def test_naive_bayes(self):
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:int(.9 * n_samples)]
y_train = y_digits[:int(.9 * n_samples)]
X_test = X_digits[int(.9 * n_samples):]
y_test = y_digits[int(.9 * n_samples):]
nb = NaiveBayes(sqlCtx)
score = nb.fit(X_train, y_train).score(X_test, y_test)
self.failUnless(score > 0.8)
def testNaiveBayesSK1(self):
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:.9 * n_samples]
y_train = y_digits[:.9 * n_samples]
X_test = X_digits[.9 * n_samples:]
y_test = y_digits[.9 * n_samples:]
nb = NaiveBayes(sqlCtx)
score = nb.fit(X_train, y_train).score(X_test, y_test)
self.failUnless(score > 0.85)
def testNaiveBayesSK1(self):
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:.9 * n_samples]
y_train = y_digits[:.9 * n_samples]
X_test = X_digits[.9 * n_samples:]
y_test = y_digits[.9 * n_samples:]
nb = NaiveBayes(sqlCtx)
score = nb.fit(X_train, y_train).score(X_test, y_test)
self.failUnless(score > 0.85)
def test_naive_bayes(self):
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:int(.9 * n_samples)]
y_train = y_digits[:int(.9 * n_samples)]
X_test = X_digits[int(.9 * n_samples):]
y_test = y_digits[int(.9 * n_samples):]
nb = NaiveBayes(sqlCtx)
score = nb.fit(X_train, y_train).score(X_test, y_test)
self.failUnless(score > 0.8)
def testNaiveBayesSK2(self):
categories = ['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
newsgroups_train = fetch_20newsgroups(subset='train', categories=categories)
newsgroups_test = fetch_20newsgroups(subset='test', categories=categories)
vectorizer = TfidfVectorizer()
# Both vectors and vectors_test are SciPy CSR matrix
vectors = vectorizer.fit_transform(newsgroups_train.data)
vectors_test = vectorizer.transform(newsgroups_test.data)
nb = NaiveBayes(sqlCtx)
nb.fit(vectors, newsgroups_train.target)
pred = nb.predict(vectors_test)
score = metrics.f1_score(newsgroups_test.target, pred, average='weighted')
self.failUnless(score > 0.8)
def test_naive_bayes1(self):
categories = ['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
newsgroups_train = fetch_20newsgroups(subset='train', categories=categories)
newsgroups_test = fetch_20newsgroups(subset='test', categories=categories)
vectorizer = TfidfVectorizer()
# Both vectors and vectors_test are SciPy CSR matrix
vectors = vectorizer.fit_transform(newsgroups_train.data)
vectors_test = vectorizer.transform(newsgroups_test.data)
nb = NaiveBayes(sparkSession)
mllearn_predicted = nb.fit(vectors, newsgroups_train.target).predict(vectors_test)
from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB()
sklearn_predicted = clf.fit(vectors, newsgroups_train.target).predict(vectors_test)
self.failUnless(accuracy_score(sklearn_predicted, mllearn_predicted) > 0.95 )
def test_naive_bayes1(self):
categories = ['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
newsgroups_train = fetch_20newsgroups(subset='train', categories=categories)
newsgroups_test = fetch_20newsgroups(subset='test', categories=categories)
vectorizer = TfidfVectorizer()
# Both vectors and vectors_test are SciPy CSR matrix
vectors = vectorizer.fit_transform(newsgroups_train.data)
vectors_test = vectorizer.transform(newsgroups_test.data)
nb = NaiveBayes(sparkSession)
mllearn_predicted = nb.fit(vectors, newsgroups_train.target).predict(vectors_test)
from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB()
sklearn_predicted = clf.fit(vectors, newsgroups_train.target).predict(vectors_test)
self.failUnless(accuracy_score(sklearn_predicted, mllearn_predicted) > 0.95 )
def test_naive_bayes(self):
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:int(.9 * n_samples)]
y_train = y_digits[:int(.9 * n_samples)]
X_test = X_digits[int(.9 * n_samples):]
y_test = y_digits[int(.9 * n_samples):]
nb = NaiveBayes(sparkSession)
mllearn_predicted = nb.fit(X_train, y_train).predict(X_test)
from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB()
sklearn_predicted = clf.fit(X_train, y_train).predict(X_test)
self.failUnless(accuracy_score(sklearn_predicted, mllearn_predicted) > 0.95 )
def test_naive_bayes(self):
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
n_samples = len(X_digits)
X_train = X_digits[:int(.9 * n_samples)]
y_train = y_digits[:int(.9 * n_samples)]
X_test = X_digits[int(.9 * n_samples):]
y_test = y_digits[int(.9 * n_samples):]
nb = NaiveBayes(sparkSession)
mllearn_predicted = nb.fit(X_train, y_train).predict(X_test)
from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB()
sklearn_predicted = clf.fit(X_train, y_train).predict(X_test)
self.failUnless(accuracy_score(sklearn_predicted, mllearn_predicted) > 0.95 )
def testNaiveBayesSK2(self):
categories = [
'alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space'
]
newsgroups_train = fetch_20newsgroups(subset='train',
categories=categories)
newsgroups_test = fetch_20newsgroups(subset='test',
categories=categories)
vectorizer = TfidfVectorizer()
# Both vectors and vectors_test are SciPy CSR matrix
vectors = vectorizer.fit_transform(newsgroups_train.data)
vectors_test = vectorizer.transform(newsgroups_test.data)
nb = NaiveBayes(sqlCtx)
nb.fit(vectors, newsgroups_train.target)
pred = nb.predict(vectors_test)
score = metrics.f1_score(newsgroups_test.target,
pred,
average='weighted')
self.failUnless(score > 0.8)
