Merge pull request #40 from pylint-dev/26-add-pandas-inplace-parameter-set-checker

26 add pandas inplace parameter set checker

Author: PeterHamfelt

pylint_ml/checkers/pandas/pandas_inplace.py

@@ -0,0 +1,49 @@
+# Licensed under the MIT: https://mit-license.org/
+# For details: https://github.com/pylint-dev/pylint-ml/LICENSE
+# Copyright (c) https://github.com/pylint-dev/pylint-ml/CONTRIBUTORS.txt
+
+"""Check for improper usage of the inplace parameter in pandas operations."""
+
+from __future__ import annotations
+
+from astroid import nodes
+from pylint.checkers import BaseChecker
+from pylint.checkers.utils import only_required_for_messages
+from pylint.interfaces import HIGH
+
+
+class PandasInplaceChecker(BaseChecker):
+    name = "pandas-inplace"
+    msgs = {
+        "W8109": (
+            "Avoid using 'inplace=True' in pandas operations.",
+            "pandas-inplace",
+            "Using 'inplace=True' can lead to unclear and potentially problematic code. Prefer using assignment "
+            "instead.",
+        ),
+    }
+
+    _inplace_methods = {
+        "drop",
+        "fillna",
+        "replace",
+        "rename",
+        "set_index",
+        "reset_index",
+        "sort_values",
+        "sort_index",
+        "drop_duplicates",
+        "update",
+        "clip",
+    }
+
+    @only_required_for_messages("pandas-inplace")
+    def visit_call(self, node: nodes.Call) -> None:
+        # Check if the call is to a method that supports 'inplace'
+        if isinstance(node.func, nodes.Attribute):
+            method_name = node.func.attrname
+            if method_name in self._inplace_methods:
+                for keyword in node.keywords:
+                    if keyword.arg == "inplace" and getattr(keyword.value, "value", False) is True:
+                        self.add_message("pandas-inplace", node=node, confidence=HIGH)
+                        break

tests/checkers/test_pandas/test_pandas_inplace.py

@@ -0,0 +1,104 @@
+import astroid
+import pylint.testutils
+from pylint.interfaces import HIGH
+
+from pylint_ml.checkers.pandas.pandas_inplace import PandasInplaceChecker
+
+
+class TestPandasInplaceChecker(pylint.testutils.CheckerTestCase):
+    CHECKER_CLASS = PandasInplaceChecker
+
+    def test_inplace_used_in_drop(self):
+        node = astroid.extract_node(
+            """
+            import pandas as pd
+            df = pd.DataFrame({
+                "A": [1, 2, 3],
+                "B": [4, 5, 6]
+            })
+            df.drop(columns=["A"], inplace=True)  # [pandas-inplace]
+            """
+        )
+        with self.assertAddsMessages(
+            pylint.testutils.MessageTest(
+                msg_id="pandas-inplace",
+                confidence=HIGH,
+                node=node,
+            ),
+            ignore_position=True,
+        ):
+            self.checker.visit_call(node)
+
+    def test_inplace_used_in_fillna(self):
+        node = astroid.extract_node(
+            """
+            import pandas as pd
+            df = pd.DataFrame({
+                "A": [1, None, 3],
+                "B": [4, 5, None]
+            })
+            df.fillna(0, inplace=True)  # [pandas-inplace]
+            """
+        )
+        with self.assertAddsMessages(
+            pylint.testutils.MessageTest(
+                msg_id="pandas-inplace",
+                confidence=HIGH,
+                node=node,
+            ),
+            ignore_position=True,
+        ):
+            self.checker.visit_call(node)
+
+    def test_inplace_used_in_sort_values(self):
+        node = astroid.extract_node(
+            """
+            import pandas as pd
+            df = pd.DataFrame({
+                "A": [3, 2, 1],
+                "B": [4, 5, 6]
+            })
+            df.sort_values(by="A", inplace=True)  # [pandas-inplace]
+            """
+        )
+        with self.assertAddsMessages(
+            pylint.testutils.MessageTest(
+                msg_id="pandas-inplace",
+                confidence=HIGH,
+                node=node,
+            ),
+            ignore_position=True,
+        ):
+            self.checker.visit_call(node)
+
+    def test_no_inplace(self):
+        node = astroid.extract_node(
+            """
+            import pandas as pd
+            df = pd.DataFrame({
+                "A": [1, 2, 3],
+                "B": [4, 5, 6]
+            })
+            df = df.drop(columns=["A"])  # This should not trigger any warnings
+            """
+        )
+
+        inplace_call = node.value
+
+        with self.assertNoMessages():
+            self.checker.visit_call(inplace_call)
+
+    def test_inplace_used_in_unsupported_method(self):
+        node = astroid.extract_node(
+            """
+            import pandas as pd
+            df = pd.DataFrame({
+                "A": [1, 2, 3],
+                "B": [4, 5, 6]
+            })
+            df.append({"A": 4, "B": 7}, inplace=True)  # This should not trigger any warnings
+            """
+        )
+
+        with self.assertNoMessages():
+            self.checker.visit_call(node)