Jupyter Notebooks

Four starter notebooks for EEG data analysis with Python.

#	Notebook	Description
1	`01_load_and_plot_session`	Load CSV or stream live, plot all channels
2	`02_detect_blinks`	Eye-blink artifact detection (threshold-based)
3	`03_bandpower_and_alpha`	Band powers via Welch's method, alpha tracking
4	`04_export_features_for_ml`	Windowed features → ML-ready CSV (scikit-learn)

Setup

cd notebooks
pip install -r requirements.txt
pieeg-server --mock &
jupyter lab

Live Streaming Example

import asyncio, json, websockets
 
async def stream_samples(n=1000):
    samples = []
    async with websockets.connect("ws://raspberrypi.local:1616") as ws:
        async for msg in ws:
            frame = json.loads(msg)
            samples.append(frame["channels"])
            if len(samples) >= n:
                break
    return samples

Recording Analysis

import pandas as pd
import matplotlib.pyplot as plt
 
df = pd.read_csv("../recordings/pieeg_20260401_143136.csv")
fig, axes = plt.subplots(4, 4, figsize=(16, 12), sharex=True)
for i, ax in enumerate(axes.flat):
    ax.plot(df.iloc[:, i + 1], linewidth=0.3)
    ax.set_ylabel(f"Ch {i}")
plt.tight_layout()
plt.show()

Lab Streaming Layer Native accelerator