def run_problem1(): for n in nums: training_set = rdm.sample(training, n) predicted_lables.append(train_and_predict(training_set, validation, digit_specific_collecting)[1]) error_rates = [ph.benchmark(predicted_lables[i],true_labels) for i in range(len(nums))] plt.plot(nums, error_rates) plt.xlabel("Number of Training Data") plt.ylabel('Error Rate') plt.title('Number of Training Data vs. Error Rate')
def run_problem1(): for n in nums: training_set = rdm.sample(training, n) predicted_lables.append( train_and_predict(training_set, validation, digit_specific_collecting)[1]) error_rates = [ ph.benchmark(predicted_lables[i], true_labels) for i in range(len(nums)) ] plt.plot(nums, error_rates) plt.xlabel("Number of Training Data") plt.ylabel('Error Rate') plt.title('Number of Training Data vs. Error Rate')
def run_k_folds(k_folds, C=1, specific_collecting=digit_specific_collecting, specific_true_labels=digit_specific_true_labels, dataset=digits, train_labels="train_labels", train_objects="train_images", k=10): error_rate_k_folds = 0 for i in range(k): validation_fold = k_folds[i] training_folds = [] for j in range(k): if j!=i: training_folds+=k_folds[j] svc, predicted_labels_k_folds = train_and_predict(training_folds, validation_fold, specific_collecting, C, dataset, train_labels, train_objects) true_labels_k_folds = specific_true_labels(validation_fold) error_rate = ph.benchmark(predicted_labels_k_folds, true_labels_k_folds) print "Error Rate for C=",C," is ", error_rate error_rate_k_folds += error_rate return svc, error_rate_k_folds/float(k)
def run_k_folds(k_folds, C=1, specific_collecting=digit_specific_collecting, specific_true_labels=digit_specific_true_labels, dataset=digits, train_labels="train_labels", train_objects="train_images", k=10): error_rate_k_folds = 0 for i in range(k): validation_fold = k_folds[i] training_folds = [] for j in range(k): if j != i: training_folds += k_folds[j] svc, predicted_labels_k_folds = train_and_predict( training_folds, validation_fold, specific_collecting, C, dataset, train_labels, train_objects) true_labels_k_folds = specific_true_labels(validation_fold) error_rate = ph.benchmark(predicted_labels_k_folds, true_labels_k_folds) print "Error Rate for C=", C, " is ", error_rate error_rate_k_folds += error_rate return svc, error_rate_k_folds / float(k)