GlucoPy

Python Toolbox for glycaemic signal processing

Main Features
Dependencies
Installation from source
Documentation
Examples
Collection of Python Signal Processing Library Repositories
Public Datasets

Main Features

Importing and exporting CGM signals in formats: .csv, .xslx, .xls
Glycaemic signal in units: mg/dL (default), mmol/L
Calculation of metrics like Mean, MODD, TIR, MAGE, BGI, Q-Score, etc.
Automatic summary of the metrics.
Generate Plots for analysis and visualization of the entire data or separated by day, some examples are Box Plot, Frequency Histogram, Trace Plot, Ambulatory Glucose Profile (AGP), etc.
Very easy to use all metrics are calculated calling a method of the class Gframe, and the plots are generated using that same class.

Dependencies

Installation from source

In the GlucoPy directory (same one where you found this file after cloning the repository), run:

pip install .

Documentation

The official documentation is hosted on github.io/GlucoPy/

Examples

All the Metrics are implemented as methods in the glucopy.Gframe class

Create a `Gframe` object from a .csv file

import glucopy as gp

# Read the file
gf = gp.read_csv('path/to/file.csv')

Create a `Gframe` object from a .xslx file

# Read the file
gf = gp.read_xlsx('path/to/file.xlsx')

Create a `Gframe` object from a pandas `DataFrame`

import pandas as pd

# Create a DataFrame
df = pd.read_csv('path/to/file.csv')

gf = gp.Gframe(df)

Create a `Gframe` object from GlucoPy's datasets

# Import the dataset
gf = gp.data("prueba_1")

Calculate some metrics

Check the documentation of Gframe for a complete list of metrics

# Mean
mean = gf.mean()

# MODD
modd = gf.modd()

# TIR
tir = gf.tir()

# MAGE
mage = gf.mage()

# BGI
lbgi = gf.lbgi()
hbgi = gf.hbgi()

Plots

All the plots use a Gframe object as first parameter. Check the documentation of glucopy.plot for a complete list of plots

Ambulatory Glucose Profile (AGP)

gp.plot.agp(gf)

Frequency Histogram

gp.plot.freq(gf)

MAGE Plot

gp.plot.mage(gf)

Collection of Python Signal Processing Library Repositories

Public Datasets

Awesome-CGM

This is a collection of links to publicly available continuous glucose monitoring (CGM) data.
OhioT1DM

The OhioT1DM dataset is available to researchers interested in improving the health and wellbeing of people with type 1 diabetes. It contains 8 weeks worth of data for each of 12 people with type 1 diabetes. a Data Use Agreement (DUA) is required.
ShanghaiT1DM and ShanghaiT2DM

ShanghaiT1DM and ShanghaiT2DM are publicly available Datasets for research purposes, they contain Type 1 (n = 12) and Type 2 (n = 100) diabetic patients in Shanghai, China.
CG Map

A reference resource for characterization of CGM data collected from more than 7,000 non-diabetic individuals, aged 40-70 years.

deigoodle / glucopy Goto Github PK

glucopy's Introduction

GlucoPy

Table of Contents

Main Features

Dependencies

Installation from source

Documentation

Examples

Create a Gframe object from a .csv file

Create a Gframe object from a .xslx file

Create a Gframe object from a pandas DataFrame

Create a Gframe object from GlucoPy's datasets

Calculate some metrics

Plots

Ambulatory Glucose Profile (AGP)

Frequency Histogram

MAGE Plot

Collection of Python Signal Processing Library Repositories

Public Datasets

glucopy's People

Contributors

Stargazers

Watchers

glucopy's Issues

Recommend Projects

Recommend Topics

Recommend Org

Create a `Gframe` object from a .csv file

Create a `Gframe` object from a .xslx file

Create a `Gframe` object from a pandas `DataFrame`

Create a `Gframe` object from GlucoPy's datasets