Add flake8-print in pre-commit (#939)

* Add flake8-print in pre-commit config

* Replace print statements with logging

Author: 22quinn

.flake8

@@ -1,7 +1,7 @@
 [flake8]
 max-line-length = 100
 show-source = True
-select = C,E,F,W,B
+select = C,E,F,W,B,T
 ignore = E203, E402, W503
 per-file-ignores =
     *__init__.py:F401

.pre-commit-config.yaml

@@ -19,6 +19,10 @@ repos:
       - id: flake8
         name: flake8 openml
         files: openml/*
+        additional_dependencies:
+          - flake8-print==3.1.4
       - id: flake8
         name: flake8 tests
         files: tests/*
+        additional_dependencies:
+          - flake8-print==3.1.4

openml/extensions/sklearn/extension.py

@@ -1316,7 +1316,7 @@ def _prevent_optimize_n_jobs(self, model):
                         "Could not find attribute "
                         "param_distributions."
                     )
-                print(
+                logger.warning(
                     "Warning! Using subclass BaseSearchCV other than "
                     "{GridSearchCV, RandomizedSearchCV}. "
                     "Should implement param check. "

tests/conftest.py

@@ -40,7 +40,6 @@
 # exploiting the fact that conftest.py always resides in the root directory for tests
 static_dir = os.path.dirname(os.path.abspath(__file__))
 logger.info("static directory: {}".format(static_dir))
-print("static directory: {}".format(static_dir))
 while True:
     if "openml" in os.listdir(static_dir):
         break

tests/test_datasets/test_dataset_functions.py

@@ -1160,7 +1160,9 @@ def test_publish_fetch_ignore_attribute(self):
             except Exception as e:
                 # returned code 273: Dataset not processed yet
                 # returned code 362: No qualities found
-                print("Failed to fetch dataset:{} with '{}'.".format(dataset.id, str(e)))
+                TestBase.logger.error(
+                    "Failed to fetch dataset:{} with '{}'.".format(dataset.id, str(e))
+                )
                 time.sleep(10)
                 continue
         if downloaded_dataset is None:

tests/test_study/test_study_examples.py

@@ -48,10 +48,12 @@ def test_Figure1a(self):
                 clf, task, avoid_duplicate_runs=False
             )  # run classifier on splits (requires API key)
             score = run.get_metric_fn(sklearn.metrics.accuracy_score)  # print accuracy score
-            print("Data set: %s; Accuracy: %0.2f" % (task.get_dataset().name, score.mean()))
+            TestBase.logger.info(
+                "Data set: %s; Accuracy: %0.2f" % (task.get_dataset().name, score.mean())
+            )
             run.publish()  # publish the experiment on OpenML (optional)
             TestBase._mark_entity_for_removal("run", run.run_id)
             TestBase.logger.info(
                 "collected from {}: {}".format(__file__.split("/")[-1], run.run_id)
             )
-            print("URL for run: %s/run/%d" % (openml.config.server, run.run_id))
+            TestBase.logger.info("URL for run: %s/run/%d" % (openml.config.server, run.run_id))