def learn_batch_performance_params (m_val):
testing_file = batch_performance_datasets[m_val][0]
training_file = batch_performance_datasets[m_val][1]
testing_set = file_read (testing_file)
training_set = file_read (training_file)
partition = partition_data (testing_set)
D1 = partition.training
D2 = partition.testing
perceptron_params = perceptron_learn_batch_performance_params (D1, D2)
perceptron_params_without_margin = perceptron_params.get_params (0)
perceptron_params_with_margin = perceptron_params.get_params (1)
print 'perceptron without margin acc(D2): ' + str(perceptron_params_without_margin.accuracy)
print 'perceptron with margin acc(D2): ' + str(perceptron_params_with_margin.accuracy)
print '\n\nRunning perceptron on Test set...'
perceptron_trained_without_margin = perceptron_train (batch_performance_n, training_set, perceptron_params_without_margin.gamma, perceptron_params_without_margin.eta)
perceptron_trained_with_margin = perceptron_train (batch_performance_n, training_set, perceptron_params_with_margin.gamma, perceptron_params_with_margin.eta)
perceptron_mistakes_without_margin = perceptron_test (testing_set, perceptron_trained_without_margin[0], perceptron_trained_without_margin[1])
perceptron_mistakes_with_margin = perceptron_test (testing_set, perceptron_trained_with_margin[0], perceptron_trained_with_margin[1])
print 'perecptron without margin acc(Test): ' + str(1.0 - float(perceptron_mistakes_without_margin[len(perceptron_mistakes_without_margin)-1]) / len (testing_set))
print 'perecptron with margin acc(Test): ' + str(1.0 - float(perceptron_mistakes_with_margin[len(perceptron_mistakes_with_margin)-1]) / len (testing_set))
winnow_params = winnow_learn_batch_performance_params (D1, D2)
winnow_params_without_margin = winnow_params.get_params (0)
winnow_params_with_margin = winnow_params.get_params (1)
print 'winnow without margin acc(D2): ' + str(winnow_params_without_margin.accuracy)
print 'winnow with margin acc(D2): ' + str(winnow_params_with_margin.accuracy)
print '\n\nRunning winnow on Test set...'
winnow_trained_without_margin = winnow_train (batch_performance_n, training_set, winnow_params_without_margin.gamma, winnow_params_with_margin.eta)
winnow_trained_with_margin = winnow_train (batch_performance_n, training_set, winnow_params_with_margin.gamma, winnow_params_with_margin.eta)
winnow_mistakes_without_margin = winnow_test (testing_set, winnow_trained_without_margin)
winnow_mistakes_with_margin = winnow_test (testing_set, winnow_trained_with_margin)
print 'winnow without margin acc(Test): ' + str(1.0 - float(winnow_mistakes_without_margin[len(winnow_mistakes_without_margin)-1]) / len(testing_set))
print 'winnow with margin acc(Test): ' + str(1.0 - float(winnow_mistakes_with_margin[len(winnow_mistakes_with_margin)-1]) / len(testing_set))
import perceptron as P
import numpy as np
print_stuff = True
if print_stuff:
print("\n\n\nPerceptron tests:")
Perc_X_train = np.array([[0, 1], [1, 0], [5, 4], [1, 1], [3, 3], [2, 4], [1, 6]])
Perc_Y_train = np.array([[1], [1], [-1], [1], [-1], [-1], [-1]])
[w, b] = P.perceptron_train(Perc_X_train, Perc_Y_train)
perc_test = P.perceptron_test(Perc_X_train, Perc_Y_train, w, b)
if print_stuff:
print("W from sample =", w, "B from sample =", b)
print("Test on self form sample: ", perc_test)
print("Testing for non-linearly seperable data")
Perc_stuff_X = np.array(
[[1, 0], [7, 4], [9, 6], [2, 1], [4, 8], [0, 3], [13, 5], [6, 8], [7, 3], [3, 6], [2, 1], [8, 3], [10, 2],
[3, 5], [5, 1], [1, 9], [10, 3], [4, 1], [6, 6], [2, 2]])
Perc_stuff_Y = np.array(
[[1], [1], [-1], [1], [-1], [-1], [-1], [1], [1], [-1], [1], [-1], [-1], [-1], [1], [1], [-1], [1], [-1], [-1]])
[w, b] = P.perceptron_train(Perc_stuff_X, Perc_stuff_Y)
someTest = P.perceptron_test(Perc_stuff_X, Perc_stuff_Y, w, b)
if print_stuff:
print("Non-linearly seperable data test w=", w, "b=", b, "Accuracy on self =", someTest)
Perc_random_X = np.array([[1.84724509, 2.23182926],
[1.22695894, 1.6611229],
[2.13212121, 4.63313796],
[7.78081405, 4.11930532],
[7.28450063, 3.90368111],
[1.29216053, 2.76912245],
[7.0384763, 2.80881342],
[1.22081714, 3.80955021],
yTest = np.genfromtxt(os.path.join(data_dir, 'yTest.csv'), delimiter=',')
# Visualize the image
'''
idx = 0
datapoint = XTrain[idx, 1:]
plt.imshow(datapoint.reshape((28,28), order = 'F'), cmap='gray')
plt.show()
'''
# TODO: Test perceptron_predict function, defined in perceptron.py
yPred = perceptron.perceptron_predict(w, XTrain[0])
# TODO: Test perceptron_train function, defined in perceptron.py
w = np.zeros(XTrain.shape[1])
w = perceptron.perceptron_train(w, XTrain, yTrain, 10)
# TODO: Test RBF_kernel function, defined in perceptron.py
K = perceptron.RBF_kernel(XTrain[0:5], XTrain[0:5], 10.0)
# TODO: Test kernel_perceptron_predict function, defined in perceptron.py
a = np.zeros(XTrain.shape[0])
yPred = perceptron.kernel_perceptron_predict(a, XTrain, yTrain, XTrain[0],
10.0)
# TODO: Test kernel_perceptron_train function, defined in perceptron.py
a = np.zeros(XTrain.shape[0])
a0 = perceptron.kernel_perceptron_train(a, XTrain, yTrain, 5, 100)
# TODO: Run experiments outlined in HW4 PDF
w = np.zeros(XTrain.shape[1])
C_3 = km.K_Means_better(X_2, K_3)
# Visuals for debugging, Uncomment matplot header to use
print("C_3: \n", C_3)
plt.scatter(C_3[:,0], C_3[:,1], label='centers')
plt.scatter(X_2[:,0], X_2[:,1], label='samples')
plt.title('X_2, K=3')
# plt.savefig("k_means_results_3.png") #Uncomment to save plot as file
plt.show()
# PERCEPTRON TESTING
# Hand-Tested Data
X = np.array( [[1,1], [1,-1], [-1,1], [-1,-1]] )
Y = np.array( [[1], [-1], [-1], [-1]] )
W = p.perceptron_train(X,Y)
print("Hand-Tested Data W1: ",W[0][0]," W2: ",W[0][1]," b:",W[1][0])
test_acc = p.perceptron_test(X,Y,W[0],W[1])
print("Accurancy:",test_acc,"\n")
# Percepton Test Data
X = np.array( [[0,1], [1,0], [5,4], [1,1], [3,3], [2,4], [1,6]] )
Y = np.array( [[1], [1], [-1], [1], [-1], [-1], [-1]] )
W = p.perceptron_train(X,Y)
print("Preceptron Test Data 1 W1: ",W[0][0]," W2: ",W[0][1]," b:",W[1][0])
test_acc = p.perceptron_test(X,Y,W[0],W[1])
print("Accurancy:",test_acc,"\n")
# Perceptron Test Data - Writeup
X = np.array( [[-2,1], [1,1], [1.5,-0.5], [-2,-1], [-1,-1.5], [2,-2]] )
Y = np.array( [[1], [1], [1], [-1], [-1], [-1]] )
def main():
# params to tune
bias = 0
# epochs = 20
# arrays containing train and test
train = np.array(parse_features('trainingimages', 5000))
train_labels = np.array(parse_labels('traininglabels', 5000))
test = np.array(parse_features('testimages', 1000))
test_labels = np.array(parse_labels('testlabels', 1000))
# initialize weight vectors
w = np.array([[0 for i in range(28 * 28 + 1)] for j in range(10)])
w = w.astype(float)
train_acc = [] # [0 for i in range(epochs)]
# training
# for j in range(epochs):
epochs = 1
while True:
mistakes = 0
alpha = 1.0 / (1.0 + epochs)
for i in range(5000):
mistakes += P.perceptron_train(w, alpha, train[i], train_labels[i])
train_acc.append((5000 - mistakes) / (5000.0)) # accuracy so far
print train_acc[epochs - 1], epochs
# stop training if not improving much
#if epochs != 1 and train_acc[epochs-1] - train_acc[epochs-2] < 0.001:
if epochs == 20:
break
epochs += 1
# draw training accuracies in the end
# testing
accuracy = 0
for i in range(1000):
guess = P.perceptron_decision(w, test[i])
if guess == test_labels[i]:
accuracy += 1
accuracy /= 1000.0
print "test accuracy:"
print accuracy
# building confusion matrix
confusion_counts = [[0 for i in range(10)] for j in range(10)]
confusion_totals = [[0 for i in range(10)] for j in range(10)]
confusion = [[0 for i in range(10)] for j in range(10)]
for i in range(0, 1000):
digit = test_labels[i]
for j in range(0, 10):
confusion_totals[digit][j] += 1 # the whole digit row +=1
guess = P.perceptron_decision(w, test[i])
confusion_counts[digit][guess] += 1
for i in range(0, 10):
for j in range(0, 10):
rate = (confusion_counts[i][j] + 0.0) / confusion_totals[i][j]
confusion[i][j] = "{0:.3f}".format(rate)
for i in range(0, 10):
print confusion[i]
# draw training accuracies
fig = plt.figure()
plt.xlabel('num of epochs')
plt.ylabel('training accuracy')
plt.title('Training Curve')
ax = fig.add_subplot(111)
for i, j in zip(range(epochs), train_acc):
ax.annotate(str("{0:.2f}".format(j)), xy=(i, j))
plt.plot(range(epochs), train_acc)
plt.savefig('training_curve_bias.png', bbox_inches='tight')
ptron = perceptron_learn(ptron, examples[i], true_classes[i],
learn_rate)
accuracy = perceptron_accuracy(ptron, examples, true_classes)
print("Final accuracy: " + str(accuracy))
return ptron
def plot_everything(ptron, examples):
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
for example in examples:
ax.scatter(example[0],
example[1],
example[2],
'z',
s=20,
c=[(example[0], example[1], example[2])])
xx, yy = np.meshgrid(np.arange(0, 1.1, 0.1), np.arange(0, 1.1, 0.1))
# ax + by + cz + d == 0 becomes z == (-d - ax - by)/c
z = (-ptron[3] - ptron[0] * xx - ptron[1] * yy) / ptron[2]
ax.plot_surface(xx, yy, z, alpha=0.2)
plt.show()
import perceptron
ptron = perceptron.new_perceptron()
examples, classes = perceptron.create_data()
perceptron.plot_everything(ptron, examples)
perceptron.perceptron_train(ptron, examples, classes, 0.01, 100)
perceptron.plot_everything(ptron, examples)
'--input_data_dir',
type=str,
default='../data/perceptron',
help='Directory for the perceptron dataset.')
FLAGS, unparsed = parser.parse_known_args()
print('\033[1m' + '1. Perceptron Convergence:\n' + '\033[0m')
# Read the training data for Exercise 5.
Xtrain, ttrain = read_data(FLAGS.input_data_dir + "/perceptron.txt")
print('Exercise 5(a): \n')
# Train the perceptron algorithm on the training data.
w, weights, err = perceptron_train(Xtrain, ttrain, 10)
# Print the weight vector at different epochs.
print("Weight vector at the end of each epoch:\n")
ep = []
for i in range(weights.shape[0] - 1):
print("Epoch %d:" % (i + 1))
print(weights[i + 1])
ep = np.append(ep, i + 1)
# Plot of errors at different epochs.
plt.xlabel('Epoch')
plt.ylabel("Errors")
plt.plot(ep, err, 'bo-', label='Total errors during epoch')
print("Clustering")
#test
C1 = clu.K_Means(cluX1, 3)
#print(C1)
#writeup
C2 = clu.K_Means(cluX2, 2)
print("\tK=2", C2)
C3 = clu.K_Means(cluX2, 3)
print("\tK=3", C3)
#writeup
CBetter1 = clu.K_Means_better(cluX2, 2)
print("\tBetter K=2", CBetter1)
CBetter2 = clu.K_Means_better(cluX2, 3)
print("\tBetter K=3", CBetter2)
print()
print("Perceptron")
#test
W_B1 = per.perceptron_train(perX1, perY1)
perAcc1 = per.perceptron_test(perX1, perY1, W_B1[0], W_B1[1])
#print("\tW",W_B1[0])
#print("\tB",W_B1[1])
#print("\tAccuracy", perAcc1)
#writeup
W_B2 = per.perceptron_train(perX2, perY2)
perAcc2 = per.perceptron_test(perX2, perY2, W_B2[0], W_B2[1])
print("\tW", W_B2[0])
print("\tB", W_B2[1])
print("\tAccuracy", perAcc2)
################################################################################################################################################### # filename: testPreceptron.py # author: Sara Davis # date: 10/10/2018 # version: 1.0 # description: runs testPerceptron.py ############################################################################################################################################# import numpy as np from perceptron import perceptron_train from perceptron import perceptron_test #X_test = np.array([[0,1], [1,0], [5,4], [1,1], [3,3], [2,4], [1,6]]) #should be -2, -2, 6 #Y_test = np.array([[1], [1], [0], [1], [0], [0], [0]]) X_test = np.array([[0, 0], [1, 1], [0, 1], [2, 2], [1, 0], [1, 2]]) Y_test = np.array([[-1], [1], [-1], [1], [-1], [1]]) X = np.array([[-2, 1], [1, 1], [1.5, -.5], [-2, -1], [-1, -1.5], [2, -2]]) Y = np.array([[1], [1], [1], [-1], [-1], [-1]]) W = perceptron_train(X, Y) print(W) test_acc = perceptron_test(X_test, Y_test, W[0], W[1]) print(test_acc)
X = []
Y = []
for item in x_str:
temp = [float(x) for x in item.split(',')]
X.append(temp)
if len(y_str)>0:
for item in y_str:
temp = int(item)
Y.append(temp)
X = np.array(X)
Y = np.array(Y)
return X, Y
X,Y = load_data("data_1.txt")
w,b = p.perceptron_train(X,Y)
test_acc = p.perceptron_test(X,Y,w,b)
print("Perceptron:",test_acc)
X,Y = load_data("data_2.txt")
w,b = p.perceptron_train(X,Y)
X,Y = load_data("data_1.txt")
test_acc = p.perceptron_test(X,Y,w,b)
print("Perceptron:",test_acc)
def df_test1(x):
return np.array([2*x[0]])
x = gd.gradient_descent(df_test1,np.array([5.0]),0.1)
print("Gradient Descent:", x)
# Read the training and test data.
trdata1, trlabels1 = read_examples(FLAGS.input_data_dir +
"/newsgroups_train1.txt")
trdata2, trlabels2 = read_examples(FLAGS.input_data_dir +
"/newsgroups_train2.txt")
tsdata1, tslabels1 = read_examples(FLAGS.input_data_dir +
"/newsgroups_test1.txt")
tsdata2, tslabels2 = read_examples(FLAGS.input_data_dir +
"/newsgroups_test2.txt")
# Train the perceptron algorithm on training datasets for 10,000 epochs.
w1, ws1, error1 = perceptron_train(trdata1, trlabels1, 10000)
w2, ws2, error2 = perceptron_train(trdata2, trlabels2, 10000)
# Save the returned parameter vectors from training in appropriate text files.
p1 = np.savetxt('newsgroups_model_p1.txt', w1)
p2 = np.savetxt('newsgroups_model_p2.txt', w2)
# Evaluate the perceptron algorithm on the corresponding test examples for each version by reading the parameter vectors
# from the corresponding text files.
with open('newsgroups_model_p1.txt', 'r') as f:
wp1 = f.readlines()
wp1 = np.asarray(wp1, dtype=np.float64)
# Part 1: Split Training data into training and validation set
split_training_data.run()
# Part 2: Transform each email in the training set into a feature vector
(feature_vector_list_training,
is_spam_list_training,
vocabulary_list) = create_feature_vectors.run('./output_data/training_set')
# Part 3/4: Train the data on the training set and return the last weight vector. Test the percent
# error when this weight is run on the validation set
print('\n=========================================================================================')
print('Problem 4:')
(weight_vector,
total_number_of_misclassifications,
number_of_runs) = perceptron.perceptron_train(feature_vector_list_training, is_spam_list_training)
(feature_vector_list_validation,
is_spam_list_validation,
_) = create_feature_vectors.run('./output_data/validation_set', vocabulary_list)
training_set_error = perceptron.perceptron_test(
weight_vector, feature_vector_list_training, is_spam_list_training)
validation_set_error = perceptron.perceptron_test(
weight_vector, feature_vector_list_validation, is_spam_list_validation)
print('Total number of misclassifications: ' + str(total_number_of_misclassifications))
print('Training set error: ' + str(training_set_error))
print('Validation set error: ' + str(validation_set_error))
# Part 5: Find words in the vocabulary with the most positive and negative weights
# Read the training and test data.
trdata1, trlabels1 = read_examples(FLAGS.input_data_dir +
"/newsgroups_train1.txt")
trdata2, trlabels2 = read_examples(FLAGS.input_data_dir +
"/newsgroups_train2.txt")
tsdata1, tslabels1 = read_examples(FLAGS.input_data_dir +
"/newsgroups_test1.txt")
tsdata2, tslabels2 = read_examples(FLAGS.input_data_dir +
"/newsgroups_test2.txt")
# Train the perceptron algorithm on training datasets for 10,000 epochs.
w1, _, _ = perceptron_train(trdata1, trlabels1, 10000)
w2, _, _ = perceptron_train(trdata2, trlabels2, 10000)
# Train and test the SVM algortihm on the newsgroups datasets.
svm_tra = svm.SVC(kernel='linear', C=5.0)
svm_tra.fit(trdata1, trlabels1)
pred = svm_tra.predict(tsdata1)
ac = np.mean(pred == tslabels1) * 100
print('Accuracy of linear svm on test dataset version 1: %0.3f%%.' % (ac))
svm_tra1 = svm.SVC(kernel='linear', C=5.0)
svm_tra1.fit(trdata2, trlabels2)
pred = svm_tra1.predict(tsdata2)
data, labels = read_examples(FLAGS.input_data_dir + '/spam_train_svm.txt')
data1, labels1 = read_examples(FLAGS.input_data_dir + '/spam_test_svm.txt')
print("SVM algorithm: \n")
svm = svm.SVC(C=5, kernel='linear')
svm.fit(data, labels)
svm_test = svm.predict(data1)
accuracy = np.mean(labels1 == svm_test)
print("Accuracy of SVM with linear kernel: %0.2f%%." % (accuracy * 100))
print("\nPerceptron algorithm: \n")
# Train the perceptron algorithm on the training data.
w, _, error = perceptron_train(data, labels, 50)
# Save the returned parameter vector in spam_model_p.txt.
p = np.savetxt('spam_model_p.txt', w)
# Report number of mistakes during each epoch and total number of mistakes during training.
print("\nNumber of mistakes during each epoch:")
eph = 1
for i in error:
print("Epoch %d: %d" % (eph, i))
eph += 1
print("\nTotal number of mistakes: %d" % np.sum(error))
X_t, t_t = read_data(FLAGS.input_data_dir + '/optdigits.tes')
X_t_sc = scalling(X_t)
t10 = np.zeros((len(t), 10))
for i in range(10):
for j in range(len(t)):
if t[j] == i:
t10[j, i] = 1
else:
t10[j, i] = -1
accrucys = []
for j in range(1, 21):
pred_ehp = []
for i in range(10):
w = perceptron_train(X_sc[1000:, :], t10[1000:, i], j)
w = w / np.linalg.norm(w)
pred = X_sc[:1000, :].dot(w)
pred_ehp.append(pred)
labels = np.argmax(pred_ehp, axis=0)
ac = np.mean(labels == t[:1000]) * 100
print(j, ac)
accrucys.append(ac)
print('max accrucy in epoch:', np.argmax(accrucys) + 1)
set_eph = 8
set_eph = np.argmax(accrucys) + 1
st = timeit.default_timer()
pred_ehp = []
for i in range(10):
w = perceptron_train(X_sc[1000:, :], t10[1000:, i], set_eph)