def run_research():
# a research to exam which feature is best to ignore for highest accuracy
knn_fac = classifier.knn_factory(1)
folds = [
hw3_utils.load_data('ecg_fold_' + str(i + 1) + '.pickle')
for i in range(2)
]
features_num = len(folds[0][0][0])
max_accuracy_feature = None
for run_num in range(1, 8):
if max_accuracy_feature is not None:
folds = [(np.delete(data, max_accuracy_feature, 1), labels, test)
for data, labels, test in folds]
features_num = len(folds[0][0][0])
results = [
evaluate_comp(knn_fac, folds, feature)
for feature in range(features_num)
]
max_accuracy_feature = max(results, key=lambda item: item[1])[0]
with open('my_experiments' + str(run_num) + '.csv',
'w+') as result_file:
for feature, accuracy, error in results:
line = str(feature) + ',' + str(accuracy) + ',' + str(
error) + '\n'
result_file.write(line)
def experiment_6():
knn_values_list = [1, 3, 5, 7, 13]
for k in knn_values_list:
knn_k = knn_factory(k)
res_accuracy, res_error = evaluate(knn_k, FOLDS)
output = str(k) + "," + str(res_accuracy) + "," + str(res_error)
print(output)
def experiment6(k_values=[1, 3, 5, 7, 13], num_folds=2):
filename = "experiments6.csv"
output_file = open(filename, 'w')
for k in k_values:
print("Testing classifier with k={}".format(k))
knn = classifier.knn_factory(k)
accuracy, error = cross_validation.evaluate(knn, num_folds)
output_file.write("{},{:.3f},{:.3f}\n".format(k, accuracy, error))
def run_knn():
ks = [1, 3, 5, 7, 13]
with open('experiments6.csv', 'w+') as result_file:
for k in ks:
knn_fac = classifier.knn_factory(k)
accuracy, error = utils.evaluate(knn_fac, 2)
line = str(k) + ',' + str(accuracy) + ',' + str(error) + '\n'
result_file.write(line)
print("finished: ", k)
print("FINISHED")
def KNN_test():
results = []
for k in [1, 3, 5, 7, 13]:
knn_k = knn_factory(k)
avg_accuracy, avg_error = evaluate(knn_k, 2)
results.append([k, avg_accuracy, avg_error])
with open("experiments6.csv", "w") as csv_file:
writer = csv.writer(csv_file, delimiter=',', lineterminator='\n')
for row in results:
writer.writerow(row)
def run_my_classify():
# predicts the test data with specific features
data, labels, tests = hw3_utils.load_data()
# features list to ignore that came from the research before
features_to_ignore = [90, 23, 90, 103, 36]
for feature in features_to_ignore:
data = np.delete(data, feature, 1)
tests = np.delete(tests, feature, 1)
clf = classifier.knn_factory(1).train(data, labels)
results = [clf.classify(test) for test in tests]
hw3_utils.write_prediction(results)
from sklearn.feature_selection import SelectKBest, f_classif
# question 3.2
patients, labels, test = utils.load_data()
split_crosscheck_groups([patients, labels], 2)
# question 5.1
k_list = [1, 3, 5, 7, 13]
accuracy_list = []
file_name = 'experiments6.csv'
with open(file_name, 'wb') as file:
for k in k_list:
knn_f = knn_factory(k)
accuracy, error = evaluate(knn_f, 2)
line = str(k) + "," + str(accuracy) + "," + str(error) + "\n"
accuracy_list.append(accuracy)
file.write(line.encode())
# question 5.2
plt.plot(k_list, accuracy_list)
plt.xlabel('K value')
plt.ylabel('Average accuracy')
plt.title('Part B, question 5.2')
plt.show()
# questions 7.1, 7.2
from sklearn.ensemble import RandomForestClassifier
examples, labels, test = load_data()
data = []
data.append(examples)
data.append(labels)
data_new = []
data_new.append(SelectKBest(f_classif, 100).fit_transform(examples, labels))
data_new.append(labels)
classifier.split_crosscheck_groups(data_new, 2)
print("using CUT data\n")
decision_tree = classifier.sklearn_factory_wrapper(RandomForestClassifier())
perceptron = classifier.sklearn_factory_wrapper(Perceptron())
knn = classifier.knn_factory(7)
print("knn and perceptron: \n")
ensemble = classifier.ensemble_factory([knn, perceptron])
accuracy, error = classifier.evaluate(ensemble, 2)
print("%.3f, %.3f\n" % (accuracy, error))
print("knn and decision tree: \n")
ensemble = classifier.ensemble_factory([knn, perceptron])
accuracy, error = classifier.evaluate(ensemble, 2)
print("%.3f, %.3f\n" % (accuracy, error))
print("all three: \n")
ensemble = classifier.ensemble_factory([knn, perceptron, decision_tree])
accuracy, error = classifier.evaluate(ensemble, 2)
print("%.3f, %.3f\n" % (accuracy, error))
def main():
# Variables used for debug
skip_knn = True
skip_tree = True
skip_perc = True
train_features, train_labels, test_features = load_data('data/Data.pickle')
# Split once the dataset to two folds.
folds = 2
#split_crosscheck_groups(train_features, train_labels, folds)
if skip_knn != True:
# Evaluating KNN with different k value:
k_list = [1, 3, 5, 7, 13]
acc_list = []
err_list = []
with open('experiments6.csv', mode='w', newline='') as csv_file:
exp_writer = csv.writer(csv_file)
for k in k_list:
knn_fac = knn_factory(k)
err, acc = evaluate(knn_fac, folds)
print("k=", k, " acc=", acc, " err=", err)
exp_writer.writerow([k, acc, err])
acc_list.append(acc)
err_list.append(err)
# Plot KNN Results
plt.subplot(2, 1, 1)
plt.plot(k_list, acc_list, '--', color='g')
plt.plot(k_list, acc_list, 'bo')
plt.ylabel("Accuracy")
plt.xlabel("k")
plt.xticks(k_list)
plt.subplot(2, 1, 2)
plt.plot(k_list, err_list, '--', color='r')
plt.plot(k_list, err_list, 'bo')
plt.ylabel("Error")
plt.xlabel("k")
plt.xticks(k_list)
plt.tight_layout()
plt.show()
# Perform classification for Perceptron and Tree and write to files.
with open('experiments12.csv', mode='w', newline='') as csv_file:
exp_writer = csv.writer(csv_file)
if skip_tree != True:
# Decision Tree experiment
myTree = tree.DecisionTreeClassifier(criterion="entropy")
err, acc = evaluate(myTree, folds)
print("tree acc=", acc, " tree err=", err)
exp_writer.writerow([1, acc, err])
if skip_perc != True:
# Perceptron experiment
myPerc = Perceptron(tol=1e-3, random_state=0)
err, acc = evaluate(myPerc, folds)
print("perceptron acc=", acc, " perceptron err=", err)
exp_writer.writerow([2, acc, err])
# Competition: Classify test_features
print("Triple model")
my_model = triple_model()
my_model.fit(train_features, train_labels)
res = my_model.final_predict(preprocessing.scale(test_features))
write_prediction(res)