mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +00:00
Mark Aron Szulyovszky
81c217a401
* feat(DataLoader): added load_only_returns() method * feat(Portfolio): load predictions * feat(Portfolio): normalize weights * feat(Portfolio): started integrating with portfoliobt * feat(Portfolio): include fees in the portfolio construction * feat(Portfolio): demo of pyportfolioopt * feat(Portfolio): get efficient frontier calculation to work * feat(Portfolio): add a few strategies to create weights * chore(Dependencies): remove pyportfolioopt for now * fix(Dependencies): try to install all dependencies with pip * fix(Dependencies): indentation * fix(Dependencies): corrected pytorch module name * fix(Dependencies): try to have as many modules installed by conda for the sake of sanity? * fix(Dependencies): put fracdiff into pip modules * fix(Dependencies): revert to using pip almost exclusively * feat(Portfolio): added alphalens * fix(Portfolio): got limited weights working * feat(Portfolio): trying to get alphalens to work * feat(Portfolio): alphalens working * fix(Dependencies): removed vectorbt * fix(Dependencies): use alphalens-reloaded * fix(Dependencies): added conda source for alphalens-reloaded * refactor(Portfolio): removed traces of vectorbt * feat(Reporting): factor reporting done * feat(Portfolio): added pyfolio reporting (fails bc alphalens is not working properly lol)
173 lines
6.1 KiB
Python
173 lines
6.1 KiB
Python
#%%
|
|
import pandas as pd
|
|
import numpy as np
|
|
from data_loader.load_data import load_only_returns
|
|
from data_loader.collections import data_collections
|
|
|
|
from utils.helpers import get_first_valid_return_index
|
|
from alphalens.tears import (create_returns_tear_sheet,
|
|
create_information_tear_sheet,
|
|
create_turnover_tear_sheet,
|
|
create_summary_tear_sheet,
|
|
create_full_tear_sheet,
|
|
create_event_returns_tear_sheet,
|
|
create_event_study_tear_sheet)
|
|
import alphalens
|
|
import pyfolio
|
|
|
|
from alphalens.utils import get_clean_factor_and_forward_returns
|
|
|
|
def fixed_weight(row: pd.Series, availability_row: pd.Series, allow_short: bool) -> pd.Series:
|
|
no_of_assets_available = availability_row.sum()
|
|
unit = 1 / no_of_assets_available
|
|
if allow_short:
|
|
def determine_pos(x):
|
|
if x == 0.0 or np.isnan(x):
|
|
return 0
|
|
elif x > 0.0:
|
|
return 1
|
|
else:
|
|
return -1
|
|
row = row.apply(determine_pos)
|
|
else:
|
|
row = row.apply(lambda x: 1 if x > 0.0 else 0)
|
|
return row * unit
|
|
|
|
def limit_weight(row: pd.Series) -> pd.Series:
|
|
if row.sum() > 1:
|
|
row = row / row.sum()
|
|
elif row.sum() < -1:
|
|
row = row * (1. / abs(row.sum()))
|
|
return row
|
|
|
|
def only_top_bottom_2(row: pd.Series) -> pd.Series:
|
|
row = row.copy()
|
|
row_sorted = row.sort_values()
|
|
bottom = row_sorted.iloc[:2]
|
|
top = row_sorted.iloc[-2:]
|
|
middle = row_sorted.iloc[2:-2]
|
|
for index, _ in middle.iteritems():
|
|
row[index] = 0.
|
|
|
|
if bottom.sum() > 0:
|
|
for index, _ in bottom.iteritems():
|
|
row[index] = 0.
|
|
else:
|
|
for index, _ in bottom.iteritems():
|
|
row[index] = -.025
|
|
|
|
if top.sum() < 0:
|
|
for index, _ in top.iteritems():
|
|
row[index] = 0.
|
|
else:
|
|
for index, _ in top.iteritems():
|
|
row[index] = .025
|
|
|
|
return row
|
|
|
|
def equal_weight(row: pd.Series, availability: pd.Series) -> pd.Series:
|
|
no_of_assets_available = availability.sum()
|
|
unit = 1 / no_of_assets_available
|
|
for index, _ in predictions.iteritems():
|
|
row[index] = 0. if availability[index] == 0 else unit
|
|
return row
|
|
|
|
|
|
|
|
def create_naive_portfolio_weights(predictions: pd.DataFrame, availability: pd.DataFrame, allow_short: bool) -> pd.DataFrame:
|
|
weights = predictions.copy()
|
|
assert weights.shape[1] == availability.shape[1]
|
|
for index, row in weights.iterrows():
|
|
# row = fixed_weight(row, availability.iloc[index], allow_short)
|
|
# row = row / row.sum()
|
|
# row = only_top_bottom_2(row)
|
|
# row = equal_weight(row, availability.iloc[index])
|
|
# row = limit_weight(row)
|
|
weights.iloc[index] = row
|
|
return weights
|
|
|
|
|
|
predictions = pd.read_csv('output/predictions.csv', index_col=0)
|
|
predictions.columns = ['_'.join(col.replace("model_", "").split("_")[:2]) for col in predictions.columns]
|
|
first_index = get_first_valid_return_index(predictions[predictions.columns[0]])
|
|
predictions = predictions.iloc[first_index:]
|
|
predictions.reset_index(drop=True, inplace=True)
|
|
|
|
close = load_only_returns(data_collections['daily_crypto'], 'date', 'price')
|
|
close = close.iloc[first_index:-1]
|
|
close.columns = [col.replace("_returns", "") for col in close.columns]
|
|
close = close[predictions.columns]
|
|
|
|
availability = close.applymap(lambda x: 0 if x == 0.0 or x == 0 or np.isnan(x) else 1)
|
|
|
|
weights = create_naive_portfolio_weights(predictions, availability, allow_short=True)
|
|
weights.index = close.index
|
|
|
|
weights_long = pd.melt(weights.reset_index(), id_vars=['time'], value_vars=weights.columns).set_index(['time', 'variable'])
|
|
close_long = pd.melt(close.reset_index(), id_vars=['time'], value_vars=close.columns).set_index(['time', 'variable'])
|
|
#%%
|
|
factor_data = get_clean_factor_and_forward_returns(
|
|
weights_long,
|
|
close,
|
|
# groupby=weights.columns.to_list(),
|
|
quantiles=4,
|
|
periods=(1, 2, 3, 4, 5, 6, 10),
|
|
filter_zscore=None)
|
|
|
|
#%%
|
|
factor_data.head(10)
|
|
|
|
#%%
|
|
create_full_tear_sheet(factor_data, long_short=True)
|
|
|
|
from matplotlib.backends.backend_pdf import PdfPages
|
|
|
|
mean_return_by_q_daily, std_err = alphalens.performance.mean_return_by_quantile(factor_data, by_date=True)
|
|
mean_return_by_q, std_err_by_q = alphalens.performance.mean_return_by_quantile(factor_data, by_group=False)
|
|
plot1 = alphalens.plotting.plot_quantile_returns_bar(mean_return_by_q)
|
|
plot2 = alphalens.plotting.plot_quantile_returns_violin(mean_return_by_q_daily)
|
|
plot3 = alphalens.plotting.plot_cumulative_returns_by_quantile(mean_return_by_q_daily, period='D')
|
|
full_tear = create_full_tear_sheet(factor_data, long_short=True)
|
|
avg_returns = create_event_returns_tear_sheet(factor_data, close, avgretplot=(1, 3, 5), long_short=True)
|
|
|
|
|
|
|
|
with PdfPages('output/factors.pdf') as pdf:
|
|
pdf.savefig(plot1.figure)
|
|
pdf.savefig(plot2.figure)
|
|
pdf.savefig(plot3.figure)
|
|
|
|
# create_event_returns_tear_sheet(factor_data, close, avgretplot=(1, 3, 5), long_short=True)
|
|
|
|
#%%
|
|
|
|
pf_returns, pf_positions, pf_benchmark = alphalens.performance.create_pyfolio_input(factor_data,
|
|
period='1D',
|
|
capital=100000,
|
|
long_short=True,
|
|
equal_weight=True,
|
|
quantiles=[1,4],
|
|
groups=None,
|
|
benchmark_period='1D')
|
|
|
|
pyfolio.tears.create_full_tear_sheet(pf_returns,
|
|
positions=pf_positions,
|
|
benchmark_rets=pf_benchmark)
|
|
# rebalance every n days
|
|
# weights.iloc[np.arange(len(weights)) % 7 != 0] = np.nan
|
|
|
|
|
|
|
|
|
|
# from pypfopt import risk_models
|
|
# from pypfopt import expected_returns
|
|
# from pypfopt import EfficientFrontier
|
|
# mu = expected_returns.mean_historical_return(close)
|
|
# S = risk_models.sample_cov(close)
|
|
|
|
# ef = EfficientFrontier(mu, S)
|
|
# raw_weights = ef.max_sharpe()
|
|
# cleaned_weights = ef.clean_weights()
|
|
# print(ef.portfolio_performance(verbose=True))
|
|
|