TYP: Add MyPy Error Codes (#35311)

Author: simonjayhawkins

ci/code_checks.sh

@@ -230,6 +230,11 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     invgrep -R --include="*.py" -P '# type: (?!ignore)' pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    # https://github.com/python/mypy/issues/7384
+    # MSG='Check for missing error codes with # type: ignore' ; echo $MSG
+    # invgrep -R --include="*.py" -P '# type: ignore(?!\[)' pandas
+    # RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     MSG='Check for use of foo.__class__ instead of type(foo)' ; echo $MSG
     invgrep -R --include=*.{py,pyx} '\.__class__' pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"

environment.yml

@@ -109,3 +109,4 @@ dependencies:
   - pip:
     - git+https://github.com/pandas-dev/pydata-sphinx-theme.git@master
     - git+https://github.com/numpy/numpydoc
+    - pyflakes>=2.2.0

pandas/_config/config.py

@@ -462,7 +462,7 @@ def register_option(
     for k in path:
         # NOTE: tokenize.Name is not a public constant
         # error: Module has no attribute "Name"  [attr-defined]
-        if not re.match("^" + tokenize.Name + "$", k):  # type: ignore
+        if not re.match("^" + tokenize.Name + "$", k):  # type: ignore[attr-defined]
             raise ValueError(f"{k} is not a valid identifier")
         if keyword.iskeyword(k):
             raise ValueError(f"{k} is a python keyword")

pandas/compat/pickle_compat.py

@@ -64,7 +64,7 @@ class _LoadSparseSeries:
     # https://github.com/python/mypy/issues/1020
     # error: Incompatible return type for "__new__" (returns "Series", but must return
     # a subtype of "_LoadSparseSeries")
-    def __new__(cls) -> "Series":  # type: ignore
+    def __new__(cls) -> "Series":  # type: ignore[misc]
         from pandas import Series
 
         warnings.warn(
@@ -82,7 +82,7 @@ class _LoadSparseFrame:
     # https://github.com/python/mypy/issues/1020
     # error: Incompatible return type for "__new__" (returns "DataFrame", but must
     # return a subtype of "_LoadSparseFrame")
-    def __new__(cls) -> "DataFrame":  # type: ignore
+    def __new__(cls) -> "DataFrame":  # type: ignore[misc]
         from pandas import DataFrame
 
         warnings.warn(
@@ -181,7 +181,7 @@ def __new__(cls) -> "DataFrame":  # type: ignore
 # functions for compat and uses a non-public class of the pickle module.
 
 # error: Name 'pkl._Unpickler' is not defined
-class Unpickler(pkl._Unpickler):  # type: ignore
+class Unpickler(pkl._Unpickler):  # type: ignore[name-defined]
     def find_class(self, module, name):
         # override superclass
         key = (module, name)

pandas/core/algorithms.py

@@ -427,7 +427,8 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
     if is_categorical_dtype(comps):
         # TODO(extension)
         # handle categoricals
-        return comps.isin(values)  # type: ignore
+        # error: "ExtensionArray" has no attribute "isin"  [attr-defined]
+        return comps.isin(values)  # type: ignore[attr-defined]
 
     comps, dtype = _ensure_data(comps)
     values, _ = _ensure_data(values, dtype=dtype)

pandas/core/arrays/datetimelike.py

@@ -468,6 +468,9 @@ def _ndarray(self) -> np.ndarray:
 
     def _from_backing_data(self: _T, arr: np.ndarray) -> _T:
         # Note: we do not retain `freq`
+        # error: Unexpected keyword argument "dtype" for "NDArrayBackedExtensionArray"
+        # TODO: add my error code
+        # https://github.com/python/mypy/issues/7384
         return type(self)(arr, dtype=self.dtype)  # type: ignore
 
     # ------------------------------------------------------------------
@@ -809,7 +812,8 @@ def _validate_scalar(
             value = NaT
 
         elif isinstance(value, self._recognized_scalars):
-            value = self._scalar_type(value)  # type: ignore
+            # error: Too many arguments for "object"  [call-arg]
+            value = self._scalar_type(value)  # type: ignore[call-arg]
 
         else:
             if msg is None:
@@ -1129,7 +1133,8 @@ def resolution(self) -> str:
         """
         Returns day, hour, minute, second, millisecond or microsecond
         """
-        return self._resolution_obj.attrname  # type: ignore
+        # error: Item "None" of "Optional[Any]" has no attribute "attrname"
+        return self._resolution_obj.attrname  # type: ignore[union-attr]
 
     @classmethod
     def _validate_frequency(cls, index, freq, **kwargs):

pandas/core/arrays/interval.py

@@ -1057,7 +1057,7 @@ def mid(self):
 
     # https://github.com/python/mypy/issues/1362
     # Mypy does not support decorated properties
-    @property  # type: ignore
+    @property  # type: ignore[misc]
     @Appender(
         _interval_shared_docs["is_non_overlapping_monotonic"] % _shared_docs_kwargs
     )

pandas/core/arrays/period.py

@@ -278,8 +278,8 @@ def _check_compatible_with(self, other, setitem: bool = False):
     def dtype(self) -> PeriodDtype:
         return self._dtype
 
-    # error: Read-only property cannot override read-write property  [misc]
-    @property  # type: ignore
+    # error: Read-only property cannot override read-write property
+    @property  # type: ignore[misc]
     def freq(self) -> BaseOffset:
         """
         Return the frequency object for this PeriodArray.

pandas/core/computation/expressions.py

@@ -227,7 +227,8 @@ def evaluate(op, a, b, use_numexpr: bool = True):
     if op_str is not None:
         use_numexpr = use_numexpr and _bool_arith_check(op_str, a, b)
         if use_numexpr:
-            return _evaluate(op, op_str, a, b)  # type: ignore
+            # error: "None" not callable
+            return _evaluate(op, op_str, a, b)  # type: ignore[misc]
     return _evaluate_standard(op, op_str, a, b)
 
 

pandas/core/computation/parsing.py

@@ -37,7 +37,9 @@ def create_valid_python_identifier(name: str) -> str:
     special_characters_replacements = {
         char: f"_{token.tok_name[tokval]}_"
         # The ignore here is because of a bug in mypy that is resolved in 0.740
-        for char, tokval in tokenize.EXACT_TOKEN_TYPES.items()  # type: ignore
+        for char, tokval in (
+            tokenize.EXACT_TOKEN_TYPES.items()  # type: ignore[attr-defined]
+        )
     }
     special_characters_replacements.update(
         {