QuantInvestStrats (qis)
qis - performance analytics, portfolio backtesting, risk analysis, and factsheet reporting in Python.
Quantitative Investment Strategies covers time-series and cross-sectional performance, drift-aware portfolio histories, ex-ante and ex-post risk, and reproducible reports.
Overview
The package is split into 5 main modules with the dependency path increasing sequentially as follows.
-
qis.utilsis module containing low level utilities for operations with pandas, numpy, and datetimes. -
qis.perfstatsis module for computing performance statistics and performance attribution including returns, volatilities, etc. -
qis.plotsis module for plotting and visualization apis. -
qis.modelsis module containing statistical models including filtering and regressions. -
qis.portfoliois high level module for analysis, simulation, backtesting, and reporting of quant strategies. Functionbacktest_model_portfolio()inqis.portfolio.backtester.pytakes instrument prices and simulated weights from a generic strategy and compute the total return, performance attribution, and risk analysis
Risk and tracking-error analytics are consolidated in qis.portfolio.risk. The public
qis.RiskModel is the point-in-time weights-and-covariance layer for ex-ante tracking
error, standalone group risk, factor exposures, benchmark beta and loadings,
systematic/residual tracking-error decomposition, and Euler marginal tracking-error
contributions. Ex-post analytics use portfolio and benchmark NAVs or return differences:
compute_ewma_realised_tracking_error produces a conditional annualised series, while
compute_te_ir_errors and compute_info_ratio_table produce whole-sample tracking
error and information-ratio estimates. The
weights_tracking_error_report_by_ac_subac report brings these views together with
ex-ante versus realised tracking error, ex-ante versus ex-post beta, annualised ex-post alpha,
and optional factor panels. Some established API names retain the abbreviation tre, but
all refer to tracking error.
Covariance-implied Euler attribution also lives here for the whole OSS stack:
compute_portfolio_risk_contributions returns asset contributions in volatility units,
compute_portfolio_risk_contribution_ratios returns their dimensionless shares, and
compute_group_portfolio_risk_contribution_ratios aggregates those shares over clusters,
sectors, asset classes, or any other complete labelled partition.
qis.market_data is an auxiliary module of market-data containers and FX analytics. FxRatesData holds FX spot and domestic short-rate panels and derives cross rates, covered-interest-parity forward premia, carry decomposition, and reference-currency / FX-hedged return translation of multi-asset panels, together with single- and multi-asset FX-hedging reports. FactorsData is a generic container for tradable-factor prices. Examples build the container from free Yahoo data or from Bloomberg via bbg-fetch; see the module README at src/qis/market_data/README.md for the data contract and conventions.
The repository-root examples/ directory contains runnable scripts showcasing the
analytics. It is intentionally separate from the installed qis package:
-
examples/perfstats— performance metrics on price series: quickstart usage, Sharpe vs Sortino across return frequencies, rolling performance, bond-ETF risk/return frontier, multi-figure performance reports, miss-best-worst-days impact, infrequent-returns interpolation, and an end-to-end de-levering / unsmoothing walkthrough on a bundled BDC vs private-credit dataset. -
examples/models— numba-vs-pandas EWM kernel benchmarks, multivariate EWM linear factor models, multivariate OLS, EWM correlation tables, OHLC realised-volatility estimators, intraday/overnight return decomposition, rolling correlations, and block bootstrap of price paths. -
examples/regimes— regime-conditional analytics: bull/bear/normal Sharpe attribution, conditional return boxplots by VIX regime, calendar-month seasonality, US election regime study. -
examples/portfolios— backtests usingbacktest_model_portfolio: balanced 60/40 with and without a BTC sleeve, constant-notional short, leveraged-ETF combinations, long/short pairs, vol-target / trend-following parameter sweeps, and separate offline ex-ante and ex-post tracking-error workflows. -
examples/factsheets— full multi-page factsheets for simulated and actual strategies, cross-sectional asset-class comparisons, multi-strategy parameter sweeps, and optional pybloqs-rendered variants. -
examples/plots— plotting primitives showcase: dual-axis figures, scatter with regression diagnostics. -
examples/utils— date schedules and rolling calendars: option / futures roll generation viagenerate_fixed_maturity_rolls. -
examples/case_studies— cross-cutting domain studies: VIX beta to equities and bonds, VIX term-structure correlation with SPX, conditional returns on the front-month short-VIX strategy, credit-spread regression vs equity / rates.
The examples/README.md index lists every script with a one-line
description; examples that need a Bloomberg terminal are flagged inline.
Table of contents
Installation
Install using
pip install qis
Upgrade using
pip install --upgrade qis
Close using
git clone https://github.com/ArturSepp/QuantInvestStrats.git
Core dependencies: python = ">=3.10", numba = ">=0.63.0", numpy = ">=2.0", scipy = ">=1.12.0", statsmodels = ">=0.14.0", pandas = ">=2.2.0", matplotlib = ">=3.8.0", seaborn = ">=0.13.0", openpyxl = ">=3.1.0", PyYAML = ">=6.0"
src/qis/tests/test_documentation.py asserts that this list is the dependencies table of
pyproject.toml, so it cannot drift from what pip install qis actually pulls.
Python 3.14 is supported (numba 0.63+ ships cp314 wheels).
Optional dependencies:
yfinance = ">=0.2.40" and pandas-datareader = ">=0.10.0" (examples and tests that pull free
price data — install with pip install qis[data]; never imported by library code),
pybloqs ">=1.2.13" (for producing html and pdf factsheets — install with pip install qis[reports]),
bbg-fetch ">=2.0.0" (third-party; for examples that pull data from a Bloomberg terminal)
See pyproject.toml for the full list of optional extras (reports, visualization, io, database, jupyter, dev, all).
Offline quickstart
The authoritative first-success workflow is
examples/getting_started/offline_quickstart.py.
It generates seeded data in-process, builds a live-universe-aware quarterly weight schedule,
backtests with explicit transaction costs, and prints performance plus benchmark-relative risk.
It needs only the core qis installation and writes no files.
From a repository checkout:
python examples/getting_started/offline_quickstart.py
With only pip install qis, copy the complete code from the
hosted offline quickstart.
That page includes the runnable script directly, so the README, documentation, and example cannot
develop independent full-code versions.
The Colab entry point installs the latest release from public PyPI, reports its exact version and import path, and runs that same mechanically checked source with no saved notebook outputs.
Examples
1. Visualization of price data
This is an optional network-backed plotting example. For the core-install first-success path, use the offline quickstart above.
The script is located at examples/perfstats/quickstart.py.
Run python -m examples.perfstats.quickstart from the repository root to produce the figures
below; perf1 to perf3 are excluded from the repository by .gitignore on size, so only the
last is embedded here.
import matplotlib.pyplot as plt
import seaborn as sns
import yfinance as yf
import qis
from qis import PerfStat
# define tickers and fetch price data
tickers = ['SPY', 'QQQ', 'EEM', 'TLT', 'IEF', 'SHY', 'LQD', 'HYG', 'GLD']
prices = yf.download(tickers, start="2003-12-31", end=None, ignore_tz=True, auto_adjust=True)['Close'][tickers].dropna()
# plotting price data with minimum usage
with sns.axes_style("darkgrid"):
fig, ax = plt.subplots(1, 1, figsize=(10, 7))
qis.plot_prices(prices=prices, x_date_freq='YE', ax=ax)
# 2-axis plot with drawdowns using sns styles
with sns.axes_style("darkgrid"):
fig, axs = plt.subplots(2, 1, figsize=(10, 7), tight_layout=True)
qis.plot_prices_with_dd(prices=prices, x_date_freq='YE', axs=axs)
# plot risk-adjusted performance table with excess Sharpe ratio
ust_3m_rate = yf.download('^IRX', start="2003-12-31", end=None, ignore_tz=True, auto_adjust=True)['Close'].dropna() / 100.0
# set parameters for computing performance stats including returns vols and regressions
perf_params = qis.PerfParams(freq='ME', freq_reg='QE', rates_data=ust_3m_rate)
# perf_columns is list to display different perfomance metrics from enumeration PerfStat
fig = qis.plot_ra_perf_table(prices=prices,
perf_columns=[PerfStat.TOTAL_RETURN, PerfStat.PA_RETURN, PerfStat.PA_EXCESS_RETURN,
PerfStat.VOL, PerfStat.SHARPE_RF0,
PerfStat.SHARPE_EXCESS, PerfStat.SORTINO_RATIO, PerfStat.CALMAR_RATIO,
PerfStat.MAX_DD, PerfStat.MAX_DD_VOL,
PerfStat.SKEWNESS, PerfStat.KURTOSIS],
title=f"Risk-adjusted performance: {qis.get_time_period_label(prices, date_separator='-')}",
perf_params=perf_params)
# add benchmark regression using excess returns for linear beta
# regression frequency is specified using perf_params.freq_reg
# regression alpha is multiplied using alpha_an_factor
fig, _ = qis.plot_ra_perf_table_benchmark(prices=prices,
benchmark='SPY',
perf_columns=[PerfStat.TOTAL_RETURN, PerfStat.PA_RETURN, PerfStat.PA_EXCESS_RETURN,
PerfStat.VOL, PerfStat.SHARPE_RF0,
PerfStat.SHARPE_EXCESS, PerfStat.SORTINO_RATIO, PerfStat.CALMAR_RATIO,
PerfStat.MAX_DD, PerfStat.MAX_DD_VOL,
PerfStat.SKEWNESS, PerfStat.KURTOSIS,
PerfStat.ALPHA_AN, PerfStat.BETA, PerfStat.R2],
title=f"Risk-adjusted performance: {qis.get_time_period_label(prices, date_separator='-')} benchmarked with SPY",
perf_params=perf_params)
2. Multi assets factsheet
This report is adopted for reporting the risk-adjusted performance of several assets with the goal of cross-sectional comparision
Run examples/factsheets/multi_assets.py.
3. Strategy factsheet
This report is adopted for report performance, risk, and trading statistics for either backtested or actual strategy with strategy data passed as PortfolioData object
Run examples/factsheets/strategy.py.
4. Strategy benchmark factsheet
This report is adopted for report performance and marginal comparison of strategy vs a benchmark strategy (data for both are passed using individual PortfolioData object)
Run examples/factsheets/strategy_benchmark.py.
Brinson-Fachler performance attribution (https://en.wikipedia.org/wiki/Performance_attribution)
5. Multi strategy factsheet
This report is adopted to examine the sensitivity of backtested strategy to a parameter or set of parameters:
Run examples/factsheets/multi_strategy.py.
6. Runnable examples
The examples are plain scripts under
examples/, each
runnable top to bottom. src/qis/tests/test_examples.py checks them for symbols and keyword
arguments that exist, and runs the examples that need no data vendor.
The four factsheet archetypes shown above are
multi_assets.py,
strategy.py,
strategy_benchmark.py
and
multi_strategy.py.
The consolidated tracking-error analytics are demonstrated offline in
ex_anti_tracking_error_and_risk.py
for the covariance-based ex-ante view and
ex_post_tracking_error_and_risk.py
for realised EWMA tracking error, whole-sample TE/IR, and EWMA beta/alpha.
Ecosystem
This package is part of an open-source Python stack for quantitative finance — full catalogue at github.com/ArturSepp:
| Package | Purpose |
|---|---|
qis (this package) |
Performance and risk analytics, factsheets, and visualisation |
optimalportfolios |
Portfolio construction and backtesting |
factorlasso |
Sparse factor models and factor covariance estimation |
bbg-fetch |
Bloomberg data fetching |
trendfollowing |
Trend-following systems: closed-form theory and replication |
privateassets |
Private-asset return unsmoothing and capital market assumptions |
goal-based-allocation |
Dynamic MV allocation under regime-switching jump-diffusions |
stochvolmodels |
Stochastic volatility pricing analytics |
vanilla-option-pricers |
Vectorised vanilla option pricers and implied volatility fitters |
Dependency links within the stack: optimalportfolios builds on qis and factorlasso; trendfollowing and privateassets build on qis.
Contributions
If you are interested in extending and improving QIS analytics, please consider contributing to the library.
I have found it is a good practice to isolate general purpose and low level analytics and visualizations, which can be outsourced and shared, while keeping the focus on developing high level commercial applications.
There are a number of requirements:
-
The code is Pep 8 compliant
-
Reliance on common Python data types including numpy arrays, pandas, and dataclasses.
-
Transparent naming of functions and data types with enough comments. Type annotations of functions and arguments is a must.
-
Each submodule has a unit test for core functions and a localised entry point to core functions.
-
Avoid "super" pythonic constructions. Readability is the priority.
Changelog
Release history is maintained in CHANGELOG.md.
ToDos
-
Enhanced documentation and readme examples.
-
Docstrings for key functions.
-
Reporting analytics and factsheets generation enhancing to matplotlib.
License
MIT — see LICENSE.txt.
Disclaimer
QIS package is distributed FREE & WITHOUT ANY WARRANTY under the MIT License.
See the LICENSE.txt in the release for details.
Please report any bugs or suggestions by opening an issue.
Citation
If you use QIS in your research, please cite it as:
@software{sepp2026qis,
title={qis: Implementation of visualisation and reporting analytics for Quantitative Investment Strategies},
author={Sepp, Artur},
year={2026},
version={5.11.1},
url={https://github.com/ArturSepp/QuantInvestStrats}
}
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file qis-5.11.1.tar.gz.
File metadata
- Download URL: qis-5.11.1.tar.gz
- Upload date:
- Size: 614.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
34e43f551dab7db83e52d6c3555c86104eb19000b370128619ae7fe29511ed18
|
|
| MD5 |
1621a7990bb9db0f4128c9c1560ff2e3
|
|
| BLAKE2b-256 |
aa8893a4aa18ebd42a9ae01e5db98d066d645d66d8a35c9da75171611f86e22d
|
File details
Details for the file qis-5.11.1-py3-none-any.whl.
File metadata
- Download URL: qis-5.11.1-py3-none-any.whl
- Upload date:
- Size: 716.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d97ff502b297ddbe2cdfb663eb8058753d16632d70bb86ca42f45673277e1274
|
|
| MD5 |
56014baed48a41a9ccdf6dc6f6275529
|
|
| BLAKE2b-256 |
41a4bd0d26938932f56696aef4d559a7cb88d945885554454991053c6bd5983d
|
