64 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
1Cansa	1aed22016a	Add functionality to display top middle names and surnames by region and sex with flexible filtering; (#4) ... Implement region-based limiting for cleaner, more focused data views and visualizations	2025-07-03 11:47:23 +02:00
bernard-ng	efd97911d3	feat: create evaluation dataset	2025-07-03 10:16:52 +02:00
bernard-ng	0888d94596	feat: balanced dataset loading	2025-06-30 01:32:10 +02:00
bernard-ng	eb139ee09a	fix: artifacts saving and dataset loading	2025-06-24 21:49:03 +02:00
bernard-ng	fb95c72ab7	fix: lstm model	2025-06-24 09:40:42 +02:00
1Cansa	d8980ec328	Firstnames treatment (#3) ... * feat: name processing added, first name/last name/post name extraction and display of top 10 first names * [FIX] Fix path in __init__.py and modify name analysis * [ENH] Group first names by gender, by region, by region and gender and then group first names common to both sexes by region * Update requirements.txt --------- Co-authored-by: Bernard Ngandu <31113941+bernard-ng@users.noreply.github.com>	2025-06-23 15:37:48 +02:00
bernard-ng	88bb2f207e	docs: add gender inference instructions	2025-06-21 10:53:02 +02:00
bernard-ng	25f1df46d8	feat: improve inference for logreg model	2025-06-21 10:35:48 +02:00
bernard-ng	a46a5f7924	feat: improve inference for logreg model	2025-06-21 10:34:26 +02:00
bernard-ng	33d096f8ff	fix: dataset path	2025-06-20 16:48:03 +02:00
bernard-ng	b20f96a450	fix: dependencies	2025-06-20 16:45:54 +02:00
1Cansa	c829cac51c	Add exploratory data analysis (#1) ... * feat: name processing added, first name/last name/post name extraction and display of top 10 first names * [FIX] Fix path in __init__.py and modify name analysis --------- Co-authored-by: Bernard Ngandu <31113941+bernard-ng@users.noreply.github.com>	2025-06-20 16:41:06 +02:00
bernard-ng	1d58e3ccc4	feat: add gender base models architectures	2025-06-20 16:38:48 +02:00
bernard-ng	f454ba7938	Initial commit	2025-06-19 18:45:11 +02:00