def run_logistic_regression(train_subset=45000, valid_size=5000, test=False):
train_dataset, train_labels = load_train_data()
train_dataset = reformat_dataset(train_dataset)
valid_dataset = train_dataset[:valid_size, :]
valid_labels = train_labels[:valid_size]
train_dataset = train_dataset[valid_size:valid_size + train_subset, :]
train_labels = train_labels[valid_size:valid_size + train_subset]
print 'Training set size: ', train_dataset.shape, train_labels.shape
print 'Validation set size: ', valid_dataset.shape, valid_labels.shape
print 'Training...'
logreg = LogisticRegression()
logreg.fit(train_dataset, train_labels)
train_predict = logreg.predict(train_dataset)
valid_predict = logreg.predict(valid_dataset)
train_accuracy = accuracy(train_predict, train_labels)
valid_accuracy = accuracy(valid_predict, valid_labels)
print_accuracy(train_accuracy, valid_accuracy)
# Predict test data
if (not test):
return
print 'Predicting test dataset...'
test_dataset = load_test_data()
test_dataset = test_dataset.reshape((test_dataset.shape[0], test_dataset.shape[1] *
test_dataset.shape[2] * test_dataset.shape[3]))
test_predict = logreg.predict(test_dataset)
label_matrices_to_csv(test_predict, 'submission.csv')
def get_train_valid_data(train_subset=45000,
valid_size=5000,
reformat_data=True,
reformat_label=True):
"""
Get dataset from cifar10_train.pickle file, convert the data type of numpy.float32, and
separate the dataset into training set and validation set.
Take note that train_subset + valid_size cannot be more than 50000.
Keyword arguments:
train_subset -- the number of training set
valid_size -- the number of validation set
reformat_data -- if True, reformat the dataset to 2 dimension matrix. Else, keep the dataset
as 4 dimension matrix
reformat_label -- if True, reformat the labels to (n X num_labels) dimension matrix. Else,
keep the labels as 2 dimension matrix
"""
if train_subset + valid_size > 50000:
raise Exception('train_subset + valid_size cannot be more than 50000')
train_dataset, train_labels = load_train_data()
if reformat_data:
train_dataset = reformat_dataset(train_dataset)
if reformat_label:
train_labels = reformat_labels(train_labels)
train_dataset = train_dataset.astype(np.float32)
train_labels = train_labels.astype(np.float32)
# Create a validation dataset
valid_dataset = train_dataset[:valid_size]
valid_labels = train_labels[:valid_size]
train_dataset = train_dataset[valid_size:valid_size + train_subset]
train_labels = train_labels[valid_size:valid_size + train_subset]
print 'Training set size:', train_dataset.shape, train_labels.shape
print 'Validation set size:', valid_dataset.shape, valid_labels.shape
return train_dataset, train_labels, valid_dataset, valid_labels
def get_train_valid_data(train_subset=45000,
valid_size=5000,
reformat_data=True,
reformat_label=True):
"""
Get dataset from cifar10_train.pickle file, convert the data type of numpy.float32, and
separate the dataset into training set and validation set.
Take note that train_subset + valid_size cannot be more than 50000.
Keyword arguments:
train_subset -- the number of training set
valid_size -- the number of validation set
reformat_data -- if True, reformat the dataset to 2 dimension matrix. Else, keep the dataset
as 4 dimension matrix
reformat_label -- if True, reformat the labels to (n X num_labels) dimension matrix. Else,
keep the labels as 2 dimension matrix
"""
if train_subset + valid_size > 50000:
raise Exception('train_subset + valid_size cannot be more than 50000')
train_dataset, train_labels = load_train_data()
if reformat_data:
train_dataset = reformat_dataset(train_dataset)
if reformat_label:
train_labels = reformat_labels(train_labels)
train_dataset = train_dataset.astype(np.float32)
train_labels = train_labels.astype(np.float32)
# Create a validation dataset
valid_dataset = train_dataset[:valid_size]
valid_labels = train_labels[:valid_size]
train_dataset = train_dataset[valid_size:valid_size + train_subset]
train_labels = train_labels[valid_size:valid_size + train_subset]
print 'Training set size:', train_dataset.shape, train_labels.shape
print 'Validation set size:', valid_dataset.shape, valid_labels.shape
return train_dataset, train_labels, valid_dataset, valid_labels
