Repository files navigation

QuantStats Python library that performs portfolio profiling, allowing quants and portfolio managers to understand their performance better by providing them with in-depth analytics and risk metrics.

Changelog »

1. quantstats.stats - for calculating various performance metrics, like Sharpe ratio, Win rate, Volatility, etc.
2. quantstats.plots - for visualizing performance, drawdowns, rolling statistics, monthly returns, etc.
3. quantstats.reports - for generating metrics reports, batch plotting, and creating tear sheets that can be saved as an HTML file.

Run probabilistic risk analysis with built-in Monte Carlo simulations:

mc=qs.stats.montecarlo(returns,sims=1000,bust=-0.20,goal=0.50)print(f"Bust probability:{mc.bust_probability:.1%}")print(f"Goal probability:{mc.goal_probability:.1%}")mc.plot()

Full Monte Carlo documentation »

%matplotlibinlineimportquantstatsasqs# extend pandas functionality with metrics, etc.qs.extend_pandas()# fetch the daily returns for a stockstock=qs.utils.download_returns('META')# show sharpe ratioqs.stats.sharpe(stock)# or using extend_pandas() :)stock.sharpe()

Output:

0.7604779884378278

qs.plots.snapshot(stock,title='Facebook Performance',show=True)# can also be called via:# stock.plot_snapshot(title='Facebook Performance', show=True)

Output:

You can create 7 different report tearsheets:

1. qs.reports.metrics(mode='basic|full", ...) - shows basic/full metrics
2. qs.reports.plots(mode='basic|full", ...) - shows basic/full plots
3. qs.reports.basic(...) - shows basic metrics and plots
4. qs.reports.full(...) - shows full metrics and plots
5. qs.reports.html(...) - generates a complete report as html

Let's create an html tearsheet:

# benchmark can be a pandas Series or tickerqs.reports.html(stock,"SPY")

Output will generate something like this:

View original html file

To view a complete list of available methods, run:

[fforfindir(qs.stats)iff[0]!='_']

['avg_loss','avg_return','avg_win','best','cagr','calmar','common_sense_ratio','comp','compare','compsum','conditional_value_at_risk','consecutive_losses','consecutive_wins','cpc_index','cvar','drawdown_details','expected_return','expected_shortfall','exposure','gain_to_pain_ratio','geometric_mean','ghpr','greeks','implied_volatility','information_ratio','kelly_criterion','kurtosis','max_drawdown','monthly_returns','montecarlo','montecarlo_cagr','montecarlo_drawdown','montecarlo_sharpe','outlier_loss_ratio','outlier_win_ratio','outliers','payoff_ratio','profit_factor','profit_ratio','r2','r_squared','rar','recovery_factor','remove_outliers','risk_of_ruin','risk_return_ratio','rolling_greeks','ror','sharpe','skew','sortino','adjusted_sortino','tail_ratio','to_drawdown_series','ulcer_index','ulcer_performance_index','upi','value_at_risk','var','volatility','win_loss_ratio','win_rate','worst']

[fforfindir(qs.plots)iff[0]!='_']

['daily_returns','distribution','drawdown','drawdowns_periods','earnings','histogram','log_returns','monthly_heatmap','montecarlo','montecarlo_distribution','returns','rolling_beta','rolling_sharpe','rolling_sortino','rolling_volatility','snapshot','yearly_returns']

*** Full documentation coming soon ***

QuantStats analyzesreturn series (daily, weekly, monthly returns), not discrete trade data. This means:

• Win Rate = percentage of periods with positive returns
• Consecutive Wins/Losses = consecutive positive/negative return periods
• Payoff Ratio = average winning period return / average losing period return
• Profit Factor = sum of positive returns / sum of negative returns

These metrics arevalid and useful for:

• Systematic/algorithmic strategies with regular rebalancing
• Analyzing return-series behavior over time
• Comparing strategies on a period-by-period basis

Fordiscretionary traders with multi-day trades, these period-based metrics may differ from trade-level statistics. A single 5-day trade might span 3 positive days and 2 negative days - QuantStats would count these as 3 "wins" and 2 "losses" at the daily level.

This is consistent with how all return-based analytics work (Sharpe ratio, Sortino ratio, drawdown analysis, etc.) - they operate on return periods, not discrete trade entries/exits.

In the meantime, you can get insights as to optional parameters for each method, by using Python'shelp method:

help(qs.stats.conditional_value_at_risk)

Help on function conditional_value_at_risk in module quantstats.stats:conditional_value_at_risk(returns, sigma=1, confidence=0.99)    calculates the conditional daily value-at-risk (aka expected shortfall)    quantifies the amount of tail risk an investment

Install usingpip:

$ pip install quantstats --upgrade --no-cache-dir

Install usingconda:

$ conda install -c ranaroussi quantstats

• Python >= 3.10
• pandas >= 1.5.0
• numpy >= 1.24.0
• scipy >= 1.11.0
• matplotlib >= 3.7.0
• seaborn >= 0.13.0
• tabulate >= 0.9.0
• yfinance >= 0.2.40
• plotly >= 5.0.0 (optional, for usingplots.to_plotly())

This is a new library... If you find a bug, pleaseopen an issue.

If you'd like to contribute, a great place to look is theissues marked with help-wanted.

For some reason, I couldn't find a way to tell seaborn not to return themonthly returns heatmap when instructed to save - so even if you save the plot (by passingsavefig={...}) it will still show the plot.

QuantStats is distributed under theApache Software License. See theLICENSE.txt file in the release for details.

Please drop me a note with any feedback you have.

Ran Aroussi