You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Updated dependancy versions in the `poetry.lock` file
- Removed problematic parts of flaky tests tests
- Fixed installation issue with `cupy` extra on macOS
- Fixed `torch.dtype object has no attribute 'kind'` error in`TorchRanker`
Copy file name to clipboardExpand all lines: CHANGELOG.md
+12-1Lines changed: 12 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
8
8
## Unreleased
9
9
10
10
### Added
11
-
-`leave_one_out_mask` function (`rectools.models.nn.transformers.utils.leave_one_out_mask`) for applying leave-one-out validation during transformer models training.([#292](https://github.com/MobileTeleSystems/RecTools/pull/292))
11
+
-`leave_one_out_mask` function (`rectools.models.nn.transformers.utils.leave_one_out_mask`) for applying leave-one-out validation during transformer models training ([#292](https://github.com/MobileTeleSystems/RecTools/pull/292))
12
+
13
+
### Fixed
14
+
- Installation issue with `cupy` extra on macOS ([#293](https://github.com/MobileTeleSystems/RecTools/pull/293))
15
+
-`torch.dtype object has no attribute 'kind'` error in `TorchRanker` ([#293](https://github.com/MobileTeleSystems/RecTools/pull/293))
16
+
12
17
13
18
## [0.15.0] - 17.07.2025
14
19
@@ -19,6 +24,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
19
24
### Fixed
20
25
-[Breaking] Now `LastNSplitter` guarantees taking the last ordered interaction in dataframe in case of identical timestamps ([#288](https://github.com/MobileTeleSystems/RecTools/pull/288))
21
26
27
+
22
28
## [0.14.0] - 16.05.2025
23
29
24
30
### Added
@@ -27,6 +33,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
27
33
-`map_location` and `model_params_update` arguments for the function `load_from_checkpoint` for Transformer-based models. Use `map_location` to explicitly specify the computing new device and `model_params_update` to update original model parameters (e.g. remove training-specific parameters that are not needed anymore) ([#281](https://github.com/MobileTeleSystems/RecTools/pull/281))
28
34
-`get_val_mask_func_kwargs` and `get_trainer_func_kwargs` arguments for Transformer-based models to allow keyword arguments in custom functions used for model training. ([#280](https://github.com/MobileTeleSystems/RecTools/pull/280))
29
35
36
+
30
37
## [0.13.0] - 10.04.2025
31
38
32
39
### Added
@@ -46,6 +53,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
46
53
### Changed
47
54
- Interactions extra columns are not dropped in `Dataset.filter_interactions` method [#267](https://github.com/MobileTeleSystems/RecTools/pull/267)
48
55
56
+
49
57
## [0.11.0] - 17.02.2025
50
58
51
59
### Added
@@ -60,12 +68,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
60
68
61
69
-`ImplicitRanker``rank` method compatible with `Ranker` protocol. `use_gpu` and `num_threads` params moved from `rank` method to `__init__`. [#251](https://github.com/MobileTeleSystems/RecTools/pull/251)
62
70
71
+
63
72
## [0.10.0] - 16.01.2025
64
73
65
74
### Added
66
75
-`ImplicitBPRWrapperModel` model with algorithm description in extended baselines tutorial ([#232](https://github.com/MobileTeleSystems/RecTools/pull/232), [#239](https://github.com/MobileTeleSystems/RecTools/pull/239))
67
76
- All vector models and `EASEModel` support for enabling ranking on GPU and selecting number of threads for CPU ranking. Added `recommend_n_threads` and `recommend_use_gpu_ranking` parameters to `EASEModel`, `ImplicitALSWrapperModel`, `ImplicitBPRWrapperModel`, `PureSVDModel` and `DSSMModel`. Added `recommend_use_gpu_ranking` to `LightFMWrapperModel`. GPU and CPU ranking may provide different ordering of items with identical scores in recommendation table, so this could change ordering items in recommendations since GPU ranking is now used as a default one. ([#218](https://github.com/MobileTeleSystems/RecTools/pull/218))
68
77
78
+
69
79
## [0.9.0] - 11.12.2024
70
80
71
81
### Added
@@ -105,6 +115,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
105
115
### Removed
106
116
-[Breaking]`assume_external_ids` parameter in `recommend` and `recommend_to_items` model methods ([#177](https://github.com/MobileTeleSystems/RecTools/pull/177))
0 commit comments