Documentation Home

Start here if you want to use EchoTime as a normal Python package. The human path is: load data, call one function, inspect the returned object, then export HTML only if you need to share the result.

import pandas as pd
from echotime import profile_dataset

df = pd.read_csv("my_timeseries.csv").rename(columns={"date": "timestamp"})
profile = profile_dataset(df, domain="energy")
print(profile.to_summary_card_markdown())

pip install echotime
python -c "import numpy as np; from echotime import compare_series; x=np.sin(np.linspace(0,8*np.pi,128)); y=np.sin(np.linspace(0,8*np.pi,128)+0.2); print(compare_series(x,y).to_summary_card_markdown())"

• If you already have your own table, open Getting Started first.
• If you want runnable worked examples, open Tutorials.
• If you only need integration details later, keep Advanced Integrations for last.

Getting Started

Start with your own CSV, DataFrame, or two columns and get to a first result quickly.

Tutorials

Runnable examples in the style of a human tutorial: load data, call a function, inspect the result.

API Reference

The public compare/profile surface and the result objects you will actually call from Python.

Methods Atlas

Audit EchoTime's current similarity stack, the 127 extracted methods from ts_similarity_package_v2_pkg, and the formulas behind each one.

Scenarios

Where EchoTime fits across medicine, engineering, product, and research.

Ecosystem

How EchoTime complements sktime, tsfresh, DTAIDistance, and others.

Advanced Integrations

Tool-calling and agent wrappers live here when you need them, not before.