def plot_steps(learner=None,
data=None,
criterion="sum-of-squares",
step=1,
num_steps=1000,
log_scale=True,
label=""):
"""
plots the training and test error for a learner.
data is the
learner_class is the class of the learning algorithm
criterion gives the evaluation criterion plotted on the y-axis
step specifies how many steps are run for each point on the plot
num_steps is the number of points to plot
"""
plt.ion()
plt.xlabel("step")
plt.ylabel("Average " + criterion + " error")
if log_scale:
plt.xscale('log') #plt.semilogx() #Makes a log scale
else:
plt.xscale('linear')
if data is None:
data = Data_from_file('data/holiday.csv',
num_train=19,
target_index=-1)
#data = Data_from_file('data/SPECT.csv', target_index=0)
# data = Data_from_file('data/mail_reading.csv', target_index=-1)
# data = Data_from_file('data/carbool.csv', target_index=-1)
random.seed(None) # reset seed
if learner is None:
learner = Linear_learner(data)
train_errors = []
test_errors = []
for i in range(1, num_steps + 1, step):
test_errors.append(
data.evaluate_dataset(data.test, learner.predictor, criterion))
train_errors.append(
data.evaluate_dataset(data.train, learner.predictor, criterion))
learner.display(2, "Train error:", train_errors[-1], "Test error:",
test_errors[-1])
learner.learn(num_iter=step)
plt.plot(range(1, num_steps + 1, step),
train_errors,
ls='-',
c='k',
label="training errors")
plt.plot(range(1, num_steps + 1, step),
test_errors,
ls='--',
c='k',
label="test errors")
plt.legend()
plt.pause(0.001)
plt.show(block=True)
learner.display(1, "Train error:", train_errors[-1], "Test error:",
test_errors[-1])
def plot_prediction(
learner=None,
data=None,
minx=0,
maxx=5,
step_size=0.01, # for plotting
label="function"):
plt.ion()
plt.xlabel("x")
plt.ylabel("y")
if data is None:
data = Data_from_file('data/simp_regr.csv',
prob_test=0,
boolean_features=False,
target_index=-1)
if learner is None:
learner = Linear_learner(data, squashed=False)
learner.learning_rate = 0.001
learner.learn(100)
learner.learning_rate = 0.0001
learner.learn(1000)
learner.learning_rate = 0.00001
learner.learn(10000)
learner.display(
1, "function learned is", learner.predictor_string(), "error=",
data.evaluate_dataset(data.train, learner.predictor, "sum-of-squares"))
plt.plot([e[0] for e in data.train], [e[-1] for e in data.train],
"bo",
label="data")
plt.plot(list(arange(minx, maxx, step_size)),
[learner.predictor([x]) for x in arange(minx, maxx, step_size)],
label=label)
plt.legend()
plt.draw()
def plot_polynomials(data=None,
learner_class=Linear_learner,
max_degree=5,
minx=0,
maxx=5,
num_iter=100000,
learning_rate=0.0001,
step_size=0.01, # for plotting
):
plt.ion()
plt.xlabel("x")
plt.ylabel("y")
if data is None:
data = Data_from_file('data/simp_regr.csv', prob_test=0,
boolean_features=False, target_index=-1)
plt.plot([e[0] for e in data.train], [e[-1] for e in data.train], "ko", label="data")
x_values = list(arange(minx, maxx, step_size))
line_styles = ['-', '--', '-.', ':']
colors = ['0.5', 'k', 'k', 'k', 'k']
for degree in range(max_degree):
data_aug = Data_set_augmented(data, [power_feat(n) for n in range(1, degree + 1)],
include_orig=False)
learner = learner_class(data_aug, squashed=False)
learner.learning_rate = learning_rate
learner.learn(num_iter)
learner.display(1, "For degree", degree,
"function learned is", learner.predictor_string(),
"error=", data.evaluate_dataset(data.train, learner.predictor, "sum-of-squares"))
ls = line_styles[degree % len(line_styles)]
col = colors[degree % len(colors)]
plt.plot(x_values, [learner.predictor([x]) for x in x_values], linestyle=ls, color=col,
label="degree=" + str(degree))
plt.legend(loc='upper left')
plt.draw()
def test(**args):
data = Data_from_file('data/SPECT.csv', target_index=0)
# data = Data_from_file('data/mail_reading.csv', target_index=-1)
# data = Data_from_file('data/carbool.csv', target_index=-1)
learner = Linear_learner(data, **args)
learner.learn()
print("function learned is", learner.predictor_string())
for ecrit in Data_set.evaluation_criteria:
test_error = data.evaluate_dataset(data.test, learner.predictor, ecrit)
print(" Average", ecrit, "error is", test_error)