torch compile and slighly more efficient conversions to torch from po…

…lars (#133)

* torch compile and slighly more efficient conversions to torch from polars

.github/workflows/R_CDM_check_hades.yaml

@@ -75,6 +75,10 @@ jobs:
           extra-packages: any::rcmdcheck
           needs: check
 
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
       - name: setup r-reticulate venv
         shell: Rscript {0}
         run: |

DESCRIPTION

@@ -38,7 +38,7 @@ Suggests:
 Remotes:
     ohdsi/PatientLevelPrediction,
     ohdsi/ResultModelManager
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Encoding: UTF-8
 Config/testthat/edition: 3
 Config/testthat/parallel: TRUE

NEWS.md

@@ -1,6 +1,10 @@
 
 DeepPatientLevelPrediction 2.1.0.999
 ======================
+  - Add an option to use torch compile
+  - More efficient conversions from polars to torch in dataset processing
+  - Automatically detect broken links in docs using github actions
+  - Model initialization made more flexible with classes
 
 DeepPatientLevelPrediction 2.1.0
 ======================

R/Estimator.R

@@ -33,6 +33,7 @@
 #' @param criterion loss function to use
 #' @param earlyStopping If earlyStopping should be used which stops the
 #' training of your metric is not improving
+#' @param compile if the model should be compiled before training, default FALSE
 #' @param metric either `auc` or `loss` or a custom metric to use. This is the
 #' metric used for scheduler and earlyStopping.
 #' Needs to be a list with function `fun`, mode either `min` or `max` and a
@@ -59,6 +60,7 @@ setEstimator <- function(
       useEarlyStopping = TRUE,
       params = list(patience = 4)
     ),
+    compile = FALSE,
     metric = "auc",
     accumulationSteps = NULL,
     seed = NULL) {
@@ -74,6 +76,7 @@ setEstimator <- function(
   checkIsClass(epochs, c("numeric", "integer"))
   checkHigher(epochs, 0)
   checkIsClass(earlyStopping, c("list", "NULL"))
+  checkIsClass(compile, "logical")
   checkIsClass(metric, c("character", "list"))
   checkIsClass(seed, c("numeric", "integer", "NULL"))
 
@@ -100,6 +103,7 @@ setEstimator <- function(
     epochs = epochs,
     device = device,
     earlyStopping = earlyStopping,
+    compile = compile,
     findLR = findLR,
     metric = metric,
     accumulationSteps = accumulationSteps,

inst/python/Dataset.py

@@ -50,7 +50,7 @@ def __init__(self, data, labels=None, numerical_features=None):
             .with_columns(pl.col("rowId") - 1)
             .collect()
         )
-        cat_tensor = torch.tensor(data_cat.to_numpy())
+        cat_tensor = data_cat.to_torch()
         tensor_list = torch.split(
             cat_tensor[:, 1],
             torch.unique_consecutive(cat_tensor[:, 0], return_counts=True)[1].tolist(),
@@ -90,13 +90,8 @@ def __init__(self, data, labels=None, numerical_features=None):
                 )
                 .collect()
             )
-            indices = torch.as_tensor(
-                numerical_data.select(["rowId", "columnId"]).to_numpy(),
-                dtype=torch.long,
-            )
-            values = torch.tensor(
-                numerical_data.select("covariateValue").to_numpy(), dtype=torch.float
-            )
+            indices = numerical_data.select(["rowId", "columnId"]).to_torch(dtype=pl.Int64)
+            values = numerical_data.select("covariateValue").to_torch(dtype=pl.Float32)
             self.num = torch.sparse_coo_tensor(
                 indices=indices.T,
                 values=values.squeeze(),

inst/python/Estimator.py

@@ -99,6 +99,9 @@ def __init__(self, model, model_parameters, estimator_settings):
         self.best_score = None
         self.best_epoch = None
         self.learn_rate_schedule = None
+        torch_compile = estimator_settings.get("compile", False)
+        if torch_compile:
+            self.model = torch.compile(self.model, dynamic=False)
 
     def fit(self, dataset, test_dataset):
         train_dataloader = DataLoader(