Refactor .runners: GA, MIMIC, SA, RHC (#11)

src/mlrose_ky/__init__.py

@@ -1,4 +1,4 @@
-"""MLROSe initialization file."""
+"""mlrose-ky initialization file."""
 
 # Authors: Genevieve Hayes (modified by Andrew Rollings, Kyle Nakamura)
 # License: BSD 3-clause

src/mlrose_ky/algorithms/crossovers/_crossover_base.py

@@ -34,7 +34,7 @@ class _CrossoverBase(ABC):
         'length' property.
     """
 
-    def __init__(self, optimization_problem: Any) -> None:
+    def __init__(self, optimization_problem: Any):
         """
         Initialize the CrossoverBase with the given optimization problem.
 

src/mlrose_ky/algorithms/crossovers/one_point_crossover.py

@@ -26,7 +26,7 @@ class OnePointCrossover(_CrossoverBase):
     _CrossoverBase : Abstract base class for crossover operations.
     """
 
-    def __init__(self, optimization_problem: Any) -> None:
+    def __init__(self, optimization_problem: Any):
         """
         Initialize the OnePointCrossover with the given optimization problem.
 

src/mlrose_ky/algorithms/crossovers/tsp_crossover.py

@@ -27,7 +27,7 @@ class TSPCrossover(_CrossoverBase):
     _CrossoverBase : Abstract base class for crossover operations.
     """
 
-    def __init__(self, optimization_problem: Any) -> None:
+    def __init__(self, optimization_problem: Any):
         """
         Initialize the TSPCrossover with the given optimization problem.
 

src/mlrose_ky/algorithms/crossovers/uniform_crossover.py

@@ -27,7 +27,7 @@ class UniformCrossover(_CrossoverBase):
     _CrossoverBase : Abstract base class for crossover operations.
     """
 
-    def __init__(self, optimization_problem: Any) -> None:
+    def __init__(self, optimization_problem: Any):
         """
         Initialize the UniformCrossover with the given optimization problem.
 

src/mlrose_ky/algorithms/decay/arithmetic_decay.py

@@ -41,7 +41,7 @@ class ArithDecay:
     5.25
     """
 
-    def __init__(self, init_temp: float = 1.0, decay: float = 0.0001, min_temp: float = 0.001) -> None:
+    def __init__(self, init_temp: float = 1.0, decay: float = 0.0001, min_temp: float = 0.001):
         self.init_temp: float = init_temp
         self.decay: float = decay
         self.min_temp: float = min_temp

src/mlrose_ky/algorithms/decay/custom_decay.py

@@ -29,7 +29,7 @@ class CustomSchedule:
     15
     """
 
-    def __init__(self, schedule: Callable[..., float], **kwargs) -> None:
+    def __init__(self, schedule: Callable[..., float], **kwargs):
         self.schedule: Callable[..., float] = schedule
         self.kwargs: dict = kwargs
 

src/mlrose_ky/algorithms/decay/exponential_decay.py

@@ -43,7 +43,7 @@ class ExpDecay:
     7.788007830714049
     """
 
-    def __init__(self, init_temp: float = 1.0, exp_const: float = 0.005, min_temp: float = 0.001) -> None:
+    def __init__(self, init_temp: float = 1.0, exp_const: float = 0.005, min_temp: float = 0.001):
         self.init_temp: float = init_temp
         self.exp_const: float = exp_const
         self.min_temp: float = min_temp

src/mlrose_ky/algorithms/decay/geometric_decay.py

@@ -41,7 +41,7 @@ class GeomDecay:
     7.737809374999998
     """
 
-    def __init__(self, init_temp: float = 1.0, decay: float = 0.99, min_temp: float = 0.001) -> None:
+    def __init__(self, init_temp: float = 1.0, decay: float = 0.99, min_temp: float = 0.001):
         self.init_temp: float = init_temp
         self.decay: float = decay
         self.min_temp: float = min_temp

src/mlrose_ky/algorithms/mutators/_mutator_base.py

@@ -33,8 +33,9 @@ class _MutatorBase(ABC):
         An instance of an optimization problem that the mutator will operate on.
     """
 
-    def __init__(self, opt_prob: Any) -> None:
+    def __init__(self, opt_prob: Any):
         super().__init__()
+
         self._opt_prob: Any = opt_prob
         self._length: int = opt_prob.length
 

src/mlrose_ky/algorithms/mutators/discrete_mutator.py

@@ -30,8 +30,9 @@ class DiscreteMutator(_MutatorBase):
         An instance of an optimization problem that the mutator will operate on.
     """
 
-    def __init__(self, opt_prob: Any) -> None:
+    def __init__(self, opt_prob: Any):
         super().__init__(opt_prob)
+
         self._max_val: int = opt_prob.max_val
 
     def mutate(self, child: np.ndarray, mutation_probability: float) -> np.ndarray:

src/mlrose_ky/algorithms/mutators/gene_swap_mutator.py

@@ -28,7 +28,7 @@ class SwapMutator(_MutatorBase):
         An instance of an optimization problem that the mutator will operate on.
     """
 
-    def __init__(self, opt_prob: Any) -> None:
+    def __init__(self, opt_prob: Any):
         super().__init__(opt_prob)
 
     def mutate(self, child: np.ndarray, mutation_probability: float) -> np.ndarray:

src/mlrose_ky/algorithms/mutators/single_gene_mutator.py

@@ -29,8 +29,9 @@ class ChangeOneMutator(_MutatorBase):
         An instance of an optimization problem that the mutator will operate on.
     """
 
-    def __init__(self, opt_prob: Any) -> None:
+    def __init__(self, opt_prob: Any):
         super().__init__(opt_prob)
+
         self._max_val: int = opt_prob.max_val
 
     def mutate(self, child: np.ndarray, mutation_probability: float) -> np.ndarray:

src/mlrose_ky/algorithms/mutators/single_shift_mutator.py

@@ -30,8 +30,9 @@ class ShiftOneMutator(_MutatorBase):
         An instance of an optimization problem that the mutator will operate on.
     """
 
-    def __init__(self, opt_prob: Any) -> None:
+    def __init__(self, opt_prob: Any):
         super().__init__(opt_prob)
+
         self._max_val: int = opt_prob.max_val
 
     def mutate(self, child: np.ndarray, mutation_probability: float) -> np.ndarray:

src/mlrose_ky/fitness/continuous_peaks.py

@@ -37,7 +37,7 @@ class ContinuousPeaks:
     with `max_val = 2`) optimization problems only.
     """
 
-    def __init__(self, t_pct: float = 0.1) -> None:
+    def __init__(self, t_pct: float = 0.1):
         self.t_pct: float = t_pct
         self.prob_type: str = "discrete"
 

src/mlrose_ky/fitness/max_k_color.py

@@ -110,7 +110,7 @@ def get_prob_type(self) -> str:
         """
         return self.prob_type
 
-    def set_graph(self, graph) -> None:
+    def set_graph(self, graph):
         """Set the graph edges from an external graph representation.
 
         Parameters

src/mlrose_ky/fitness/one_max.py

@@ -27,7 +27,7 @@ class OneMax:
     The One Max fitness function is suitable for use in either discrete or continuous-state optimization problems.
     """
 
-    def __init__(self) -> None:
+    def __init__(self):
         self.prob_type: str = "either"
 
     @staticmethod

src/mlrose_ky/fitness/travelling_salesperson.py

@@ -51,7 +51,7 @@ class TravellingSalesperson:
        fitness function object.
     """
 
-    def __init__(self, coords: list[tuple] = None, distances: list[tuple] = None) -> None:
+    def __init__(self, coords: list[tuple] = None, distances: list[tuple] = None):
         # Ensure that at least one of coords or distances is provided
         if coords is None and distances is None:
             raise ValueError("At least one of coords and distances must be specified.")

src/mlrose_ky/gridsearch/grid_search_mixin.py

@@ -27,7 +27,7 @@ class GridSearchMixin:
         Flag indicating whether to apply argmax to predictions and ground truths before scoring.
     """
 
-    def __init__(self, scorer_method: Callable = None) -> None:
+    def __init__(self, scorer_method: Callable = None):
         """
         Initializes the GridSearchMixin with a specified scoring method.
 

src/mlrose_ky/neural/_nn_base.py

@@ -27,7 +27,7 @@ def __init__(self):
         pass
 
     @abstractmethod
-    def fit(self, X: np.ndarray, y: np.ndarray = None, init_weights: np.ndarray = None) -> None:
+    def fit(self, X: np.ndarray, y: np.ndarray = None, init_weights: np.ndarray = None):
         """
         Fit the neural network to the data.
 

src/mlrose_ky/neural/_nn_core.py

@@ -8,6 +8,7 @@
 
 import numpy as np
 from sklearn.preprocessing import LabelBinarizer
+
 from mlrose_ky.algorithms.decay import GeomDecay
 from mlrose_ky.algorithms.ga import genetic_alg
 from mlrose_ky.algorithms.rhc import random_hill_climb
@@ -71,7 +72,7 @@ def __init__(
         self.predicted_probs: np.ndarray = np.array([])
         self.fitness_curve: list[float] = []
 
-    def _validate(self) -> None:
+    def _validate(self):
         """Validate the model parameters."""
         if (not isinstance(self.max_iters, int) and self.max_iters != np.inf) or self.max_iters < 0:
             raise ValueError(f"max_iters must be a positive integer, got {self.max_iters}.")
@@ -109,7 +110,7 @@ def _validate(self) -> None:
                 f"'random_hill_climb', 'simulated_annealing', 'genetic_alg', 'gradient_descent', got {self.algorithm}."
             )
 
-    def _validate_input(self, y: np.ndarray) -> None:
+    def _validate_input(self, y: np.ndarray):
         """
         Add classes_ attribute based on classes present in y.
 

src/mlrose_ky/neural/activation/identity.py

@@ -4,6 +4,7 @@
 # License: BSD 3-clause
 
 import warnings
+
 import numpy as np
 
 from mlrose_ky.decorators import short_name

src/mlrose_ky/neural/linear_regression.py

@@ -4,6 +4,7 @@
 # License: BSD 3-clause
 
 from sklearn.base import RegressorMixin
+
 from mlrose_ky.algorithms.decay import GeomDecay
 from ._nn_core import _NNCore
 

src/mlrose_ky/neural/nn_classifier.py

@@ -3,9 +3,11 @@
 # Authors: Genevieve Hayes (modified by Andrew Rollings, Kyle Nakamura)
 # License: BSD 3-clause
 
+from typing import Any, Optional, Callable
+
 import numpy as np
+
 from mlrose_ky.neural._nn_base import _NNBase
-from typing import Any, Optional, Callable
 
 
 class NNClassifier(_NNBase):

src/mlrose_ky/opt_probs/continuous_opt.py

@@ -2,14 +2,15 @@
 
 from typing import Any
 
-# Authors: Genevieve Hayes (modified by Andrew Rollings, Kyle Nakamura)
-# License: BSD 3-clause
-
 import numpy as np
 
 from mlrose_ky.opt_probs.opt_prob import _OptProb
 
 
+# Authors: Genevieve Hayes (modified by Andrew Rollings, Kyle Nakamura)
+# License: BSD 3-clause
+
+
 class ContinuousOpt(_OptProb):
     """Class for defining continuous-state optimization problems.
 
@@ -77,7 +78,7 @@ def calculate_updates(self) -> list:
         """
         return self.fitness_fn.calculate_updates()
 
-    def find_neighbors(self) -> None:
+    def find_neighbors(self):
         """Find all neighbors of the current state."""
         # Pre-allocate a NumPy array for neighbors (maximum of 2 * length neighbors)
         neighbors_matrix = np.zeros((2 * self.length, self.length))
@@ -145,7 +146,7 @@ def random_neighbor(self) -> np.ndarray:
 
         return neighbor
 
-    def random_pop(self, pop_size: int) -> None:
+    def random_pop(self, pop_size: int):
         """Create a population of random state vectors.
 
         Parameters
@@ -221,7 +222,7 @@ def reproduce(self, parent_1: np.ndarray, parent_2: np.ndarray, mutation_prob: f
 
         return child
 
-    def reset(self) -> None:
+    def reset(self):
         """Set the current state vector to a random value and reset its fitness."""
         self.state = self.random()
         self.fitness_evaluations = 0

src/mlrose_ky/opt_probs/discrete_opt.py

@@ -106,7 +106,7 @@ def __init__(
         self._mut_mask: np.ndarray | None = None
         self._mut_inf: np.ndarray | None = None
 
-    def eval_node_probs(self) -> None:
+    def eval_node_probs(self):
         """Update probability density estimates."""
         mutual_info = self._get_mutual_info_impl()
 
@@ -143,7 +143,7 @@ def eval_node_probs(self) -> None:
         self.node_probs = probs
         self.parent_nodes = parent
 
-    def set_mimic_fast_mode(self, fast_mode: bool) -> None:
+    def set_mimic_fast_mode(self, fast_mode: bool):
         """Enable or disable MIMIC fast mode."""
         if fast_mode:
             mut_mask = np.zeros([self.length, self.length], dtype=bool)
@@ -214,7 +214,7 @@ def _get_mutual_info_fast(self) -> np.ndarray:
 
         return mutual_info
 
-    def find_neighbors(self) -> None:
+    def find_neighbors(self):
         """Find all neighbors of the current state."""
         self.neighbors = []
 
@@ -233,7 +233,7 @@ def find_neighbors(self) -> None:
                     neighbor[i] = j
                     self.neighbors.append(neighbor)
 
-    def find_sample_order(self) -> None:
+    def find_sample_order(self):
         """Determine order in which to generate sample vector elements."""
         sample_order = []
         last = [0]
@@ -253,7 +253,7 @@ def find_sample_order(self) -> None:
 
         self.sample_order = sample_order
 
-    def find_top_pct(self, keep_pct: float) -> None:
+    def find_top_pct(self, keep_pct: float):
         """Select samples with fitness in the top keep_pct percentile.
 
         Parameters
@@ -318,7 +318,7 @@ def random_neighbor(self) -> np.ndarray:
 
         return neighbor
 
-    def random_pop(self, pop_size: int) -> None:
+    def random_pop(self, pop_size: int):
         """Create a population of random state vectors.
 
         Parameters
@@ -367,7 +367,7 @@ def reproduce(self, parent_1: np.ndarray, parent_2: np.ndarray, mutation_prob: f
         child = self._crossover.mate(parent_1, parent_2)
         return self._mutator.mutate(child, mutation_prob)
 
-    def reset(self) -> None:
+    def reset(self):
         """Set the current state vector to a random value and get its fitness."""
         self.state = self.random()
         self.fitness = self.eval_fitness(self.state)

src/mlrose_ky/opt_probs/flip_flop_opt.py

@@ -80,11 +80,11 @@ def __init__(
         state = np.random.randint(2, size=self.length)
         self.set_state(state)
 
-    def evaluate_population_fitness(self) -> None:
+    def evaluate_population_fitness(self):
         """Calculate fitness for the current population."""
         self.pop_fitness = self.fitness_fn.evaluate_many(self.population)
 
-    def random_pop(self, pop_size: int) -> None:
+    def random_pop(self, pop_size: int):
         """Create a population of random state vectors.
 
         Parameters

src/mlrose_ky/opt_probs/opt_prob.py

@@ -113,7 +113,7 @@ def eval_fitness(self, state: np.ndarray) -> float:
         self.fitness_evaluations += 1
         return fitness
 
-    def eval_mate_probs(self) -> None:
+    def eval_mate_probs(self):
         """Calculate the probability of each member of the population reproducing."""
         pop_fitness = np.copy(self.pop_fitness)
 
@@ -210,7 +210,7 @@ def get_state(self) -> np.ndarray:
         """
         return self.state
 
-    def set_population(self, new_population: np.ndarray) -> None:
+    def set_population(self, new_population: np.ndarray):
         """Set a new population and evaluate its fitness.
 
         Parameters
@@ -221,11 +221,11 @@ def set_population(self, new_population: np.ndarray) -> None:
         self.population = new_population
         self.evaluate_population_fitness()
 
-    def evaluate_population_fitness(self) -> None:
+    def evaluate_population_fitness(self):
         """Evaluate the fitness of the current population."""
         self.pop_fitness = np.array([self.eval_fitness(indiv) for indiv in self.population])
 
-    def set_state(self, new_state: np.ndarray) -> None:
+    def set_state(self, new_state: np.ndarray):
         """Set a new state vector and evaluate its fitness.
 
         Parameters