API reference

API Reference Overview

On this page4

This page lists every module in the FinLab package and what each one does. Writing a strategy usually takes four of them, in this order:

from finlab import data, backtest

data.set_market('us')
close = data.get('price:adj_close')            # finlab.data: load data
position = close >= close.rolling(300).max()   # FinlabDataFrame: write the rule
report = backtest.sim(position, resample='M')  # finlab.backtest: backtest
report.display()                               # finlab.report: read the results

Look up the others when you need them. Each page opens with a "Which function to use" table, then documents every function with its call, parameters and defaults, return value and examples.

From data to backtest

Module	Purpose
finlab	Sign in to FinLab and manage your credentials.
finlab.data	Load U.S. and other market data, search datasets, set the stock universe and cache, and compute technical indicators.
FinlabDataFrame	Align data of different frequencies, write selection rules, take the top names by rank, and set entry and exit signals.
finlab.backtest	Turn a position signal into a historical backtest, with rebalancing, stops and trading costs.
finlab.report	Read the backtest report: metrics, equity curve, trade log, uploading and sharing.

Analyze and improve a strategy

Module	Purpose
finlab.analysis	Check liquidity, MAE/MFE, stability across periods, drawdowns and excess return.
finlab.optimize	Backtest every combination of several conditions and compare them.
finlab.tools	Event studies and factor analysis.
finlab.ml	Build machine-learning features and labels and train prediction models.
finlab.plot	Plot price candlesticks, treemaps, radar and river charts of financial data, and strategy performance.

Combine strategies and trade live

Module	Purpose
finlab.portfolio	Combine strategies, allocate weights, and sync positions with the cloud.
finlab.online	Connect broker accounts, compare holdings and place orders.
finlab.market	Define a market's price data, benchmark and trading rules, or add a market of your own.

Next steps

Quickstart Run your first backtest in five minutes.
Module architecture How the modules fit together.
Load data Fundamentals, filings and how to find a dataset's name.
Backtesting Rebalance frequency, stops, fees and the trade log.

Was this page helpful?