sk = raw_input("Enter number of nearest neighbors to consider or 'S' to sweep values [S]: ") or 's'
if sk.lower() == 's':
print("Sweeping k")
k_list = [1, 3, 5, 7, 21, 101, 401]
else:
k_list = [int(sk)]
validation_errors = zeros((len(k_list), len(n_list)))
for l, n in enumerate(n_list):
for j, k in enumerate(k_list):
xj = x[:n]
tj = t[:n]
start = time.time()
for i, xi in enumerate(x_eval):
ti = knn_classify(xj, tj, xi, k, euclidean_distance)
if ti != t_eval[i]:
validation_errors[j,l] += 1
end = time.time()
print("K = %d, N = %d, Validation Errors = %d, Time = %f"%(k,n,validation_errors[j,l],end-start))
print(" ")
if len(k_list) > 1:
plot(k_list, validation_errors[:,0].flatten()/len(x_eval)*100, 'x-', label="N = %d"%(n_list[0]))
xlabel('Neighbors Considered')
ylabel('Validation Errors %')
legend(loc='best')
xscale('log')
grid(True,which="both",ls="-")
savefig("results/Task_2.eps")
savetxt("results/Task_2.csv", array(zip(k_list, validation_errors[:,0])), fmt='%i %i')
x_test = x_test_f + x_test_m
t_test = np.hstack((np.ones(len(x_test_f)), np.zeros(len(x_test_m))))
xto = x_train
xteo = x_test
x_train = [rgb2gray(imresize(x, (32,32))) for x in x_train]
x_validation = [rgb2gray(imresize(x, (32,32))) for x in x_validation]
x_test = [rgb2gray(imresize(x, (32,32))) for x in x_test]
krange = [i for j in (range(1,10), range(11, len(x_train),5), [len(x_train)]) for i in j]
validation_errors = np.zeros(len(krange))
validation_distances = defaultdict(list)
for j, k in enumerate(krange):
for i, xi in enumerate(x_validation):
ti, _ = knn_classify(x_train, t_train, xi, k, euclidean_distance, validation_distances[i])
if ti != t_validation[i]:
validation_errors[j] += 1
print "K = %d - Validation Errors = %d (%d%%)" %(k, validation_errors[j], validation_errors[j]/len(x_validation)*100)
best_ki = np.where(validation_errors == validation_errors.min())[0]
best_k = np.array(krange)[best_ki]
best_perf = validation_errors[best_ki]/len(x_validation)*100
np.savetxt("results/part_5/eval_performance.csv", np.array(zip(best_k, best_perf)), fmt='%i %i')
print "Best values for k: %s\n" %best_k
test_errors = np.zeros(len(best_k))
test_distances = defaultdict(list)
trigger = 0
nl=0
from favorite_language_data import coord_language_pairs
from matplotlib import pyplot
from k_nearest_neighbors import knn_classify
for k in [1, 3, 5, 7]:
correct_predictions = 0
for city in coord_language_pairs:
other_cities = [
other_city for other_city in coord_language_pairs
if other_city != city
]
predicted_language = knn_classify(k, other_cities, city[0])
actual_language = city[1]
print('coords, actual_language, predicted_language = %s, %s, %s' %
(city[0], actual_language, predicted_language))
plots = {"Java": ([], []), "Python": ([], []), "R": ([], [])}
markers = {"Java": "o", "Python": "s", "R": "^"}
colors = {"Java": "r", "Python": "b", "R": "g"}
for (latitude, longitude), language in coord_language_pairs:
plots[language][0].append(latitude)
plots[language][1].append(longitude)
for language, (x, y) in plots.items():
pyplot.scatter(x,
y,
color=colors[language],
from decision_tree_classification import dt_classify
from kernel_svm import ksvm_classify
from logistic_regression import logreg_classify
from naive_bayes import nb_classify
from k_nearest_neighbors import knn_classify
from random_forest_classification import rf_classify
from support_vector_machine import lsvm_classify
print('Decision Tree Model: ', dt_classify('breast_cancer.csv'))
print('Random Forrest Model: ', rf_classify('breast_cancer.csv'))
print('K-NN Model: ', knn_classify('breast_cancer.csv'))
print('Linear SVM Model: ', lsvm_classify('breast_cancer.csv'))
print('Kernel SVM Model: ', ksvm_classify('breast_cancer.csv'))
print('Logistic Regression Model: ', logreg_classify('breast_cancer.csv'))
print('Naive Bayes Model: ', nb_classify('breast_cancer.csv'))
"Enter number of nearest neighbors to consider or 'S' to sweep values [S]: "
) or 's'
if sk.lower() == 's':
print("Sweeping k")
k_list = [1, 3, 5, 7, 21, 101, 401]
else:
k_list = [int(sk)]
validation_errors = zeros((len(k_list), len(n_list)))
for l, n in enumerate(n_list):
for j, k in enumerate(k_list):
xj = x[:n]
tj = t[:n]
start = time.time()
for i, xi in enumerate(x_eval):
ti = knn_classify(xj, tj, xi, k, euclidean_distance)
if ti != t_eval[i]:
validation_errors[j, l] += 1
end = time.time()
print("K = %d, N = %d, Validation Errors = %d, Time = %f" %
(k, n, validation_errors[j, l], end - start))
print(" ")
if len(k_list) > 1:
plot(k_list,
validation_errors[:, 0].flatten() / len(x_eval) * 100,
'x-',
label="N = %d" % (n_list[0]))
xlabel('Neighbors Considered')
ylabel('Validation Errors %')
legend(loc='best')
from decision_tree_classification import dt_classify
from kernel_svm import ksvm_classify
from logistic_regression import logreg_classify
from naive_bayes import nb_classify
from k_nearest_neighbors import knn_classify
from random_forest_classification import rf_classify
from support_vector_machine import lsvm_classify
logreg_classify('../Restaurant_Reviews.tsv')
print('********************************************')
knn_classify('../Restaurant_Reviews.tsv')
print('********************************************')
dt_classify('../Restaurant_Reviews.tsv')
print('********************************************')
ksvm_classify('../Restaurant_Reviews.tsv')
print('********************************************')
lsvm_classify('../Restaurant_Reviews.tsv')
print('********************************************')
rf_classify('../Restaurant_Reviews.tsv')
0, 20)
genders = ['Male', 'Female']
x_train = x_train_f + x_train_m
t_train = np.hstack((np.ones(len(x_train_f)), np.zeros(len(x_train_m))))
x_test = x_test_f + x_test_m
t_test = np.hstack((np.ones(len(x_test_f)), np.zeros(len(x_test_m))))
# Resize to 32x32 and convert to grayscale
x_train_bw = [rgb2gray(imresize(x, (32, 32))) for x in x_train]
x_test_bw = [rgb2gray(imresize(x, (32, 32))) for x in x_test]
# Classify pictures in test set
for xi in np.random.permutation(len(x_test_bw)):
ti, nn = knn_classify(x_train_bw, t_train, x_test_bw[xi], 5)
# Plot image with classification
plt.subplot(121)
plt.imshow(x_test[xi])
plt.axis('off')
plt.title(genders[int(ti)],
color=('green' if ti == t_test[xi] else 'red'),
weight='bold')
# Plot nearest neighbors
idx = [3, 4, 7, 8, 11]
for i, nni in enumerate(nn):
plt.subplot(3, 4, idx[i])
plt.imshow(x_train[nni])
plt.axis('off')
plt.title(genders[int(t_train[nni])])
