def test_pipeline_fit_internal_pd_stage(self):
X = pd.DataFrame({'a': [1, 2, 3]})
y = pd.Series([1, 2, 3])
p = pd_pipeline.make_pipeline(pd_linear_model.LinearRegression())
self.assertTrue(isinstance(p, FrameMixin))
pd_p = frame(p)
y_hat = pd_p.fit(X, y).predict(X)
self.assertTrue(isinstance(y_hat, pd.Series))
def test_pipeline_fit(self):
X = pd.DataFrame({'a': [1, 2, 3]})
y = pd.Series([1, 2, 3])
# Tmp Ami - make verify that are framemixins
p = pd_pipeline.make_pipeline(pd_linear_model.LinearRegression())
self.assertTrue(isinstance(p, FrameMixin))
pd_p = frame(p)
pd_p = pd_p.fit(X, y)
y_hat = pd_p.fit(X, y).predict(X)
self.assertTrue(isinstance(y_hat, pd.Series))
_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(
(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(
(pipeline.make_pipeline(decomposition.PCA(),
linear_model.LinearRegression()),
pd_pipeline.make_pipeline(pd_decomposition.PCA(),
pd_linear_model.LinearRegression()), True))
_estimators.append((linear_model.LogisticRegression(),
pd_linear_model.LogisticRegression(), True))
_estimators.append((cluster.KMeans(random_state=42),
pd_cluster.KMeans(random_state=42), True))
_estimators.append(
(cluster.KMeans(random_state=42),
pickle.loads(pickle.dumps(pd_cluster.KMeans(random_state=42))), True))
_estimators.append((neighbors.KNeighborsClassifier(),
pd_neighbors.KNeighborsClassifier(), True))
_estimators.append(
(ensemble.GradientBoostingClassifier(random_state=42),
pd_ensemble.GradientBoostingClassifier(random_state=42), True))
_estimators.append((pipeline.make_union(decomposition.PCA(n_components=2),
feature_selection.SelectKBest(k=1)),
pd_decomposition.PCA(n_components=2) +
def test_make_pipeline(self):
p = pd_pipeline.make_pipeline(pd_preprocessing.StandardScaler(),
pd_linear_model.LinearRegression())