def test_transform(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings("../Dataset/00-91-Drugs-All-In-One-File.csv", "../Dataset/VariableSetting.csv")
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
model = svm.SVR()
velocity = Velocity()
velocity_matrix = velocity.create_first_velocity()
# define the first population
# validation of a row generating random row for
population = Population(velocity_matrix=velocity_matrix)
population.create_first_population()
debpso = DEBPSO(population.population_matrix[0])
debpso.fit(data_manager.inputs[SplitTypes.Train], data_manager.targets[SplitTypes.Train])
data_manager.transformed_input[SplitTypes.Train] = debpso.transform(data_manager.inputs[SplitTypes.Train])
print("Population 0 row sum ", population.population_matrix[0].sum())
print("Selected feature descriptors",debpso.sel_descriptors_for_curr_population)
print("Transformed array", data_manager.transformed_input[SplitTypes.Train])
def test_run_experiment_for_DEBPSO_population_With_Velocity(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings(
"../Dataset/00-91-Drugs-All-In-One-File.csv",
"../Dataset/VariableSetting.csv")
#output_filename = FileManager.create_output_file()
#rescaling_normalizer = RescalingNormalizer()
#scikit_normalizer = ScikitNormalizer()
#data_manager = DataManager(normalizer=scikit_normalizer)
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
#data_manager.feature_selector = debpso
feature_selection_algo = None
model = None
if VariableSetting.Feature_Selection_Algorithm == 'GA' and VariableSetting.Model == 'SVM':
#feature_selection_algo = GA()
model = svm.SVR()
elif VariableSetting.Feature_Selection_Algorithm == 'DEBPSO' and VariableSetting.Model == 'SVM':
feature_selection_algo = DEBPSO()
model = svm.SVR()
experiment = Experiment(data_manager, model, feature_selection_algo)
experiment.run_experiment()
def test_verify_variable_assignment(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings(
"../Dataset/00-91-Drugs-All-In-One-File.csv",
"../Dataset/VariableSetting.csv")
print("Population ", VariableSetting.Population_Size)
print("Descriptor_Selection_Probability ",
VariableSetting.Descriptor_Selection_Probability)
print("Unfit ", VariableSetting.Unfit)
print("Required_r2_Train ", VariableSetting.Required_r2_Train)
print("Required_r2_Valid ", VariableSetting.Required_r2_Valid)
print("Required_r2_Test ", VariableSetting.Required_r2_Test)
print("Generation ", VariableSetting.Generation)
print("Stop_time ", VariableSetting.Stop_time)
print("Initial_alpha ", VariableSetting.Initial_alpha)
print("Ending_alpha ", VariableSetting.Ending_alpha)
print("Beta ", VariableSetting.Beta)
print("Gamma ", VariableSetting.Gamma)
print("Scaling_Factor ", VariableSetting.Scaling_Factor)
print("Crossover_Rate ", VariableSetting.Crossover_Rate)
print("No_of_Drugs ", VariableSetting.No_of_Drugs)
print("No_of_Descriptors ", VariableSetting.No_of_Descriptors)
print("Feature_Selection_Algorithm ",
VariableSetting.Feature_Selection_Algorithm)
print("Model ", VariableSetting.Model)
def test_fit(self):
#file_path = "../Dataset/00-91-Drugs-All-In-One-File.csv"
#loaded_data = FileManager.load_file(file_path)
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings("../Dataset/00-91-Drugs-All-In-One-File.csv", "../Dataset/VariableSetting.csv")
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
model = svm.SVR()
velocity = Velocity()
velocity_matrix = velocity.create_first_velocity()
# define the first population
# validation of a row generating random row for
population = Population(velocity_matrix=velocity_matrix)
population.create_first_population()
debpso = DEBPSO(population.population_matrix[1])
debpso.fit(data_manager.inputs[SplitTypes.Train], data_manager.targets[SplitTypes.Train])
def test_transform(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings(
"../Dataset/00-91-Drugs-All-In-One-File.csv",
"../Dataset/VariableSetting.csv")
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
model = svm.SVR()
velocity = Velocity()
velocity_matrix = velocity.create_first_velocity()
# define the first population
# validation of a row generating random row for
population = Population(velocity_matrix=velocity_matrix)
population.create_first_population()
debpso = DEBPSO(population.population_matrix[0])
debpso.fit(data_manager.inputs[SplitTypes.Train],
data_manager.targets[SplitTypes.Train])
data_manager.transformed_input[SplitTypes.Train] = debpso.transform(
data_manager.inputs[SplitTypes.Train])
print("Population 0 row sum ", population.population_matrix[0].sum())
print("Selected feature descriptors",
debpso.sel_descriptors_for_curr_population)
print("Transformed array",
data_manager.transformed_input[SplitTypes.Train])
def test_fit(self):
#file_path = "../Dataset/00-91-Drugs-All-In-One-File.csv"
#loaded_data = FileManager.load_file(file_path)
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings(
"../Dataset/00-91-Drugs-All-In-One-File.csv",
"../Dataset/VariableSetting.csv")
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
model = svm.SVR()
velocity = Velocity()
velocity_matrix = velocity.create_first_velocity()
# define the first population
# validation of a row generating random row for
population = Population(velocity_matrix=velocity_matrix)
population.create_first_population()
debpso = DEBPSO(population.population_matrix[1])
debpso.fit(data_manager.inputs[SplitTypes.Train],
data_manager.targets[SplitTypes.Train])
def test_run_experiment_for_DEBPSO_population_With_Velocity(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings("../Dataset/00-91-Drugs-All-In-One-File.csv", "../Dataset/VariableSetting.csv")
#output_filename = FileManager.create_output_file()
#rescaling_normalizer = RescalingNormalizer()
#scikit_normalizer = ScikitNormalizer()
#data_manager = DataManager(normalizer=scikit_normalizer)
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
#data_manager.feature_selector = debpso
feature_selection_algo = None
model = None
if VariableSetting.Feature_Selection_Algorithm == 'GA' and VariableSetting.Model == 'SVM':
#feature_selection_algo = GA()
model = svm.SVR()
elif VariableSetting.Feature_Selection_Algorithm == 'DEBPSO' and VariableSetting.Model == 'SVM':
feature_selection_algo = DEBPSO()
model = svm.SVR()
experiment = Experiment(data_manager, model, feature_selection_algo)
experiment.run_experiment()
def test_run_experiment_for_DEBPSO_population_With_Velocity(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings("../Dataset/00-91-Drugs-All-In-One-File.csv", "../Dataset/VariableSetting.csv")
#output_filename = FileManager.create_output_file()
zero_one_normalizer = ZeroOneMinMaxNormalizer()
data_manager = DataManager(normalizer=zero_one_normalizer)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
print("Train Data", data_manager.inputs)
def test_run_experiment_for_DEBPSO_population_With_Velocity(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings(
"../Dataset/00-91-Drugs-All-In-One-File.csv",
"../Dataset/VariableSetting.csv")
#output_filename = FileManager.create_output_file()
zero_one_normalizer = ZeroOneMinMaxNormalizer()
data_manager = DataManager(normalizer=zero_one_normalizer)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
print("Train Data", data_manager.inputs)
def test_verify_variable_assignment(self):
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings("../Dataset/00-91-Drugs-All-In-One-File.csv", "../Dataset/VariableSetting.csv")
print("Population ", VariableSetting.Population_Size)
print("Descriptor_Selection_Probability ", VariableSetting.Descriptor_Selection_Probability)
print("Unfit ", VariableSetting.Unfit)
print("Required_r2_Train ", VariableSetting.Required_r2_Train)
print("Required_r2_Valid ", VariableSetting.Required_r2_Valid)
print("Required_r2_Test ", VariableSetting.Required_r2_Test)
print("Generation ", VariableSetting.Generation)
print("Stop_time ", VariableSetting.Stop_time)
print("Initial_alpha ", VariableSetting.Initial_alpha)
print("Ending_alpha ", VariableSetting.Ending_alpha)
print("Beta ", VariableSetting.Beta)
print("Gamma ", VariableSetting.Gamma)
print("Scaling_Factor ", VariableSetting.Scaling_Factor)
print("Crossover_Rate ", VariableSetting.Crossover_Rate)
print("No_of_Drugs ", VariableSetting.No_of_Drugs)
print("No_of_Descriptors ", VariableSetting.No_of_Descriptors)
print("Feature_Selection_Algorithm ", VariableSetting.Feature_Selection_Algorithm)
print("Model ", VariableSetting.Model)
from sklearn.linear_model import RandomizedLasso, LinearRegression
from sklearn.svm import LinearSVC
from src.DEBPSO import DEBPSO
from src.Experiment import Experiment
from src.Normalizer import ZeroOneMinMaxNormalizer
from sklearn.preprocessing import MinMaxScaler
from src.Population import Population
from src.ReadData import ReadData
from src.SplitTypes import SplitTypes
from src.FileManager import FileManager
from src.DataManager import DataManager
from src.VariableSetting import VariableSetting
from src.Velocity import Velocity
read_data = ReadData()
loaded_data = read_data.read_data_and_set_variable_settings(
"../Dataset/00-91-Drugs-All-In-One-File.csv",
"../Dataset/VariableSetting.csv")
output_filename = FileManager.create_output_file()
#normalizer = ZeroOneMinMaxNormalizer()
#normalizer = MinMaxScaler()
normalizer = None
data_manager = DataManager(normalizer=normalizer)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets()
#data_manager.feature_selector = debpso
#set feature selection algorithm based on variable settings