_factor):
"""
calculate_ret_stats - Calculates return statistics for an asset's returns including IR, vol, ret and drawdowns
Parameters
----------
returns_df : DataFrame
asset returns
ann_factor : int
annualisation factor to use on return statistics
Returns
-------
DataFrame
"""
calculations = Calculations()
self._rets = returns_df.mean(axis=0) * ann_factor
self._vol = returns_df.std(axis=0) * math.sqrt(ann_factor)
self._inforatio = self._rets / self._vol
self._kurtosis = returns_df.kurtosis(axis=0) / math.sqrt(ann_factor)
index_df = calculations.create_mult_index(returns_df)
# max2here = pandas.expanding_max(index_df)
max2here = index_df.expanding(min_periods=1).max()
dd2here = index_df / max2here - 1
self._dd = dd2here.min()
self._yoy_rets = index_df.resample('A').mean().pct_change()
def report_single_var_regression(self, y, x, y_variable_names, x_variable_names, statistic,
pretty_index = None):
if not(isinstance(statistic, list)): statistic = [statistic]
# conduct the regression
stats = Calculations.linear_regression_single_vars(y, x, y_variable_names, x_variable_names)
if pretty_index is None: pretty_index = x_variable_names
# strip out the field(s) from the regression output which we want
stats_df = Calculations.strip_linear_regression_output(pretty_index, stats, statistic)
# stats_df = stats_df.sort_index()
return stats_df
def calculate_ret_stats_from_prices(self, prices_df, ann_factor):
"""Calculates return statistics for an asset's price
Parameters
----------
prices_df : DataFrame
asset prices
ann_factor : int
annualisation factor to use on return statistics
Returns
-------
DataFrame
"""
calculations = Calculations()
self.calculate_ret_stats(calculations.calculate_returns(prices_df),
ann_factor)
def report_single_var_regression(self,
y,
x,
y_variable_names,
x_variable_names,
statistic,
pretty_index=None):
if not (isinstance(statistic, list)): statistic = [statistic]
# conduct the regression
stats = Calculations.linear_regression_single_vars(
y, x, y_variable_names, x_variable_names)
if pretty_index is None: pretty_index = x_variable_names
# strip out the field(s) from the regression output which we want
stats_df = Calculations.strip_linear_regression_output(
pretty_index, stats, statistic)
return stats_df
#
# Copyright 2020 Cuemacro
#
# See the License for the specific language governing permissions and limitations under the License.
#
import pandas as pd
import dask.dataframe as dd
from findatapy.timeseries.calculations import Calculations
from tcapy.util.loggermanager import LoggerManager
from tcapy.util.utilfunc import UtilFunc
util_func = UtilFunc()
calculations = Calculations()
file_extension = 'parquet'
csv_output = '/data/csv_output/'
ticker_mkt = ['EURUSD', 'GBPUSD', 'AUDUSD', 'NZDUSD', 'USDCAD', 'USDCHF', 'EURNOK', 'EURSEK', 'USDJPY']
ticker_combined_mkt = ['EURUSD', 'GBPUSD', 'AUDUSD', 'NZDUSD', 'USDCAD', 'USDJPY']
def create_resampled_spot_data(resample_freq='1min', data_vendor='dukascopy'):
logger = LoggerManager.getLogger(__name__)
csv_input_folder = '/data/csv_dump/' + data_vendor + '/'
for ticker in ticker_mkt:
