Quickstart

Install

pip install "biosqi[data,ui]"

The base package supports NumPy and delimited-text inputs. The data extra adds WFDB and EDF/BDF readers; ui adds the local FastAPI dashboard.

Open the dashboard

biosqi view

The browser communicates only with a server bound to localhost. Uploaded recordings are processed in memory and are not sent to an external service.

Score from the command line

biosqi score recording.csv \
  --sample-rate 250 \
  --signal-type ecg \
  --window 10 \
  --threshold 0.70 \
  --output result.json

Generate a self-contained report or export the usability mask:

biosqi report recording.npz --signal-type ppg --output report.html
biosqi mask recording.npz --signal-type ppg --output mask.csv

Python

from biosqi.analysis import analyze
from biosqi.io import read_recording
from biosqi.types import SignalType

recording = read_recording(
    "recording.npz",
    signal_type=SignalType.ECG,
)
result = analyze(recording, threshold=0.70)

print(result.scores)
print(result.mask)

For plain .npy, .csv, .tsv, or .txt inputs, provide the sample rate. NPZ archives may include data, sample_rate, and channel_names arrays.