def read_data(only_2_features=True):
iris = datasets.load_iris()
X, y = iris.data, iris.target
if only_2_features:
X = X[:, :2]
return X, y
if __name__ == '__main__':
X, y = read_data()
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2)
svm1 = svm.SVC()
svm1.fit(X, y)
ax1.set_title("SVC linear")
plot_areas(lambda x: svm1.predict(x), 0.1, X, ax1)
plot_2d_classes(X, y, 'ryb', ax1)
svm2 = svm.SVC(kernel='poly', degree=2)
svm2.fit(X, y)
ax2.set_title("SVC polynomial, deg: 2")
plot_areas(lambda x: svm2.predict(x), 0.1, X, ax2)
plot_2d_classes(X, y, 'ryb', ax2)
svm3 = svm.SVC(kernel='poly', degree=3)
svm3.fit(X, y)
ax3.set_title("SVC polynomial, deg: 3")
plot_areas(lambda x: svm3.predict(x), 0.1, X, ax3)
plot_2d_classes(X, y, 'ryb', ax3)
svm4 = svm.SVC(kernel='poly', degree=6)
svm4.fit(X, y)
ax4.set_title("SVC polynomial, deg: 6")
plot_areas(lambda x: svm4.predict(x), 0.1, X, ax4)
plot_2d_classes(X, y, 'ryb', ax4)
cnn_percents = []
for i in range(10):
X_training, y_training, X_test, y_test = split_dataset(X, y, 0.7)
if cnn:
len_before = X_training.shape[0]
X_training, y_training = cnn_transform(X_training, y_training, k, metric)
len_after = X_training.shape[0]
cnn_percents.append(float(len_after) / float(len_before) * 100.0)
predictions = []
for i in range(X_test.shape[0]):
predictions.append(kNN(X_training, X_training, y_training, X_test[i, :], k, metric))
if SHOW_PREDICTIONS_AND_REAL_VALUES:
print('Prediction, actual:')
for i in range(X_test.shape[0]):
print(predictions[i], y_test[i])
correct = 0
for i in range(len(predictions)):
if y_test[i] == predictions[i]:
correct += 1
accuracies.append(float(correct) / float(len(predictions)) * 100.0)
print("Accuracy:", str(np.mean(accuracies)) + '%', 'StdDev:', np.std(accuracies))
if cnn:
print("CNN:", str(np.mean(cnn_percents)) + '%', 'StdDev:', np.std(cnn_percents))
else:
if cnn:
X, y = cnn_transform(X, y, k, metric)
plot_areas(lambda x: kNN(X, X, y, x, k, metric), 0.1, X)
plot_2d_classes(X, y, 'ryb')
cnn_str = '_cnn' if cnn else ''
plt.savefig('plots/k' + str(k) + '_' + metric.__name__ + cnn_str + '.png')
def kmeanspp_init(X, k):
means = []
rand_index = np.random.random_integers(0, len(X) - 1)
means.append(X[rand_index])
for x in range(1, k):
min_distances = [np.min([euclidean(x, mean) for mean in means]) ** 2 for x in X]
probs = [min_distances[i] / sum(min_distances) for i in range(len(min_distances))]
new_mean_index = np.random.choice([x for x in range(len(X))], p=probs)
means.append(X[new_mean_index])
return np.array(means)
if __name__ == '__main__':
X, y = generate_dataset(100)
colors = ['r', 'g', 'b', 'w', 'c', 'm', 'y', 'k', '0.75']
plot_2d_classes(X, y, colors)
plt.gca().set_title("Dataset")
plt.savefig('partA/dataset.png')
fig = plt.figure()
ax = plt.gca()
iterations = 50
k = 9
reps = 5
for method in [random_init, forgy_init, random_partition_init, kmeanspp_init]:
print(method)
qualities = []
for _ in range(reps):
for i, quality in k_means(method, X, k, iterations):
qualities.append((i, quality))
avgs = []
stds = []
new_means[y[i]][j] += X[i][j]
points_num[y[i]] += 1
print(points_num)
for i in range(k):
for j in range(2):
if points_num[i] > 0:
new_means[i][j] /= float(points_num[i])
sums = [0 for i in range(k)]
for i in range(X.shape[0]):
sums[y[i]] += metric(new_means[y[i]], X[i, :])
sum = np.sum(sums)
if sum - best_sum > -EPSILON:
break
best_sum = sum
means = new_means
print(means)
return means, y
if __name__ == '__main__':
X = read_data()
k = 3
means, y = kMeans(X, k)
plot_2d_classes(X, np.array(y), 'ryb')
colors = 'ryb'
for i in range(k):
[x, y] = means[i]
plt.plot(x, y, '^', c=colors[i])
plt.show()
return np.array([np.average(clusters[i], axis=0) for i in range(k)])
def kmeanspp_init(X, k):
means = []
rand_index = np.random.random_integers(0, len(X) - 1)
means.append(X[rand_index])
for x in range(1, k):
min_distances = [np.min([euclidean(x, mean) for mean in means]) ** 2 for x in X]
probs = [min_distances[i] / sum(min_distances) for i in range(len(min_distances))]
new_mean_index = np.random.choice([x for x in range(len(X))], p=probs)
means.append(X[new_mean_index])
return np.array(means)
if __name__ == '__main__':
X, y = generate_dataset(100)
colors = ['r', 'g', 'b', 'w', 'c', 'm', 'y', 'k', '0.75']
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2)
axs = [ax1, ax2, ax3, ax4]
iterations = 50
k = 9
ax_i = 0
for method in [random_init, forgy_init, random_partition_init, kmeanspp_init]:
print(method.__name__[:-5])
y_m = k_means(method, X, k, iterations)
plot_2d_classes(X, y_m, colors, axs[ax_i])
axs[ax_i].set_title(method.__name__[:-5])
ax_i += 1
plt.savefig('partA/clusters.png')
