def test_CCA_PLSCannonical(self, algo):
n = 500
with tm.RNGContext(1):
# 2 latents vars:
l1 = np.random.normal(size=n)
l2 = np.random.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + np.random.normal(size=4 * n).reshape((n, 4))
Y = latents + np.random.normal(size=4 * n).reshape((n, 4))
X_train = X[:n // 2]
Y_train = Y[:n // 2]
X_test = X[n // 2:]
Y_test = Y[n // 2:]
train = pdml.ModelFrame(X_train, target=Y_train)
test = pdml.ModelFrame(X_test, target=Y_test)
# check multi target columns
self.assertTrue(train.has_target())
tm.assert_numpy_array_equal(train.data.values, X_train)
tm.assert_numpy_array_equal(train.target.values, Y_train)
tm.assert_numpy_array_equal(test.data.values, X_test)
tm.assert_numpy_array_equal(test.target.values, Y_test)
expected = pd.MultiIndex.from_tuples([('.target', 0), ('.target', 1),
('.target', 2), ('.target', 3)])
tm.assert_index_equal(train.target_name, expected)
self.assertEqual(train.data.shape, X_train.shape)
self.assertEqual(train.target.shape, Y_train.shape)
mod1 = getattr(train.cross_decomposition, algo)(n_components=2)
mod2 = getattr(cd, algo)(n_components=2)
train.fit(mod1)
mod2.fit(X_train, Y_train)
# 2nd cols are different on travis-CI
self.assert_numpy_array_almost_equal(mod1.x_weights_[:, 0],
mod2.x_weights_[:, 0])
self.assert_numpy_array_almost_equal(mod1.y_weights_[:, 0],
mod2.y_weights_[:, 0])
result_tr = train.transform(mod1)
result_test = test.transform(mod1)
expected_tr = mod2.transform(X_train, Y_train)
expected_test = mod2.transform(X_test, Y_test)
self.assertIsInstance(result_tr, pdml.ModelFrame)
self.assertIsInstance(result_test, pdml.ModelFrame)
self.assert_numpy_array_almost_equal(result_tr.data.values[:, 0],
expected_tr[0][:, 0])
self.assert_numpy_array_almost_equal(result_tr.target.values[:, 0],
expected_tr[1][:, 0])
self.assert_numpy_array_almost_equal(result_test.data.values[:, 0],
expected_test[0][:, 0])
self.assert_numpy_array_almost_equal(result_test.target.values[:, 0],
expected_test[1][:, 0])
def test_grid_search(self):
tuned_parameters = [{'kernel': ['rbf'], 'gamma': [1e-3, 1e-4],
'C': [1, 10, 100]},
{'kernel': ['linear'], 'C': [1, 10, 100]}]
df = pdml.ModelFrame(datasets.load_digits())
cv = df.model_selection.GridSearchCV(df.svm.SVC(C=1), tuned_parameters, cv=5)
with tm.RNGContext(1):
df.fit(cv)
result = df.model_selection.describe(cv)
expected = pd.DataFrame(cv.cv_results_)
self.assertIsInstance(result, pdml.ModelFrame)
tm.assert_frame_equal(result, expected)
def test_grid_search(self):
tuned_parameters = [{'max_depth': [3, 4], 'n_estimators': [50, 100]}]
df = pdml.ModelFrame(datasets.load_digits())
cv = df.model_selection.GridSearchCV(df.xgb.XGBClassifier(),
tuned_parameters,
cv=5)
with tm.RNGContext(1):
df.fit(cv)
result = df.model_selection.describe(cv)
expected = pd.DataFrame(cv.cv_results_)
self.assertIsInstance(result, pdml.ModelFrame)
tm.assert_frame_equal(result, expected)
def test_grid_search(self):
tuned_parameters = [{'max_depth': [3, 4],
'n_estimators': [50, 100]}]
df = pdml.ModelFrame(datasets.load_digits())
cv = df.grid_search.GridSearchCV(df.xgb.XGBClassifier(), tuned_parameters, cv=5)
with tm.RNGContext(1):
df.fit(cv)
result = df.grid_search.describe(cv)
expected = pd.DataFrame({'mean': [0.89705064, 0.91764051, 0.91263216, 0.91930996],
'std': [0.03244061, 0.03259985, 0.02764891, 0.0266436],
'max_depth': [3, 3, 4, 4],
'n_estimators': [50, 100, 50, 100]},
columns=['mean', 'std', 'max_depth', 'n_estimators'])
self.assertIsInstance(result, pdml.ModelFrame)
self.assert_frame_equal(result, expected)
def test_grid_search(self):
tuned_parameters = [{
'kernel': ['rbf'],
'gamma': [1e-3, 1e-4],
'C': [1, 10, 100]
}, {
'kernel': ['linear'],
'C': [1, 10, 100]
}]
df = pdml.ModelFrame(datasets.load_digits())
cv = df.grid_search.GridSearchCV(df.svm.SVC(C=1),
tuned_parameters,
cv=5)
with tm.RNGContext(1):
df.fit(cv)
result = df.grid_search.describe(cv)
expected = pd.DataFrame(
{
'mean': [
0.97161937, 0.9476906, 0.97273233, 0.95937674, 0.97273233,
0.96271564, 0.94936004, 0.94936004, 0.94936004
],
'std': [
0.01546977, 0.0221161, 0.01406514, 0.02295168, 0.01406514,
0.01779749, 0.01911084, 0.01911084, 0.01911084
],
'C': [1, 1, 10, 10, 100, 100, 1, 10, 100],
'gamma': [
0.001, 0.0001, 0.001, 0.0001, 0.001, 0.0001, np.nan,
np.nan, np.nan
],
'kernel': ['rbf'] * 6 + ['linear'] * 3
},
columns=['mean', 'std', 'C', 'gamma', 'kernel'])
self.assertTrue(isinstance(result, pdml.ModelFrame))
self.assert_frame_equal(result, expected)