def test_sparse_tf_idf():
hv = SparseHashingVectorizer(dim=1000000, probes=3)
hv.vectorize(JUNK_FOOD_DOCS)
hv.vectorize(NOTJUNK_FOOD_DOCS)
# extract the TF-IDF data
X = hv.get_tfidf()
assert_equal(X.shape, (11, 1000000))
# label junk food as -1, the others as +1
y = np.ones(X.shape[0])
y[:6] = -1
# train and test a classifier
clf = SparseLinearSVC(C=10).fit(X[1:-1], y[1:-1])
assert_equal(clf.predict(X[0, :]), [-1])
assert_equal(clf.predict(X[-1, :]), [1])
class SVM:
def __init__(self, training, classes, vocabulary):
vocabulary = load(vocabulary)
self.cv = CountVectorizer(vocabulary = vocabulary.tolist())
self.samples = load(training).tolist()
self.classes = load(classes)
self.classifier = LinearSVC()
self.classifier.fit(self.samples, self.classes)
def classify(self, text):
features = self.cv.transform([text])
return self.classifier.predict(features)[0]
print "done in %fs" % (time() - t0)
print "Predicting the labels of the test set..."
print "%d documents" % len(news_test.filenames)
print "%d categories" % len(news_test.target_names)
print "Extracting features from the dataset using the same vectorizer"
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in news_test.filenames))
y_test = news_test.target
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_test.shape
print "Predicting the outcomes of the testing set"
t0 = time()
pred = clf.predict(X_test)
print "done in %fs" % (time() - t0)
<<<<<<< HEAD
print "precision: %0.3f" % precision(y_test, pred)
print "recall: %0.3f" % recall(y_test, pred)
print "f1_score: %0.3f" % f1_score(y_test, pred)
=======
print "Classification report on test set:"
print classification_report(news_test.target, pred,
class_names=news_test.target_names)
>>>>>>> remote
cm = confusion_matrix(y_test, pred)
print "Confusion matrix:"
'C': 10,
'dual': False,
'eps': 1e-4,
}
print "parameters:", parameters
t0 = time()
clf = LinearSVC(**parameters).fit(news_train.data, news_train.target)
print "done in %fs" % (time() - t0)
print "Percentage of non zeros coef: %f" % (np.mean(clf.coef_ != 0) * 100)
print "Loading 20 newsgroups test set... "
t0 = time()
news_test = load_mlcomp('20news-18828', 'test', sparse=True)
print "done in %fs" % (time() - t0)
print "Predicting the labels of the test set..."
t0 = time()
pred = clf.predict(news_test.data)
print "done in %fs" % (time() - t0)
print "Classification accuracy: %f" % (np.mean(pred == news_test.target) * 100)
cm = confusion_matrix(news_test.target, pred)
print "Confusion matrix:"
print cm
# Show confusion matrix
pl.matshow(cm)
pl.title('Confusion matrix')
pl.colorbar()
pl.show()
print "done in %fs" % (time() - t0)
print "Predicting the labels of the test set..."
print "%d documents" % len(news_test.filenames)
print "%d categories" % len(news_test.target_names)
print "Extracting features from the dataset using the same vectorizer"
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in news_test.filenames))
y_test = news_test.target
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_test.shape
print "Predicting the outcomes of the testing set"
t0 = time()
pred = clf.predict(X_test)
print "done in %fs" % (time() - t0)
print "Classification report on test set for classifier:"
print clf
print
print classification_report(y_test, pred, class_names=news_test.target_names)
cm = confusion_matrix(y_test, pred)
print "Confusion matrix:"
print cm
# Show confusion matrix
pl.matshow(cm)
pl.title("Confusion matrix")
pl.colorbar()
