Add pandas iterrows checker

Author: Peter Hamfelt

.idea/.gitignore

@@ -0,0 +1,41 @@
+# 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 usage of the deprecated pandas DataFrame.bool() method."""
+
+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
+
+# Todo add version deprecated
+
+
+class PandasDataFrameBoolChecker(BaseChecker):
+    name = "pandas-dataframe-bool"
+    msgs = {
+        "W8104": (
+            "Use of deprecated pandas DataFrame.bool() method",
+            "pandas-dataframe-bool",
+            "Avoid using the deprecated pandas DataFrame.bool() method.",
+        ),
+    }
+
+    @only_required_for_messages("pandas-dataframe-bool")
+    def visit_call(self, node: nodes.Call) -> None:
+        if isinstance(node.func, nodes.Attribute):
+            method_name = getattr(node.func, "attrname", None)
+
+            if method_name == "bool":
+                # Check if the object calling .bool() has a name starting with 'df_'
+                object_name = getattr(node.func.expr, "name", None)
+                if object_name and self._is_valid_dataframe_name(object_name):
+                    self.add_message("pandas-dataframe-bool", node=node, confidence=HIGH)
+
+    @staticmethod
+    def _is_valid_dataframe_name(name: str) -> bool:
+        """Check if the DataFrame name starts with 'df_'."""
+        return name.startswith("df_")

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,38 @@
+# 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 usage of the inefficient pandas DataFrame.iterrows() method."""
+
+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 PandasIterrowsChecker(BaseChecker):
+    name = "pandas-iterrows"
+    msgs = {
+        "W8106": (
+            "Usage of pandas DataFrame.iterrows() detected",
+            "pandas-iterrows",
+            "Avoid using DataFrame.iterrows() for large datasets. Consider using vectorized operations or "
+            ".itertuples() instead.",
+        ),
+    }
+
+    @only_required_for_messages("pandas-iterrows")
+    def visit_call(self, node: nodes.Call) -> None:
+        if isinstance(node.func, nodes.Attribute):
+            method_name = getattr(node.func, "attrname", None)
+            if method_name == "iterrows":
+                object_name = getattr(node.func.expr, "name", None)
+                if object_name and self._is_dataframe_name(object_name):
+                    self.add_message("pandas-iterrows", node=node, confidence=HIGH)
+
+    @staticmethod
+    def _is_dataframe_name(name: str) -> bool:
+        """Check if the object name suggests it's a DataFrame (e.g., starts with 'df_')."""
+        return name.startswith("df_")

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,36 @@
+# 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 consistent naming of pandas DataFrame variables."""
+
+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 PandasDataFrameNamingChecker(BaseChecker):
+    name = "pandas-dataframe-naming"
+    msgs = {
+        "W8103": (
+            "Pandas DataFrame variable names should start with 'df_' followed by descriptive text",
+            "pandas-dataframe-naming",
+            "Ensure that pandas DataFrame variables follow the naming convention.",
+        ),
+    }
+
+    @only_required_for_messages("pandas-dataframe-naming")
+    def visit_assign(self, node: nodes.Assign) -> None:
+        if isinstance(node.value, nodes.Call):
+            func_name = getattr(node.value.func, "attrname", None)
+            module_name = getattr(node.value.func.expr, "name", None)
+
+            if func_name == "DataFrame" and module_name == "pd":
+                for target in node.targets:
+                    if isinstance(target, nodes.AssignName):
+                        var_name = target.name
+                        if not var_name.startswith("df_") or len(var_name) <= 3:
+                            self.add_message("pandas-dataframe-naming", node=node, confidence=HIGH)