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 __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 __init__(self):
self.filedata = FromDataFileMLR.DataFromFile()
self.fitnessdata = FromFinessFileMLR.FitnessResults()
def __init__(self):
self.fitnessdata = FromFinessFileMLR.FitnessResults()