dsipts 1.1.12__py3-none-any.whl → 1.1.15__py3-none-any.whl

{dsipts-1.1.12.dist-info → dsipts-1.1.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dsipts
-Version: 1.1.12
+Version: 1.1.15
 Summary: Unified library for timeseries modelling
 Author-email: Andrea Gobbi <agobbi@fbk.eu>
 Project-URL: Homepage, https://github.com/DSIP-FBK/DSIPTS
@@ -398,6 +398,8 @@ and then open the url (http://127.0.0.1:43800)[http://127.0.0.1:43800]. It will
 
 
 ## TODO
+[ ] some models can not work in a non-autoregressive way (target past variable is required). Relax some constraints in the forward loop can help this
+
 [ ] reduce test time 
 
 [ ] add pre-commit hook for code checking (`ruff check --ignore E501,E722 .`)
@@ -406,15 +408,12 @@ and then open the url (http://127.0.0.1:43800)[http://127.0.0.1:43800]. It will
 
 [ ] clean code and standardize documentation
 
-[ ] add more sintetic data
-
 [ ] check all the code in the README 
 
 [ ] check architecture description (which model can be used under certain assumption) 
 
 [ ] complete the classification part (loss function + inference step)
 
-
 [ ] check D3VAE, it seems broken in some configurations
 
 [ ] add hybrid models https://www.sciencedirect.com/science/article/pii/S138912862400118X
@@ -425,11 +424,60 @@ and then open the url (http://127.0.0.1:43800)[http://127.0.0.1:43800]. It will
 
 [ ] add https://github.com/decisionintelligence/pathformer
 
-[x] add Duet
+[ ] in 1.1.5 we split the future and past categorical variables. D3VAE &^ Diffusion to be revised 
+
+[ ] all snippet of code and notebook must be review in 1.1.5 (categorical past and future, embedding layer parameters)
 
-[x] add categorical support to Crossformer, Samformer 
 
-[ ] in 1.1.5 we split the future and past categorical variables. D3VAE, Diffusion, TTM need to be revised 
 
-[ ] all snippet of code and notebook must be review in 1.1.5 (categorical past and future, embedding layer parameters)
+## 1.1.14 (2025-12-02)
+- Add CHANGELOG to the pip page
+- Bug fixing for non autoregressive models
+- Added TimesNet, TimeKAN
+- Added 0 shot and full shot TTM
+- added more option parameter to define an experiment (`split_params`, `optim_config` and `train_config`)
+## 1.1.13 (2025-12-02)
+
+- Added weight for the WeightedRandomSampler (only for the training part)
+- Bug fixing when using groups in the categorical variables
+- TTM fixed for working with zeropad for shorter sequences and future covariates
+
+## 1.1.12 (2025-11-07)
+- Bug fixing dynamo stuff for `TTM`
+- Bug fixing loading weights after training process ('dynamo module can not load weights`)
+- Force to not compile some models (there are piece of code that are not aligned with dynamo)
+- Bug fixing test configurations
 
+## 1.1.11 (2025-11-06)
+- Added `torch.compile` for better performance on recent GPU
+- Stable `TTM` model according to version 1.1.5, still under debug, use at your own risk
+- Bux Fixing `cprs` inference (now produces 3 quantiles: `[0.05, 0.5, 0.95]`). The `persistence_weight` is the value of `alpha` in the paper (between 0 and 1)
+
+## 1.1.9 (2025-09-19)
+- Added `cprs` https://arxiv.org/pdf/2412.15832v1 loss function. In this case use the quantile parameter to ask for the ensembles: `quantiles = [1,2,3,4,5,6,7,8,9,10]` will create 10 ensembles. For now the inference part will return just the mean, TODO: estimate a confidence interval with the ensembles 
+- Added `long_lag` the L1 error will be modulated with a linear weight depending on the lag in the future: the penalization goes from `1` to `persistence_weight`
+
+## 1.1.8 (2025-09-12)
+- Added `Simple` model (just two linear layers)
+
+## 1.1.7 (2025-09-08)
+- bug fixing `DilatedConv`
+## 1.1.5 (2025-08-29)
+- rewriting most of the modules for handling different future and past categorical variables
+- extension of categorical and future covariates in almost all the models
+- `uv` full management of the package
+- refactoring almost all the structure and documentation
+
+## 1.1.4 (2025-08-22)
+- added `restart: true` tro model configuration to restart the training procedure: carefurl the max_epochs should be increased if you need to retrain
+
+## 1.1.4 (2025-07-29)
+- bug fixing tuner learning rate
+- added TTM model and TimeXer
+- added compatibility with newer version of lightening and torch
+
+## 1.1.1 
+- added [SAM optimizer](https://arxiv.org/pdf/2402.10198) 
+```bash
+ python train.py  --config-dir=config_test --config-name=config architecture=itransformer dataset.path=/home/agobbi/Projects/ExpTS/data train_config.dirpath=tmp inference=tmp model_configs.optim=SAM +optim_config.rho=0.5
+ ```

{dsipts-1.1.12.dist-info → dsipts-1.1.15.dist-info}/RECORD

@@ -1,11 +1,12 @@
-dsipts/__init__.py,sha256=UWmrBJ2LLoRCKLOyTBSJAw9n31o8ZwNjLoRAax5Wll8,1694
+dsipts/__init__.py,sha256=2KK6XbUewsjmQQ6-zNMKIcFP01jtcXskcwr3qZwQToE,1822
+dsipts/version.py,sha256=-YHzv8tja4CPgI4M3Z_0Bj8CLGmAigr5FWkvYuc_I64,22
 dsipts/data_management/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dsipts/data_management/monash.py,sha256=aZxq9FbIH6IsU8Lwou1hAokXjgOAK-wdl2VAeFg2k4M,13075
 dsipts/data_management/public_datasets.py,sha256=yXFzOZZ-X0ZG1DoqVU-zFmEGVMc2033YDQhRgYxY8ws,6793
 dsipts/data_structure/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-dsipts/data_structure/data_structure.py,sha256=KVkjTVjc7NznJIou4LYGzMbzE7ye-K3ll65GEgn2qKg,60814
+dsipts/data_structure/data_structure.py,sha256=QO2z0gtR2lv1t9DuYF3S1LSz1Ecux0CjL1G9lT5lGaY,64928
 dsipts/data_structure/modifiers.py,sha256=qlry9dfw8pEE0GrvgwROZJkJ6oPpUnjEHPIG5qIetss,7948
-dsipts/data_structure/utils.py,sha256=QwfKPZgSy6DIw5n6ztOdPJIAnzo4EnlMTgRbpiWnyko,6593
+dsipts/data_structure/utils.py,sha256=ZL-z_InmFUkge5kQoHSrev1t6nyve9sTYTVeA75Or-I,6689
 dsipts/models/Autoformer.py,sha256=nUQvPC_qtajLT1AHdNJmF_P3ZL01j3spkZ4ubxdGF3g,8497
 dsipts/models/CrossFormer.py,sha256=ClW6H_hrtLJH0iqTC7q_ya_Bwc_Xu-0lpAN5w2DSUYk,6526
 dsipts/models/D3VAE.py,sha256=d1aY6kGjBSxZncN-KPWpdUGunu182ng2QFInGFrKYQM,6903
@@ -17,19 +18,21 @@ dsipts/models/ITransformer.py,sha256=2WXqqEvnWH2DqRQyXfGm4Eg4_q32GFy2XnNeoTl-KmY
 dsipts/models/Informer.py,sha256=gxCdU2KkNhadyMujBA5A0eP6SPN4Q0IkEIogLYwvz5k,6970
 dsipts/models/LinearTS.py,sha256=vXaGpbbkfdpzpTEWZ1hs6QI6j3vDvevD3SyKQXo6Sdg,9151
 dsipts/models/PatchTST.py,sha256=1O09cPMg8USdkt5q6szTiz5dIY45kizsf6gt6vLKnQo,9119
-dsipts/models/Persistent.py,sha256=URwyaBb0M7zbPXSGMImtHlwC9XCy-OquFCwfWvn3P70,1249
+dsipts/models/Persistent.py,sha256=CPHLgqAIPWbxYqzCNpxB2kh8J2-LJsvrbv9OVC72A8o,1301
 dsipts/models/RNN.py,sha256=RnsRDAQ2z5-XNaJVZd6Q7z23WvPR2uLVdi7BNQyF7QE,9685
 dsipts/models/Samformer.py,sha256=Kt7B9ID3INtFDAVKIM1LTly5-UfKCaVZ9uxAJmYv6B4,5606
 dsipts/models/Simple.py,sha256=8wRSO-gh_Z6Sl8fYMV-RIXIL0RrO5u5dDtsaq-OsKg0,3960
 dsipts/models/TFT.py,sha256=JiI90ikfP8aaR_rtczu8CyGMNLTgml13aYQifgIC_yo,13888
 dsipts/models/TIDE.py,sha256=S1KlKqFOR3jJ9DDiTqeaKvya9hYBsNHBVqwJsYX3FLU,13094
-dsipts/models/TTM.py,sha256=lOOo5dR5nOmf37cND6C8ft8TVl0kzNeraIuABw7eI5g,5897
+dsipts/models/TTM.py,sha256=CGKtO992_ty5_AX27llMd1TsvKLP8ZKpR8Xbx1F8Ws4,6625
+dsipts/models/TimeKAN.py,sha256=bJEIJZIksi0jhN9ZttXezATwxJj9DkWjO1WNwDD5Fbw,4686
 dsipts/models/TimeXER.py,sha256=EkmlHfT2RegY6Ce6q8EUEV1a_WZ6SkYibnOZXqsyd_8,7111
+dsipts/models/TimesNet.py,sha256=1OekvmqZidfPqoSMFsG7pK6Xcgen8IMTEu0n9ZQMEPc,3895
 dsipts/models/VQVAEA.py,sha256=sNJi8UZh-10qEIKcZK3SzhlOFUUjvqjoglzeZBFaeZM,13789
 dsipts/models/VVA.py,sha256=BnPkJ0Nzue0oShSHZVRNlf5RvT0Iwtf9bx19vLB9Nn0,11939
 dsipts/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-dsipts/models/base.py,sha256=Gqsycy8ZXGaIVx9vvmYRpBCqdUxGE4tvC5ltgxlpEYY,19640
-dsipts/models/base_v2.py,sha256=03cueZExRhkJyBVIHuUPB8sjsCd5Go1HJAR81CADg-c,19896
+dsipts/models/base.py,sha256=aWvtDiBnmONsJ96tgaZRewB_yrqI8yvlAlH6PdpWrLA,20099
+dsipts/models/base_v2.py,sha256=BNmBQXMDnGsZABu0nOu8d3f3anNQZbgNBCwlMr-k8lQ,20346
 dsipts/models/utils.py,sha256=kjTwyktNCFMpPUy6zoleBCSKlvMvK_Jkgyh2T1OXg3E,24497
 dsipts/models/autoformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dsipts/models/autoformer/layers.py,sha256=xHt8V1lKdD1cIvgxXdDbI_EqOz4zgOQ6LP8l7M1pAxM,13276
@@ -64,6 +67,10 @@ dsipts/models/samformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG
 dsipts/models/samformer/utils.py,sha256=62p5fzippKwZpqZBQghrHyA_ANeaFa-TC5EM4L6Q7DE,5583
 dsipts/models/tft/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dsipts/models/tft/sub_nn.py,sha256=6UDI0BvxEcF5N1_Wx3-WL0PO99k8QtI7JTsEAaosb5k,8881
+dsipts/models/timekan/Layers.py,sha256=T-saVZFYHkMtbXgD8eIp2q_ZM4fcItNzw4PUo4KC-gM,10771
+dsipts/models/timekan/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dsipts/models/timesnet/Layers.py,sha256=Jh42klg2QFSnE1vLH35uZXp8A8xo6cvj3d3gTuvym64,3460
+dsipts/models/timesnet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dsipts/models/timexer/Layers.py,sha256=-QG4a70sBQFoRoE6CfisOkKhm4kIdB21DBtQ4V-7fHw,4699
 dsipts/models/timexer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dsipts/models/ttm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -76,7 +83,7 @@ dsipts/models/vva/minigpt.py,sha256=bg0JddqSD322uxSGexen3nPXL_hGTsk3vNLR62d7-w8,
 dsipts/models/vva/vqvae.py,sha256=RzCQ_M9xBprp7_x20dSV3EQqlO0FjPUGWV-qdyKrQsM,19680
 dsipts/models/xlstm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dsipts/models/xlstm/xLSTM.py,sha256=ZKZZmffmIq1Vb71CR4GSyM8viqVx-u0FChxhcNgHub8,10081
-dsipts-1.1.12.dist-info/METADATA,sha256=nxE2kAg9RvG5Py27sMNbQ-mUIu9mtZrDo2WocLpJdQ4,24795
-dsipts-1.1.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dsipts-1.1.12.dist-info/top_level.txt,sha256=i6o0rf5ScFwZK21E89dSKjVNjUBkrEQpn0-Vij43748,7
-dsipts-1.1.12.dist-info/RECORD,,
+dsipts-1.1.15.dist-info/METADATA,sha256=1i5fPSZJxFoQPkvf-PVwHf6faoD6vFhixMDucbowQdM,27477
+dsipts-1.1.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dsipts-1.1.15.dist-info/top_level.txt,sha256=i6o0rf5ScFwZK21E89dSKjVNjUBkrEQpn0-Vij43748,7
+dsipts-1.1.15.dist-info/RECORD,,