automl · benjamc · Jul 24, 2024 · Jul 7, 2022 · Jul 7, 2022 · Jul 7, 2022
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,12 @@
+# 2.2.0
+
+## Features
+- Add example to specify total budget (fidelity units) instead of n_trials for multi-fidelity/Hyperband (#1121)
+
+## Dependencies
+- Update numpy NaN (#1122) and restrict numpy version
+- Upgrade to ConfigSpace 1.x.x (#1124)
+
 # 2.1.0
 
 ## Improvements

diff --git a/CITATION.cff b/CITATION.cff
@@ -9,7 +9,7 @@ date-released: "2016-08-17"
 url: "https://automl.github.io/SMAC3/master/index.html"
 repository-code: "https://github.com/automl/SMAC3"
 
-version: "2.1.0"
+version: "2.2.0"
 
 type: "software"
 keywords:

diff --git a/Makefile b/Makefile
@@ -5,7 +5,7 @@ SHELL := /bin/bash
 
 NAME := SMAC3
 PACKAGE_NAME := smac
-VERSION := 2.1.0
+VERSION := 2.2.0
 
 DIR := "${CURDIR}"
 SOURCE_DIR := ${PACKAGE_NAME}

diff --git a/benchmark/src/benchmark.py b/benchmark/src/benchmark.py
@@ -17,6 +17,8 @@
 from collections import defaultdict
 from pathlib import Path
 
+from smac.utils.numpyencoder import NumpyEncoder
+
 import pandas as pd
 from src.tasks import TASKS  # noqa: E402
 from src.utils.exceptions import NotSupportedError  # noqa: E402
@@ -79,7 +81,7 @@ def _save_data(self) -> None:
         """Saves the internal data to the file."""
         print("Saving data...")
         with open(str(RAW_FILENAME), "w") as f:
-            json.dump(self._data, f, indent=4)
+            json.dump(self._data, f, indent=4, cls=NumpyEncoder)
 
     def _fill_keys(self) -> None:
         """Fill data with keys based on computer name, tasks, and selected version."""

diff --git a/benchmark/src/models/ac_branin.py b/benchmark/src/models/ac_branin.py
@@ -20,7 +20,7 @@ def configspace(self) -> ConfigurationSpace:
         x2 = Float("x2", (0, 15), default=7.5)
 
         # Add hyperparameters and conditions to our configspace
-        cs.add_hyperparameters([x2])
+        cs.add([x2])
 
         return cs
 

diff --git a/benchmark/src/models/branin.py b/benchmark/src/models/branin.py
@@ -20,7 +20,7 @@ def configspace(self) -> ConfigurationSpace:
         x2 = Float("x2", (0, 15), default=0)
 
         # Add hyperparameters and conditions to our configspace
-        cs.add_hyperparameters([x1, x2])
+        cs.add([x1, x2])
 
         return cs
 

diff --git a/benchmark/src/models/himmelblau.py b/benchmark/src/models/himmelblau.py
@@ -19,7 +19,7 @@ def configspace(self) -> ConfigurationSpace:
         y = Float("y", (-5, 5))
 
         # Add hyperparameters and conditions to our configspace
-        cs.add_hyperparameters([x, y])
+        cs.add([x, y])
 
         return cs
 

diff --git a/benchmark/src/models/mlp.py b/benchmark/src/models/mlp.py
@@ -33,7 +33,7 @@ def configspace(self) -> ConfigurationSpace:
         learning_rate_init = Float("learning_rate_init", (0.0001, 1.0), default=0.001, log=True)
 
         # Add all hyperparameters at once:
-        cs.add_hyperparameters([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
+        cs.add([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
 
         # Adding conditions to restrict the hyperparameter space...
         # ... since learning rate is used when solver is 'sgd'.
@@ -44,7 +44,7 @@ def configspace(self) -> ConfigurationSpace:
         use_batch_size = InCondition(child=batch_size, parent=solver, values=["sgd", "adam"])
 
         # We can also add multiple conditions on hyperparameters at once:
-        cs.add_conditions([use_lr, use_batch_size, use_lr_init])
+        cs.add([use_lr, use_batch_size, use_lr_init])
 
         return cs
 

diff --git a/benchmark/src/models/svm.py b/benchmark/src/models/svm.py
@@ -34,8 +34,8 @@ def configspace(self) -> ConfigurationSpace:
         use_gamma_value = InCondition(child=gamma_value, parent=gamma, values=["value"])
 
         # Add hyperparameters and conditions to our configspace
-        cs.add_hyperparameters([kernel, C, shrinking, degree, coef, gamma, gamma_value])
-        cs.add_conditions([use_degree, use_coef, use_gamma, use_gamma_value])
+        cs.add([kernel, C, shrinking, degree, coef, gamma, gamma_value])
+        cs.add([use_degree, use_coef, use_gamma, use_gamma_value])
 
         return cs
 

diff --git a/docs/3_getting_started.rst b/docs/3_getting_started.rst
@@ -27,7 +27,7 @@ ranges and default values.
         "species": ["mouse", "cat", "dog"],   # Categorical
     })
 
-Please see the documentation of `ConfigSpace <https://automl.github.io/ConfigSpace/main/>`_ for more details.
+Please see the documentation of `ConfigSpace <https://automl.github.io/ConfigSpace/latest/>`_ for more details.
 
 
 Target Function

diff --git a/docs/advanced_usage/9_parallelism.rst b/docs/advanced_usage/9_parallelism.rst
@@ -21,39 +21,6 @@ SMAC supports multiple workers natively via Dask. Just specify ``n_workers`` in
     When using multiple workers, SMAC is not reproducible anymore.
 
 
-.. warning ::
-
-    You cannot use resource limitation (pynisher, via the `scenario` arguments `trail_walltime_limit` and `trial_memory_limit`).
-    This is because pynisher works by running your function inside of a subprocess.
-    Once in the subprocess, the resources will be limited for that process before running your function. 
-    This does not work together with pickling - which is required by dask to schedule jobs on the cluster, even on a local one.
-
-
-.. warning ::
-
-    Start/run SMAC inside ``if __name__ == "__main__"`` in your script otherwise Dask is not able to correctly
-    spawn jobs and probably this runtime error will be raised:
-
-    .. code-block ::
-
-        RuntimeError: 
-            An attempt has been made to start a new process before the
-            current process has finished its bootstrapping phase.
-
-            This probably means that you are not using fork to start your
-            child processes and you have forgotten to use the proper idiom
-            in the main module:
-
-                if __name__ == '__main__':
-                    freeze_support()
-                    ...
-
-            The "freeze_support()" line can be omitted if the program
-            is not going to be frozen to produce an executable.
-
-
-
-
 Running on a Cluster
 --------------------
 You can also pass a custom dask client, e.g. to run on a slurm cluster.

diff --git a/docs/conf.py b/docs/conf.py
@@ -12,6 +12,8 @@
     "version": version,
     "versions": {
         f"v{version}": "#",
+        "v2.2.0": "https://automl.github.io/SMAC3/v2.2.0/",
+        "v2.1.0": "https://automl.github.io/SMAC3/v2.1.0/",
         "v2.0.1": "https://automl.github.io/SMAC3/v2.0.1/",
         "v2.0.0": "https://automl.github.io/SMAC3/v2.0.0/",
         "v2.0.0b1": "https://automl.github.io/SMAC3/v2.0.0b1/",

diff --git a/examples/1_basics/1_quadratic_function.py b/examples/1_basics/1_quadratic_function.py
@@ -26,7 +26,7 @@ class QuadraticFunction:
     def configspace(self) -> ConfigurationSpace:
         cs = ConfigurationSpace(seed=0)
         x = Float("x", (-5, 5), default=-5)
-        cs.add_hyperparameters([x])
+        cs.add([x])
 
         return cs
 

diff --git a/examples/1_basics/2_svm_cv.py b/examples/1_basics/2_svm_cv.py
@@ -46,8 +46,8 @@ def configspace(self) -> ConfigurationSpace:
         use_gamma_value = InCondition(child=gamma_value, parent=gamma, values=["value"])
 
         # Add hyperparameters and conditions to our configspace
-        cs.add_hyperparameters([kernel, C, shrinking, degree, coef, gamma, gamma_value])
-        cs.add_conditions([use_degree, use_coef, use_gamma, use_gamma_value])
+        cs.add([kernel, C, shrinking, degree, coef, gamma, gamma_value])
+        cs.add([use_degree, use_coef, use_gamma, use_gamma_value])
 
         return cs
 

diff --git a/examples/1_basics/3_ask_and_tell.py b/examples/1_basics/3_ask_and_tell.py
@@ -20,7 +20,7 @@ def configspace(self) -> ConfigurationSpace:
         cs = ConfigurationSpace(seed=0)
         x0 = Float("x0", (-5, 10), default=-3)
         x1 = Float("x1", (-5, 10), default=-4)
-        cs.add_hyperparameters([x0, x1])
+        cs.add([x0, x1])
 
         return cs
 

diff --git a/examples/1_basics/4_callback.py b/examples/1_basics/4_callback.py
@@ -27,7 +27,7 @@ def configspace(self) -> ConfigurationSpace:
         cs = ConfigurationSpace(seed=0)
         x0 = Float("x0", (-5, 10), default=-3)
         x1 = Float("x1", (-5, 10), default=-4)
-        cs.add_hyperparameters([x0, x1])
+        cs.add([x0, x1])
 
         return cs
 

diff --git a/examples/1_basics/5_continue.py b/examples/1_basics/5_continue.py
@@ -47,7 +47,7 @@ class QuadraticFunction:
     def configspace(self) -> ConfigurationSpace:
         cs = ConfigurationSpace(seed=0)
         x = Float("x", (-5, 5), default=-5)
-        cs.add_hyperparameters([x])
+        cs.add([x])
 
         return cs
 

diff --git a/examples/1_basics/6_priors.py b/examples/1_basics/6_priors.py
@@ -95,13 +95,13 @@ def configspace(self) -> ConfigurationSpace:
             "learning_rate_init",
             lower=1e-5,
             upper=1.0,
-            mu=np.log(1e-3),
-            sigma=np.log(10),
+            mu=1e-3,  # will be transformed to log space later
+            sigma=10,  # will be transformed to log space later
             log=True,
         )
 
         # Add all hyperparameters at once:
-        cs.add_hyperparameters([n_layer, n_neurons, activation, optimizer, batch_size, learning_rate_init])
+        cs.add([n_layer, n_neurons, activation, optimizer, batch_size, learning_rate_init])
 
         return cs
 

diff --git a/examples/1_basics/7_parallelization_cluster.py b/examples/1_basics/7_parallelization_cluster.py
@@ -6,6 +6,9 @@
 SLURM cluster. If you do not want to use a cluster but your local machine, set dask_client
 to `None` and pass `n_workers` to the `Scenario`.
 
+Sometimes, the submitted jobs by the slurm client might be cancelled once it starts. In that
+case, you could try to start your job from a computing node
+
 :warning: On some clusters you cannot spawn new jobs when running a SLURMCluster inside a
 job instead of on the login node. No obvious errors might be raised but it can hang silently.
 
@@ -41,7 +44,7 @@ def configspace(self) -> ConfigurationSpace:
         cs = ConfigurationSpace(seed=0)
         x0 = Float("x0", (-5, 10), default=-5, log=False)
         x1 = Float("x1", (0, 15), default=2, log=False)
-        cs.add_hyperparameters([x0, x1])
+        cs.add([x0, x1])
 
         return cs
 
@@ -77,7 +80,7 @@ def train(self, config: Configuration, seed: int = 0) -> float:
     model = Branin()
 
     # Scenario object specifying the optimization "environment"
-    scenario = Scenario(model.configspace, deterministic=True, n_trials=100)
+    scenario = Scenario(model.configspace, deterministic=True, n_trials=100, trial_walltime_limit=100)
 
     # Create cluster
     n_workers = 4  # Use 4 workers on the cluster
@@ -97,6 +100,10 @@ def train(self, config: Configuration, seed: int = 0) -> float:
         walltime="00:10:00",
         processes=1,
         log_directory="tmp/smac_dask_slurm",
+        # if you would like to limit the resources consumption of each function evaluation with pynisher, you need to
+        # set nanny as False
+        # Otherwise, an error `daemonic processes are not allowed to have children` will raise!
+        nanny=False  # if you do not use pynisher to limit the memory/time usage, feel free to set this one as True
     )
     cluster.scale(jobs=n_workers)
 

diff --git a/examples/2_multi_fidelity/1_mlp_epochs.py b/examples/2_multi_fidelity/1_mlp_epochs.py
@@ -65,7 +65,7 @@ def configspace(self) -> ConfigurationSpace:
         learning_rate_init = Float("learning_rate_init", (0.0001, 1.0), default=0.001, log=True)
 
         # Add all hyperparameters at once:
-        cs.add_hyperparameters([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
+        cs.add([n_layer, n_neurons, activation, solver, batch_size, learning_rate, learning_rate_init])
 
         # Adding conditions to restrict the hyperparameter space...
         # ... since learning rate is only used when solver is 'sgd'.
@@ -76,7 +76,7 @@ def configspace(self) -> ConfigurationSpace:
         use_batch_size = InCondition(child=batch_size, parent=solver, values=["sgd", "adam"])
 
         # We can also add multiple conditions on hyperparameters at once:
-        cs.add_conditions([use_lr, use_batch_size, use_lr_init])
+        cs.add([use_lr, use_batch_size, use_lr_init])
 
         return cs
 

diff --git a/examples/2_multi_fidelity/2_sgd_datasets.py b/examples/2_multi_fidelity/2_sgd_datasets.py
@@ -76,7 +76,7 @@ def configspace(self) -> ConfigurationSpace:
         learning_rate = Categorical("learning_rate", ["constant", "invscaling", "adaptive"], default="constant")
         eta0 = Float("eta0", (0.00001, 1), default=0.1, log=True)
         # Add the parameters to configuration space
-        cs.add_hyperparameters([alpha, l1_ratio, learning_rate, eta0])
+        cs.add([alpha, l1_ratio, learning_rate, eta0])
 
         return cs