replace sklearn.datasets.load_boston()

Author: jlwalke2

examples/full_lifecycle.py

@@ -16,9 +16,9 @@
 from sasctl.services import model_management as mm
 
 
-data = sklearn.datasets.load_boston()
-X = pd.DataFrame(data.data, columns=data.feature_names)
-y = pd.DataFrame(data.target, columns=['Price'])
+data = pd.read_csv('data/boston_house_prices.csv').rename(columns={'medv': 'Price'})
+X = data.drop(columns=['Price'])
+y = data['Price']
 
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
 

tests/integration/test_tasks.py

@@ -47,16 +47,14 @@ def sklearn_logistic_model():
 
 
 @pytest.fixture
-def sklearn_linear_model():
+def sklearn_linear_model(boston_dataset):
     """A Scikit-Learn linear regression fit to Boston housing data."""
 
     pd = pytest.importorskip('pandas')
-    datasets = pytest.importorskip('sklearn.datasets')
     linear_model = pytest.importorskip('sklearn.linear_model')
 
-    data = datasets.load_boston()
-    X = pd.DataFrame(data.data, columns=data.feature_names)
-    y = pd.DataFrame(data.target, columns=['Price'])
+    X = boston_dataset.drop(columns=['Price'])
+    y = boston_dataset['Price']
 
     with warnings.catch_warnings():
         warnings.simplefilter('ignore')