clf = LinearSVC(**parameters).fit(X_train, y_train)
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... "
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
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:"
# split a training set and a test set
filenames_train, filenames_test = data_train.filenames, data_test.filenames
y_train, y_test = data_train.target, data_test.target
print "Extracting features from the training dataset using a sparse vectorizer"
t0 = time()
vectorizer = Vectorizer()
X_train = vectorizer.fit_transform((open(f).read() for f in filenames_train))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
print
print "Extracting features from the test dataset using the same vectorizer"
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in filenames_test))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_test.shape
print
################################################################################
# Benchmark classifiers
def benchmark(clf):
print 80 * '_'
print "Training: "
print clf
t0 = time()
clf.fit(X_train, y_train)
train_time = time() - t0
print "train time: %0.3fs" % train_time
clf = SGDClassifier(**parameters).fit(X_train, y_train)
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... "
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
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)
# split a training set and a test set
filenames_train, filenames_test = data_train.filenames, data_test.filenames
y_train, y_test = data_train.target, data_test.target
print "Extracting features from the training dataset using a sparse vectorizer"
t0 = time()
vectorizer = Vectorizer()
X_train = vectorizer.fit_transform((open(f).read() for f in filenames_train))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
print
print "Extracting features from the test dataset using the same vectorizer"
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in filenames_test))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_test.shape
print
################################################################################
# Benchmark classifiers
def benchmark(clf):
print 80 * '_'
print "Training: "
print clf
t0 = time()
clf.fit(X_train, y_train)
train_time = time() - t0
print "train time: %0.3fs" % train_time