def prob_5():
arff = Arff('datasets/cars.arff')
arff.shuffle()
test = arff.create_subset_arff(slice(arff.instance_count//10))
training = arff.create_subset_arff(slice(arff.instance_count//10,None))
tf = test.get_features()
tl = test.get_labels()
splits = k_fold_cv(arff)
arff = arff.create_subset_arff(slice(arff.instance_count//4,None))
d = DecisionTreeLearner()
d.train(arff.get_features(), arff.get_labels())
a = d.tree
arff = Arff('datasets/voting.arff')
arff.shuffle()
arff = arff.create_subset_arff(slice(arff.instance_count//4,None))
d = DecisionTreeLearner()
d.train(arff.get_features(), arff.get_labels())
b = d.tree
return a, b
def prob_3(weighted_d = False):
test_arff = Arff("housing_testing_data.arff")
train_arff = Arff("housing_training_data.arff")
test_arff.shuffle()
train_arff.shuffle()
test_arff.normalize()
train_arff.normalize()
K = [1, 3, 5, 7, 9, 11, 13, 15]
A = []
for k_hat in K:
test_data = np.hstack((test_arff.get_features().data, test_arff.get_labels().data))
train_data = np.hstack((train_arff.get_features().data, train_arff.get_labels().data))
KNNC = KNNClassifier(k_hat, train_data, test_data)
A.append(KNNC.get_accuracy_regress(weighted_d))
plt.plot(K, A, label="")
t = "KNN Regression M.S.E Housing"
if weighted_d:
t += "(weighted-d)"
weighted_d
plt.title(t)
plt.xlabel("K")
plt.ylabel("M.S.E")
# plt.legend()
plt.show()
def main():
arff = Arff(sys.argv[1])
pl = PerceptronLearner()
features = arff.get_features()
labels = arff.get_labels()
accuracy_matrix = np.zeros((5, 20))
for i in range(5):
pl.train(features, labels)
a = pl.accuracy_tracker[:20]
# pad to make 20 wide
a = np.pad(a, (0, 20 - len(a)), 'constant', constant_values=a[-1])
accuracy_matrix[i] = a
# Average the accuracies of each step
print(accuracy_matrix)
avg_accuracy = np.sum(accuracy_matrix, axis=0) / 5
print(avg_accuracy)
plt.plot(1 - avg_accuracy)
plt.xlabel("Epochs")
plt.ylabel("Avg Misclassification Rate")
plt.title("Avg Misclassification Rate Over Epochs")
plt.show()
def setUp(self):
path = os.path.join(utils.get_root(), "test/datasets/cm1_req.arff")
data = Arff(arff=path)
self.features = data.get_features()
self.labels = data.get_labels()
self.learner = BaselineLearner()
def prob0haccomplete():
arff = Arff('datasets/labor.arff', label_count=1)
# Trim the id column
arff = arff.create_subset_arff(col_idx=slice(1, None))
arff = arff.get_features()
hac = HAC(simple=False)
hac.train(arff, verbose=True, printk=[5])
def prob0():
arff = Arff('datasets/labor.arff', label_count=1)
# Trim the id column
arff = arff.create_subset_arff(col_idx=slice(1, None))
arff = arff.get_features()
km = KMeans(5)
km.train(arff, verbose=True, centers=arff.data[:5])
def prob_0():
arff = Arff('datasets/lenses.arff')
d = DecisionTreeLearner()
f = arff.get_features()
l = arff.get_labels()
d.train(f,l)
print(d.tree)
def main():
arff = Arff(sys.argv[1])
features = arff.get_features()
labels = arff.get_labels()
pl = PerceptronLearner()
pl.train(features, labels)
visualize_training(features, labels, pl)
def setup():
arff = Arff('datasets/labor.arff', label_count=1)
# Trim the id column
arff = arff.create_subset_arff(col_idx=slice(1, None))
arff = arff.get_features()
hac = HAC()
hac.nominal_indicies = np.where(np.array(arff.attr_types) == 'nominal')[0]
print('33,44', hac.get_distance(arff.data[33], arff.data[44]))
print('25,34', hac.get_distance(arff.data[25], arff.data[34]))
def prob_3():
print('cars')
arff = Arff('datasets/cars.arff')
arff.shuffle()
d = DecisionTreeLearner()
d.train(arff.get_features(), arff.get_labels())
a = d.tree
print()
print('voting')
arff = Arff('datasets/voting.arff')
arff.shuffle()
d = DecisionTreeLearner()
d.train(arff.get_features(), arff.get_labels())
b = d.tree
return a, b
def prob_2(weighted_d = False):
""" """
k = 3
test_arff = Arff("magic_telescope_testing_data.arff")
train_arff = Arff("magic_telescope_training_data.arff")
test_arff.shuffle()
train_arff.shuffle()
# attributes = test_arff.get_attr_names()
test_data = np.hstack((test_arff.get_features().data, test_arff.get_labels().data))
train_data = np.hstack((train_arff.get_features().data, train_arff.get_labels().data))
KNNC = KNNClassifier(k, train_data, test_data)
acc = KNNC.get_accuracy(weighted_d)
test_arff.normalize()
train_arff.normalize()
n_test_data = np.hstack((test_arff.get_features().data, test_arff.get_labels().data))
n_train_data = np.hstack((train_arff.get_features().data, train_arff.get_labels().data))
n_KNNC = KNNClassifier(k, n_test_data, n_train_data)
acc_n = n_KNNC.get_accuracy(weighted_d)
# print(np.array([[acc,acc_n]]))
print(acc,acc_n)
# show_table(["Not Normalized" "Normailzed"], ["Accuracy"], np.array([[acc,acc_n]]), title = "Normalized vs Non-normalized, k=3")
K = [1, 3, 5, 7, 9, 11, 13, 15]
A = []
for k_hat in K:
# n_test_data = np.hstack((test_arff.get_features().data, test_arff.get_labels().data))
# n_train_data = np.hstack((train_arff.get_features().data, train_arff.get_labels().data))
n_KNNC = KNNClassifier(k_hat, n_train_data, n_test_data)
A.append(n_KNNC.get_accuracy(weighted_d))
plt.plot(K, A, label="")
t = "KNN Accuracy Telesc. "
if weighted_d:
t += "(weighted-d)"
plt.title(t)
plt.xlabel("K")
plt.ylabel("Accuracy")
# plt.legend()
plt.show()
def prob_6():
""" """
k = 3
test_arff = Arff("magic_telescope_testing_data.arff")
train_arff = Arff("magic_telescope_training_data.arff")
test_arff.shuffle()
train_arff.shuffle()
test_arff.normalize()
train_arff.normalize()
K = [1, 3, 5]
T = []
A = []
T_KSM = []
A_KSM = []
for k_hat in K:
test_data = np.hstack((test_arff.get_features().data, test_arff.get_labels().data))
train_data = np.hstack((train_arff.get_features().data, train_arff.get_labels().data))
KNNC = KNNClassifier(k_hat, train_data, test_data)
t = time.time()
A.append(KNNC.get_accuracy())
T.append(time.time() - t)
KNNC.induce_KSM()
t = time.time()
A_KSM.append(KNNC.get_accuracy())
T_KSM.append(time.time() - t)
ax = plt.axes(projection='3d')
ax.plot(K, A, T, label="No-KSM")
ax.plot(K, A_KSM, T_KSM, label="KSM")
ax.set_xlabel('K')
ax.set_ylabel('Accuracy')
ax.set_zlabel('Time')
t = "KNN Accuracy w/ IKSM"
plt.title(t)
plt.legend()
plt.show()
def test_get_features(self):
""" Tests construction of Arff from path, arff, numpy array
"""
# Create a Matrix object from arff
credit = Arff(arff=self.credit_data_path, label_count=1)
credit.label_count=0
np.testing.assert_equal(credit.data, credit.get_features().data)
## Test label inference
credit.label_count = 5
self.assertEqual(credit.get_labels().shape, (690, 5))
## Copy last 8 columns
credit2 = Arff(credit, col_idx=slice(-8, None))
self.assertEqual(credit2.label_count, 5)
self.assertEqual((690,3), credit2.get_features().shape)
## Verify 0 labels
credit.label_count = 0
self.assertEqual((690, 16), credit.get_features().shape)
self.assertEqual((690, 0), credit.get_labels().shape)
def prob2():
iris = Arff('datasets/iris.arff')
features = iris.get_features()
# features.normalize()
# Train k means for 2-7
ks = [2, 3, 4, 5, 6, 7]
for k in ks:
km = KMeans(k)
km.train(features)
hac2 = HAC(simple=False)
hac2.train(features, printk=ks)
def prob_3():
# Use regression knn on housing price prediction dataset
train = Arff('datasets/housing_train.arff')
test = Arff('datasets/housing_test.arff')
train.normalize()
test.normalize()
krange = np.arange(1, 16, 2)
mses = []
for k in krange:
knn = KNN(k)
preds = knn.knn(train.get_features(), train.get_labels(),
test.get_features())
mse = sum((preds - np.ravel(test.get_labels().data))**2) / len(preds)
mses.append(mse)
plt.plot(krange, mses)
plt.title("K Size Versus MSE on Housing Prices")
plt.xlabel("K")
plt.ylabel("Mean Squared Error")
plt.show()
def test_cases():
# test_1()
attr_types = [
"real",
"real",
"real",
"real",
"cat",
"real",
"cat",
"real",
"real",
"cat",
"real",
"cat",
"cat",
"cat",
"cat",
"cat",
"cat"
]
attr_idx = [
[],
[],
[],
[],
['none','tcf','tc'],
[],
['none','ret_allw','empl_contr'],
[],
[],
['yes','no'],
[],
['below_average','average','generous'],
['yes','no'],
['none','half','full'],
['yes','no'],
['none','half','full'],
['bad','good']
]
k = 5
arff = Arff("labor.arff")
arff.normalize()
features = arff.get_features().data
labels = arff.get_labels().data
# attributes = arff.get_attr_names()
data = np.hstack((features, labels))[:, 1:]
kmc = KMC(k, data, data, attr_types, attr_idx)
kmc.train(tol=0)
def prob_4_telescope():
# Repeat experiments for magic telescope and housing using weights (w = 1/dist**2)
train = Arff('datasets/magic_telescope_train.arff')
test = Arff('datasets/magic_telescope_test.arff')
train.normalize()
test.normalize()
krange = np.arange(1, 16, 2)
accs = []
for k in krange:
knn = KNN(k, weighting=True)
predictions = knn.knn(train.get_features(), train.get_labels(),
test.get_features())
acc = predictions == np.ravel(test.get_labels().data)
print("k:", k, "accuracy:", sum(acc) / len(acc))
accs.append(sum(acc) / len(acc))
plt.plot(krange, accs)
plt.title("K Size Versus Accuracy")
plt.xlabel("K")
plt.ylabel("Accuracy")
plt.show()
def prob_4_housing():
# Repeat experiments for magic telescope and housing using weights (w = 1/dist**2)
train = Arff('datasets/housing_train.arff')
test = Arff('datasets/housing_test.arff')
train.normalize()
test.normalize()
krange = np.arange(1, 16, 2)
mses = []
for k in krange:
knn = KNN(k, weighting=True)
preds = knn.knn_regression(train.get_features(), train.get_labels(),
test.get_features())
mse = np.sum(
(preds - np.ravel(test.get_labels().data))**2, axis=0) / len(preds)
mses.append(mse)
plt.plot(krange, mses)
plt.title("K Size Versus MSE on Housing (Weighted)")
plt.xlabel("K")
plt.ylabel("Mean Squared Error")
plt.show()
def prob_2():
# try first without normalizing
train = Arff('datasets/magic_telescope_train.arff')
test = Arff('datasets/magic_telescope_test.arff')
k = KNN(3)
predictions = k.knn(train.get_features(), train.get_labels(),
test.get_features())
acc = predictions == np.ravel(test.get_labels().data)
print("Before normalization:", sum(acc) / len(acc))
train.normalize()
test.normalize()
predictions = k.knn(train.get_features(), train.get_labels(),
test.get_features())
acc = predictions == np.ravel(test.get_labels().data)
print("After normalization:", sum(acc) / len(acc))
print("PART TWO:")
krange = np.arange(1, 16, 2)
accs = []
for k in krange:
knn = KNN(k)
predictions = knn.knn(train.get_features(), train.get_labels(),
test.get_features())
acc = predictions == np.ravel(test.get_labels().data)
print("k:", k, "accuracy:", sum(acc) / len(acc))
accs.append(sum(acc) / len(acc))
plt.plot(krange, accs)
plt.title("K Size Versus Accuracy")
plt.xlabel("K")
plt.ylabel("Accuracy")
plt.show()
from toolkit.perceptron_learner import PerceptronLearner
from toolkit.arff import Arff
import sys
import numpy as np
def rnd4(obj):
if isinstance(obj, np.ndarray):
return obj
elif isinstance(obj, (int, float, complex)):
return "{:.4f}".format(obj)
arff = Arff(sys.argv[1])
features = arff.get_features()
labels = arff.get_labels()
pl = PerceptronLearner()
weights = []
for i in range(10):
pl.train(features, labels)
weights.append(pl.weights)
avg_weights = np.sum(weights, axis=0) / 10
names = arff.get_attr_names()
for i in range(len(avg_weights)):
print(rnd4(avg_weights[i]), names[i])
