def compare_dataset_size(train_datasets, test_dataset, K=10, out_dir="."):
""" Generate plot to compare effects of dataset size.
Args:
- train_datasets (list of dict): A list of training datasets from the same distribution.
- test_dataset (dict): The test dataset.
- K (int): The degree of the polynomial to fit. Note: 1 <= K <= 10
"""
model = PolynomialRegression(K=K)
title = "Comparing Effects of Dataset Size"
x_label = "Dataset size"
y_label = "Error (Log Scale)"
# One for training error, one for testing error
labels = ("Train Error", "Test Error")
x_s = [[], []]
y_s = [[], []]
test_X = test_dataset["X"]
test_Y = test_dataset["Y"]
for dataset in train_datasets:
train_X = dataset["X"]
train_Y = dataset["Y"]
num_samples = len(train_X)
x_s[0].append(num_samples)
x_s[1].append(num_samples)
model.fit(train_X, train_Y)
train_loss = model.compute_mse(train_X, train_Y)
test_loss = model.compute_mse(test_X, test_Y)
y_s[0].append(np.log(train_loss))
y_s[1].append(np.log(test_loss))
visualize(x_s,
y_s,
labels,
title,
x_label,
y_label,
savefig=True,
out_dir=out_dir)
def compare_regularization(train_dataset,
test_dataset,
K,
l2_coefs,
title_prefix="",
out_dir="."):
""" Generate plot to compare effects of model complexity
"""
title = f"{title_prefix}Comparing Effects of Regularization"
x_label = "L2 Coefficient (Lambda Term) 1e-2"
y_label = "Error (Log Scale)"
labels = ("Train Error", "Test Error")
x_s = [[], []]
y_s = [[], []]
train_X = train_dataset["X"]
train_Y = train_dataset["Y"]
test_X = test_dataset["X"]
test_Y = test_dataset["Y"]
for l2_coef in l2_coefs:
x_s[0].append(l2_coef * 1e2)
x_s[1].append(l2_coef * 1e2)
model = PolynomialRegression(K)
model.fit_with_l2_regularization(train_X, train_Y, l2_coef)
train_loss = model.compute_mse(train_X, train_Y)
test_loss = model.compute_mse(test_X, test_Y)
y_s[0].append(np.log(train_loss))
y_s[1].append(np.log(test_loss))
visualize(x_s,
y_s,
labels,
title,
x_label,
y_label,
savefig=True,
out_dir=out_dir)
def compare_model_complexity(train_dataset,
test_dataset,
Ks,
title_prefix="",
out_dir="."):
""" Generate plot to compare effects of model complexity
"""
title = f"{title_prefix}Comparing Effects of Model Complexity"
x_label = "Model Complexity (Degree of Polynomial)"
y_label = "Error (Log Scale)"
labels = ("Train Error", "Test Error")
x_s = [[], []]
y_s = [[], []]
train_X = train_dataset["X"]
train_Y = train_dataset["Y"]
test_X = test_dataset["X"]
test_Y = test_dataset["Y"]
for K in Ks:
x_s[0].append(K)
x_s[1].append(K)
model = PolynomialRegression(K)
model.fit(train_X, train_Y)
train_loss = model.compute_mse(train_X, train_Y)
test_loss = model.compute_mse(test_X, test_Y)
y_s[0].append(np.log(train_loss))
y_s[1].append(np.log(test_loss))
visualize(x_s,
y_s,
labels,
title,
x_label,
y_label,
savefig=True,
out_dir=out_dir)