def test_logistic_random_data(self):
X_train, X_test, y_train, y_test = get_classification_data(n_classes=2)
logistic = LogisticRegression(sparkSession)
logistic.fit(X_train, y_train)
mllearn_predicted = logistic.predict(X_test)
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
self.failUnless(
test_accuracy_score(sklearn_logistic.predict(X_test),
mllearn_predicted, y_test, 0.95))
def test_logistic(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):]
logistic = LogisticRegression(sparkSession)
logistic.fit(X_train, y_train)
mllearn_predicted = logistic.predict(X_test)
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
self.failUnless(accuracy_score(sklearn_logistic.predict(X_test), mllearn_predicted) > 0.95) # We are comparable to a similar algorithm in scikit learn
def test_logistic(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):]
logistic = LogisticRegression(sparkSession)
logistic.fit(X_train, y_train)
mllearn_predicted = logistic.predict(X_test)
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
self.failUnless(accuracy_score(sklearn_logistic.predict(X_test), mllearn_predicted) > 0.95) # We are comparable to a similar algorithm in scikit learn
def test_logistic_sk2(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):]
# Convert to DataFrame for i/o: current way to transfer data
logistic = LogisticRegression(sparkSession, transferUsingDF=True)
logistic.fit(X_train, y_train)
mllearn_predicted = logistic.predict(X_test)
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
self.failUnless(accuracy_score(sklearn_logistic.predict(X_test), mllearn_predicted) > 0.95) # We are comparable to a similar algorithm in scikit learn
def test_logistic_sk2(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):]
# Convert to DataFrame for i/o: current way to transfer data
logistic = LogisticRegression(sparkSession, transferUsingDF=True)
logistic.fit(X_train, y_train)
mllearn_predicted = logistic.predict(X_test)
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
self.failUnless(accuracy_score(sklearn_logistic.predict(X_test), mllearn_predicted) > 0.95) # We are comparable to a similar algorithm in scikit learn
