Reformat signal into a list (#147)

* Make Dataset contain a dictionary * Extend signal to a list of strings * Align with set_max_iterations * Turn signal into list * Parameterise and test multiple signals * Update CHANGELOG.md * Relax test_multiple_signals assertion * Create test_dataset.py * Update Dataset to accept PyBaMM Solution * Update test_problem.py * Move signal to BaseProblem * Add test on signal type
pybop-team · Dec 14, 2023 · 14881c3 · 14881c3
1 parent c80e0d8
commit 14881c3
Show file tree

Hide file tree

Showing 23 changed files with 395 additions and 231 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -12,6 +12,7 @@
 - [#116](https://github.com/pybop-team/PyBOP/issues/116) - Adds PSO, SNES, XNES, ADAM, and IPropMin optimisers to PintsOptimisers() class
 - [#38](https://github.com/pybop-team/PyBOP/issues/38) - Restructures the Problem classes ahead of adding a design optimisation example
 - [#120](https://github.com/pybop-team/PyBOP/issues/120) - Updates the parameterisation test settings including the number of iterations
+- [#145](https://github.com/pybop-team/PyBOP/issues/145) - Reformats Dataset to contain a dictionary and signal into a list of strings
 
 ## Bug Fixes
 

diff --git a/examples/notebooks/spm_nlopt.ipynb b/examples/notebooks/spm_nlopt.ipynb
@@ -277,11 +277,13 @@
       "outputs": [],
       "source": [
         "pyb_model = pybop.lithium_ion.SPM()\n",
-        "dataset = [\n",
-        "    pybop.Dataset(\"Time [s]\", synthetic_sol[\"Time [s]\"].data),\n",
-        "    pybop.Dataset(\"Current function [A]\", synthetic_sol[\"Current [A]\"].data),\n",
-        "    pybop.Dataset(\"Terminal voltage [V]\", corrupt_V),\n",
-        "]"
+        "dataset = pybop.Dataset(\n",
+        "    {\n",
+        "        \"Time [s]\": synthetic_sol[\"Time [s]\"].data,\n",
+        "        \"Current function [A]\": synthetic_sol[\"Current [A]\"].data,\n",
+        "        \"Terminal voltage [V]\": corrupt_V,\n",
+        "    }\n",
+        ")"
       ]
     },
     {

diff --git a/examples/scripts/ecm_CMAES.py b/examples/scripts/ecm_CMAES.py
@@ -61,11 +61,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_CMAES.py b/examples/scripts/spm_CMAES.py
@@ -25,12 +25,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-# Form dataset for optimisation
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_IRPropMin.py b/examples/scripts/spm_IRPropMin.py
@@ -24,11 +24,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_SNES.py b/examples/scripts/spm_SNES.py
@@ -24,11 +24,13 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_XNES.py b/examples/scripts/spm_XNES.py
@@ -24,11 +24,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_adam.py b/examples/scripts/spm_adam.py
@@ -25,12 +25,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-# Dataset definition
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_descent.py b/examples/scripts/spm_descent.py
@@ -25,12 +25,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-# Dataset definition
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_nlopt.py b/examples/scripts/spm_nlopt.py
@@ -3,11 +3,13 @@
 
 # Form dataset
 Measurements = pd.read_csv("examples/scripts/Chen_example.csv", comment="#").to_numpy()
-dataset = [
-    pybop.Dataset("Time [s]", Measurements[:, 0]),
-    pybop.Dataset("Current function [A]", Measurements[:, 1]),
-    pybop.Dataset("Voltage [V]", Measurements[:, 2]),
-]
+dataset = pybop.Dataset(
+    {
+        "Time [s]": Measurements[:, 0],
+        "Current function [A]": Measurements[:, 1],
+        "Voltage [V]": Measurements[:, 2],
+    }
+)
 
 # Define model
 parameter_set = pybop.ParameterSet.pybamm("Chen2020")
@@ -30,7 +32,7 @@
 ]
 
 # Define the cost to optimise
-signal = "Voltage [V]"
+signal = ["Voltage [V]"]
 problem = pybop.FittingProblem(model, parameters, dataset, signal=signal, init_soc=0.98)
 cost = pybop.RootMeanSquaredError(problem)
 

diff --git a/examples/scripts/spm_pso.py b/examples/scripts/spm_pso.py
@@ -24,11 +24,14 @@
 values = model.predict(t_eval=t_eval)
 corrupt_values = values["Voltage [V]"].data + np.random.normal(0, sigma, len(t_eval))
 
-dataset = [
-    pybop.Dataset("Time [s]", t_eval),
-    pybop.Dataset("Current function [A]", values["Current [A]"].data),
-    pybop.Dataset("Voltage [V]", corrupt_values),
-]
+# Form dataset
+dataset = pybop.Dataset(
+    {
+        "Time [s]": t_eval,
+        "Current function [A]": values["Current [A]"].data,
+        "Voltage [V]": corrupt_values,
+    }
+)
 
 # Generate problem, cost function, and optimisation class
 problem = pybop.FittingProblem(model, parameters, dataset)

diff --git a/examples/scripts/spm_scipymin.py b/examples/scripts/spm_scipymin.py
@@ -3,11 +3,13 @@
 
 # Form dataset
 Measurements = pd.read_csv("examples/scripts/Chen_example.csv", comment="#").to_numpy()
-dataset = [
-    pybop.Dataset("Time [s]", Measurements[:, 0]),
-    pybop.Dataset("Current function [A]", Measurements[:, 1]),
-    pybop.Dataset("Voltage [V]", Measurements[:, 2]),
-]
+dataset = pybop.Dataset(
+    {
+        "Time [s]": Measurements[:, 0],
+        "Current function [A]": Measurements[:, 1],
+        "Voltage [V]": Measurements[:, 2],
+    }
+)
 
 # Define model
 parameter_set = pybop.ParameterSet.pybamm("Chen2020")
@@ -30,7 +32,7 @@
 ]
 
 # Define the cost to optimise
-signal = "Voltage [V]"
+signal = ["Voltage [V]"]
 problem = pybop.FittingProblem(model, parameters, dataset, signal=signal, init_soc=0.98)
 cost = pybop.RootMeanSquaredError(problem)
 

diff --git a/pybop/_dataset.py b/pybop/_dataset.py
@@ -18,20 +18,22 @@ class Dataset:
 
     """
 
-    def __init__(self, name, data):
+    def __init__(self, data_dictionary):
         """
         Initialize a Dataset instance with a name and data.
 
         Parameters
         ----------
-        name : str
-            The name for the dataset.
-        data : array-like
+        data_dictionary : dict or instance of pybamm.solvers.solution.Solution
             The experimental data to store within the dataset.
         """
 
-        self.name = name
-        self.data = data
+        if isinstance(data_dictionary, pybamm.solvers.solution.Solution):
+            data_dictionary = data_dictionary.get_data_dict()
+        if not isinstance(data_dictionary, dict):
+            raise ValueError("The input to pybop.Dataset must be a dictionary.")
+        self.data = data_dictionary
+        self.names = self.data.keys()
 
     def __repr__(self):
         """
@@ -40,9 +42,9 @@ def __repr__(self):
         Returns
         -------
         str
-            A string that includes the name and data of the dataset.
+            A string that includes the type and contents of the dataset.
         """
-        return f"Dataset: {self.name} \n Data: {self.data}"
+        return f"Dataset: {type(self.data)} \n Contains: {self.names}"
 
     def Interpolant(self):
         """