Skip to content

ts-shape¤

PyPI Python License: MIT

ts-shape is a pandas library for manufacturing and IIoT time series. It works on long-format signal data (systime, uuid, value_*) and provides loaders, filters, feature extraction and event detectors for production, quality, engineering, maintenance, energy and supply-chain questions: OEE, downtime, SPC rules, setpoint response, drift and more. Every detector takes a DataFrame and returns a DataFrame, and any detector output can be turned into an OCEL 2.0 or XES event log for process mining.

pip install ts-shape

import ts_shape

# Synthetic data in the standard long format; use a loader or pandas for your own
df = ts_shape.make_timeseries(["press:temp"], n_points=2000, n_outliers=5)

print(ts_shape.profile(df).summary())   # signal kinds, gaps, resets, duplicates

outliers = ts_shape.OutlierDetectionEvents(df, value_column="value_double")
events = outliers.detect_outliers_zscore(threshold=4.0)

log = ts_shape.to_event_log(events, detector="OutlierDetectionEvents.detect_outliers_zscore")
print(log.events[["ocel:activity", "ocel:timestamp", "ts_shape:value"]])

Where to go next¤