unlabeled_set = indices[n_labeled_points:]
# #############################################################################
# Shuffle everything around
y_train = np.copy(y)
y_train[unlabeled_set] = -1
# #############################################################################
# Learn with LabelSpreading
lp_model = label_propagation.LabelSpreading(gamma=.25, max_iter=20)
lp_model.fit(X, y_train)
predicted_labels = lp_model.transduction_[unlabeled_set]
true_labels = y[unlabeled_set]
cm = confusion_matrix(true_labels, predicted_labels, labels=lp_model.classes_)
print("Label Spreading model: %d labeled & %d unlabeled points (%d total)" %
(n_labeled_points, n_total_samples - n_labeled_points, n_total_samples))
print(classification_report(true_labels, predicted_labels))
print("Confusion matrix")
print(cm)
# #############################################################################
# Calculate uncertainty values for each transduced distribution
pred_entropies = stats.distributions.entropy(lp_model.label_distributions_.T)
# #############################################################################
# Pick the top 10 most uncertain labels
])
# TASK: Fit the pipeline on the training set
clf.fit(docs_train, y_train)
# TASK: Predict the outcome on the testing set in a variable named y_predicted
y_predicted = clf.predict(docs_test)
# Print the classification report
print(
metrics.classification_report(y_test,
y_predicted,
target_names=dataset.target_names))
# Plot the confusion matrix
cm = metrics.confusion_matrix(y_test, y_predicted)
print(cm)
#import matlotlib.pyplot as plt
#plt.matshow(cm, cmap=plt.cm.jet)
#plt.show()
# Predict the result on some short new sentences:
sentences = [
'This is a language detection test.',
'Ceci est un test de d\xe9tection de la langue.',
'Dies ist ein Test, um die Sprache zu erkennen.',
]
predicted = clf.predict(sentences)
for s, p in zip(sentences, predicted):
clf = clf.fit(X_train_pca, y_train)
print("done in %0.3fs" % (time() - t0))
print("Best estimator found by grid search:")
print(clf.best_estimator_)
# #############################################################################
# Quantitative evaluation of the model quality on the test set
print("Predicting people's names on the test set")
t0 = time()
y_pred = clf.predict(X_test_pca)
print("done in %0.3fs" % (time() - t0))
print(classification_report(y_test, y_pred, target_names=target_names))
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))
# #############################################################################
# Qualitative evaluation of the predictions using matplotlib
def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
"""Helper function to plot a gallery of portraits"""
plt.figure(figsize=(1.8 * n_col, 2.4 * n_row))
plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
for i in range(n_row * n_col):
plt.subplot(n_row, n_col, i + 1)
plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray)
plt.title(titles[i], size=12)
plt.xticks(())
plt.yticks(())
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
plt.title('Training: %i' % label)
# To apply a classifier on this data, we need to flatten the image, to
# turn the data in a (samples, feature) matrix:
n_samples = len(digits.images)
data = digits.images.reshape((n_samples, -1))
# Create a classifier: a support vector classifier
classifier = svm.SVC(gamma=0.001)
# We learn the digits on the first half of the digits
classifier.fit(data[:n_samples // 2], digits.target[:n_samples // 2])
# Now predict the value of the digit on the second half:
expected = digits.target[n_samples // 2:]
predicted = classifier.predict(data[n_samples // 2:])
print("Classification report for classifier %s:\n%s\n" %
(classifier, metrics.classification_report(expected, predicted)))
print("Confusion matrix:\n%s" % metrics.confusion_matrix(expected, predicted))
images_and_predictions = list(zip(digits.images[n_samples // 2:], predicted))
for index, (image, prediction) in enumerate(images_and_predictions[:4]):
plt.subplot(2, 4, index + 5)
plt.axis('off')
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
plt.title('Prediction: %i' % prediction)
plt.show()
def plot_confusion_matrix(y_true,
y_pred,
classes,
normalize=False,
title=None,
cmap=plt.cm.Blues):
"""
This function prints and plots the confusion matrix.
Normalization can be applied by setting `normalize=True`.
"""
if not title:
if normalize:
title = 'Normalized confusion matrix'
else:
title = 'Confusion matrix, without normalization'
# Compute confusion matrix
cm = confusion_matrix(y_true, y_pred)
# Only use the labels that appear in the data
classes = classes[unique_labels(y_true, y_pred)]
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
print("Normalized confusion matrix")
else:
print('Confusion matrix, without normalization')
print(cm)
fig, ax = plt.subplots()
im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
ax.figure.colorbar(im, ax=ax)
# We want to show all ticks...
ax.set(
xticks=np.arange(cm.shape[1]),
yticks=np.arange(cm.shape[0]),
# ... and label them with the respective list entries
xticklabels=classes,
yticklabels=classes,
title=title,
ylabel='True label',
xlabel='Predicted label')
# Rotate the tick labels and set their alignment.
plt.setp(ax.get_xticklabels(),
rotation=45,
ha="right",
rotation_mode="anchor")
# Loop over data dimensions and create text annotations.
fmt = '.2f' if normalize else 'd'
thresh = cm.max() / 2.
for i in range(cm.shape[0]):
for j in range(cm.shape[1]):
ax.text(j,
i,
format(cm[i, j], fmt),
ha="center",
va="center",
color="white" if cm[i, j] > thresh else "black")
fig.tight_layout()
return ax