Merge branch 'master' of https://github.com/jack-mcivor/ngboost into …

…feature/py311

README.md

@@ -32,11 +32,15 @@ Probabilistic regression example on the Boston housing dataset:
 ```python
 from ngboost import NGBRegressor
 
-from sklearn.datasets import load_boston
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import mean_squared_error
 
-X, Y = load_boston(True)
+#Load Boston housing dataset
+data_url = "http://lib.stat.cmu.edu/datasets/boston"
+raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+X = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+Y = raw_df.values[1::2, 2]
+
 X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
 ngb = NGBRegressor().fit(X_train, Y_train)

RELEASE_NOTES.md

@@ -1,5 +1,9 @@
 # RELEASE NOTES
 
+## Version 0.4.2
+* Fix deprecated numpy type alias. This was causing a warning with NumPy >=1.20 and an error with NumPy >=1.24
+* Remove pandas as a declared dependency
+
 ## Version 0.4.1
 ### Added `partial_fit` method for incremental learning
 

examples/regression.py

@@ -1,13 +1,18 @@
-from sklearn.datasets import load_boston
+import numpy as np
+import pandas as pd
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import train_test_split
 
 from ngboost import NGBRegressor
 from ngboost.distns import Normal
 
 if __name__ == "__main__":
+    # Load Boston housing dataset
+    data_url = "http://lib.stat.cmu.edu/datasets/boston"
+    raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+    X = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+    Y = raw_df.values[1::2, 2]
 
-    X, Y = load_boston(return_X_y=True)
     X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
     ngb = NGBRegressor(Dist=Normal).fit(X_train, Y_train)

examples/survival.py

@@ -1,14 +1,18 @@
 import numpy as np
-from sklearn.datasets import load_boston
+import pandas as pd
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import train_test_split
 
 from ngboost import NGBSurvival
 from ngboost.distns import LogNormal
 
 if __name__ == "__main__":
+    # Load Boston housing dataset
+    data_url = "http://lib.stat.cmu.edu/datasets/boston"
+    raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+    X = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+    Y = raw_df.values[1::2, 2]
 
-    X, Y = load_boston(return_X_y=True)
     X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
     # introduce administrative censoring

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ngboost"
-version = "0.4.1dev"
+version = "0.4.2dev"
 description = "Library for probabilistic predictions via gradient boosting."
 authors = ["Stanford ML Group <[email protected]>"]
 readme = "README.md"

tests/test_distns.py

@@ -2,6 +2,8 @@
 
 import numpy as np
 import pytest
+from sklearn.datasets import fetch_california_housing, load_breast_cancer
+from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeRegressor
 
 from ngboost import NGBClassifier, NGBRegressor, NGBSurvival
@@ -29,6 +31,26 @@
 Tuple4Array = Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]
 Tuple5Array = Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray, np.ndarray]
 
+# pylint: disable=redefined-outer-name
+@pytest.fixture(scope="module")
+def regression_data():
+    data = fetch_california_housing()
+    X, y = data["data"][:1000], data["target"][:1000]
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42
+    )
+    return X_train, X_test, y_train, y_test
+
+
+@pytest.fixture(scope="module")
+def classification_data():
+    data = load_breast_cancer()
+    X, y = data["data"][:1000], data["target"][:1000]
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42
+    )
+    return X_train, X_test, y_train, y_test
+
 
 @pytest.mark.slow
 @pytest.mark.parametrize(
@@ -42,8 +64,8 @@
         DecisionTreeRegressor(criterion="friedman_mse", max_depth=5),
     ],
 )
-def test_dists_runs_on_examples_logscore(dist: Distn, learner, california_housing_data):
-    X_train, X_test, y_train, y_test = california_housing_data
+def test_dists_runs_on_examples_logscore(dist: Distn, learner, regression_data):
+    X_train, X_test, y_train, y_test = regression_data
     # TODO: test early stopping features
     ngb = NGBRegressor(Dist=dist, Score=LogScore, Base=learner, verbose=False)
     ngb.fit(X_train, y_train)
@@ -61,8 +83,8 @@ def test_dists_runs_on_examples_logscore(dist: Distn, learner, california_housin
         DecisionTreeRegressor(criterion="friedman_mse", max_depth=5),
     ],
 )
-def test_dists_runs_on_examples_crpscore(dist: Distn, learner, california_housing_data):
-    X_train, X_test, y_train, y_test = california_housing_data
+def test_dists_runs_on_examples_crpscore(dist: Distn, learner, regression_data):
+    X_train, X_test, y_train, y_test = regression_data
     # TODO: test early stopping features
     ngb = NGBRegressor(Dist=dist, Score=CRPScore, Base=learner, verbose=False)
     ngb.fit(X_train, y_train)
@@ -106,8 +128,8 @@ def test_survival_runs_on_examples(
         DecisionTreeRegressor(criterion="friedman_mse", max_depth=3),
     ],
 )
-def test_bernoulli(learner, breast_cancer_data: Tuple4Array):
-    X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = breast_cancer_data
+def test_bernoulli(learner, classification_data: Tuple4Array):
+    X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = classification_data
     # test early stopping features
     # test other args, n_trees, LR, minibatching- args as fixture
     ngb = NGBClassifier(Dist=Bernoulli, Score=LogScore, Base=learner, verbose=False)
@@ -127,8 +149,8 @@ def test_bernoulli(learner, breast_cancer_data: Tuple4Array):
         DecisionTreeRegressor(criterion="friedman_mse", max_depth=3),
     ],
 )
-def test_categorical(k: int, learner, breast_cancer_data: Tuple4Array):
-    X_train, X_test, y_train, _ = breast_cancer_data
+def test_categorical(k: int, learner, classification_data: Tuple4Array):
+    X_train, X_test, y_train, _ = classification_data
     dist = k_categorical(k)
     y_train = np.random.randint(0, k, (len(y_train)))
     # test early stopping features