Living with Machines

histLM

Neural Language Models for Historical Research

DiachronicEmb-BigHistData

Tools to train and explore diachronic word embeddings from Big Historical Data

nnanno

nnanno is a collection of tools that sample, annotate and apply computer vision to the Newspaper Navigator dataset

deduplify

A Python tool to search for and remove duplicated files in messy datasets

D3_JS_viz_in_a_Python_Jupyter_notebook

Tutorial code showing how to put a D3 JavaScript visualisation in a Python Jupyter notebook.

alto2txt

Convert ALTO XML to plain text + minimal metadata

dhoxss-text2tech

Materials for the Text to Tech workshop at the Digital Humanities Oxford Summer School

T-Res

A Toponym Resolution Pipeline for Digitised Historical Newspapers

DeezyMatch_tutorials

Collection of tutorials for DeezyMatch (https://github.com/Living-with-machines/DeezyMatch)

github_stats_report

Living with Machines GitHub Stats report

label-studio-converter

Create ready-to-use Label Studio pre-populated JSON files from popular OCR formats.

zooniverse-analysis-workshop

Jupyter Notebooks for processing Zooniverse classification and subject files

lwmdb

A django-based library for managing the Living with Machines newspapers metadata database schema

subsamplr

A tool for representative subsampling

TargetedSenseDisambiguation

Repository for the work on Targeted Sense Disambiguation

TheLivingMachine

Computational Approaches to the Nineteenth-Century Language of Technology

.github

alto2txt2fixture

Converts metadata from alto2txt into JSON data with corresponding relational IDs for ingestion into a relational database

AzureAudit

A tool to audit the contents of Azure Storage

gh_orgstats

GitHub stats for Github Organizations

hmd_url_generator

Generate a weekly update of available British Library Heritage Made Digital Newspapers as a json file

jisc-wrangler

Tool for restructuring data in the JISC 19th Century British Library Newspaper collection

links-in-the-chain

Data visualisations for the "Links in the chain" LwM book chapter

newspapers

Public repository for open access material relating to historical newspapers

OS_jpg_to_geotiff

Create Geotiffs from OS Old Series 1 inch jpgs with 4 clicks.

PressDirectories

Code and Data for Mitchell's Newspaper Press Directories

VisualisingPressDirectories

Source code for cleaning pipeline and web app pairing the Press Directories dataset with general elections results.

wiki2gaz

A series of scripts to create a gazetteer from a Wikipedia and Wikidata dump

wrangle-ukds-trade-directories

Consolidate UKDS Trade Directories and metadata into a better file structure

zoonyper

Code to make it easy to import and process Zooniverse annotations and their metadata in Python/Jupyter Notebooks