def main():
fileW = FromFinessFileMLR.createAnOutputFile()
model = mlr.MLR()
#Number of descriptor should be 396 and number of population should be 50 or more
numOfPop = 50
numOfFea = 396
unfit = 1000
# Final model requirements
R2req_train = .6
R2req_validate = .5
R2req_test = .5
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY = FromDataFileMLR.getAllOfTheData(
)
TrainX, ValidateX, TestX = FromDataFileMLR.rescaleTheData(
TrainX, ValidateX, TestX)
unfit = 1000
fittingStatus = unfit
"""Create a population based on the number of features selected, in this case 10, from the pool of features"""
population = DifferentialEvolution.Create_A_Population(numOfPop, numOfFea)
fittingStatus, fitness = FromFinessFileMLR.validate_model(model,fileW, population, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
def append_to_file(new_vector, fileW):
#print new_vector
model = DE_BPSO_model.DE_BPSO_MODEL()
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY = FromDataFileMLR.getAllOfTheData(
)
TrainX, ValidateX, TestX = FromDataFileMLR.rescaleTheData(
TrainX, ValidateX, TestX)
FromFinessFileMLR.validate_model_and_append(model,fileW, new_vector, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
def main():
# BPSO parameters
num_pop = 50
num_feat = 385
num_gens = 1000
# initialize objects
model = mlr.MLR()
fdf = FromDataFileMLR.FromDataFileMLR()
fff = FromFinessFileMLR.FromFinessFileMR(fdf)
bpso = BinaryParticleSwarmOptimization(model, fff, num_pop, num_feat,
num_gens)
# load in data from files
trainX, trainY, validateX, validateY, testX, testY = fdf.getAllOfTheData()
trainX, validateX, testX = fdf.rescaleTheData(trainX, validateX, testX)
# BPSO algorithm
bpso.create_initial_population()
bpso.evaluate_population(trainX, trainY, validateX, validateY, testX,
testY)
bpso.create_initial_velocity()
initial_local_best_matrix, initial_local_fitness = bpso.create_initial_local_best_matrix(
)
bpso.create_initial_global_best_row()
bpso.evolve_population(initial_local_best_matrix, initial_local_fitness,
trainX, trainY, validateX, validateY, testX, testY)
def main():
np.random.seed()
# initialize objects
fileW = createAnOutputFile()
model = mlr.MLR()
# load in data from files
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY = FromDataFileMLR.getAllOfTheData(
)
TrainX, ValidateX, TestX = FromDataFileMLR.rescaleTheData(
TrainX, ValidateX, TestX)
# DE_BPSO algorithm
velocity = create_initial_velocity()
population = create_initial_population(velocity, Lambda=0.01)
x, fitness = FromFinessFileMLR.validate_model(model,fileW, population, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
local_best_matrix, local_fitness = create_initial_local_best_matrix(
population, fitness)
create_initial_global_best_row(local_best_matrix, local_fitness)
evolve_population(population, fitness, velocity, local_best_matrix, local_fitness, \
model, fileW, TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
def __init__(self, numOfPop, numOfFea):
self.filedata = FromDataFileMLR.DataFromFile()
self.fitnessdata = FromFinessFileMLR.FitnessResults()
self.NofIterations = 2000
self.alpha = 0.5
self.GlobalBestRow = ndarray(numOfFea)
self.GlobalBestFitness = 10000
self.VelocityM = ndarray((numOfPop, numOfFea))
self.LocalBestM = ndarray((numOfPop, numOfFea))
self.LocalBestM_Fit = ndarray(numOfPop)
def cal_fitness_DE(new_vector):
#print new_vector
model = DE_BPSO_model.MLR()
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY = FromDataFileMLR.getAllOfTheData(
)
TrainX, ValidateX, TestX = FromDataFileMLR.rescaleTheData(
TrainX, ValidateX, TestX)
fitness = FromFinessFileMLR.validate_single_model(model, new_vector, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
return fitness
def __init__(self, numOfPop, numOfFea):
# Acquires and formats data from Train, Validation, Test .csv files
self.filedata = FromDataFileMLR.DataFromFile()
# Performs data analysis on training, validation, and test data
self.analyzer = FromFinessFileMLR.FitnessResults()
self.NumIterations = 1000
self.alpha = 0.5 # starting alpha value
self.GlobalBestRow = ndarray(
numOfFea) # best-fitting population yet found
self.GlobalBestFitness = 10000 # fitness of GlobalBestRow, initialized very high
self.VelocityM = ndarray((numOfPop, numOfFea)) # Velocity matrix
self.LocalBestM = ndarray((numOfPop, numOfFea)) # local best matrix
self.LocalBestM_Fit = ndarray(numOfPop) # local best matrix fitnesses
def main():
# Number of descriptor should be 385 and number of population should be 50 or more
numOfPop = 50
numOfFea = 385
# create an object of Multiple Linear Regression model.
# The class is located in mlr file
model = mlr.MLR()
filedata = FromDataFileMLR.DataFromFile()
fitnessdata = FromFinessFileMLR.FitnessResults()
analyzer = Fitness(numOfPop, numOfFea)
# create an output file. Name the object to be FileW
fileW = analyzer.createAnOutputFile()
# we continue exhancing the model; however if after 1000 iteration no
# enhancement is done, we can quit
unfit = 1000
# Final model requirements: The following is used to evaluate each model. The minimum
# values for R^2 of training should be 0.6, R^2 of Validation should be 0.5 and R^2 of
# test should be 0.5
R2req_train = .6
R2req_validate = .5
R2req_test = .5
# getAllOfTheData is in FromDataFileMLR file. The following places the data
# (training data, validation data, and test data) into associated matrices
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY = filedata.getAllOfTheData(
)
TrainX, ValidateX, TestX = filedata.rescaleTheData(TrainX, ValidateX,
TestX)
fittingStatus = unfit
population = analyzer.createInitialPopulation(numOfPop, numOfFea)
fittingStatus, fitness = fitnessdata.validate_model(model,fileW, population, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
analyzer.CreateInitialVelocity(numOfPop, numOfFea)
copyto(analyzer.LocalBestM,
population) #initializing LocalBestMatrix as the initial population
copyto(analyzer.LocalBestM_Fit, fitness)
analyzer.FindGlobalBestRow()
analyzer.PerformOneMillionIteration(numOfPop, numOfFea, population, fitness, model, fileW, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
def main():
# GA parameters
num_pop = 50
num_feat = 385
num_gens = 1000
# initialize objects
model = mlr.MLR()
fdf = FromDataFileMLR.FromDataFileMLR()
fff = FromFinessFileMLR.FromFinessFileMR(fdf)
GA = GeneticAlgorithm(model, fff, num_pop, num_feat, num_gens)
# load in data from files
trainX, trainY, validateX, validateY, testX, testY = fdf.getAllOfTheData()
trainX, validateX, testX = fdf.rescaleTheData(trainX, validateX, testX)
# genetic algorithm
GA.create_initial_population()
GA.evaluate_population(trainX, trainY, validateX, validateY, testX, testY)
GA.evolve_population(trainX, trainY, validateX, validateY, testX, testY)
def main():
# DE parameters
num_pop = 50
num_feat = 385
num_gens = 100
# initialize objects
model = mlr.MLR()
FDF = FromDataFileMLR.FromDataFileMLR()
FFF = FromFinessFileMLR.FromFinessFileMR(FDF)
DE = DifferentialEvolution(model, FFF, num_pop, num_feat, num_gens)
# load in data from files
trainX, trainY, validateX, validateY, testX, testY = FDF.getAllOfTheData()
trainX, validateX, testX = FDF.rescaleTheData(trainX, validateX, testX)
# differential evolution algorithm
DE.create_initial_population()
DE.evaluate_population(trainX, trainY, validateX, validateY, testX, testY)
DE.evolve_population(trainX, trainY, validateX, validateY, testX, testY)
def evolve_population(initial_population, initial_fitness, initial_velocity,
initial_local_best_matrix, initial_local_fitness, model,
fileW, TrainX, TrainY, ValidateX, ValidateY, TestX,
TestY):
print('gen #' + str(0) + '\t\t min fit: ' + str(initial_fitness.min()) +
'\t\t avg fit: ' + str(np.average(initial_fitness)))
alpha = 0.5
for i in range(1, numOfGens):
velocity = update_velocity(initial_velocity, initial_population)
population = create_new_population(numOfPop, numOfFea,
initial_population, velocity,
initial_local_best_matrix, alpha, i)
x, fitness = FromFinessFileMLR.validate_model(model, fileW, population, \
TrainX, TrainY, ValidateX, ValidateY, TestX, TestY)
local_best_matrix, local_fitness = update_local_best_matrix(
population, fitness, initial_local_best_matrix,
initial_local_fitness)
update_global_best_row(local_best_matrix, local_fitness)
alpha = alpha - (0.17 / numOfGens)
print('gen #' + str(i) + '\t\t min fit: ' + str(fitness.min()) +
'\t\t avg fit: ' + str(np.average(fitness)))
def __init__(self):
self.DataFile = FromDataFileMLR.DataMLR()
self.FitnessFile = FromFinessFileMLR.FitnessMLR()
def evaluate_population(model, fileW, population, trainX, trainY, validateX,
validateY, testX, testY):
fittingStatus, fitness = FromFinessFileMLR.validate_model(
model, fileW, population, trainX, trainY, validateX, validateY, testX,
testY)
return fitness
def __init__(self):
self.fitnessdata = FromFinessFileMLR.FitnessResults()
def __init__(self):
self.DF = FromDataFileMLR.DataFile()
self.FF = FromFinessFileMLR.FitnessFile()
def __init__(self):
self.filedata = FromDataFileMLR.DataFromFile()
self.fitnessdata = FromFinessFileMLR.FitnessResults()
import time # provides timing for benchmarks from numpy import * # provides complex math and array functions from sklearn import svm # provides Support Vector Regression import csv import math import sys # Local files created by me import mlr import FromDataFileMLR import FromFinessFileMLR import BPSO """Create the output file""" fileW = FromFinessFileMLR.createAnOutputFile() #fileW = 0 model = mlr.MLR() start = time.time() #Number of descriptor should be 396 and number of population should be 50 or more """Number of population""" numOfPop = 50 """Number of total features""" numOfFea = 396 # Final model requirements R2req_train = .6 R2req_validate = .5 R2req_test = .5 alpha = 0.5
Compute a better fitness function """ import time # provides timing for benchmarks from numpy import * # provides complex math and array functions from sklearn import svm # provides Support Vector Regression import csv import math import sys # Local files created by me import mlr import FromDataFileMLR import FromFinessFileMLR import DifferentialEvolution fileW = FromFinessFileMLR.createAnOutputFile() #fileW = 0 model = mlr.MLR() #Number of descriptor should be 396 and number of population should be 50 or more """Number of population""" numOfPop = 50 """Number of total feautres""" #numOfFea = 396 numOfFea = 385 # Final model requirements R2req_train = .6 R2req_validate = .5 R2req_test = .5