def test_p_y_x_knn(self):
data = TEST_DATA['p_y_x_KNN']
p_y_x_expected = data['p_y_x']
p_y_x = p_y_x_knn(data['y'], data['K'])
self.assertEqual(np.shape(p_y_x), (40, 4))
np.testing.assert_almost_equal(p_y_x, p_y_x_expected)
def test_p_y_x_knn(self):
y = TEST_DATA['p_y_x_KNN']['y']
K = TEST_DATA['p_y_x_KNN']['K']
p_y_x_expected = TEST_DATA['p_y_x_KNN']['p_y_x']
p_y_x = p_y_x_knn(y, K)
self.assertEqual(np.shape(p_y_x), (40, 4))
np.testing.assert_almost_equal(p_y_x, p_y_x_expected)
def predict(x):
"""
Funkcja pobiera macierz przykladow zapisanych w macierzy X o wymiarach NxD i zwraca wektor y o wymiarach Nx1,
gdzie kazdy element jest z zakresu {0, ..., 35} i oznacza znak rozpoznany na danym przykladzie.
:param x: macierz o wymiarach NxD
:return: wektor o wymiarach Nx1
"""
x_train = get_learn_data()[0]
y_train = get_learn_data()[1]
distances_array = hamming_distance(x, x_train)
sorted_labels = sort_train_labels_knn(distances_array, y_train)
each_class_probability = p_y_x_knn(sorted_labels, 1)
predicted_vector = np.argmax(each_class_probability,axis=AXIS_COLUMNS) + 1
#add 1 to all vector class
return predicted_vector
def run_training():
data = load_data()
# KNN model selection
k_values = range(1, 201, 2)
print(
'\n------------- Selekcja liczby sasiadow dla modelu dla KNN -------------'
)
print(
'-------------------- Wartosci k: 1, 3, ..., 200 -----------------------'
)
print(
'--------------------- To moze potrwac ok. 1 min ------------------------'
)
error_best, best_k, errors = model_selection_knn(data['Xval'],
data['Xtrain'],
data['yval'],
data['ytrain'], k_values)
print('Najlepsze k: {num1} i najlepszy blad: {num2:.4f}'.format(
num1=best_k, num2=error_best))
print('\n--- Wcisnij klawisz, aby kontynuowac ---')
classification_KNN_vs_no_neighbours(k_values, errors)
a_values = [1, 3, 10, 30, 100, 300, 1000]
b_values = [1, 3, 10, 30, 100, 300, 1000]
print(
'\n----------------- Selekcja parametrow a i b dla NB --------------------'
)
print(
'--------- Wartosci a i b: 1, 3, 10, 30, 100, 300, 1000 -----------------'
)
print(
'--------------------- To moze potrwac ok. 1 min ------------------------'
)
# NB model selection
error_best, best_a, best_b, errors = model_selection_nb(
data['Xtrain'], data['Xval'], data['ytrain'], data['yval'], a_values,
b_values)
print('Najlepsze a: {}, b: {} i najlepszy blad: {:.4f}'.format(
best_a, best_b, error_best))
print('\n--- Wcisnij klawisz, aby kontynuowac ---')
plot_a_b_errors(errors, a_values, b_values)
p_x_y = estimate_p_x_y_nb(data['Xtrain'], data['ytrain'], best_a, best_b)
classes_no = p_x_y.shape[0]
print(
'\n------Wizualizacja najbardziej popularnych slow dla poszczegolnych klas------'
)
print(
'--Sa to slowa o najwyzszym prawdopodobienstwie w danej klasie dla modelu NB--'
)
try:
groupnames = data['groupnames']
words = {}
for x in range(classes_no):
indices = np.argsort(p_x_y[x, :])[::-1][:50]
words[groupnames[x]] = {
word: prob
for word, prob in zip(data['wordlist'][indices], p_x_y[
x, indices])
}
word_clouds(words.values(), words.keys())
except Exception:
print('---Wystapil problem z biblioteka wordcloud--- ')
print('\n--- Wcisnij klawisz, aby kontynuowac ---')
print(
'\n----------------Porownanie bledow dla KNN i NB---------------------'
)
Dist = hamming_distance(data['Xtest'], data['Xtrain'])
y_sorted = sort_train_labels_knn(Dist, data['ytrain'])
p_y_x = p_y_x_knn(y_sorted, best_k)
error_KNN = classification_error(p_y_x, data['ytest'])
p_y = estimate_a_priori_nb(data['ytrain'])
p_y_x = p_y_x_nb(p_y, p_x_y, data['Xtest'])
error_NB = classification_error(p_y_x, data['ytest'])
plot_error_NB_KNN(error_NB, error_KNN)
print('\n--- Wcisnij klawisz, aby kontynuowac ---')
def run_training():
data = load_data()
# KNN model selection
k_values = range(1, 201, 2)
print('\n------------- Model selection for KNN -------------')
print(
'-------------------- Values k: 1, 3, ..., 200 -----------------------'
)
print(
'--------------------- Calculation may take up to 1 min ------------------------'
)
error_best, best_k, errors = model_selection_knn(data['Xval'],
data['Xtrain'],
data['yval'],
data['ytrain'], k_values)
print('The best k: {num1} and the best error: {num2:.4f}'.format(
num1=best_k, num2=error_best))
print('\n--- Press any key to continue ---')
classification_KNN_vs_no_neighbours(k_values, errors)
a_values = [1, 3, 10, 30, 100, 300, 1000]
b_values = [1, 3, 10, 30, 100, 300, 1000]
print(
'\n----------------- Model selection for a and b --------------------')
print(
'--------- Values a and b: 1, 3, 10, 30, 100, 300, 1000 -----------------'
)
print(
'--------------------- Calculation may take up to 1 min ------------------------'
)
# NB model selection
error_best, best_a, best_b, errors = model_selection_nb(
data['Xtrain'], data['Xval'], data['ytrain'], data['yval'], a_values,
b_values)
print('The best a: {}, b: {} and the best error: {:.4f}'.format(
best_a, best_b, error_best))
print('\n--- Press any key to continue ---')
plot_a_b_errors(errors, a_values, b_values)
p_x_y = estimate_p_x_y_nb(data['Xtrain'], data['ytrain'], best_a, best_b)
classes_no = p_x_y.shape[0]
print('\n------ Visualization of most popular words for each class ------')
print(
'-- These are words that are most probable for each class and NB model --'
)
try:
groupnames = data['groupnames']
words = {}
for x in range(classes_no):
indices = np.argsort(p_x_y[x, :])[::-1][:50]
words[groupnames[x]] = {
word: prob
for word, prob in zip(data['wordlist'][indices], p_x_y[
x, indices])
}
word_clouds(words.values(), words.keys())
except Exception:
print('--- A problem with wordcloud library --- ')
print('\n--- Press any key to continue ---')
print(
'\n---------------- Comparison of KNN and NB errors ---------------------'
)
Dist = hamming_distance(data['Xtest'], data['Xtrain'])
y_sorted = sort_train_labels_knn(Dist, data['ytrain'])
p_y_x = p_y_x_knn(y_sorted, best_k)
error_KNN = classification_error(p_y_x, data['ytest'])
p_y = estimate_a_priori_nb(data['ytrain'])
p_y_x = p_y_x_nb(p_y, p_x_y, data['Xtest'])
error_NB = classification_error(p_y_x, data['ytest'])
plot_error_NB_KNN(error_NB, error_KNN)
print('\n--- Press any key to continue ---')
def test_p_y_x_knn(self):
data = test_data['p_y_x_KNN']
out = p_y_x_knn(data['y'], data['K'])
max_diff = np.max(np.abs(data['p_y_x'] - out))
self.assertAlmostEqual(max_diff, 0, 8)
