def test_perceptron():
iris = DataSet(name="iris")
classes = ["setosa", "versicolor", "virginica"]
iris.classes_to_numbers()
perceptron = PerceptronLearner(iris)
# PerceptronLearner might be wrong. Just check if prediction is in range
assert perceptron([5, 3, 1, 0.1]) in range(len(classes))
def test_neural_network_learner():
iris = DataSet(name="iris")
classes = ["setosa", "versicolor", "virginica"]
iris.classes_to_numbers()
nNL = NeuralNetLearner(iris)
# NeuralNetLearner might be wrong. Just check if prediction is in range
assert nNL([5, 3, 1, 0.1]) in range(len(classes))
def test_perceptron():
iris = DataSet(name="iris")
iris.classes_to_numbers()
classes_number = len(iris.values[iris.target])
perceptron = PerceptronLearner(iris)
tests = [([5, 3, 1, 0.1], 0), ([6, 3, 4, 1.1], 1), ([7.5, 4, 6, 2], 2)]
assert grade_learner(perceptron, tests) >= 2
def test_neural_network_learner():
iris = DataSet(name="iris")
classes = ["setosa", "versicolor", "virginica"]
iris.classes_to_numbers(classes)
nNL = NeuralNetLearner(iris, [5], 0.15, 75)
tests = [([5, 3, 1, 0.1], 0), ([6, 3, 3, 1.5], 1), ([7.5, 4, 6, 2], 2)]
assert grade_learner(nNL, tests) >= 2
def test_means_and_deviation():
iris = DataSet(name="iris")
means, deviations = iris.find_means_and_deviations()
assert round(means["setosa"][0], 3) == 5.006
assert round(means["versicolor"][0], 3) == 5.936
assert round(means["virginica"][0], 3) == 6.588
assert round(deviations["setosa"][0], 3) == 0.352
assert round(deviations["versicolor"][0], 3) == 0.516
assert round(deviations["virginica"][0], 3) == 0.636
def test_means_and_deviation():
iris = DataSet(name="iris")
means, deviations = iris.find_means_and_deviations()
assert round(means["setosa"][0], 3) == 5.006
assert round(means["versicolor"][0], 3) == 5.936
assert round(means["virginica"][0], 3) == 6.588
assert round(deviations["setosa"][0], 3) == 0.352
assert round(deviations["versicolor"][0], 3) == 0.516
assert round(deviations["virginica"][0], 3) == 0.636
def test_perceptron():
iris = DataSet(name="iris")
iris.classes_to_numbers()
classes_number = len(iris.values[iris.target])
perceptron = PerceptronLearner(iris)
tests = [([5, 3, 1, 0.1], 0),
([5, 3.5, 1, 0], 0),
([6, 3, 4, 1.1], 1),
([6, 2, 3.5, 1], 1),
([7.5, 4, 6, 2], 2),
([7, 3, 6, 2.5], 2)]
assert grade_learner(perceptron, tests) > 1/2
assert err_ratio(perceptron, iris) < 0.4
def test_naive_bayes():
iris = DataSet(name='iris')
# discrete
nbd = NaiveBayesLearner(iris, continuous=False)
assert nbd([5, 3, 1, 0.1]) == 'setosa'
assert nbd([6, 3, 4, 1.1]) == 'versicolor'
assert nbd([7.7, 3, 6, 2]) == 'virginica'
# continuous
nbc = NaiveBayesLearner(iris, continuous=True)
assert nbc([5, 3, 1, 0.1]) == 'setosa'
assert nbc([6, 5, 3, 1.5]) == 'versicolor'
assert nbc([7, 3, 6.5, 2]) == 'virginica'
# simple
data1 = 'a' * 50 + 'b' * 30 + 'c' * 15
dist1 = CountingProbDist(data1)
data2 = 'a' * 30 + 'b' * 45 + 'c' * 20
dist2 = CountingProbDist(data2)
data3 = 'a' * 20 + 'b' * 20 + 'c' * 35
dist3 = CountingProbDist(data3)
dist = {
('First', 0.5): dist1,
('Second', 0.3): dist2,
('Third', 0.2): dist3
}
nbs = NaiveBayesLearner(dist, simple=True)
assert nbs('aab') == 'First'
assert nbs(['b', 'b']) == 'Second'
assert nbs('ccbcc') == 'Third'
def test_decision_tree_learner():
iris = DataSet(name="iris")
dTL = DecisionTreeLearner(iris)
assert dTL([5, 3, 1, 0.1]) == "setosa"
assert dTL([6, 5, 3, 1.5]) == "versicolor"
assert dTL([7.5, 4, 6, 2]) == "virginica"
def test_k_nearest_neighbors():
iris = DataSet(name="iris")
kNN = NearestNeighborLearner(iris, k=3)
assert kNN([5, 3, 1, 0.1]) == "setosa"
assert kNN([6, 5, 3, 1.5]) == "versicolor"
assert kNN([7.5, 4, 6, 2]) == "virginica"
def test_neural_network_learner():
iris = DataSet(name="iris")
classes = ["setosa","versicolor","virginica"]
iris.classes_to_numbers(classes)
nNL = NeuralNetLearner(iris, [5], 0.15, 75)
tests = [([5, 3, 1, 0.1], 0),
([5, 3.5, 1, 0], 0),
([6, 3, 4, 1.1], 1),
([6, 2, 3.5, 1], 1),
([7.5, 4, 6, 2], 2),
([7, 3, 6, 2.5], 2)]
assert grade_learner(nNL, tests) >= 2/3
assert err_ratio(nNL, iris) < 0.25
def show_iris(i=0, j=1, k=2):
"""Plots the iris dataset in a 3D plot.
The three axes are given by i, j and k,
which correspond to three of the four iris features."""
from mpl_toolkits.mplot3d import Axes3D
plt.rcParams.update(plt.rcParamsDefault)
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
iris = DataSet(name="iris")
buckets = iris.split_values_by_classes()
features = ["Sepal Length", "Sepal Width", "Petal Length", "Petal Width"]
f1, f2, f3 = features[i], features[j], features[k]
a_setosa = [v[i] for v in buckets["setosa"]]
b_setosa = [v[j] for v in buckets["setosa"]]
c_setosa = [v[k] for v in buckets["setosa"]]
a_virginica = [v[i] for v in buckets["virginica"]]
b_virginica = [v[j] for v in buckets["virginica"]]
c_virginica = [v[k] for v in buckets["virginica"]]
a_versicolor = [v[i] for v in buckets["versicolor"]]
b_versicolor = [v[j] for v in buckets["versicolor"]]
c_versicolor = [v[k] for v in buckets["versicolor"]]
for c, m, sl, sw, pl in [('b', 's', a_setosa, b_setosa, c_setosa),
('g', '^', a_virginica, b_virginica, c_virginica),
('r', 'o', a_versicolor, b_versicolor, c_versicolor)]:
ax.scatter(sl, sw, pl, c=c, marker=m)
ax.set_xlabel(f1)
ax.set_ylabel(f2)
ax.set_zlabel(f3)
plt.show()
def show_iris(i=0, j=1, k=2):
"""Plots the iris dataset in a 3D plot.
The three axes are given by i, j and k,
which correspond to three of the four iris features."""
from mpl_toolkits.mplot3d import Axes3D
plt.rcParams.update(plt.rcParamsDefault)
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
iris = DataSet(name="iris")
buckets = iris.split_values_by_classes()
features = ["Sepal Length", "Sepal Width", "Petal Length", "Petal Width"]
f1, f2, f3 = features[i], features[j], features[k]
a_setosa = [v[i] for v in buckets["setosa"]]
b_setosa = [v[j] for v in buckets["setosa"]]
c_setosa = [v[k] for v in buckets["setosa"]]
a_virginica = [v[i] for v in buckets["virginica"]]
b_virginica = [v[j] for v in buckets["virginica"]]
c_virginica = [v[k] for v in buckets["virginica"]]
a_versicolor = [v[i] for v in buckets["versicolor"]]
b_versicolor = [v[j] for v in buckets["versicolor"]]
c_versicolor = [v[k] for v in buckets["versicolor"]]
for c, m, sl, sw, pl in [('b', 's', a_setosa, b_setosa, c_setosa),
('g', '^', a_virginica, b_virginica, c_virginica),
('r', 'o', a_versicolor, b_versicolor, c_versicolor)]:
ax.scatter(sl, sw, pl, c=c, marker=m)
ax.set_xlabel(f1)
ax.set_ylabel(f2)
ax.set_zlabel(f3)
plt.show()
def test_naive_bayes():
iris = DataSet(name="iris")
# Discrete
nBD = NaiveBayesLearner(iris)
assert nBD([5, 3, 1, 0.1]) == "setosa"
assert nBD([6, 5, 3, 1.5]) == "versicolor"
assert nBD([7, 3, 6.5, 2]) == "virginica"
# Continuous
nBC = NaiveBayesLearner(iris, continuous=True)
assert nBC([5, 3, 1, 0.1]) == "setosa"
assert nBC([6, 5, 3, 1.5]) == "versicolor"
assert nBC([7, 3, 6.5, 2]) == "virginica"
def test_k_nearest_neighbors():
iris = DataSet(name="iris")
kNN = NearestNeighborLearner(iris, k=3)
assert kNN([5, 3, 1, 0.1]) == "setosa"
def test_naive_bayes():
iris = DataSet(name="iris")
nB = NaiveBayesLearner(iris)
assert nB([5, 3, 1, 0.1]) == "setosa"
def test_plurality_learner():
zoo = DataSet(name="zoo")
pL = PluralityLearner(zoo)
assert pL([]) == "mammal"
def test_decision_tree_learner():
iris = DataSet(name="iris")
dTL = DecisionTreeLearner(iris)
assert dTL([5, 3, 1, 0.1]) == "setosa"
def test_exclude():
iris = DataSet(name='iris', exclude=[3])
assert iris.inputs == [0, 1, 2]
