0.14.35

tests use accelerator="cpu"

Author: bartzbeielstein

notebooks/00_spotPython_tests.ipynb

@@ -4119,6 +4119,101 @@
         "total_sum\n"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/Users/bartz/miniforge3/envs/spotCondaEnv/lib/python3.11/site-packages/lightning/pytorch/utilities/parsing.py:198: Attribute 'act_fn' is an instance of `nn.Module` and is already saved during checkpointing. It is recommended to ignore them using `self.save_hyperparameters(ignore=['act_fn'])`.\n",
+            "GPU available: True (mps), used: True\n",
+            "TPU available: False, using: 0 TPU cores\n",
+            "IPU available: False, using: 0 IPUs\n",
+            "HPU available: False, using: 0 HPUs\n",
+            "\n",
+            "  | Name   | Type       | Params | In sizes | Out sizes\n",
+            "-------------------------------------------------------------\n",
+            "0 | layers | Sequential | 15.9 K | [8, 10]  | [8, 1]   \n",
+            "-------------------------------------------------------------\n",
+            "15.9 K    Trainable params\n",
+            "0         Non-trainable params\n",
+            "15.9 K    Total params\n",
+            "0.064     Total estimated model params size (MB)\n",
+            "/Users/bartz/miniforge3/envs/spotCondaEnv/lib/python3.11/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:441: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n",
+            "/Users/bartz/miniforge3/envs/spotCondaEnv/lib/python3.11/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:441: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n",
+            "`Trainer.fit` stopped: `max_epochs=2` reached.\n",
+            "/Users/bartz/miniforge3/envs/spotCondaEnv/lib/python3.11/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:441: The 'test_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.\n"
+          ]
+        },
+        {
+          "data": {
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+              "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+              "│<span style=\"color: #008080; text-decoration-color: #008080\">         hp_metric         </span>│<span style=\"color: #800080; text-decoration-color: #800080\">      29018.087890625      </span>│\n",
+              "│<span style=\"color: #008080; text-decoration-color: #008080\">         val_loss          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">      29018.087890625      </span>│\n",
+              "└───────────────────────────┴───────────────────────────┘\n",
+              "</pre>\n"
+            ],
+            "text/plain": [
+              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+              "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+              "│\u001b[36m \u001b[0m\u001b[36m        hp_metric        \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m     29018.087890625     \u001b[0m\u001b[35m \u001b[0m│\n",
+              "│\u001b[36m \u001b[0m\u001b[36m        val_loss         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m     29018.087890625     \u001b[0m\u001b[35m \u001b[0m│\n",
+              "└───────────────────────────┴───────────────────────────┘\n"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from torch.utils.data import DataLoader\n",
+        "from spotPython.data.diabetes import Diabetes\n",
+        "from spotPython.light.regression.netlightregression import NetLightRegression\n",
+        "from torch import nn\n",
+        "import lightning as L\n",
+        "\n",
+        "\n",
+        "def test_net_light_regression_class():\n",
+        "    BATCH_SIZE = 8\n",
+        "\n",
+        "    dataset = Diabetes()\n",
+        "    train_loader = DataLoader(dataset, batch_size=BATCH_SIZE)\n",
+        "    test_loader = DataLoader(dataset, batch_size=BATCH_SIZE)\n",
+        "    val_loader = DataLoader(dataset, batch_size=BATCH_SIZE)\n",
+        "\n",
+        "    net_light_regression = NetLightRegression(\n",
+        "        l1=128,\n",
+        "        epochs=10,\n",
+        "        batch_size=BATCH_SIZE,\n",
+        "        initialization=\"Default\",\n",
+        "        act_fn=nn.ReLU(),\n",
+        "        optimizer=\"Adam\",\n",
+        "        dropout_prob=0.1,\n",
+        "        lr_mult=0.1,\n",
+        "        patience=5,\n",
+        "        _L_in=10,\n",
+        "        _L_out=1,\n",
+        "        _torchmetric=\"mean_squared_error\",\n",
+        "    )\n",
+        "    trainer = L.Trainer(\n",
+        "        max_epochs=2,\n",
+        "        enable_progress_bar=False,\n",
+        "    )\n",
+        "    trainer.fit(net_light_regression, train_loader, val_loader)\n",
+        "    res = trainer.test(net_light_regression, test_loader)\n",
+        "    # test if the entry 'hp_metric' is in the res dict\n",
+        "    assert \"hp_metric\" in res[0].keys()\n",
+        "\n",
+        "test_net_light_regression_class()"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -4143,7 +4238,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.11.8"
+      "version": "3.11.7"
     }
   },
   "nbformat": 4,

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotpython"
-version = "0.14.34"
+version = "0.14.35"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]

src/spotPython/data/lightdatamodule.py

@@ -4,7 +4,6 @@
 from typing import Optional
 
 
-
 class LightDataModule(L.LightningDataModule):
     """
     A LightningDataModule for handling data.
@@ -94,7 +93,6 @@ def __init__(
         self.num_workers = num_workers
         self.scaler = scaler
 
-
     def prepare_data(self) -> None:
         """Prepares the data for use."""
         # download
@@ -157,12 +155,12 @@ def setup(self, stage: Optional[str] = None) -> None:
                 data_tensors_train = [data.clone().detach().requires_grad_(True) for data, target in self.data_train]
                 target_tensors_train = [target.clone().detach() for data, target in self.data_train]
                 self.data_train = TensorDataset(torch.stack(data_tensors_train), torch.stack(target_tensors_train))
-                #print(self.data_train)
+                # print(self.data_train)
                 self.data_val = [(self.scaler.transform(data), target) for data, target in self.data_val]
                 data_tensors_val = [data.clone().detach().requires_grad_(True) for data, target in self.data_val]
                 target_tensors_val = [target.clone().detach() for data, target in self.data_val]
                 self.data_val = TensorDataset(torch.stack(data_tensors_val), torch.stack(target_tensors_val))
-               
+
         # Assign test dataset for use in dataloader(s)
         if stage == "test" or stage is None:
             print(f"test_size: {test_size} used for test dataset.")
@@ -174,7 +172,7 @@ def setup(self, stage: Optional[str] = None) -> None:
                 data_tensors_test = [data.clone().detach().requires_grad_(True) for data, target in self.data_test]
                 target_tensors_test = [target.clone().detach() for data, target in self.data_test]
                 self.data_test = TensorDataset(torch.stack(data_tensors_test), torch.stack(target_tensors_test))
-               
+
         # if stage == "predict" or stage is None:
         #     print(f"test_size, full_train_size: {test_size}, {full_train_size}")
         #     generator_predict = torch.Generator().manual_seed(self.test_seed)
@@ -194,9 +192,13 @@ def setup(self, stage: Optional[str] = None) -> None:
             )
             if self.scaler is not None:
                 self.data_predict = [(self.scaler.transform(data), target) for data, target in self.data_predict]
-                data_tensors_predict= [data.clone().detach().requires_grad_(True) for data, target in self.data_predict]
+                data_tensors_predict = [
+                    data.clone().detach().requires_grad_(True) for data, target in self.data_predict
+                ]
                 target_tensors_predict = [target.clone().detach() for data, target in self.data_predict]
-                self.data_predict = TensorDataset(torch.stack(data_tensors_predict), torch.stack(target_tensors_predict))
+                self.data_predict = TensorDataset(
+                    torch.stack(data_tensors_predict), torch.stack(target_tensors_predict)
+                )
 
     def train_dataloader(self) -> DataLoader:
         """
@@ -297,5 +299,3 @@ def predict_dataloader(self) -> DataLoader:
         # apply fit_transform to the val data
         return DataLoader(self.data_test, batch_size=self.batch_size, num_workers=self.num_workers)
         return DataLoader(self.data_predict, batch_size=len(self.data_predict), num_workers=self.num_workers)
-
-

src/spotPython/utils/init.py

@@ -407,7 +407,7 @@ def fun_control_init(
         "prep_model_name": prep_model_name,
         "progress_file": progress_file,
         "save_model": False,
-        "scaler":scaler,
+        "scaler": scaler,
         "scenario": scenario,
         "seed": seed,
         "show_batch_interval": 1_000_000,

src/spotPython/utils/scaler.py

@@ -1,9 +1,11 @@
 import torch
 
+
 class TorchStandardScaler:
     """
     A class for scaling data using standardization with torch tensors.
     """
+
     def fit(self, x):
         """
         Compute the mean and standard deviation of the input tensor.
@@ -16,7 +18,7 @@ def fit(self, x):
             raise TypeError("Input should be a torch tensor")
         self.mean = x.mean(0, keepdim=True)
         self.std = x.std(0, unbiased=False, keepdim=True)
-    
+
     def transform(self, x):
         """
         Scale the input tensor using the computed mean and standard deviation.
@@ -30,11 +32,11 @@ def transform(self, x):
         """
         if not torch.is_tensor(x):
             raise TypeError("Input should be a torch tensor")
-        if not hasattr(self, 'mean') or not hasattr(self, 'std'):
+        if not hasattr(self, "mean") or not hasattr(self, "std"):
             raise RuntimeError("Must fit scaler before transforming data")
         x = (x - self.mean) / (self.std + 1e-7)
         return x
-    
+
     def fit_transform(self, x):
         """
         Fit the scaler to the input tensor and then scale the tensor.
@@ -47,11 +49,11 @@ def fit_transform(self, x):
         return self.transform(x)
 
 
-
 class TorchMinMaxScaler:
     """
     A class for scaling data using min-max normalization with PyTorch tensors.
     """
+
     def fit(self, x):
         """
         Fit the scaler to the input data.
@@ -65,7 +67,7 @@ def fit(self, x):
             raise TypeError("Input should be a torch tensor")
         self.min = x.min(0, keepdim=True).values
         self.max = x.max(0, keepdim=True).values
-    
+
     def transform(self, x):
         """
         Transform the input data using the fitted scaler.
@@ -80,11 +82,11 @@ def transform(self, x):
         """
         if not torch.is_tensor(x):
             raise TypeError("Input should be a torch tensor")
-        if not hasattr(self, 'min') or not hasattr(self, 'max'):
+        if not hasattr(self, "min") or not hasattr(self, "max"):
             raise RuntimeError("Must fit scaler before transforming data")
         x = (x - self.min) / (self.max - self.min + 1e-7)
         return x
-    
+
     def fit_transform(self, x):
         """
         Fit the scaler to the input data and transform it.
@@ -97,4 +99,4 @@ def fit_transform(self, x):
         - TypeError: If the input is not a torch tensor.
         """
         self.fit(x)
-        return self.transform(x)
+        return self.transform(x)

test/test_net_light_regression_class.py

@@ -30,6 +30,7 @@ def test_net_light_regression_class():
     trainer = L.Trainer(
         max_epochs=2,
         enable_progress_bar=False,
+        accelerator="cpu",
     )
     trainer.fit(net_light_regression, train_loader, val_loader)
     res = trainer.test(net_light_regression, test_loader)

test/test_optimizer_handler.py

@@ -27,7 +27,7 @@ def test_optimizer_handler_adam():
         _L_out=1,
         _torchmetric="mean_squared_error",
     )
-    trainer = L.Trainer(max_epochs=2, enable_progress_bar=False)
+    trainer = L.Trainer(accelerator="cpu", max_epochs=2, enable_progress_bar=False)
     trainer.fit(net_light_base, train_loader, val_loader)
     # Adam uses a lr which is calculated as lr=lr_mult * 0.001, so this value
     # should be 0.1 * 0.001 = 0.0001
@@ -55,7 +55,7 @@ def test_optimizer_handler_adadelta():
         _L_out=1,
         _torchmetric="mean_squared_error",
     )
-    trainer = L.Trainer(max_epochs=2, enable_progress_bar=False)
+    trainer = L.Trainer(accelerator="cpu", max_epochs=2, enable_progress_bar=False)
     trainer.fit(net_light_base, train_loader, val_loader)
     # Adadelta uses a lr which is calculated as lr=lr_mult * 1.0, so this value
     # should be 1.0 * 0.1 = 0.1

test/test_testmodel.py

@@ -9,7 +9,7 @@
 
 
 def test_testmodel():
-    fun_control = fun_control_init(_L_in=10, _L_out=1, _torchmetric="mean_squared_error")
+    fun_control = fun_control_init(_L_in=10, _L_out=1, _torchmetric="mean_squared_error", accelerator="cpu")
 
     dataset = Diabetes()
     set_control_key_value(control_dict=fun_control, key="data_set", value=dataset, replace=True)

test/test_trainmodel.py

@@ -9,7 +9,7 @@
 
 
 def test_trainmodel():
-    fun_control = fun_control_init(_L_in=10, _L_out=1, _torchmetric="mean_squared_error")
+    fun_control = fun_control_init(_L_in=10, _L_out=1, _torchmetric="mean_squared_error", accelerator="cpu")
 
     dataset = Diabetes()
     set_control_key_value(control_dict=fun_control, key="data_set", value=dataset, replace=True)