Discover @jhajagos Open Source projects

Janos Hajagos (@jhajagos)

jhajagos

Stars
51
Global Rank 325,088 (Top 12 %)
Followers 26
Following 7
Registered about 11 years ago
Most used languages

Python
62.5 %

Jupyter Notebook
18.8 %

PLpgSQL 6.3 %

PLSQL 6.3 %

SQL 6.3 %

DocGraph

Code related to DocGraph analysis

health-open-data-workshop

Materials and reproducible workflows for working with health care data

Jupyter Notebook

RxNormPrescribePostgreSQL

Code for working with the RxNorm Current Prescribable Content in a PostgreSQL environment

CensusGeographyTools

A set of tools for working with the summary files from the US Census

Jupyter Notebook

RxNormRDF

A script to convert RxNorm to RDF

Dockers4HealthCareDB2HDF52ML

Set of of dockers for building HDF5 for machine learning from health care data stored in the OHDSI DB

PreparedSource2OHDSI

Spark based mapper for converting EHR data to OHDSI

TransformDBtoHDF5ML

The library transforms rows from a relational database table into a nested document and then to a standard matrix file format. The document structure consists of nested dictionaries and is formatted in a human readable JSON format. The self describing matrix format is HDF5 which can be read by a wide range of scientific programming environments including: Matlab, Ccikits via h5py, Mathematica and R. This code started out as a mapper for relational data into a format that could be used to easily train machine learning algorithms for hospital readmission and quality work. The examples in the tests are formatted around this use case. The two programs "build_document_mapping_from_db.py" and "build_hdf5_matrix_from_document.py" are not limited to the readmission use case and have been designed to scale with data size.

ExcelBlackBox

Code for treating an Excel Spreadsheet as function which takes input and produces an ouput. The code requires that you have Excel installed on MS Windows machine with Python and the win32 library.

SynthMedTopia

Code for generating synthetic health care data and transforming real and synthetic data into a format for machine learning

MedicarePrescriberAnalysis

An analysis of the files released by ProPublica for the Prescriber Data

DataExtractTransformScore

A pipeline for extracting and transforming data

ParsingHealthKitExport

Notebooks and analysis for extracting out your data from Apple HealthKit export

Jupyter Notebook

CommonDataModelMapper

Utility functions and classes for mapping code to a common data model

HealthcareAnalyticTools

A repository for integrating and analyzing public data sources for healthcare in the United States.

UMLS2SKOS