def main():
x, y = dataloader(mode='train', reduced=False)
x_test = dataloader(mode='test', reduced=False)
'''For the dataloader there are two modes train and test, depending on the dataset loaded.'''
x = standardize(x)
x_test = standardize(x_test)
config = Config(batch_size=120,
num_epochs=400,
learning_rate=5 * 10**-4,
lambda_=2.15443469003e-05,
mode='train')
log_class = LogisticClassifier(config, (build_polynomial(x), y))
log_class.train(show_every=10)
predictions_test = log_class.predict_submission(
log_class(build_polynomial(x_test)))
create_csv_submission(np.arange(350000, 350000 + x_test.shape[0]),
predictions_test, 'dataset/submission_0x.csv')
def main():
x, y = dataloader(mode='train', reduced=False)
x_test = dataloader(mode='test', reduced=False)
x = standardize(x)
x_test = standardize(x_test)
config = Config(batch_size=120,
num_epochs=300,
learning_rate=5 * 10**-4,
lambda_=2.15443469003e-05,
mode='train')
ensemble = EnsembleClassifiers(config,
build_polynomial(x),
y,
50,
LogisticClassifier,
label='ensemble_50_log')
ensemble.train()
predictions_test = ensemble.predict(ensemble(build_polynomial(x_test)))
create_csv_submission(np.arange(350000, 350000 + x_test.shape[0]),
predictions_test, 'dataset/submission_0x.csv')
def find_best_batch(batch_sizes):
x, y = dataloader(mode='train', reduced=False)
x = standardize(x)
best_size = 0
best_accuracy = 0
for idx, batch_size in enumerate(batch_sizes):
print('Ensemble nr ' + str(idx) + 30 * '=')
config = Config(batch_size=batch_size, num_epochs=300, learning_rate=5 * 10 ** -4,
lambda_= 2.16e-05)
ensemble = EnsembleClassifiers(config, build_polynomial(x), y, 2, LogisticClassifier,
label='ensemble_' + str(idx))
ensemble.train()
print("ensemble accuracy " + str(ensemble.accuracy) + 30 * "=")
if ensemble.accuracy > best_accuracy:
best_accuracy = ensemble.accuracy
best_size = batch_size
print("best_lambda :", best_size)
def find_best_regularizer(lambdas):
"""Hyperparamenter search for regularization constant"""
x, y = dataloader(mode='train', reduced=False)
x = standardize(x)
best_lambda = 0
best_accuracy = 0
for idx, lambda_ in enumerate(lambdas):
print('Ensemble nr ' + str(idx) + 30 * '=')
config = Config(batch_size=200, num_epochs=200, learning_rate=5 * 10 ** -4, lambda_=lambda_)
ensemble = EnsembleClassifiers(config, build_polynomial(x), y, 10, LogisticClassifier,
label='ensemble_' + str(idx))
ensemble.train()
print("ensemble accuracy " + str(ensemble.accuracy) + 30 * "=")
if ensemble.accuracy > best_accuracy:
best_accuracy = ensemble.accuracy
best_lambda = lambda_
print("best_lambda :", best_lambda)
from torch import optim
import torch
import torch.utils.data
import numpy as np
from torch.autograd import Variable
from torch import nn
import torch.nn.functional as f
from src.utils import dataloader, standardize, split_data, build_polynomial
x, y = dataloader(mode='train', reduced=False)
x = standardize(x)
train_dataset, test_dataset = split_data(x, y, ratio=0.9)
test_data, test_target = test_dataset
train_data, train_target = train_dataset
test_data = build_polynomial(test_data)
train_data = build_polynomial(train_data)
num_features = np.shape(train_data)[1]
train = torch.utils.data.TensorDataset(
torch.from_numpy(train_data).type(torch.FloatTensor),
torch.from_numpy(train_target).type(torch.LongTensor))
train_loader = torch.utils.data.DataLoader(train, batch_size=128, shuffle=True)
test = torch.utils.data.TensorDataset(
torch.from_numpy(test_data).type(torch.FloatTensor),
torch.from_numpy(test_target).type(torch.LongTensor))
test_loader = torch.utils.data.DataLoader(test, batch_size=128, shuffle=True)
class SimpleNN(torch.nn.Module):
def __init__(self,
batch_size=128,
# find_best_regularizer(np.logspace(-5, -2, 10))
x, y = dataloader(mode='train', reduced=False)
x_test = dataloader(mode='test', reduced=False)
# print(x.shape)
# print(x_test.shape)
x = standardize(x)
x_test = standardize(x_test)
# train_dataset, test_dataset = split_data(x, y, ratio=0.9)
# train_set = (build_polynomial(train_dataset[0]), train_dataset[1])
# test_set = (build_polynomial(test_dataset[0]), test_dataset[1])
# # # # x = dataloader(mode='test', reduced=False)
# # # # x = standardize(x)
# # # # x = build_polynomial(x)
config = Config(batch_size=120, num_epochs=400, learning_rate=5 * 10 ** -4,
lambda_=2.15443469003e-05, mode='train')
log_class = LogisticClassifier(config, (build_polynomial(x), y))
log_class.train(show_every=1p)
predictions_test = log_class.predict_submission(log_class(build_polynomial(x_test)))
log_class.plot_accuracy()
log_class.plot_convergence()
ensemble = EnsembleClassifiers(config, build_polynomial(x), y, 5, LogisticClassifier,
label='ensemble_2_log')
#
ensemble.train()
# ensemble.plot_convergence()
# ensemble.plot_accuracy()
# ensemble.save()
# # ensemble.load_weights()
predictions_test = ensemble.predict(ensemble(build_polynomial(x_test)))
create_csv_submission(np.arange(350000, 350000 + x_test.shape[0]), predictions_test,
'dataset/submission_10.csv')