def test_file_manager(self):
file_manager = FileManager()
file_manager.load_file("../Datasets/test.data")
normalize_data_1 = [[2.0, 2.0, 2.0, 2.0, [0, 1, 0]]]
normalize_data_2 = [[1.0, 1.0, 1.0, 1.0, [1, 0, 0]]]
self.assertEqual(file_manager.get_train_data(), normalize_data_1)
self.assertEqual(file_manager.get_test_data(), normalize_data_2)
def __init__(self, initial_population, generations):
"""
A genetic algorithm is used to learn the weights and bias of a topology
fixed network.
"""
super().__init__(initial_population)
#self.expected_precision = expected_precision
self.generation_span = generations
self.precision = 0
self.epoch = 0
self.num_inputs = 4
self.neurons_per_layer = [self.num_inputs, 4, 3]
# Build Fixed Neural Network, with 4 inputs
self.neural_network = NeuralNetwork(self.num_inputs)
# The neural network has 3 layers with 3,4 and 3 neurons in each
self.neural_network.buildFixed(self.neurons_per_layer)
self.test_values = 20
# Parse data set
file_manager = FileManager()
file_manager.load_file("../Datasets/iris.data")
self.train_data = file_manager.get_train_data()
self.test_data = file_manager.get_test_data()
self.neurons_position = []
self.x_plot = []
self.y_plot = []
def main():
# Parse data set
file_manager = FileManager()
file_manager.load_file("../Datasets/iris.data")
train_data = file_manager.get_train_data()
test_data = file_manager.get_test_data()
number_of_epochs = 2000
# Training data can be shuffled
# shuffle(train_data)
"""
Genetic Algorithm (Tarea 3)
"""
# -------------------------------------------------
genetic = GeneticFixedTopology(100, 1000)
best_neural_network = genetic.run()
genetic.plot_results()
def test_fit(self):
file_path = "../Dataset/00-91-Drugs-All-In-One-File.csv"
loaded_data = FileManager.load_file(file_path)
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets(test_split=0.15,
train_split=0.70)
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])
print("Population 1 row sum ", population.population_matrix[1].sum())
print("Selected feature descriptors",
debpso.sel_descriptors_for_curr_population)
def read_data_and_set_variable_settings(self, data_file_path, variable_file_path):
loaded_data = FileManager.load_file(data_file_path)
no_of_drugs = loaded_data.shape[0]
no_of_descriptors = loaded_data.shape[1] - 1 # excluding the last column that is the y axis
variables = FileManager.load_variable_file(variable_file_path)
VariableSetting.set_variables(variables, no_of_drugs, no_of_descriptors)
return loaded_data
def read_data_and_set_variable_settings(self, data_file_path,
variable_file_path):
loaded_data = FileManager.load_file(data_file_path)
no_of_drugs = loaded_data.shape[0]
no_of_descriptors = loaded_data.shape[
1] - 1 # excluding the last column that is the y axis
variables = FileManager.load_variable_file(variable_file_path)
VariableSetting.set_variables(variables, no_of_drugs,
no_of_descriptors)
return loaded_data
def test_fit(self):
file_path = "../Dataset/00-91-Drugs-All-In-One-File.csv"
loaded_data = FileManager.load_file(file_path)
data_manager = DataManager(normalizer=None)
data_manager.set_data(loaded_data)
data_manager.split_data_into_train_valid_test_sets(test_split=0.15, train_split=0.70)
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])
print("Population 1 row sum ", population.population_matrix[1].sum())
print("Selected feature descriptors",debpso.sel_descriptors_for_curr_population)
from src.FileManager import FileManager
from src.DataManager import DataManager
from src.Population import Population
from src.Normalizer import *
no_of_populations = 50 # should be 50 population
no_of_descriptors = 385 # should be 385 descriptors
unfit = 1000
required_r2 = {}
required_r2[SplitTypes.Train] = .6
required_r2[SplitTypes.Valid] = .5
required_r2[SplitTypes.Test] = .5
file_path = "../Dataset/00-91-Drugs-All-In-One-File.csv"
loaded_data = FileManager.load_file(file_path)
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(test_split=0.15, train_split=0.70)
model = svm.SVR()
population = Population()
population.load_data()
import numpy as np
import Bio
print(Bio.__version__)
exit(0)
from src.FileManager import FileManager
__author__ = 'FalguniT'
#Ehux JGI Fasta file
Ehux_JGI_file_path = "../data/Ehux_JGI.fasta"
Ehux_JGI_data = FileManager.load_file(Ehux_JGI_file_path)
#Geph Blast output file
Geph_file_path = "../data/Ehux_Geph_Blast_060916.txt.p1"
Geph_data = FileManager.load_file(Geph_file_path)
Geph_count = len(Geph_data)
print("geph count", Geph_count)
#ISO blast output file
ISO_file_path = "../data/Ehux_ISO_Blast_060916.txt.p1"
ISO_data = FileManager.load_file(ISO_file_path)
ISO_count = len(ISO_data)
print("ISO_ count", ISO_count)
#Strains 92A blast
strains_92A_file_path = "../data/Ehux_strains_92A_Blast_060816.txt.p1"
strains_92A_data = FileManager.load_file(strains_92A_file_path)
strains_92A_count = len(strains_92A_data)
