scikit-learn · jeremiedbb · Jul 28, 2022 · Nov 29, 2020 · Nov 30, 2020 · Nov 30, 2020
diff --git a/doc/whats_new/v1.2.rst b/doc/whats_new/v1.2.rst
@@ -220,6 +220,16 @@ Changelog
 - |Fix| Fixed error message of :class:`metrics.coverage_error` for 1D array input.
   :pr:`23548` by :user:`Hao Chun Chang <haochunchang>`.
 
+:mod:`sklearn.multioutput`
+..........................
+
+- |Feature| Added boolean `verbose` flag to classes:
+  :class:`multioutput.ClassifierChain` and :class:`multioutput.RegressorChain`.
+  :pr:`23977` by :user:`Eric Fiegel <efiegel>`,
+  :user:`Chiara Marmo <cmarmo>`,
+  :user:`Lucy Liu <lucyleeow>`, and
+  :user:`Guillaume Lemaitre <glemaitre>`.
+
 :mod:`sklearn.naive_bayes`
 ..........................
 

diff --git a/sklearn/multioutput.py b/sklearn/multioutput.py
@@ -23,10 +23,14 @@
 from .base import BaseEstimator, clone, MetaEstimatorMixin
 from .base import RegressorMixin, ClassifierMixin, is_classifier
 from .model_selection import cross_val_predict
+from .utils import check_random_state, _print_elapsed_time
 from .utils.metaestimators import available_if
-from .utils import check_random_state
-from .utils.validation import check_is_fitted, has_fit_parameter, _check_fit_params
 from .utils.multiclass import check_classification_targets
+from .utils.validation import (
+    check_is_fitted,
+    has_fit_parameter,
+    _check_fit_params,
+)
 from .utils.fixes import delayed
 from .utils._param_validation import HasMethods
 
@@ -538,11 +542,19 @@ def _check(self):
 
 
 class _BaseChain(BaseEstimator, metaclass=ABCMeta):
-    def __init__(self, base_estimator, *, order=None, cv=None, random_state=None):
+    def __init__(
+        self, base_estimator, *, order=None, cv=None, random_state=None, verbose=False
+    ):
         self.base_estimator = base_estimator
         self.order = order
         self.cv = cv
         self.random_state = random_state
+        self.verbose = verbose
+
+    def _log_message(self, *, estimator_idx, n_estimators, processing_msg):
+        if not self.verbose:
+            return None
+        return f"({estimator_idx} of {n_estimators}) {processing_msg}"
 
     @abstractmethod
     def fit(self, X, Y, **fit_params):
@@ -602,8 +614,14 @@ def fit(self, X, Y, **fit_params):
         del Y_pred_chain
 
         for chain_idx, estimator in enumerate(self.estimators_):
+            message = self._log_message(
+                estimator_idx=chain_idx + 1,
+                n_estimators=len(self.estimators_),
+                processing_msg=f"Processing order {self.order_[chain_idx]}",
+            )
             y = Y[:, self.order_[chain_idx]]
-            estimator.fit(X_aug[:, : (X.shape[1] + chain_idx)], y, **fit_params)
+            with _print_elapsed_time("Chain", message):
+                estimator.fit(X_aug[:, : (X.shape[1] + chain_idx)], y, **fit_params)
             if self.cv is not None and chain_idx < len(self.estimators_) - 1:
                 col_idx = X.shape[1] + chain_idx
                 cv_result = cross_val_predict(
@@ -702,6 +720,11 @@ class ClassifierChain(MetaEstimatorMixin, ClassifierMixin, _BaseChain):
         Pass an int for reproducible output across multiple function calls.
         See :term:`Glossary <random_state>`.
 
+    verbose : bool, default=False
+        If True, chain progress is output as each model is completed.
+
+        .. versionadded:: 1.2
+
     Attributes
     ----------
     classes_ : list
@@ -903,6 +926,11 @@ class RegressorChain(MetaEstimatorMixin, RegressorMixin, _BaseChain):
         Pass an int for reproducible output across multiple function calls.
         See :term:`Glossary <random_state>`.
 
+    verbose : bool, default=False
+        If True, chain progress is output as each model is completed.
+
+        .. versionadded:: 1.2
+
     Attributes
     ----------
     estimators_ : list

diff --git a/sklearn/tests/test_multioutput.py b/sklearn/tests/test_multioutput.py
@@ -2,6 +2,7 @@
 import numpy as np
 import scipy.sparse as sp
 from joblib import cpu_count
+import re
 
 from sklearn.utils._testing import assert_almost_equal
 from sklearn.utils._testing import assert_array_equal
@@ -10,6 +11,8 @@
 from sklearn.base import clone
 from sklearn.datasets import make_classification
 from sklearn.datasets import load_linnerud
+from sklearn.datasets import make_multilabel_classification
+from sklearn.datasets import make_regression
 from sklearn.ensemble import GradientBoostingRegressor, RandomForestClassifier
 from sklearn.exceptions import NotFittedError
 from sklearn.linear_model import Lasso
@@ -18,15 +21,17 @@
 from sklearn.linear_model import Ridge
 from sklearn.linear_model import SGDClassifier
 from sklearn.linear_model import SGDRegressor
+from sklearn.linear_model import LinearRegression
 from sklearn.metrics import jaccard_score, mean_squared_error
 from sklearn.multiclass import OneVsRestClassifier
 from sklearn.multioutput import ClassifierChain, RegressorChain
 from sklearn.multioutput import MultiOutputClassifier
 from sklearn.multioutput import MultiOutputRegressor
 from sklearn.svm import LinearSVC
+from sklearn.tree import DecisionTreeClassifier
 from sklearn.base import ClassifierMixin
 from sklearn.utils import shuffle
-from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import GridSearchCV, train_test_split
 from sklearn.dummy import DummyRegressor, DummyClassifier
 from sklearn.pipeline import make_pipeline
 from sklearn.impute import SimpleImputer
@@ -702,6 +707,47 @@ def test_classifier_chain_tuple_invalid_order():
         chain.fit(X, y)
 
 
+def test_classifier_chain_verbose(capsys):
+    X, y = make_multilabel_classification(
+        n_samples=100, n_features=5, n_classes=3, n_labels=3, random_state=0
+    )
+    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+
+    pattern = (
+        r"\[Chain\].*\(1 of 3\) Processing order 0, total=.*\n"
+        r"\[Chain\].*\(2 of 3\) Processing order 1, total=.*\n"
+        r"\[Chain\].*\(3 of 3\) Processing order 2, total=.*\n$"
+    )
+
+    classifier = ClassifierChain(
+        DecisionTreeClassifier(),
+        order=[0, 1, 2],
+        random_state=0,
+        verbose=True,
+    )
+    classifier.fit(X_train, y_train)
+    assert re.match(pattern, capsys.readouterr()[0])
+
+
+def test_regressor_chain_verbose(capsys):
+    X, y = make_regression(n_samples=125, n_targets=3, random_state=0)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+
+    pattern = (
+        r"\[Chain\].*\(1 of 3\) Processing order 1, total=.*\n"
+        r"\[Chain\].*\(2 of 3\) Processing order 0, total=.*\n"
+        r"\[Chain\].*\(3 of 3\) Processing order 2, total=.*\n$"
+    )
+    regressor = RegressorChain(
+        LinearRegression(),
+        order=[1, 0, 2],
+        random_state=0,
+        verbose=True,
+    )
+    regressor.fit(X_train, y_train)
+    assert re.match(pattern, capsys.readouterr()[0])
+
+
 def test_multioutputregressor_ducktypes_fitted_estimator():
     """Test that MultiOutputRegressor checks the fitted estimator for
     predict. Non-regression test for #16549."""