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(
         {

pandas/core/computation/pytables.py

@@ -63,7 +63,7 @@ def _resolve_name(self):
             return self.name
 
     # read-only property overwriting read/write property
-    @property  # type: ignore
+    @property  # type: ignore[misc]
     def value(self):
         return self._value
 

pandas/core/config_init.py

@@ -327,7 +327,7 @@ def is_terminal() -> bool:
     """
     try:
         # error: Name 'get_ipython' is not defined
-        ip = get_ipython()  # type: ignore
+        ip = get_ipython()  # type: ignore[name-defined]
     except NameError:  # assume standard Python interpreter in a terminal
         return True
     else:

pandas/core/dtypes/common.py

@@ -136,11 +136,13 @@ def ensure_int_or_float(arr: ArrayLike, copy: bool = False) -> np.array:
     """
     # TODO: GH27506 potential bug with ExtensionArrays
     try:
-        return arr.astype("int64", copy=copy, casting="safe")  # type: ignore
+        # error: Unexpected keyword argument "casting" for "astype"
+        return arr.astype("int64", copy=copy, casting="safe")  # type: ignore[call-arg]
     except TypeError:
         pass
     try:
-        return arr.astype("uint64", copy=copy, casting="safe")  # type: ignore
+        # error: Unexpected keyword argument "casting" for "astype"
+        return arr.astype("uint64", copy=copy, casting="safe")  # type: ignore[call-arg]
     except TypeError:
         if is_extension_array_dtype(arr.dtype):
             return arr.to_numpy(dtype="float64", na_value=np.nan)

pandas/core/dtypes/dtypes.py

@@ -635,7 +635,8 @@ class DatetimeTZDtype(PandasExtensionDtype):
 
     def __init__(self, unit: Union[str_type, "DatetimeTZDtype"] = "ns", tz=None):
         if isinstance(unit, DatetimeTZDtype):
-            unit, tz = unit.unit, unit.tz  # type: ignore
+            # error: "str" has no attribute "tz"
+            unit, tz = unit.unit, unit.tz  # type: ignore[attr-defined]
 
         if unit != "ns":
             if isinstance(unit, str) and tz is None:

pandas/core/dtypes/generic.py

@@ -7,7 +7,7 @@ def create_pandas_abc_type(name, attr, comp):
 
     # https://github.com/python/mypy/issues/1006
     # error: 'classmethod' used with a non-method
-    @classmethod  # type: ignore
+    @classmethod  # type: ignore[misc]
     def _check(cls, inst) -> bool:
         return getattr(inst, attr, "_typ") in comp
 

pandas/core/frame.py

@@ -2164,10 +2164,14 @@ def to_stata(
             from pandas.io.stata import StataWriter as statawriter
         elif version == 117:
             # mypy: Name 'statawriter' already defined (possibly by an import)
-            from pandas.io.stata import StataWriter117 as statawriter  # type: ignore
+            from pandas.io.stata import (  # type: ignore[no-redef]
+                StataWriter117 as statawriter,
+            )
         else:  # versions 118 and 119
             # mypy: Name 'statawriter' already defined (possibly by an import)
-            from pandas.io.stata import StataWriterUTF8 as statawriter  # type: ignore
+            from pandas.io.stata import (  # type: ignore[no-redef]
+                StataWriterUTF8 as statawriter,
+            )
 
         kwargs: Dict[str, Any] = {}
         if version is None or version >= 117:
@@ -2178,7 +2182,7 @@ def to_stata(
             kwargs["version"] = version
 
         # mypy: Too many arguments for "StataWriter"
-        writer = statawriter(  # type: ignore
+        writer = statawriter(  # type: ignore[call-arg]
             path,
             self,
             convert_dates=convert_dates,
@@ -3578,7 +3582,13 @@ def extract_unique_dtypes_from_dtypes_set(
             extracted_dtypes = [
                 unique_dtype
                 for unique_dtype in unique_dtypes
-                if issubclass(unique_dtype.type, tuple(dtypes_set))  # type: ignore
+                # error: Argument 1 to "tuple" has incompatible type
+                # "FrozenSet[Union[ExtensionDtype, str, Any, Type[str],
+                # Type[float], Type[int], Type[complex], Type[bool]]]";
+                # expected "Iterable[Union[type, Tuple[Any, ...]]]"
+                if issubclass(
+                    unique_dtype.type, tuple(dtypes_set)  # type: ignore[arg-type]
+                )
             ]
             return extracted_dtypes
 
@@ -5250,7 +5260,8 @@ def f(vals):
     # TODO: Just move the sort_values doc here.
     @Substitution(**_shared_doc_kwargs)
     @Appender(NDFrame.sort_values.__doc__)
-    def sort_values(  # type: ignore[override] # NOQA # issue 27237
+    # error: Signature of "sort_values" incompatible with supertype "NDFrame"
+    def sort_values(  # type: ignore[override]
         self,
         by,
         axis=0,

pandas/core/generic.py

@@ -589,9 +589,9 @@ def swapaxes(self: FrameOrSeries, axis1, axis2, copy=True) -> FrameOrSeries:
 
         # ignore needed because of NDFrame constructor is different than
         # DataFrame/Series constructors.
-        return self._constructor(new_values, *new_axes).__finalize__(  # type: ignore
-            self, method="swapaxes"
-        )
+        return self._constructor(
+            new_values, *new_axes  # type: ignore[arg-type]
+        ).__finalize__(self, method="swapaxes")
 
     def droplevel(self: FrameOrSeries, level, axis=0) -> FrameOrSeries:
         """
@@ -4011,7 +4011,11 @@ def add_prefix(self: FrameOrSeries, prefix: str) -> FrameOrSeries:
         f = functools.partial("{prefix}{}".format, prefix=prefix)
 
         mapper = {self._info_axis_name: f}
-        return self.rename(**mapper)  # type: ignore
+        # error: Incompatible return value type (got "Optional[FrameOrSeries]",
+        # expected "FrameOrSeries")
+        # error: Argument 1 to "rename" of "NDFrame" has incompatible type
+        # "**Dict[str, partial[str]]"; expected "Union[str, int, None]"
+        return self.rename(**mapper)  # type: ignore[return-value, arg-type]
 
     def add_suffix(self: FrameOrSeries, suffix: str) -> FrameOrSeries:
         """
@@ -4070,7 +4074,11 @@ def add_suffix(self: FrameOrSeries, suffix: str) -> FrameOrSeries:
         f = functools.partial("{}{suffix}".format, suffix=suffix)
 
         mapper = {self._info_axis_name: f}
-        return self.rename(**mapper)  # type: ignore
+        # error: Incompatible return value type (got "Optional[FrameOrSeries]",
+        # expected "FrameOrSeries")
+        # error: Argument 1 to "rename" of "NDFrame" has incompatible type
+        # "**Dict[str, partial[str]]"; expected "Union[str, int, None]"
+        return self.rename(**mapper)  # type: ignore[return-value, arg-type]
 
     def sort_values(
         self,

pandas/core/indexes/base.py

@@ -885,7 +885,8 @@ def _format_data(self, name=None) -> str_t:
         if self.inferred_type == "string":
             is_justify = False
         elif self.inferred_type == "categorical":
-            if is_object_dtype(self.categories):  # type: ignore
+            # error: "Index" has no attribute "categories"
+            if is_object_dtype(self.categories):  # type: ignore[attr-defined]
                 is_justify = False
 
         return format_object_summary(
@@ -940,7 +941,8 @@ def _format_with_header(self, header, na_rep="NaN") -> List[str_t]:
             if mask.any():
                 result = np.array(result)
                 result[mask] = na_rep
-                result = result.tolist()  # type: ignore
+                # error: "List[str]" has no attribute "tolist"
+                result = result.tolist()  # type: ignore[attr-defined]
         else:
             result = trim_front(format_array(values, None, justify="left"))
         return header + result

pandas/core/indexes/datetimelike.py

@@ -54,7 +54,8 @@ def _join_i8_wrapper(joinf, with_indexers: bool = True):
     Create the join wrapper methods.
     """
 
-    @staticmethod  # type: ignore
+    # error: 'staticmethod' used with a non-method
+    @staticmethod  # type: ignore[misc]
     def wrapper(left, right):
         if isinstance(left, (np.ndarray, ABCIndex, ABCSeries, DatetimeLikeArrayMixin)):
             left = left.view("i8")
@@ -95,7 +96,10 @@ class DatetimeIndexOpsMixin(ExtensionIndex):
     _bool_ops: List[str] = []
     _field_ops: List[str] = []
 
-    hasnans = cache_readonly(DatetimeLikeArrayMixin._hasnans.fget)  # type: ignore
+    # error: "Callable[[Any], Any]" has no attribute "fget"
+    hasnans = cache_readonly(
+        DatetimeLikeArrayMixin._hasnans.fget  # type: ignore[attr-defined]
+    )
     _hasnans = hasnans  # for index / array -agnostic code
 
     @property

pandas/core/internals/blocks.py

@@ -2744,7 +2744,8 @@ def _block_shape(values: ArrayLike, ndim: int = 1) -> ArrayLike:
             # TODO(EA2D): https://github.com/pandas-dev/pandas/issues/23023
             # block.shape is incorrect for "2D" ExtensionArrays
             # We can't, and don't need to, reshape.
-            values = values.reshape(tuple((1,) + shape))  # type: ignore
+            # error: "ExtensionArray" has no attribute "reshape"
+            values = values.reshape(tuple((1,) + shape))  # type: ignore[attr-defined]
     return values
 
 

pandas/core/ops/array_ops.py

@@ -349,7 +349,8 @@ def fill_bool(x, left=None):
         filler = fill_int if is_self_int_dtype and is_other_int_dtype else fill_bool
 
         res_values = na_logical_op(lvalues, rvalues, op)
-        res_values = filler(res_values)  # type: ignore
+        # error: Cannot call function of unknown type
+        res_values = filler(res_values)  # type: ignore[operator]
 
     return res_values
 

pandas/core/resample.py

@@ -967,7 +967,7 @@ def __init__(self, obj, *args, **kwargs):
             setattr(self, attr, kwargs.get(attr, getattr(parent, attr)))
 
         # error: Too many arguments for "__init__" of "object"
-        super().__init__(None)  # type: ignore
+        super().__init__(None)  # type: ignore[call-arg]
         self._groupby = groupby
         self._groupby.mutated = True
         self._groupby.grouper.mutated = True

pandas/core/series.py

@@ -571,7 +571,8 @@ def _values(self):
         """
         return self._mgr.internal_values()
 
-    @Appender(base.IndexOpsMixin.array.__doc__)  # type: ignore
+    # error: Decorated property not supported
+    @Appender(base.IndexOpsMixin.array.__doc__)  # type: ignore[misc]
     @property
     def array(self) -> ExtensionArray:
         return self._mgr._block.array_values()
@@ -4921,7 +4922,10 @@ def to_timestamp(self, freq=None, how="start", copy=True) -> "Series":
 
         if not isinstance(self.index, PeriodIndex):
             raise TypeError(f"unsupported Type {type(self.index).__name__}")
-        new_index = self.index.to_timestamp(freq=freq, how=how)  # type: ignore
+        # error: "PeriodIndex" has no attribute "to_timestamp"
+        new_index = self.index.to_timestamp(  # type: ignore[attr-defined]
+            freq=freq, how=how
+        )
         return self._constructor(new_values, index=new_index).__finalize__(
             self, method="to_timestamp"
         )

pandas/core/tools/datetimes.py

@@ -309,7 +309,7 @@ def _convert_listlike_datetimes(
         if tz == "utc":
             # error: Item "DatetimeIndex" of "Union[DatetimeArray, DatetimeIndex]" has
             # no attribute "tz_convert"
-            arg = arg.tz_convert(None).tz_localize(tz)  # type: ignore
+            arg = arg.tz_convert(None).tz_localize(tz)  # type: ignore[union-attr]
         return arg
 
     elif is_datetime64_ns_dtype(arg_dtype):