def test_fit_plus_transform(self):
iris, features = _load_iris()
decomp = trans(pd_decomposition.PCA(n_components=2), None,
['pc1', 'pc2'])
tr = decomp.fit(iris).transform(iris)
self.assertEqual(set(tr.columns), set(['pc1', 'pc2']))
def test_direct_single(self):
iris, features = _load_iris()
trn = pd_decomposition.PCA()
unpickled_trn = pickle.loads(pickle.dumps(trn))
pca_unpickled = unpickled_trn.fit_transform(iris[features])
pca = trn.fit_transform(iris[features])
self.assertTrue(pca_unpickled.equals(pca))
def test_cv(self):
digits, features = _load_digits()
clf = pd_decomposition.PCA() | pd_linear_model.LogisticRegression()
estimator = PDGridSearchCV(
clf, {
'pca__n_components': [20, 40, 64],
'logisticregression__C': np.logspace(-4, 4, 3)
})
if _level < 1:
return
estimator.fit(digits[features], digits.digit)
def test_direct_pipe_adapter(self):
clf = pd_decomposition.PCA() | pd_linear_model.LinearRegression()
unpickled_clf = pickle.loads(pickle.dumps(clf))
_iris, _features = _load_iris()
_dataset_names.append('iris')
_Xs.append(_iris[_features])
_ys.append(_iris['class'])
_Xs.append(_iris[_features])
_ys.append(_iris['class'] == _iris['class'].values[0])
_iris = _iris.copy()
_iris.index = ['i%d' % i for i in range(len(_iris))]
_dataset_names.append('iris_str_index')
_Xs.append(_iris[_features])
_ys.append(_iris['class'])
_estimators = []
_estimators.append(
(preprocessing.StandardScaler(), pd_preprocessing.StandardScaler(), True))
_estimators.append((decomposition.PCA(), pd_decomposition.PCA(), True))
_estimators.append((linear_model.LinearRegression(),
frame(pd_linear_model.LinearRegression()), True))
_estimators.append((linear_model.LinearRegression(),
pd_linear_model.LinearRegression(), True))
_estimators.append(
(pipeline.make_pipeline(decomposition.PCA(),
linear_model.LinearRegression()),
pd_decomposition.PCA() | pd_linear_model.LinearRegression(), True))
_estimators.append(
(pipeline.make_pipeline(feature_selection.SelectKBest(k=2),
decomposition.PCA(),
linear_model.LinearRegression()),
pd_feature_selection.SelectKBest(k=2) | pd_decomposition.PCA()
| pd_linear_model.LinearRegression(), True))
_estimators.append(