rename multiple classes

surfaces/_base_test_function.py

@@ -3,18 +3,7 @@
 # License: MIT License
 
 
-import time
-import numpy as np
-import pandas as pd
-from functools import reduce
-
-from hyperactive import Hyperactive
-from hyperactive.optimizers import GridSearchOptimizer
-
-from ..machine_learning.data_collector import SurfacesDataCollector
-
-
-class ObjectiveFunction:
+class BaseTestFunction:
     explanation = """ """
 
     dimensions = " "
@@ -26,77 +15,9 @@ def __init__(self, metric="score", input_type="dictionary", sleep=0):
         self.input_type = input_type
         self.sleep = sleep
 
-        self.sql_data = SurfacesDataCollector()
-
-    def search_space(self, min=-5, max=5, step=0.1, value_typ="array"):
-        search_space_ = {}
-
-        for dim in range(self.n_dim):
-            dim_str = "x" + str(dim)
-
-            values = np.arange(min, max, step)
-            if value_typ == "list":
-                values = list(values)
-            search_space_[dim_str] = values
-
-        return search_space_
-
-    def collect_data(self, if_exists="append"):
-        para_names = list(self.search_space().keys())
-        search_data_cols = para_names + ["score"]
-        search_data = pd.DataFrame([], columns=search_data_cols)
-        search_data_length = 0
-
-        dim_sizes_list = [len(array) for array in self.search_space().values()]
-        search_space_size = reduce((lambda x, y: x * y), dim_sizes_list)
-
-        while search_data_length < search_space_size:
-            hyper = Hyperactive(verbosity=["progress_bar"])
-            hyper.add_search(
-                self.objective_function_dict,
-                self.search_space(value_typ="list"),
-                initialize={},
-                n_iter=search_space_size,
-                optimizer=GridSearchOptimizer(direction="orthogonal"),
-                memory_warm_start=search_data,
-            )
-            hyper.run()
-
-            search_data = pd.concat(
-                [search_data, hyper.search_data(self.objective_function_dict)],
-                ignore_index=True,
-            )
-
-            search_data = search_data.drop_duplicates(subset=para_names)
-            search_data_length = len(search_data)
-
-        self.sql_data.save(self.__name__, search_data, if_exists)
-
     def load_search_data(self):
         try:
             dataframe = self.sql_data.load(self.__name__)
         except:
             print("Path 2 database: ", self.sql_data.path)
         return dataframe
-
-    def return_metric(self, loss):
-        if self.metric == "score":
-            return -loss
-        elif self.metric == "loss":
-            return loss
-
-    def objective_function_np(self, *args):
-        para = {}
-        for i, arg in enumerate(args):
-            dim_str = "x" + str(i)
-            para[dim_str] = arg
-
-        return self.objective_function_dict(para)
-
-    def __call__(self, *input):
-        time.sleep(self.sleep)
-
-        if self.input_type == "dictionary":
-            return self.objective_function_dict(*input)
-        elif self.input_type == "arrays":
-            return self.objective_function_np(*input)

surfaces/machine_learning_functions/base_machine_learning_function.py

@@ -12,9 +12,10 @@
 from hyperactive import Hyperactive
 from hyperactive.optimizers import GridSearchOptimizer
 from ..data_collector import SurfacesDataCollector
+from .._base_test_function import BaseTestFunction
 
 
-class BaseMachineLearningFunction:
+class MachineLearningFunction(BaseTestFunction):
     def __init__(self, input_type="dictionary", sleep=0):
         self.input_type = input_type
         self.sleep = sleep
@@ -53,13 +54,6 @@ def collect_data(self, if_exists="append"):
 
         self.sql_data.save(self.__name__, search_data, if_exists)
 
-    def load_search_data(self):
-        try:
-            dataframe = self.sql_data.load(self.__name__)
-        except:
-            print("Path 2 database: ", self.sql_data.path)
-        return dataframe
-
     def objective_function_dict(self, params):
         try:
             parameter_d = params.para_dict

surfaces/machine_learning_functions/tabular_classifiers.py

@@ -6,10 +6,10 @@
 from sklearn.model_selection import cross_val_score
 from .datasets import digits_data, wine_data, iris_data
 
-from .base_machine_learning_function import BaseMachineLearningFunction
+from .base_machine_learning_function import MachineLearningFunction
 
 
-class KNeighborsClassifierFunction(BaseMachineLearningFunction):
+class KNeighborsClassifierFunction(MachineLearningFunction):
     __name__ = "k_neighbors_classifier"
 
     def __init__(self, input_type="dictionary", sleep=0):

surfaces/machine_learning_functions/tabular_regressors.py

@@ -7,10 +7,10 @@
 from sklearn.model_selection import cross_val_score
 from .datasets import diabetes_data
 
-from .base_machine_learning_function import BaseMachineLearningFunction
+from .base_machine_learning_function import MachineLearningFunction
 
 
-class KNeighborsRegressorFunction(BaseMachineLearningFunction):
+class KNeighborsRegressorFunction(MachineLearningFunction):
     __name__ = "k_neighbors_regressor"
 
     def __init__(self, input_type="dictionary", sleep=0):
@@ -33,7 +33,7 @@ def model(self, params):
         return scores.mean()
 
 
-class GradientBoostingRegressorFunction(BaseMachineLearningFunction):
+class GradientBoostingRegressorFunction(MachineLearningFunction):
     __name__ = "gradient_boosting_regressor"
 
     def __init__(self, input_type="dictionary", sleep=0):

surfaces/mathematical_functions/__init__.py

@@ -9,7 +9,7 @@
 from .rosenbrock_function import RosenbrockFunction
 from .beale_function import BealeFunction
 from .himmelblaus_function import HimmelblausFunction
-from .hölder_table_function import HölderTableFunction
+from .hoelder_table_function import HölderTableFunction
 from .cross_in_tray_function import CrossInTrayFunction
 from .simionescu_function import SimionescuFunction
 from .easom_function import EasomFunction

surfaces/mathematical_functions/_base_objective_function.py

@@ -12,9 +12,10 @@
 from hyperactive.optimizers import GridSearchOptimizer
 
 from ..data_collector import SurfacesDataCollector
+from .._base_test_function import BaseTestFunction
 
 
-class ObjectiveFunction:
+class MathematicalFunction(BaseTestFunction):
     explanation = """ """
 
     dimensions = " "
@@ -72,13 +73,6 @@ def collect_data(self, if_exists="append"):
 
         self.sql_data.save(self.__name__, search_data, if_exists)
 
-    def load_search_data(self):
-        try:
-            dataframe = self.sql_data.load(self.__name__)
-        except:
-            print("Path 2 database: ", self.sql_data.path)
-        return dataframe
-
     def return_metric(self, loss):
         if self.metric == "score":
             return -loss

surfaces/mathematical_functions/ackley_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class AckleyFunction(ObjectiveFunction):
+class AckleyFunction(MathematicalFunction):
     name = "Ackley Function"
     _name_ = "ackley_function"
     __name__ = "AckleyFunction"

surfaces/mathematical_functions/beale_function.py

@@ -3,10 +3,10 @@
 # License: MIT License
 
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class BealeFunction(ObjectiveFunction):
+class BealeFunction(MathematicalFunction):
     name = "Beale Function"
     _name_ = "beale_function"
     __name__ = "BealeFunction"
@@ -26,8 +26,8 @@ def objective_function_dict(self, params):
         y = params["x1"]
 
         loss1 = (self.A - x + x * y) ** 2
-        loss2 = (self.B - x + x * y ** 2) ** 2
-        loss3 = (self.C - x + x * y ** 3) ** 2
+        loss2 = (self.B - x + x * y**2) ** 2
+        loss3 = (self.C - x + x * y**3) ** 2
 
         loss = loss1 + loss2 + loss3
 

surfaces/mathematical_functions/booth_function.py

@@ -3,10 +3,10 @@
 # License: MIT License
 
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class BoothFunction(ObjectiveFunction):
+class BoothFunction(MathematicalFunction):
     name = "Booth Function"
     _name_ = "booth_function"
     __name__ = "BoothFunction"

surfaces/mathematical_functions/bukin_function_n6.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class BukinFunctionN6(ObjectiveFunction):
+class BukinFunctionN6(MathematicalFunction):
     name = "Bukin Function N6"
     _name_ = "bukin_function_n6"
     __name__ = "BukinFunctionN6"
@@ -21,6 +21,6 @@ def objective_function_dict(self, params):
         x = params["x0"]
         y = params["x1"]
 
-        loss = 100 * np.sqrt(np.abs(y - 0.01 * x ** 2)) + 0.01 * np.abs(x + 10)
+        loss = 100 * np.sqrt(np.abs(y - 0.01 * x**2)) + 0.01 * np.abs(x + 10)
 
         return self.return_metric(loss)

surfaces/mathematical_functions/cross_in_tray_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class CrossInTrayFunction(ObjectiveFunction):
+class CrossInTrayFunction(MathematicalFunction):
     name = "Cross In Tray Function"
     _name_ = "cross_in_tray_function"
     __name__ = "CrossInTrayFunction"
@@ -34,7 +34,7 @@ def objective_function_dict(self, params):
         y = params["x1"]
 
         loss1 = np.sin(self.angle * x) * np.sin(self.angle * y)
-        loss2 = np.exp(abs(self.B - (np.sqrt(x ** 2 + y ** 2) / np.pi)) + 1)
+        loss2 = np.exp(abs(self.B - (np.sqrt(x**2 + y**2) / np.pi)) + 1)
 
         loss = -self.A * (np.abs(loss1 * loss2)) ** 0.1
 

surfaces/mathematical_functions/drop_wave_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class DropWaveFunction(ObjectiveFunction):
+class DropWaveFunction(MathematicalFunction):
     name = "Drop Wave Function"
     _name_ = "drop_wave_function"
     __name__ = "DropWaveFunction"
@@ -21,8 +21,8 @@ def objective_function_dict(self, params):
         x = params["x0"]
         y = params["x1"]
 
-        loss = -(1 + np.cos(12 * np.sqrt(x ** 2 + y ** 2))) / (
-            0.5 * (x ** 2 + y ** 2) + 2
+        loss = -(1 + np.cos(12 * np.sqrt(x**2 + y**2))) / (
+            0.5 * (x**2 + y**2) + 2
         )
 
         return self.return_metric(loss)

surfaces/mathematical_functions/easom_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class EasomFunction(ObjectiveFunction):
+class EasomFunction(MathematicalFunction):
     name = "Easom Function"
     _name_ = "easom_function"
     __name__ = "EasomFunction"

surfaces/mathematical_functions/eggholder_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class EggholderFunction(ObjectiveFunction):
+class EggholderFunction(MathematicalFunction):
     name = "Eggholder Function"
     _name_ = "eggholder_function"
     __name__ = "EggholderFunction"

surfaces/mathematical_functions/goldstein_price_function.py

@@ -3,10 +3,10 @@
 # License: MIT License
 
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class GoldsteinPriceFunction(ObjectiveFunction):
+class GoldsteinPriceFunction(MathematicalFunction):
     name = "Goldstein Price Function"
     _name_ = "goldstein_price_function"
     __name__ = "GoldsteinPriceFunction"
@@ -20,10 +20,10 @@ def objective_function_dict(self, params):
         y = params["x1"]
 
         loss1 = 1 + (x + y + 1) ** 2 * (
-            19 - 14 * x + 3 * x ** 2 - 14 * y + 6 * x * y + 3 * y ** 2
+            19 - 14 * x + 3 * x**2 - 14 * y + 6 * x * y + 3 * y**2
         )
         loss2 = 30 + (2 * x - 3 * y) ** 2 * (
-            18 - 32 * x + 12 * x ** 2 + 48 * y - 36 * x * y + 27 * y ** 2
+            18 - 32 * x + 12 * x**2 + 48 * y - 36 * x * y + 27 * y**2
         )
 
         loss = loss1 * loss2

surfaces/mathematical_functions/gramacy_and_lee_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class GramacyAndLeeFunction(ObjectiveFunction):
+class GramacyAndLeeFunction(MathematicalFunction):
     name = "Gramacy And Lee Function"
     _name_ = "gramacy_and_lee_function"
     __name__ = "GramacyAndLeeFunction"

surfaces/mathematical_functions/griewank_function.py

@@ -5,10 +5,10 @@
 
 import numpy as np
 
-from ._base_objective_function import ObjectiveFunction
+from ._base_objective_function import MathematicalFunction
 
 
-class GriewankFunction(ObjectiveFunction):
+class GriewankFunction(MathematicalFunction):
     name = "Griewank Function"
     _name_ = "griewank_function"
     __name__ = "GriewankFunction"
@@ -24,7 +24,7 @@ def objective_function_dict(self, params):
             dim_str = "x" + str(dim)
             x = params[dim_str]
 
-            loss_sum += x ** 2 / 4000
+            loss_sum += x**2 / 4000
             loss_product *= np.cos(x / np.sqrt(dim + 1))
 
         loss = loss_sum - loss_product + 1