Add peak-to-peak interval features to tsfresh
Project description
tsfresh_ppi
This package provides some peak-to-peak interval (PPI) variability features to augment tsfresh
[1].
Currently, tsfresh
will find and count peaks using a couple of different methods.
However, it does not measure the variability in timing between those peaks.
Installation
Option 1: Clone this repo. Install prereqs from requirements.txt
. Then install the cloned directory, e.g. with pip3 install -e [repo path]
.
Option 2: Install directly from PyPI (tsfresh-ppi
).
Usage
from tsfresh import extract_features
from tsfresh_ppi import get_fc_parameters
my_signal = ... # some pandas DataFrame
# The default way to extract features with tsfresh looks something like this:
features = extract_features(
my_signal,
...
)
# This is how to get all of the default tsfresh features, plus default PPI features:
fc_params_with_ppi = get_fc_parameters()
features = extract_features(
my_signal,
default_fc_parameters = fc_params_with_ppi,
...
)
References
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tsfresh_ppi-2021.8.29.tar.gz
(6.4 kB
view details)
Built Distribution
File details
Details for the file tsfresh_ppi-2021.8.29.tar.gz
.
File metadata
- Download URL: tsfresh_ppi-2021.8.29.tar.gz
- Upload date:
- Size: 6.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/3.7.2 pkginfo/1.5.0.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2c1106bc81a0215310eefa93d440a338a14f618d0cd4108609a8a6effa9dcde9 |
|
MD5 | 888deeed9bd4c2e979378a52efbbb430 |
|
BLAKE2b-256 | cb719ae083189323ea5c6e7812142cb924c6b25a9428833ed2660edb71f2c476 |
File details
Details for the file tsfresh_ppi-2021.8.29-py3-none-any.whl
.
File metadata
- Download URL: tsfresh_ppi-2021.8.29-py3-none-any.whl
- Upload date:
- Size: 6.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/3.7.2 pkginfo/1.5.0.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 557241c488257cde3c2f6c3bf9c3a011fa9cd100117fe03bbdfbde66d1cb02b8 |
|
MD5 | 9218db57fec5044b69b211a30dca7f05 |
|
BLAKE2b-256 | f0bbc1ad519668f6ac5a45b3642f8a50c164b54a0998e34a95ffe95b8cab0f5f |