def lead_lag_disc_regression(returns_data, period, lookback, shift):
# Creating frequent returns data
week_chunks = np.array_split(returns_data.copy().cumsum(),
returns_data.shape[0] / period)
PC_proj_weekly = pd.DataFrame(
[] * returns_data.shape[0],
columns=returns_data.columns,
index=[week.index[0] for week in week_chunks])
for week in week_chunks:
PC_proj_weekly.loc[week.index[0]] = week.sum()
# Linear regression on weekly returns with 1 weeks shifted predictors
PC_proj_weekly_ll_one = PC_proj_weekly.copy()
PC_proj_weekly_ll_one.iloc[:, 0] = PC_proj_weekly_ll_one.iloc[:, 0].shift(
periods=shift)
rolling_lr(PC_proj_weekly_ll_one.iloc[:, 0],
PC_proj_weekly_ll_one.iloc[:, 1:],
lookback,
intercept=False)
week_chunks = np.array_split(simp_avg_daily_percent.copy(),
simp_avg_daily_percent.shape[0] / 5)
simp_avg_daily_pc_week_sum = pd.DataFrame(
[] * simp_avg_daily_percent.shape[0],
columns=simp_avg_daily_percent.columns,
index=[week.index[0] for week in week_chunks])
for week in week_chunks:
simp_avg_daily_pc_week_sum.loc[week.index[0]] = week.sum()
# Linear regression on weekly returns with 1 weeks shifted predictors
simp_avg_daily_pc_weekly_ll = simp_avg_daily_pc_week_sum.copy()
simp_avg_daily_pc_weekly_ll.iloc[:,
0] = simp_avg_daily_pc_week_sum.iloc[:,
0].shift(
periods
=1)
test = rolling_lr(simp_avg_daily_pc_weekly_ll.iloc[:, 0],
simp_avg_daily_pc_weekly_ll.iloc[:, 1:],
150,
intercept=False)
# test = rolling_lasso(simp_avg_daily_pc_weekly_ll.iloc[:,0], simp_avg_daily_pc_weekly_ll.iloc[:,1:], 150, intercept = False, alph = 0)
# test = rolling_ridge(simp_avg_daily_pc_weekly_ll.iloc[:,0], simp_avg_daily_pc_weekly_ll.iloc[:,1:], 150, intercept = False, alph = 2)
# series_plot([simp_avg_daily_pc_weekly_ll.iloc[:,0], simp_avg_daily_pc_weekly_ll['WTI Crude Oil']],'Oil Price against commodities')
#%%
# # series_plot([commodities_2013.mean(axis=1) - trimmed_dates['NYMEX WTI Crude Oil']],'Oil Price against commodities')
# # series_plot([commodities_2013.mean(axis=1) - trimmed_dates['NYMEX WTI Crude Oil']],'Oil Price against commodities')
# series_plot([commodities_2013.mean(axis=1) - trimmed_dates['ICE US Dollar Index']],'Oil Price against commodities')
# series_plot([commodities_2013.mean(axis=1) - trimmed_dates['NYMEX WTI Crude Oil']],'Oil Price against commodities')
# Create column for average of currency basket
cur_commod_avg = pd.DataFrame(trimmed_dates[[
'CME Australian Dollar AUD', 'CME Mexican Peso', 'CME Canadian Dollar CAD'
]].mean(axis=1),
columns=['Commodity Currencies Simp Avg'])
# Create empty residual dataframe
residual_df = pd.DataFrame().reindex_like(commodities_2013)
# Perfrom rolling regression and fill residual dataframe for each contract in commodities basket
for i, contract in enumerate(commodities_2013):
# Take prediction from rolling linear regression
pred = rolling_lr(pd.DataFrame(commodities_2013[contract]),
cur_commod_avg,
lookback=200,
intercept=False)[1]
# Set residual column for current contract
residual_df[contract] = commodities_2013[contract] - pred['Prediction']
# Output progress
print('{} residuals completed {}/{}'.format(contract, i + 1,
commodities_2013.shape[1]))
residual_df = residual_df.fillna(method='ffill')
#%% Trading strategy:
# Long bottom three negative residuals, Short top three postive residuals.
# Create empty signals df
signal_df = pd.DataFrame([0]).reindex_like(residual_df)
signal_df = signal_df.fillna(0)
from lin_reg_analysis import rolling_lr, commodities_2013
from preprocessing import trimmed_dates, df_dict
from PlottingFunctions import series_plot
import pandas as pd
import numpy as np
#%%
# Create average currency column
cur_commod_avg = pd.DataFrame(trimmed_dates[[
'CME Australian Dollar AUD', 'CME Mexican Peso', 'CME Canadian Dollar CAD'
]].mean(axis=1),
columns=['Commodity Currencies Simp Avg'])
# Create empty beta df
beta_df = pd.DataFrame().reindex_like(commodities_2013)
# Perfrom rolling regression and fill residual df
for i, contract in enumerate(commodities_2013):
beta = rolling_lr(pd.DataFrame(commodities_2013[contract]),
pd.DataFrame(commodities_2013.mean(axis=1)),
lookback=150,
intercept=False)
beta_df[contract] = beta[0]
print('{} betas computed {}/{}'.format(contract, i + 1,
commodities_2013.shape[1]))
# %%
# Initialise balance and price series
live_prices = df_dict['Close'].fillna(method='backfill')
# .copy().fillna(method = 'ffill')
# Split into monthly chunks
monthly_beta = np.array_split(beta_df.dropna(), 150)
month_index = [month.index[0] for month in monthly_beta]
# Create df of monthly signals for each contract