Commit Graph

26 Commits

Author SHA1 Message Date
a7f2413acb loaders: parquet — preserve column dtypes from arrow schema 2026-03-11 16:52:37 +00:00
6a0db0c9af requirements: pin numpy<2 (breaks downstream) 2026-03-05 16:52:37 +00:00
1b6d4029a7 eval: plots — switch to plotnine for ggplot-style 2026-02-27 16:52:37 +00:00
19e33bbcc4 transforms: feature — drop deprecated FeatureUnion 2026-02-21 16:52:37 +00:00
e82d2e5ba6 tests: cover the date-parsing edge cases 2026-02-15 16:52:37 +00:00
52e2e1abff loaders: csv — chunked reading for >1GB files 2026-02-09 16:52:37 +00:00
c3cf8fd49c eval: metrics — add F1 + ROC AUC 2026-02-03 16:52:37 +00:00
02da0820a2 transforms: clean — handle inf and nan separately 2026-01-28 16:52:37 +00:00
082409ef95 loaders: parquet — handle nullable columns 2026-01-22 16:52:37 +00:00
235b9fcf34 eval: plots — fix legend ordering 2026-01-16 16:52:37 +00:00
95c97b76c3 loaders: drop deprecated read_excel path 2026-01-10 16:52:37 +00:00
f760a83d87 setup: bump python_requires from 3.10 to 3.11 2026-01-04 16:52:37 +00:00
ef3c863eb0 transforms: clean — log row drop counts per rule 2025-12-29 16:52:37 +00:00
6ec8867a7e eval: metrics — handle multi-class classification 2025-12-23 16:52:37 +00:00
0046842ec5 tests: add property-based tests for clean.py via hypothesis 2025-12-17 16:52:37 +00:00
1940e3aa03 loaders: parquet — preserve column dtypes from arrow schema 2025-12-11 16:52:37 +00:00
14f2b3693d requirements: pin numpy<2 (breaks downstream) 2025-12-05 16:52:37 +00:00
975d3a843b eval: plots — switch to plotnine for ggplot-style 2025-11-29 16:52:37 +00:00
4fa681cb4c transforms: feature — drop deprecated FeatureUnion 2025-11-23 16:52:37 +00:00
449c88c0d5 tests: cover the date-parsing edge cases 2025-11-17 16:52:37 +00:00
e24af4cb54 loaders: csv — chunked reading for >1GB files 2025-11-11 16:52:37 +00:00
008871890d eval: metrics — add F1 + ROC AUC 2025-11-05 16:52:37 +00:00
2940209d38 transforms: clean — handle inf and nan separately 2025-10-30 16:52:37 +00:00
64fb019c06 loaders: parquet — handle nullable columns 2025-10-24 16:52:37 +00:00
2bdc62409a init: scaffold ml-pipeline-utils repository structure 2025-10-18 16:52:37 +00:00
35da2c819e Initial commit 2026-04-16 17:22:29 +02:00