def load_iris_dataset(self):
# Loading the Iris dataset from scikit-learn.
# The classes are already converted to integer labels where 0=Iris-Setosa, 1=Iris-Versicolor, 2=Iris-Virginica.
iris = datasets.load_iris()
x = iris.data[:, [2, 3]]
y = iris.target
print('Class labels:', np.unique(y))
# plotter data and save it to file
Plotter.plot_iris_data_set(x, FilesystemUtils.get_test_resources_plot_file_name(
'ScikitLearn-Iris-Training-Set.png'))
# Splitting data into 70% training and 30% test data
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=1, stratify=y)
print('Labels counts in y:', np.bincount(y))
print('Labels counts in y_train:', np.bincount(y_train))
print('Labels counts in y_test:', np.bincount(y_test))
# Standardize features
sc = StandardScaler()
sc.fit(x_train)
x_train_std = sc.transform(x_train)
sc.fit(x_test)
x_test_std = sc.transform(x_test)
self.x_train = x_train_std
self.y_train = y_train
self.x_test = x_test_std
self.y_test = y_test
def setUp(self):
# load subset of Iris data
iris_data_reader = IrisDataReader(
FilesystemUtils.get_resources_data_file_name('iris/iris.data'))
self.x, self.y = iris_data_reader.get_data()
# plotter data and save it to file
Plotter.plot_iris_data_set(
self.x,
FilesystemUtils.get_test_resources_plot_file_name(
'adaline/Adaline-Training-Set.png'))
def test_adaline_with_stochastic_update(self):
# standardize features
x_std: np.matrix = np.copy(self.x)
x_std[:, 0] = (self.x[:, 0] - self.x[:, 0].mean()) / self.x[:, 0].std()
x_std[:, 1] = (self.x[:, 1] - self.x[:, 1].mean()) / self.x[:, 1].std()
# plotter data and save it to file
Plotter.plot_iris_data_set(
x_std,
FilesystemUtils.get_test_resources_plot_file_name(
'adaline/AdalineSGD-Standardized-Training-Set.png'))
# train adaline on standardized features with a small number of epochs
adaline = AdalineSGD(learning_rate=0.01, num_epochs=15)
adaline.fit(x_std, self.y)
# plot learning curve
curve = {
'cost_length': len(adaline.cost),
'cost': adaline.cost,
'marker': 'o',
'x_label': 'Epochs',
'y_label': 'log(Sum-squared-error)',
'title': 'Adaline - Learning rate 0.01'
}
Plotter.plot_learning_curve(
curve,
FilesystemUtils.get_test_resources_plot_file_name(
'adaline/AdalineSGD-Learning-Curve-Standardized-Features.png'))
# plot decision boundary
Plotter.plot_decision_boundary(
x_std,
self.y,
classifier=adaline,
diagram_options={
'x_label': 'sepal length [cm]',
'y_label': 'petal length [cm]',
'legend': 'upper left'
},
image_file_path=FilesystemUtils.get_test_resources_plot_file_name(
'adaline/AdalineSGD-Decision-Boundary-Standardized-Features.png'
))
adaline.partial_fit(x_std[0, :], self.y[0])
def setUp(self):
# load subset of Iris data
iris = datasets.load_iris()
x_train = iris.data[:, [2, 3]]
y_train = iris.target
# consider only 0 and 1 labels
x_train_01_subset = x_train[(y_train == 0) | (y_train == 1)]
y_train_01_subset = y_train[(y_train == 0) | (y_train == 1)]
# Standardize features
sc = StandardScaler()
sc.fit(x_train_01_subset)
self.x = sc.transform(x_train_01_subset)
self.y = y_train_01_subset
print('Class labels:', np.unique(self.y))
# plotter data and save it to file
Plotter.plot_iris_data_set(
self.x,
FilesystemUtils.get_test_resources_plot_file_name(
'logistic_regression/LogisticRegressionBGD-Training-Set.png'))