clf = GridSearchCV(
SVC(), tuned_parameters, scoring='%s_macro' % score
)
clf.fit(X_train, y_train)
print("Best parameters set found on development set:")
print()
print(clf.best_params_)
print()
print("Grid scores on development set:")
print()
means = clf.cv_results_['mean_test_score']
stds = clf.cv_results_['std_test_score']
for mean, std, params in zip(means, stds, clf.cv_results_['params']):
print("%0.3f (+/-%0.03f) for %r"
% (mean, std * 2, params))
print()
print("Detailed classification report:")
print()
print("The model is trained on the full development set.")
print("The scores are computed on the full evaluation set.")
print()
y_true, y_pred = y_test, clf.predict(X_test)
print(classification_report(y_true, y_pred))
print()
# Note the problem is too easy: the hyperparameter plateau is too flat and the
# output model is the same for precision and recall with ties in quality.
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
uncertainty_index = np.argsort(pred_entropies)[-10:]
# #############################################################################
# Plot
f = plt.figure(figsize=(7, 5))
# the pipeline instance should stored in a variable named clf
clf = Pipeline([
('vec', vectorizer),
('clf', Perceptron()),
])
# 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.',
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()
from mrex.datasets import samples_generator
from mrex.feature_selection import SelectKBest, f_regression
from mrex.pipeline import make_pipeline
from mrex.model_selection import train_test_split
from mrex.metrics import classification_report
print(__doc__)
# import some data to play with
X, y = samples_generator.make_classification(n_features=20,
n_informative=3,
n_redundant=0,
n_classes=4,
n_clusters_per_class=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
# ANOVA SVM-C
# 1) anova filter, take 3 best ranked features
anova_filter = SelectKBest(f_regression, k=3)
# 2) svm
clf = svm.LinearSVC()
anova_svm = make_pipeline(anova_filter, clf)
anova_svm.fit(X_train, y_train)
y_pred = anova_svm.predict(X_test)
print(classification_report(y_test, y_pred))
coef = anova_svm[:-1].inverse_transform(anova_svm['linearsvc'].coef_)
print(coef)
)
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(())
logistic.C = 6000
# Training RBM-Logistic Pipeline
rbm_features_classifier.fit(X_train, Y_train)
# Training the Logistic regression classifier directly on the pixel
raw_pixel_classifier = clone(logistic)
raw_pixel_classifier.C = 100.
raw_pixel_classifier.fit(X_train, Y_train)
# #############################################################################
# Evaluation
Y_pred = rbm_features_classifier.predict(X_test)
print("Logistic regression using RBM features:\n%s\n" %
(metrics.classification_report(Y_test, Y_pred)))
Y_pred = raw_pixel_classifier.predict(X_test)
print("Logistic regression using raw pixel features:\n%s\n" %
(metrics.classification_report(Y_test, Y_pred)))
# #############################################################################
# Plotting
plt.figure(figsize=(4.2, 4))
for i, comp in enumerate(rbm.components_):
plt.subplot(10, 10, i + 1)
plt.imshow(comp.reshape((8, 8)),
cmap=plt.cm.gray_r,
interpolation='nearest')
plt.xticks(())
