gaitsetpy 0.2.0

A Python package for gait analysis using sensor data.

GaitSetPy

GaitSetPy is a Python package for gait analysis and recognition. This package provides tools and algorithms to process and analyze gait data, enabling researchers and developers to build applications for gait recognition and clinical gait assessment.

Features

• Gait data preprocessing
• Feature extraction
• Gait recognition algorithms
• Visualization tools

Supported Datasets

IMU Sensor Based

• Daphnet: https://archive.ics.uci.edu/dataset/245/daphnet+freezing+of+gait

• MobiFall: https://bmi.hmu.gr/the-mobifall-and-mobiact-datasets-2/

• HAR-UP (formerly UPFall): https://sites.google.com/up.edu.mx/har-up/

• URFall: https://fenix.ur.edu.pl/~mkepski/ds/uf.html

• Activity Net - Arduous : https://www.mad.tf.fau.de/research/activitynet/wearable-multi-sensor-gait-based-daily-activity-data/

Pressure Sensor Based

• Physionet Gait in Parkinson's Disease: https://physionet.org/content/gaitpdb/1.0.0/

Installation

From PyPI:

pip install gaitsetpy

From source:

git clone https://github.com/Alohomora-Labs/gaitSetPy.git
python setup.py install

Optionally, also install requirements

pip install -r requirements.txt

Usage

Daphnet Dataset (class-based API)

import gaitsetpy as gsp

# Load dataset via class-based loader
loader = gsp.DaphnetLoader()
data, names = loader.load_data("data/daphnet")

# Create sliding windows and extract features
windows = loader.create_sliding_windows(data, names, window_size=192, step_size=32)
extractor = gsp.GaitFeatureExtractor()
features = extractor.extract_features(windows[0]['windows'], fs=64)

# Optional: visualize using analyzer
from gaitsetpy.eda import SensorStatisticsAnalyzer
analyzer = SensorStatisticsAnalyzer()
analyzer.visualize(
    windows[0]['windows'],
    features,
    sensor_name="shank",
    start_idx=0,
    end_idx=1000,
    num_windows=15
)

HAR-UP Dataset (class-based API)

import gaitsetpy as gsp

# Load HAR-UP data via class-based loader
loader = gsp.HARUPLoader()
harup_data, harup_names = loader.load_data("data/harup")

# Create sliding windows
window_size = 100  # 1 second at 100Hz
step_size = 50     # 0.5 second overlap
windows = loader.create_sliding_windows(harup_data, harup_names, window_size, step_size)

# Extract features using dataset-specific method or feature extractor
features_data = loader.extract_features(windows)

# Train and evaluate a Random Forest (class-based)
rf_model = gsp.RandomForestModel(n_estimators=50, random_state=42, max_depth=10)
rf_model.train(features_data if isinstance(features_data, list) else features)
metrics = rf_model.evaluate(features_data if isinstance(features_data, list) else features)
print(metrics.get('accuracy'))

# Load a saved model (optional)
rf_model.load_model("gaitsetpy/classification/weights/random_forest_model_40_10.pkl")

Documentation

For detailed documentation and API reference, please visit the official documentation.

Contributing

We welcome contributions! Please read our contributing guidelines to get started.

License

This project is licensed under the GNU GPL License. See the LICENSE file for more details.

Contact

For any questions or inquiries, please contact us at [e-mail] or [e-mail].