feat: make synthetic runners use dataframes and rename inputs so stat…

src/autora/experiment_runner/synthetic/abstract/template_experiment.py

@@ -15,7 +15,7 @@
     >>> s.name
     'Template Experiment'
 
-    >>> s.variables
+    >>> s.variables # doctest: +ELLIPSIS
     VariableCollection(...)
 
     >>> s.domain()
@@ -25,8 +25,8 @@
            [3]])
 
     >>> s.ground_truth  # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE
-    functools.partial(<function template_experiment.<locals>.experiment_runner at 0x...>,
-                      added_noise_=0.0)
+    functools.partial(<function template_experiment.<locals>.run at 0x...>,
+                      added_noise=0.0)
 
     >>> s.ground_truth(1.)
     2.0
@@ -38,30 +38,31 @@
            [4.]])
 
 
-    >>> s.experiment_runner  # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE
-    <function template_experiment.<locals>.experiment_runner at 0x...>
+    >>> s.run  # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE
+    <function template_experiment.<locals>.run at 0x...>
 
-    >>> s.experiment_runner(1.)
-    1.8697820493137682
+    >>> s.run(1., random_state=42)
+    2.003047170797544
 
-    >>> s.experiment_runner(s.domain())
-    array([[1.01278404],
-           [1.96837574],
-           [2.99831988],
-           [3.91469561]])
+    >>> s.run(s.domain(), random_state=42)
+    array([[1.00304717],
+           [1.98960016],
+           [3.00750451],
+           [4.00940565]])
 
     >>> s.plotter()
     >>> plt.show()  # doctest: +SKIP
 
     Generate a new version of the experiment with different parameters:
-    >>> new_params = dict(s.params, **dict(random_state=190))
+    >>> new_params = dict(s.params)
     >>> s.factory_function(**new_params)  # doctest: +ELLIPSIS
-    SyntheticExperimentCollection(..., params={..., 'random_state': 190}, ...)
+    SyntheticExperimentCollection(...)
 
 """
 
 
 from functools import partial
+from typing import Optional
 
 import numpy as np
 from numpy.typing import ArrayLike
@@ -73,22 +74,17 @@
 def template_experiment(
     # Add any configurable parameters with their defaults here:
     name: str = "Template Experiment",
-    added_noise: float = 0.1,
-    random_state: int = 42,
 ):
     """
     A template for synthetic experiments.
 
     Parameters:
-        added_noise: standard deviation of gaussian noise added to output
-        random_state: seed for random number generator
+        name: name of the experiment
     """
 
     params = dict(
         # Include all parameters here:
         name=name,
-        added_noise=added_noise,
-        random_state=random_state,
     )
 
     # Define variables
@@ -100,15 +96,19 @@ def template_experiment(
     )
 
     # Define experiment runner
-    rng = np.random.default_rng(random_state)
 
-    def experiment_runner(x: ArrayLike, added_noise_=added_noise):
+    def run(
+        conditions: ArrayLike,
+        added_noise: float = 0.01,
+        random_state: Optional[int] = None,
+    ):
         """A function which simulates noisy observations."""
-        x_ = np.array(x)
-        y = x_ + 1.0 + rng.normal(0, added_noise_, size=x_.shape)
+        rng = np.random.default_rng(random_state)
+        x_ = np.array(conditions)
+        y = x_ + 1.0 + rng.normal(0, added_noise, size=x_.shape)
         return y
 
-    ground_truth = partial(experiment_runner, added_noise_=0.0)
+    ground_truth = partial(run, added_noise=0.0)
     """A function which simulates perfect observations"""
 
     def domain():
@@ -137,7 +137,7 @@ def plotter(model=None):
         name=name,
         description=template_experiment.__doc__,
         variables=variables,
-        experiment_runner=experiment_runner,
+        run=run,
         ground_truth=ground_truth,
         domain=domain,
         plotter=plotter,

src/autora/experiment_runner/synthetic/economics/expected_value_theory.py

@@ -1,6 +1,8 @@
 from functools import partial
+from typing import Optional, Union
 
 import numpy as np
+import pandas as pd
 
 from autora.experiment_runner.synthetic.utilities import SyntheticExperimentCollection
 from autora.variable import DV, IV, ValueType, VariableCollection
@@ -73,8 +75,6 @@ def expected_value_theory(
     resolution=10,
     minimum_value=-1,
     maximum_value=1,
-    added_noise: float = 0.01,
-    random_state: int = 180,
 ):
     """
     Expected Value Theory
@@ -86,9 +86,6 @@ def expected_value_theory(
         resolution:
         minimum_value:
         maximum_value:
-        added_noise:
-        random_state:
-
     """
 
     params = dict(
@@ -98,17 +95,19 @@ def expected_value_theory(
         resolution=resolution,
         choice_temperature=choice_temperature,
         value_lambda=value_lambda,
-        added_noise=added_noise,
-        random_state=random_state,
     )
 
-    rng = np.random.default_rng(random_state)
-
     variables = get_variables(
         minimum_value=minimum_value, maximum_value=maximum_value, resolution=resolution
     )
 
-    def experiment_runner(X: np.ndarray, added_noise_=added_noise):
+    def run(
+        conditions: Union[pd.DataFrame, np.ndarray, np.recarray],
+        added_noise: float = 0.01,
+        random_state: Optional[int] = None,
+    ):
+        rng = np.random.default_rng(random_state)
+        X = np.array(conditions)
         Y = np.zeros((X.shape[0], 1))
         for idx, x in enumerate(X):
             value_A = value_lambda * x[0]
@@ -117,8 +116,8 @@ def experiment_runner(X: np.ndarray, added_noise_=added_noise):
             probability_a = x[1]
             probability_b = x[3]
 
-            expected_value_A = value_A * probability_a + rng.normal(0, added_noise_)
-            expected_value_B = value_B * probability_b + rng.normal(0, added_noise_)
+            expected_value_A = value_A * probability_a + rng.normal(0, added_noise)
+            expected_value_B = value_B * probability_b + rng.normal(0, added_noise)
 
             # compute probability of choosing option A
             p_choose_A = np.exp(expected_value_A / choice_temperature) / (
@@ -128,9 +127,12 @@ def experiment_runner(X: np.ndarray, added_noise_=added_noise):
 
             Y[idx] = p_choose_A
 
-        return Y
+        experiment_data = pd.DataFrame(conditions)
+        experiment_data.columns = [v.name for v in variables.independent_variables]
+        experiment_data[variables.dependent_variables[0].name] = Y
+        return experiment_data
 
-    ground_truth = partial(experiment_runner, added_noise_=0.0)
+    ground_truth = partial(run, added_noise=0.0)
 
     def domain():
         X = np.array(
@@ -186,7 +188,7 @@ def plotter(model=None):
         name=name,
         description=expected_value_theory.__doc__,
         variables=variables,
-        experiment_runner=experiment_runner,
+        run=run,
         ground_truth=ground_truth,
         domain=domain,
         plotter=plotter,

src/autora/experiment_runner/synthetic/economics/prospect_theory.py

@@ -1,6 +1,8 @@
 from functools import partial
+from typing import Optional, Union
 
 import numpy as np
+import pandas as pd
 
 from autora.experiment_runner.synthetic.economics.expected_value_theory import (
     get_variables,
@@ -10,7 +12,6 @@
 
 def prospect_theory(
     name="Prospect Theory",
-    added_noise=0.01,
     choice_temperature=0.1,
     value_alpha=0.88,
     value_beta=0.88,
@@ -20,7 +21,6 @@ def prospect_theory(
     resolution=10,
     minimum_value=-1,
     maximum_value=1,
-    rng=np.random.default_rng(),
 ):
     """
     Parameters from
@@ -44,7 +44,6 @@ def prospect_theory(
     """
 
     params = dict(
-        added_noise=added_noise,
         choice_temperature=choice_temperature,
         value_alpha=value_alpha,
         value_beta=value_beta,
@@ -54,15 +53,20 @@ def prospect_theory(
         resolution=resolution,
         minimum_value=minimum_value,
         maximum_value=maximum_value,
-        rng=rng,
         name=name,
     )
 
     variables = get_variables(
         minimum_value=minimum_value, maximum_value=maximum_value, resolution=resolution
     )
 
-    def experiment_runner(X: np.ndarray, added_noise_=added_noise):
+    def run(
+        conditions: Union[pd.DataFrame, np.ndarray, np.recarray],
+        added_noise=0.01,
+        random_state: Optional[int] = None,
+    ):
+        rng = np.random.default_rng(random_state)
+        X = np.array(conditions)
         Y = np.zeros((X.shape[0], 1))
         for idx, x in enumerate(X):
             # power value function according to:
@@ -113,8 +117,8 @@ def experiment_runner(X: np.ndarray, added_noise_=added_noise):
                 x[3] ** coefficient + (1 - x[3]) ** coefficient
             ) ** (1 / coefficient)
 
-            expected_value_A = value_A * probability_a + rng.normal(0, added_noise_)
-            expected_value_B = value_B * probability_b + rng.normal(0, added_noise_)
+            expected_value_A = value_A * probability_a + rng.normal(0, added_noise)
+            expected_value_B = value_B * probability_b + rng.normal(0, added_noise)
 
             # compute probability of choosing option A
             p_choose_A = np.exp(expected_value_A / choice_temperature) / (
@@ -124,9 +128,12 @@ def experiment_runner(X: np.ndarray, added_noise_=added_noise):
 
             Y[idx] = p_choose_A
 
-        return Y
+        experiment_data = pd.DataFrame(conditions)
+        experiment_data.columns = [v.name for v in variables.independent_variables]
+        experiment_data[variables.dependent_variables[0].name] = Y
+        return experiment_data
 
-    ground_truth = partial(experiment_runner, added_noise_=0.0)
+    ground_truth = partial(run, added_noise=0.0)
 
     def domain():
         v_a = variables.independent_variables[0].allowed_values
@@ -188,7 +195,7 @@ def plotter(model=None):
         params=params,
         variables=variables,
         domain=domain,
-        experiment_runner=experiment_runner,
+        run=run,
         ground_truth=ground_truth,
         plotter=plotter,
         factory_function=prospect_theory,