def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
sel_error = np.array(
[0]) # Numpy indices to select images that are misclassified.
i = 0 # should be the label number corresponding the largest classification error
# Plot with mnist plot
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=labels[i],
k_plots=10,
prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
C = 3e-4
linSVM = svm.SVC(kernel="linear", decision_function_shape='ovr', C=C)
linSVM.fit(x_train, y_train)
labels = range(1, 6)
y_pred = linSVM.predict(x_test)
conf_matrix = confusion_matrix(y_test, y_pred)
plot_confusion_matrix(conf_matrix, labels)
most_misclassified_prob = []
for col in range(conf_matrix.shape[1]):
item_count = 0
most_misclassified_value = 0
for row in range(conf_matrix.shape[0]):
item_count += conf_matrix[row, col]
if row != col and most_misclassified_value < conf_matrix[row, col]:
most_misclassified_value = conf_matrix[row, col]
most_misclassified_prob.append(most_misclassified_value / item_count)
i = np.argmax(most_misclassified_prob) + 1
sel_error = np.array(
[]) # Numpy indices to select images that are misclassified.
for j in range(y_pred.shape[0]):
if y_pred[j] == i and y_pred[j] != y_test[j]:
sel_error = np.append(sel_error, j)
if len(sel_error) == 10:
break
sel_error = sel_error.astype(int)
# Plot with mnist plot
plot_mnist(x_test[sel_error],
y_pred[sel_error],
labels=labels[i - 1],
k_plots=10,
prefix='Predicted class')
def ex_3():
data = load_data('data_mnist.json')
x_train, y_train, x_test, y_test = \
data['X'], data['Y'].ravel(), data['XT'], data['YT'].ravel()
plot_mnist(x_train, y_train)
ex_3_a(x_train, y_train, x_test, y_test)
def ex_3():
data = load_data('data_mnist.json')
# Normalize data from [0,255] to [0,1]
x_train, y_train, x_test, y_test = \
data['X'] / 255, data['Y'].ravel(), data['XT'] / 255, data['YT'].ravel()
plot_mnist(x_train, y_train)
ex_3_a(x_train, y_train, x_test, y_test)
ex_3_b(x_train, y_train, x_test, y_test)
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 images classified as the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
lin = svm.SVC(decision_function_shape='ovr', kernel='linear')
lin.fit(x_train, y_train)
y_test_predict =lin.predict(x_test)
score_train = lin.score(x_train, y_train)
score_test = lin.score(x_test, y_test)
cm = confusion_matrix(y_test, y_test_predict)
plot_confusion_matrix(cm, labels)
#print(cm)
diff_list = y_test_predict == y_test
# indexes of all missclassiefied images
misclassifieds = [i for i, val in enumerate(diff_list) if val == False]
# remove diagonal elements from cm for later processing
cm_no_diagonal = cm
np.fill_diagonal(cm_no_diagonal, 0)
#print(cm_no_diagonal)
errors_per_class = np.sum(cm_no_diagonal, axis=0)
#print(errors_per_class)
sel_err = np.array(misclassifieds) # CHANGE ME! Numpy indices to select all images that are misclassified.
i = np.argmax(errors_per_class) # CHANGE ME! Should be the label number corresponding the largest classification error.
#print(i)
# Plot with mnist plot
plot_mnist(x_test[sel_err], y_test_predict[sel_err], labels=labels[i], k_plots=10, prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
SVMlin = svm.SVC(decision_function_shape='ovr', C=10, kernel='linear')
SVMlin.fit(x_train, y_train)
scorelin_train = SVMlin.score(x_train, y_train)
scorelin_test = SVMlin.score(x_test, y_test)
y_pred = SVMlin.predict(x_test)
conf_M = confusion_matrix(y_test, y_pred)
most_missclass = np.argmin(np.diagonal(conf_M)) + 1
plot_confusion_matrix(conf_M, labels)
print(most_missclass)
index_3 = np.where(y_test == 3)
sel_err1 = np.array(
[0]) # Numpy indices to select images that are misclassified.
sel_err = np.array(
[0]) # Numpy indices to select images that are misclassified.
sel_err1 = y_pred[(y_pred[index_3] - y_test[index_3] != 0) == True]
print(sel_err1)
sel_err = index_3[np.asarray(sel_err1)]
print(index_3, np.where(y_pred[index_3] - y_test[index_3] != 0))
i = most_missclass # should be the label number corresponding the largest classification error
# Plot with mnist plot
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=labels[i],
k_plots=10,
prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
C = 0.0003
clf = svm.SVC(C=C, kernel='linear', decision_function_shape='ovr')
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
labels = range(1, 6)
plot_confusion_matrix(confusion_matrix(y_test, y_pred), labels)
sel_error = np.array(
[0]) # Numpy indices to select images that are misclassified.
i = 0 # should be the label number corresponding the largest classification error
#in order to find the most missclassified we sum up the missclassified of every label and then we find the one with maximum error
sums = np.zeros((5, ))
k = 0
for j in y_pred:
if j != y_test[k]:
sums[y_test[k] - 1] += 1
sel_error = np.append(sel_error, k)
k += 1
i = np.argmax(sums)
# Plot with mnist plot
plot_mnist(x_test[sel_error],
y_pred[sel_error],
labels=labels[i],
k_plots=10,
prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
linear = svm.SVC(kernel='linear', C=10, decision_function_shape='ovr')
linear.fit(x_train, y_train)
y_pred = linear.predict(x_test)
cm = confusion_matrix(y_test, y_pred)
plot_confusion_matrix(cm, labels)
errors = np.zeros(5)
for i in range(5):
for j in range(5):
if i != j:
errors[j] += cm[i][j]
max_err_label = np.argmax(
errors
) + 1 # should be the label number corresponding the largest classification error
indices = np.nonzero(y_pred == max_err_label)[0].astype(int)
sel_err = np.array(
[],
dtype=int) # Numpy indices to select images that are misclassified.
for i in indices:
if y_test[i] != y_pred[i]:
sel_err = np.insert(sel_err, sel_err.size, i)
# Plot with mnist plot
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=max_err_label,
k_plots=10,
prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
svc_ovo = svm.SVC(kernel='linear', decision_function_shape='ovo',
C=10).fit(x_train, y_train)
y_pred = svc_ovo.predict(x_test)
cm = confusion_matrix(y_test, y_pred)
plot_confusion_matrix(cm, labels)
cp = cm
np.fill_diagonal(cp, 0)
i = np.argmax(
np.max(cp, axis=0)
) # should be the label number corresponding the largest classification error
sel_err = np.argwhere(np.not_equal(
y_test,
y_pred)) # Numpy indices to select images that are misclassified.
import pdb
pdb.set_trace()
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=labels[i],
k_plots=10,
prefix='Real class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 images classified as the most misclassified digit using plot_mnist.
###########
clf = svm.SVC(kernel="linear", decision_function_shape='ovr', C=10)
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
labels = range(1, 6)
plot_confusion_matrix(confusion_matrix(y_test, y_pred), labels)
print("conf: ", confusion_matrix(y_test, y_pred))
sel_err = np.array([
9, 25, 643, 654, 668, 685, 696, 727, 738, 739
]) # CHANGE ME! Numpy indices to select all images that are misclassified.
i = 0 # CHANGE ME! Should be the label number corresponding the largest classification error.
i = 2
j = 0
print("sel_err ", sel_err)
# Plot with mnist plot
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=labels[i],
k_plots=10,
prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
# TODO:
# Train multi-class SVMs with a LINEAR kernel
# Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
# Find the index for which you get the highest error rate.
# Plot the confusion matrix with plot_confusion_matrix.
# Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
svc = svm.SVC(C=10, kernel=LINEAR)
svc.fit(x_train, y_train)
y_pred = svc.predict(x_test)
con_matrix = confusion_matrix(y_test, y_pred, labels)
plot_confusion_matrix(con_matrix, labels)
sel_error = np.where(y_test != y_pred)
error_list = y_pred[sel_error]
occurences = Counter(error_list)
# should be the label number corresponding the largest classification error
i = max(occurences)
print("Label corresponding to the largest classification error : ", i)
plot_mnist(x_test[sel_error],
y_pred[sel_error],
labels=i,
k_plots=10,
prefix='Predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
labels = range(1, 6)
clf = svm.SVC(kernel="linear", C=3e-4, decision_function_shape='ovr')
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
cm = confusion_matrix(y_test, y_pred, labels)
plot_confusion_matrix(cm, labels)
sel_err = np.where(
y_test !=
y_pred) # Numpy indices to select images that are misclassified.
np.fill_diagonal(cm, 0)
i, j = np.unravel_index(cm.argmax(), cm.shape)
# Plot with mnist plot
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=labels[i],
k_plots=10,
prefix='predicted class')
def ex_3_b(x_train, y_train, x_test, y_test):
"""
Solution for exercise 3 b)
:param x_train: Training samples (2-dimensional)
:param y_train: Training labels
:param x_test: Testing samples (2-dimensional)
:param y_test: Testing labels
:return:
"""
###########
## TODO:
## Train multi-class SVMs with a LINEAR kernel
## Use the sklearn.metrics.confusion_matrix to plot the confusion matrix.
## Find the index for which you get the highest error rate.
## Plot the confusion matrix with plot_confusion_matrix.
## Plot the first 10 occurrences of the most misclassified digit using plot_mnist.
###########
# helper variables
m = 0
c = 10
kernel_mode = 'linear'
# init linear svm and train it
lin_svm = svm.SVC(kernel=kernel_mode, C=c)
lin_svm.fit(x_train, y_train)
# pred y to plot conf matrix
y_pred = lin_svm.predict(x_test)
cm = confusion_matrix(y_test, y_pred)
print(cm)
plot_confusion_matrix(cm, lin_svm.classes_)
# helper variables
most_misclassified_number = 0
temp_m = cm[0][0]
# searching for the most missclassifed number/label
for m in range(1, 5):
if (temp_m > cm[m][m]):
temp_m = cm[m][m]
most_misclassified_number = m
# given labels
labels = range(1, 6)
# helper variables
temp_list = []
image_counter = 0
max_pred = len(y_pred)
m = 0
# getting indices of missclassified numbers
for m in range(0, max_pred):
if (labels[most_misclassified_number] == y_pred[m]):
if (y_test[m] != y_pred[m]):
# add the missclassified image-index to the list
temp_list.append(m)
image_counter = image_counter + 1
# if we have 10 images stop
if (image_counter == 10):
break
# given output/plot --------------------------------------------------------------------------------
# Numpy indices to select images that are misclassified.
sel_err = np.array(temp_list)
# should be the label number corresponding the largest classification error
i = most_misclassified_number
# Plot with mnist plot
plot_mnist(x_test[sel_err],
y_pred[sel_err],
labels=labels[i],
k_plots=10,
prefix='Predicted class')
