print("Loading MNIST Training data...")
X_train, y_train = mu.load_mnist(dataset='training')
y_train_true = mnist_two_filter(y_train)
print("True number of twos in training set:",np.sum(y_train_true))
# Perform grid search to find best regularization constant and threshold?
if find_best_lam:
print("Finding optimal lambda and threshold via regularization path.")
thresh_arr = np.linspace(-0.2,1.,num)
err_val = np.zeros((num,num))
err_train = np.zeros((num,num))
# Split training data into subtraining set, validation set
X_tr, y_tr, X_val, y_val = val.split_data(X_train, y_train, frac=frac, seed=seed)
# Filter y values to 0, 1 labels
y_tr_true = mnist_two_filter(y_tr)
y_val_true = mnist_two_filter(y_val)
# Loop over thresholds
for i in range(num):
# Internally loop over lambdas in regularization path
err_val[i,:], err_train[i,:], lams = val.linear_reg_path(X_tr, y_tr_true, X_val,
y_val_true, ri.fit_ridge,
lammax=lammax,
scale=scale,
num=num, error_func=val.loss_01,
thresh=thresh_arr[i], **kwargs)
print("Loading data...")
# Load a text file of integers:
y = np.loadtxt("../Data/hw1-data/star_labels.txt", dtype=np.int)
y = y.reshape(len(y), 1)
# Load a text file of feature names:
featureNames = open(
"../Data/hw1-data/star_features.txt").read().splitlines()
# Load a csv of floats as a sparse matrix:
X = io.mmread("../Data/hw1-data/star_data.mtx").tocsc()
# Split into training set, testing set
X_train, y_train, X_test, y_test = val.split_data(X,
y,
frac=test_frac,
seed=seed)
# Now split training set into training set, validation set
X_train, y_train, X_val, y_val = val.split_data(X_train,
y_train,
frac=val_frac,
seed=seed)
print("Train shapes:", X_train.shape, y_train.shape)
print("Val shapes:", X_val.shape, y_val.shape)
print("Test shapes:", X_test.shape, y_test.shape)
# Run analysis if answer cache doesn't exist
if not os.path.exists(cache):
print("Cache does not exist, running analysis...")
X_train, y_train = mu.load_mnist(dataset='training')
y_train_true = mnist_two_filter(y_train)
print("True number of twos in training set:", np.sum(y_train_true))
# Perform grid search to find best regularization constant and threshold?
if find_best_lam:
print("Finding optimal lambda and threshold via regularization path.")
thresh_arr = np.linspace(-0.2, 1., num)
err_val = np.zeros((num, num))
err_train = np.zeros((num, num))
# Split training data into subtraining set, validation set
X_tr, y_tr, X_val, y_val = val.split_data(X_train,
y_train,
frac=frac,
seed=seed)
# Filter y values to 0, 1 labels
y_tr_true = mnist_two_filter(y_tr)
y_val_true = mnist_two_filter(y_val)
# Loop over thresholds
for i in range(num):
# Internally loop over lambdas in regularization path
err_val[i, :], err_train[i, :], lams = val.linear_reg_path(
X_tr,
y_tr_true,
X_val,
y_val_true,
ri.fit_ridge,
# Run!
print("Loading data...")
# Load a text file of integers:
y = np.loadtxt("../Data/hw1-data/star_labels.txt", dtype=np.int)
y = y.reshape(len(y),1)
# Load a text file of feature names:
featureNames = open("../Data/hw1-data/star_features.txt").read().splitlines()
# Load a csv of floats as a sparse matrix:
X = io.mmread("../Data/hw1-data/star_data.mtx").tocsc()
# Split into training set, testing set
X_train, y_train, X_test, y_test = val.split_data(X, y, frac=test_frac, seed=seed)
# Now split training set into training set, validation set
X_train, y_train, X_val, y_val = val.split_data(X_train, y_train, frac=val_frac,
seed=seed)
print("Train shapes:",X_train.shape,y_train.shape)
print("Val shapes:",X_val.shape,y_val.shape)
print("Test shapes:",X_test.shape,y_test.shape)
# Run analysis if answer cache doesn't exist
if not os.path.exists(cache):
print("Cache does not exist, running analysis...")
# Set maximum lambda, minimum lambda
lammax = lu.compute_max_lambda(X_train,y_train)