diff --git a/.circleci/config.yml b/.circleci/config.yml index 50ff7a81ae103..2c52d7aee4e28 100644 --- a/.circleci/config.yml +++ b/.circleci/config.yml @@ -15,7 +15,6 @@ jobs: - checkout - run: .circleci/setup_env.sh - run: | - sudo apt-get update && sudo apt-get install -y libegl1 libopengl0 PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH \ LD_PRELOAD=$HOME/miniconda3/envs/pandas-dev/lib/libgomp.so.1:$LD_PRELOAD \ ci/run_tests.sh diff --git a/doc/source/whatsnew/v2.3.0.rst b/doc/source/whatsnew/v2.3.0.rst index 0751554d87dc8..473d67acf6e74 100644 --- a/doc/source/whatsnew/v2.3.0.rst +++ b/doc/source/whatsnew/v2.3.0.rst @@ -107,10 +107,10 @@ Conversion Strings ^^^^^^^ - Bug in :meth:`Series.rank` for :class:`StringDtype` with ``storage="pyarrow"`` incorrectly returning integer results in case of ``method="average"`` and raising an error if it would truncate results (:issue:`59768`) +- Bug in :meth:`Series.replace` with :class:`StringDtype` when replacing with a non-string value was not upcasting to ``object`` dtype (:issue:`60282`) - Bug in :meth:`Series.str.replace` when ``n < 0`` for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`59628`) - Bug in ``ser.str.slice`` with negative ``step`` with :class:`ArrowDtype` and :class:`StringDtype` with ``storage="pyarrow"`` giving incorrect results (:issue:`59710`) - Bug in the ``center`` method on :class:`Series` and :class:`Index` object ``str`` accessors with pyarrow-backed dtype not matching the python behavior in corner cases with an odd number of fill characters (:issue:`54792`) -- Interval ^^^^^^^^ @@ -119,7 +119,7 @@ Interval Indexing ^^^^^^^^ -- +- Fixed bug in :meth:`Index.get_indexer` round-tripping through string dtype when ``infer_string`` is enabled (:issue:`55834`) - Missing diff --git a/pandas/_libs/index.pyi b/pandas/_libs/index.pyi index 75db47bf3160e..9c3791a642768 100644 --- a/pandas/_libs/index.pyi +++ b/pandas/_libs/index.pyi @@ -68,6 +68,9 @@ class MaskedUInt16Engine(MaskedIndexEngine): ... class MaskedUInt8Engine(MaskedIndexEngine): ... class MaskedBoolEngine(MaskedUInt8Engine): ... +class StringObjectEngine(ObjectEngine): + def __init__(self, values: object, na_value) -> None: ... + class BaseMultiIndexCodesEngine: levels: list[np.ndarray] offsets: np.ndarray # ndarray[uint64_t, ndim=1] diff --git a/pandas/_libs/index.pyx b/pandas/_libs/index.pyx index ee6a11ddab004..365cc7c3cecfc 100644 --- a/pandas/_libs/index.pyx +++ b/pandas/_libs/index.pyx @@ -532,6 +532,32 @@ cdef class ObjectEngine(IndexEngine): return loc +cdef class StringObjectEngine(ObjectEngine): + + cdef: + object na_value + bint uses_na + + def __init__(self, ndarray values, na_value): + super().__init__(values) + self.na_value = na_value + self.uses_na = na_value is C_NA + + cdef bint _checknull(self, object val): + if self.uses_na: + return val is C_NA + else: + return util.is_nan(val) + + cdef _check_type(self, object val): + if isinstance(val, str): + return val + elif self._checknull(val): + return self.na_value + else: + raise KeyError(val) + + cdef class DatetimeEngine(Int64Engine): cdef: diff --git a/pandas/_libs/lib.pyi b/pandas/_libs/lib.pyi index b9fd970e68f5b..71a4d3ae2575f 100644 --- a/pandas/_libs/lib.pyi +++ b/pandas/_libs/lib.pyi @@ -86,6 +86,7 @@ def maybe_convert_objects( safe: bool = ..., convert_numeric: bool = ..., convert_non_numeric: Literal[False] = ..., + convert_string: Literal[False] = ..., convert_to_nullable_dtype: Literal[False] = ..., dtype_if_all_nat: DtypeObj | None = ..., ) -> npt.NDArray[np.object_ | np.number]: ... @@ -97,6 +98,7 @@ def maybe_convert_objects( safe: bool = ..., convert_numeric: bool = ..., convert_non_numeric: bool = ..., + convert_string: bool = ..., convert_to_nullable_dtype: Literal[True] = ..., dtype_if_all_nat: DtypeObj | None = ..., ) -> ArrayLike: ... @@ -108,6 +110,7 @@ def maybe_convert_objects( safe: bool = ..., convert_numeric: bool = ..., convert_non_numeric: bool = ..., + convert_string: bool = ..., convert_to_nullable_dtype: bool = ..., dtype_if_all_nat: DtypeObj | None = ..., ) -> ArrayLike: ... diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx index c23f907aecfab..f72d6a5dad877 100644 --- a/pandas/_libs/lib.pyx +++ b/pandas/_libs/lib.pyx @@ -2498,6 +2498,7 @@ def maybe_convert_objects(ndarray[object] objects, bint convert_numeric=True, # NB: different default! bint convert_to_nullable_dtype=False, bint convert_non_numeric=False, + bint convert_string=True, object dtype_if_all_nat=None) -> "ArrayLike": """ Type inference function-- convert object array to proper dtype @@ -2741,7 +2742,17 @@ def maybe_convert_objects(ndarray[object] objects, seen.object_ = True elif seen.str_: - if using_string_dtype() and is_string_array(objects, skipna=True): + if convert_to_nullable_dtype and is_string_array(objects, skipna=True): + from pandas.core.arrays.string_ import StringDtype + + dtype = StringDtype() + return dtype.construct_array_type()._from_sequence(objects, dtype=dtype) + + elif ( + convert_string + and using_string_dtype() + and is_string_array(objects, skipna=True) + ): from pandas.core.arrays.string_ import StringDtype dtype = StringDtype(na_value=np.nan) diff --git a/pandas/compat/__init__.py b/pandas/compat/__init__.py index 38fb0188df5ff..5e82853109015 100644 --- a/pandas/compat/__init__.py +++ b/pandas/compat/__init__.py @@ -33,6 +33,7 @@ pa_version_under14p1, pa_version_under16p0, pa_version_under17p0, + pa_version_under18p0, ) if TYPE_CHECKING: @@ -191,6 +192,7 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]: "pa_version_under14p1", "pa_version_under16p0", "pa_version_under17p0", + "pa_version_under18p0", "HAS_PYARROW", "IS64", "ISMUSL", diff --git a/pandas/compat/pyarrow.py b/pandas/compat/pyarrow.py index 7fa197c4a9824..f579b8a45d386 100644 --- a/pandas/compat/pyarrow.py +++ b/pandas/compat/pyarrow.py @@ -17,6 +17,7 @@ pa_version_under15p0 = _palv < Version("15.0.0") pa_version_under16p0 = _palv < Version("16.0.0") pa_version_under17p0 = _palv < Version("17.0.0") + pa_version_under18p0 = _palv < Version("18.0.0") HAS_PYARROW = True except ImportError: pa_version_under10p1 = True @@ -28,4 +29,5 @@ pa_version_under15p0 = True pa_version_under16p0 = True pa_version_under17p0 = True + pa_version_under18p0 = False HAS_PYARROW = False diff --git a/pandas/core/arrays/arrow/array.py b/pandas/core/arrays/arrow/array.py index e8ce1f4526f89..0c1e1d0c63c85 100644 --- a/pandas/core/arrays/arrow/array.py +++ b/pandas/core/arrays/arrow/array.py @@ -1633,7 +1633,11 @@ def _accumulate( else: data_to_accum = data_to_accum.cast(pa.int64()) - result = pyarrow_meth(data_to_accum, skip_nulls=skipna, **kwargs) + try: + result = pyarrow_meth(data_to_accum, skip_nulls=skipna, **kwargs) + except pa.ArrowNotImplementedError as err: + msg = f"operation '{name}' not supported for dtype '{self.dtype}'" + raise TypeError(msg) from err if convert_to_int: result = result.cast(pa_dtype) @@ -2285,6 +2289,20 @@ def _groupby_op( **kwargs, ): if isinstance(self.dtype, StringDtype): + if how in [ + "prod", + "mean", + "median", + "cumsum", + "cumprod", + "std", + "sem", + "var", + "skew", + ]: + raise TypeError( + f"dtype '{self.dtype}' does not support operation '{how}'" + ) return super()._groupby_op( how=how, has_dropped_na=has_dropped_na, diff --git a/pandas/core/arrays/base.py b/pandas/core/arrays/base.py index abfe2369b0d0d..62ca2a45fb941 100644 --- a/pandas/core/arrays/base.py +++ b/pandas/core/arrays/base.py @@ -2369,6 +2369,20 @@ def _groupby_op( # GH#43682 if isinstance(self.dtype, StringDtype): # StringArray + if op.how in [ + "prod", + "mean", + "median", + "cumsum", + "cumprod", + "std", + "sem", + "var", + "skew", + ]: + raise TypeError( + f"dtype '{self.dtype}' does not support operation '{how}'" + ) if op.how not in ["any", "all"]: # Fail early to avoid conversion to object op._get_cython_function(op.kind, op.how, np.dtype(object), False) diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py index aae9f98032eff..e163a9df8ee10 100644 --- a/pandas/core/arrays/string_.py +++ b/pandas/core/arrays/string_.py @@ -726,20 +726,9 @@ def _values_for_factorize(self) -> tuple[np.ndarray, libmissing.NAType | float]: return arr, self.dtype.na_value - def __setitem__(self, key, value) -> None: - value = extract_array(value, extract_numpy=True) - if isinstance(value, type(self)): - # extract_array doesn't extract NumpyExtensionArray subclasses - value = value._ndarray - - key = check_array_indexer(self, key) - scalar_key = lib.is_scalar(key) - scalar_value = lib.is_scalar(value) - if scalar_key and not scalar_value: - raise ValueError("setting an array element with a sequence.") - - # validate new items - if scalar_value: + def _maybe_convert_setitem_value(self, value): + """Maybe convert value to be pyarrow compatible.""" + if lib.is_scalar(value): if isna(value): value = self.dtype.na_value elif not isinstance(value, str): @@ -749,8 +738,11 @@ def __setitem__(self, key, value) -> None: "instead." ) else: + value = extract_array(value, extract_numpy=True) if not is_array_like(value): value = np.asarray(value, dtype=object) + elif isinstance(value.dtype, type(self.dtype)): + return value else: # cast categories and friends to arrays to see if values are # compatible, compatibility with arrow backed strings @@ -760,11 +752,26 @@ def __setitem__(self, key, value) -> None: "Invalid value for dtype 'str'. Value should be a " "string or missing value (or array of those)." ) + return value - mask = isna(value) - if mask.any(): - value = value.copy() - value[isna(value)] = self.dtype.na_value + def __setitem__(self, key, value) -> None: + value = self._maybe_convert_setitem_value(value) + + key = check_array_indexer(self, key) + scalar_key = lib.is_scalar(key) + scalar_value = lib.is_scalar(value) + if scalar_key and not scalar_value: + raise ValueError("setting an array element with a sequence.") + + if not scalar_value: + if value.dtype == self.dtype: + value = value._ndarray + else: + value = np.asarray(value) + mask = isna(value) + if mask.any(): + value = value.copy() + value[isna(value)] = self.dtype.na_value super().__setitem__(key, value) @@ -846,7 +853,7 @@ def _reduce( else: return nanops.nanall(self._ndarray, skipna=skipna) - if name in ["min", "max", "sum"]: + if name in ["min", "max", "argmin", "argmax", "sum"]: result = getattr(self, name)(skipna=skipna, axis=axis, **kwargs) if keepdims: return self._from_sequence([result], dtype=self.dtype) diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py index 7a92b7306beea..d4263f7488a14 100644 --- a/pandas/core/dtypes/cast.py +++ b/pandas/core/dtypes/cast.py @@ -87,8 +87,8 @@ if TYPE_CHECKING: from collections.abc import ( + Collection, Sequence, - Sized, ) from pandas._typing import ( @@ -1163,6 +1163,7 @@ def convert_dtypes( def maybe_infer_to_datetimelike( value: npt.NDArray[np.object_], + convert_to_nullable_dtype: bool = False, ) -> np.ndarray | DatetimeArray | TimedeltaArray | PeriodArray | IntervalArray: """ we might have a array (or single object) that is datetime like, @@ -1200,6 +1201,7 @@ def maybe_infer_to_datetimelike( # numpy would have done it for us. convert_numeric=False, convert_non_numeric=True, + convert_to_nullable_dtype=convert_to_nullable_dtype, dtype_if_all_nat=np.dtype("M8[ns]"), ) @@ -1584,7 +1586,7 @@ def _maybe_box_and_unbox_datetimelike(value: Scalar, dtype: DtypeObj): return _maybe_unbox_datetimelike(value, dtype) -def construct_1d_object_array_from_listlike(values: Sized) -> np.ndarray: +def construct_1d_object_array_from_listlike(values: Collection) -> np.ndarray: """ Transform any list-like object in a 1-dimensional numpy array of object dtype. @@ -1602,10 +1604,11 @@ def construct_1d_object_array_from_listlike(values: Sized) -> np.ndarray: ------- 1-dimensional numpy array of dtype object """ - # numpy will try to interpret nested lists as further dimensions, hence - # making a 1D array that contains list-likes is a bit tricky: + # numpy will try to interpret nested lists as further dimensions in np.array(), + # hence explicitly making a 1D array using np.fromiter result = np.empty(len(values), dtype="object") - result[:] = values + for i, obj in enumerate(values): + result[i] = obj return result @@ -1754,6 +1757,13 @@ def can_hold_element(arr: ArrayLike, element: Any) -> bool: except (ValueError, TypeError): return False + if dtype == "string": + try: + arr._maybe_convert_setitem_value(element) # type: ignore[union-attr] + return True + except (ValueError, TypeError): + return False + # This is technically incorrect, but maintains the behavior of # ExtensionBlock._can_hold_element return True diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py index 296a601288f9d..c8e2ccc7bdaeb 100644 --- a/pandas/core/groupby/groupby.py +++ b/pandas/core/groupby/groupby.py @@ -4394,9 +4394,9 @@ def quantile( starts, ends = lib.generate_slices(splitter._slabels, splitter.ngroups) def pre_processor(vals: ArrayLike) -> tuple[np.ndarray, DtypeObj | None]: - if is_object_dtype(vals.dtype): + if isinstance(vals.dtype, StringDtype) or is_object_dtype(vals.dtype): raise TypeError( - "'quantile' cannot be performed against 'object' dtypes!" + f"dtype '{vals.dtype}' does not support operation 'quantile'" ) inference: DtypeObj | None = None diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py index 5da327a82c02b..ad39907e7400e 100644 --- a/pandas/core/indexes/base.py +++ b/pandas/core/indexes/base.py @@ -884,6 +884,8 @@ def _engine( # error: Item "ExtensionArray" of "Union[ExtensionArray, # ndarray[Any, Any]]" has no attribute "_ndarray" [union-attr] target_values = self._data._ndarray # type: ignore[union-attr] + elif is_string_dtype(self.dtype) and not is_object_dtype(self.dtype): + return libindex.StringObjectEngine(target_values, self.dtype.na_value) # type: ignore[union-attr] # error: Argument 1 to "ExtensionEngine" has incompatible type # "ndarray[Any, Any]"; expected "ExtensionArray" @@ -6133,7 +6135,6 @@ def _should_fallback_to_positional(self) -> bool: def get_indexer_non_unique( self, target ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: - target = ensure_index(target) target = self._maybe_cast_listlike_indexer(target) if not self._should_compare(target) and not self._should_partial_index(target): @@ -6695,7 +6696,16 @@ def _maybe_cast_listlike_indexer(self, target) -> Index: """ Analogue to maybe_cast_indexer for get_indexer instead of get_loc. """ - return ensure_index(target) + target_index = ensure_index(target) + if ( + not hasattr(target, "dtype") + and self.dtype == object + and target_index.dtype == "string" + ): + # If we started with a list-like, avoid inference to string dtype if self + # is object dtype (coercing to string dtype will alter the missing values) + target_index = Index(target, dtype=self.dtype) + return target_index @final def _validate_indexer( diff --git a/pandas/core/interchange/from_dataframe.py b/pandas/core/interchange/from_dataframe.py index 4162ebc33f0d6..53f18883ea3ad 100644 --- a/pandas/core/interchange/from_dataframe.py +++ b/pandas/core/interchange/from_dataframe.py @@ -6,6 +6,8 @@ import numpy as np +from pandas._config import using_string_dtype + from pandas.compat._optional import import_optional_dependency from pandas.errors import SettingWithCopyError @@ -124,8 +126,6 @@ def protocol_df_chunk_to_pandas(df: DataFrameXchg) -> pd.DataFrame: ------- pd.DataFrame """ - # We need a dict of columns here, with each column being a NumPy array (at - # least for now, deal with non-NumPy dtypes later). columns: dict[str, Any] = {} buffers = [] # hold on to buffers, keeps memory alive for name in df.column_names(): @@ -324,8 +324,12 @@ def string_column_to_ndarray(col: Column) -> tuple[np.ndarray, Any]: # Add to our list of strings str_list[i] = string - # Convert the string list to a NumPy array - return np.asarray(str_list, dtype="object"), buffers + if using_string_dtype(): + res = pd.Series(str_list, dtype="str") + else: + res = np.asarray(str_list, dtype="object") # type: ignore[assignment] + + return res, buffers # type: ignore[return-value] def parse_datetime_format_str(format_str, data) -> pd.Series | np.ndarray: diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py index 917a65348b7a3..5be83aa38011b 100644 --- a/pandas/core/internals/blocks.py +++ b/pandas/core/internals/blocks.py @@ -84,6 +84,7 @@ ABCNumpyExtensionArray, ABCSeries, ) +from pandas.core.dtypes.inference import is_re from pandas.core.dtypes.missing import ( is_valid_na_for_dtype, isna, @@ -115,6 +116,7 @@ PeriodArray, TimedeltaArray, ) +from pandas.core.arrays.string_ import StringDtype from pandas.core.base import PandasObject import pandas.core.common as com from pandas.core.computation import expressions @@ -476,7 +478,9 @@ def split_and_operate(self, func, *args, **kwargs) -> list[Block]: # Up/Down-casting @final - def coerce_to_target_dtype(self, other, warn_on_upcast: bool = False) -> Block: + def coerce_to_target_dtype( + self, other, warn_on_upcast: bool = False, using_cow: bool = False + ) -> Block: """ coerce the current block to a dtype compat for other we will return a block, possibly object, and not raise @@ -528,7 +532,14 @@ def coerce_to_target_dtype(self, other, warn_on_upcast: bool = False) -> Block: f"{self.values.dtype}. Please report a bug at " "https://github.com/pandas-dev/pandas/issues." ) - return self.astype(new_dtype, copy=False) + copy = False + if ( + not using_cow + and isinstance(self.dtype, StringDtype) + and self.dtype.storage == "python" + ): + copy = True + return self.astype(new_dtype, copy=copy, using_cow=using_cow) @final def _maybe_downcast( @@ -552,7 +563,12 @@ def _maybe_downcast( return blocks nbs = extend_blocks( - [blk.convert(using_cow=using_cow, copy=not using_cow) for blk in blocks] + [ + blk.convert( + using_cow=using_cow, copy=not using_cow, convert_string=False + ) + for blk in blocks + ] ) if caller == "fillna": if len(nbs) != len(blocks) or not all( @@ -625,6 +641,7 @@ def convert( *, copy: bool = True, using_cow: bool = False, + convert_string: bool = True, ) -> list[Block]: """ Attempt to coerce any object types to better types. Return a copy @@ -637,7 +654,10 @@ def convert( if self.ndim != 1 and self.shape[0] != 1: blocks = self.split_and_operate( - Block.convert, copy=copy, using_cow=using_cow + Block.convert, + copy=copy, + using_cow=using_cow, + convert_string=convert_string, ) if all(blk.dtype.kind == "O" for blk in blocks): # Avoid fragmenting the block if convert is a no-op @@ -655,6 +675,7 @@ def convert( res_values = lib.maybe_convert_objects( values, # type: ignore[arg-type] convert_non_numeric=True, + convert_string=convert_string, ) refs = None if ( @@ -840,6 +861,7 @@ def replace( mask: npt.NDArray[np.bool_] | None = None, using_cow: bool = False, already_warned=None, + convert_string=None, ) -> list[Block]: """ replace the to_replace value with value, possible to create new @@ -879,7 +901,7 @@ def replace( else: return [self] if inplace else [self.copy()] - elif self._can_hold_element(value): + elif self._can_hold_element(value) or (self.dtype == "string" and is_re(value)): # TODO(CoW): Maybe split here as well into columns where mask has True # and rest? blk = self._maybe_copy(using_cow, inplace) @@ -904,7 +926,11 @@ def replace( if get_option("future.no_silent_downcasting") is True: blocks = [blk] else: - blocks = blk.convert(copy=False, using_cow=using_cow) + blocks = blk.convert( + copy=False, + using_cow=using_cow, + convert_string=convert_string or self.dtype != _dtype_obj, + ) if len(blocks) > 1 or blocks[0].dtype != blk.dtype: warnings.warn( # GH#54710 @@ -926,12 +952,14 @@ def replace( if value is None or value is NA: blk = self.astype(np.dtype(object)) else: - blk = self.coerce_to_target_dtype(value) + blk = self.coerce_to_target_dtype(value, using_cow=using_cow) return blk.replace( to_replace=to_replace, value=value, inplace=True, mask=mask, + using_cow=using_cow, + convert_string=convert_string, ) else: @@ -946,6 +974,7 @@ def replace( inplace=True, mask=mask[i : i + 1], using_cow=using_cow, + convert_string=convert_string, ) ) return blocks @@ -958,6 +987,7 @@ def _replace_regex( inplace: bool = False, mask=None, using_cow: bool = False, + convert_string: bool = True, already_warned=None, ) -> list[Block]: """ @@ -980,16 +1010,26 @@ def _replace_regex( ------- List[Block] """ - if not self._can_hold_element(to_replace): + if not is_re(to_replace) and not self._can_hold_element(to_replace): # i.e. only if self.is_object is True, but could in principle include a # String ExtensionBlock if using_cow: return [self.copy(deep=False)] return [self] if inplace else [self.copy()] - rx = re.compile(to_replace) + if is_re(to_replace) and self.dtype not in [object, "string"]: + # only object or string dtype can hold strings, and a regex object + # will only match strings + return [self.copy(deep=False)] + + if not ( + self._can_hold_element(value) or (self.dtype == "string" and is_re(value)) + ): + block = self.astype(np.dtype(object)) + else: + block = self._maybe_copy(using_cow, inplace) - block = self._maybe_copy(using_cow, inplace) + rx = re.compile(to_replace) replace_regex(block.values, rx, value, mask) @@ -1007,7 +1047,9 @@ def _replace_regex( ) already_warned.warned_already = True - nbs = block.convert(copy=False, using_cow=using_cow) + nbs = block.convert( + copy=False, using_cow=using_cow, convert_string=convert_string + ) opt = get_option("future.no_silent_downcasting") if (len(nbs) > 1 or nbs[0].dtype != block.dtype) and not opt: warnings.warn( @@ -1046,9 +1088,13 @@ def replace_list( values._replace(to_replace=src_list, value=dest_list, inplace=True) return [blk] + convert_string = self.dtype != _dtype_obj + # Exclude anything that we know we won't contain pairs = [ - (x, y) for x, y in zip(src_list, dest_list) if self._can_hold_element(x) + (x, y) + for x, y in zip(src_list, dest_list) + if (self._can_hold_element(x) or (self.dtype == "string" and is_re(x))) ] if not len(pairs): if using_cow: @@ -1128,6 +1174,7 @@ def replace_list( inplace=inplace, regex=regex, using_cow=using_cow, + convert_string=convert_string, ) if using_cow and i != src_len: @@ -1150,7 +1197,9 @@ def replace_list( nbs = [] for res_blk in result: converted = res_blk.convert( - copy=True and not using_cow, using_cow=using_cow + copy=True and not using_cow, + using_cow=using_cow, + convert_string=convert_string, ) if len(converted) > 1 or converted[0].dtype != res_blk.dtype: warnings.warn( @@ -1180,6 +1229,7 @@ def _replace_coerce( inplace: bool = True, regex: bool = False, using_cow: bool = False, + convert_string: bool = True, ) -> list[Block]: """ Replace value corresponding to the given boolean array with another @@ -1209,6 +1259,7 @@ def _replace_coerce( inplace=inplace, mask=mask, using_cow=using_cow, + convert_string=convert_string, ) else: if value is None: @@ -1232,6 +1283,7 @@ def _replace_coerce( inplace=inplace, mask=mask, using_cow=using_cow, + convert_string=convert_string, ) # --------------------------------------------------------------------- @@ -1686,7 +1738,7 @@ def fillna( return nbs if limit is not None: - mask[mask.cumsum(self.ndim - 1) > limit] = False + mask[mask.cumsum(self.values.ndim - 1) > limit] = False if inplace: nbs = self.putmask( @@ -2112,7 +2164,7 @@ def where( res_values = arr._where(cond, other).T except (ValueError, TypeError): if self.ndim == 1 or self.shape[0] == 1: - if isinstance(self.dtype, IntervalDtype): + if isinstance(self.dtype, (IntervalDtype, StringDtype)): # TestSetitemFloatIntervalWithIntIntervalValues blk = self.coerce_to_target_dtype(orig_other) nbs = blk.where(orig_other, orig_cond, using_cow=using_cow) @@ -2314,7 +2366,7 @@ def fillna( using_cow: bool = False, already_warned=None, ) -> list[Block]: - if isinstance(self.dtype, IntervalDtype): + if isinstance(self.dtype, (IntervalDtype, StringDtype)): # Block.fillna handles coercion (test_fillna_interval) return super().fillna( value=value, diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py index 137648ee52bf7..64fac5fcfcdc2 100644 --- a/pandas/core/internals/construction.py +++ b/pandas/core/internals/construction.py @@ -1042,8 +1042,9 @@ def convert(arr): if dtype is None: if arr.dtype == np.dtype("O"): # i.e. maybe_convert_objects didn't convert - arr = maybe_infer_to_datetimelike(arr) - if dtype_backend != "numpy" and arr.dtype == np.dtype("O"): + convert_to_nullable_dtype = dtype_backend != "numpy" + arr = maybe_infer_to_datetimelike(arr, convert_to_nullable_dtype) + if convert_to_nullable_dtype and arr.dtype == np.dtype("O"): new_dtype = StringDtype() arr_cls = new_dtype.construct_array_type() arr = arr_cls._from_sequence(arr, dtype=new_dtype) diff --git a/pandas/io/_util.py b/pandas/io/_util.py index 50a97f1059b5c..9373888e28d28 100644 --- a/pandas/io/_util.py +++ b/pandas/io/_util.py @@ -1,13 +1,27 @@ from __future__ import annotations -from typing import Callable +from typing import ( + TYPE_CHECKING, + Literal, +) import numpy as np +from pandas._config import using_string_dtype + +from pandas._libs import lib +from pandas.compat import pa_version_under18p0 from pandas.compat._optional import import_optional_dependency import pandas as pd +if TYPE_CHECKING: + from collections.abc import Callable + + import pyarrow + + from pandas._typing import DtypeBackend + def _arrow_dtype_mapping() -> dict: pa = import_optional_dependency("pyarrow") @@ -29,10 +43,46 @@ def _arrow_dtype_mapping() -> dict: } -def arrow_string_types_mapper() -> Callable: +def _arrow_string_types_mapper() -> Callable: pa = import_optional_dependency("pyarrow") - return { + mapping = { pa.string(): pd.StringDtype(na_value=np.nan), pa.large_string(): pd.StringDtype(na_value=np.nan), - }.get + } + if not pa_version_under18p0: + mapping[pa.string_view()] = pd.StringDtype(na_value=np.nan) + + return mapping.get + + +def arrow_table_to_pandas( + table: pyarrow.Table, + dtype_backend: DtypeBackend | Literal["numpy"] | lib.NoDefault = lib.no_default, + null_to_int64: bool = False, + to_pandas_kwargs: dict | None = None, +) -> pd.DataFrame: + if to_pandas_kwargs is None: + to_pandas_kwargs = {} + + pa = import_optional_dependency("pyarrow") + + types_mapper: type[pd.ArrowDtype] | None | Callable + if dtype_backend == "numpy_nullable": + mapping = _arrow_dtype_mapping() + if null_to_int64: + # Modify the default mapping to also map null to Int64 + # (to match other engines - only for CSV parser) + mapping[pa.null()] = pd.Int64Dtype() + types_mapper = mapping.get + elif dtype_backend == "pyarrow": + types_mapper = pd.ArrowDtype + elif using_string_dtype(): + types_mapper = _arrow_string_types_mapper() + elif dtype_backend is lib.no_default or dtype_backend == "numpy": + types_mapper = None + else: + raise NotImplementedError + + df = table.to_pandas(types_mapper=types_mapper, **to_pandas_kwargs) + return df diff --git a/pandas/io/feather_format.py b/pandas/io/feather_format.py index 68c73483add3f..1bdb732cb10de 100644 --- a/pandas/io/feather_format.py +++ b/pandas/io/feather_format.py @@ -13,11 +13,10 @@ from pandas.util._decorators import doc from pandas.util._validators import check_dtype_backend -import pandas as pd from pandas.core.api import DataFrame from pandas.core.shared_docs import _shared_docs -from pandas.io._util import arrow_string_types_mapper +from pandas.io._util import arrow_table_to_pandas from pandas.io.common import get_handle if TYPE_CHECKING: @@ -128,16 +127,4 @@ def read_feather( pa_table = feather.read_table( handles.handle, columns=columns, use_threads=bool(use_threads) ) - - if dtype_backend == "numpy_nullable": - from pandas.io._util import _arrow_dtype_mapping - - return pa_table.to_pandas(types_mapper=_arrow_dtype_mapping().get) - - elif dtype_backend == "pyarrow": - return pa_table.to_pandas(types_mapper=pd.ArrowDtype) - - elif using_string_dtype(): - return pa_table.to_pandas(types_mapper=arrow_string_types_mapper()) - else: - raise NotImplementedError + return arrow_table_to_pandas(pa_table, dtype_backend=dtype_backend) diff --git a/pandas/io/json/_json.py b/pandas/io/json/_json.py index 9414f45215029..c0499ce750cf0 100644 --- a/pandas/io/json/_json.py +++ b/pandas/io/json/_json.py @@ -40,7 +40,6 @@ from pandas.core.dtypes.dtypes import PeriodDtype from pandas import ( - ArrowDtype, DataFrame, Index, MultiIndex, @@ -52,6 +51,7 @@ from pandas.core.reshape.concat import concat from pandas.core.shared_docs import _shared_docs +from pandas.io._util import arrow_table_to_pandas from pandas.io.common import ( IOHandles, dedup_names, @@ -997,18 +997,7 @@ def read(self) -> DataFrame | Series: if self.engine == "pyarrow": pyarrow_json = import_optional_dependency("pyarrow.json") pa_table = pyarrow_json.read_json(self.data) - - mapping: type[ArrowDtype] | None | Callable - if self.dtype_backend == "pyarrow": - mapping = ArrowDtype - elif self.dtype_backend == "numpy_nullable": - from pandas.io._util import _arrow_dtype_mapping - - mapping = _arrow_dtype_mapping().get - else: - mapping = None - - return pa_table.to_pandas(types_mapper=mapping) + return arrow_table_to_pandas(pa_table, dtype_backend=self.dtype_backend) elif self.engine == "ujson": if self.lines: if self.chunksize: diff --git a/pandas/io/orc.py b/pandas/io/orc.py index 5706336b71697..d7f473a929568 100644 --- a/pandas/io/orc.py +++ b/pandas/io/orc.py @@ -9,16 +9,13 @@ Literal, ) -from pandas._config import using_string_dtype - from pandas._libs import lib from pandas.compat._optional import import_optional_dependency from pandas.util._validators import check_dtype_backend -import pandas as pd from pandas.core.indexes.api import default_index -from pandas.io._util import arrow_string_types_mapper +from pandas.io._util import arrow_table_to_pandas from pandas.io.common import ( get_handle, is_fsspec_url, @@ -117,21 +114,7 @@ def read_orc( pa_table = orc.read_table( source=source, columns=columns, filesystem=filesystem, **kwargs ) - if dtype_backend is not lib.no_default: - if dtype_backend == "pyarrow": - df = pa_table.to_pandas(types_mapper=pd.ArrowDtype) - else: - from pandas.io._util import _arrow_dtype_mapping - - mapping = _arrow_dtype_mapping() - df = pa_table.to_pandas(types_mapper=mapping.get) - return df - else: - if using_string_dtype(): - types_mapper = arrow_string_types_mapper() - else: - types_mapper = None - return pa_table.to_pandas(types_mapper=types_mapper) + return arrow_table_to_pandas(pa_table, dtype_backend=dtype_backend) def to_orc( diff --git a/pandas/io/parquet.py b/pandas/io/parquet.py index cc33c87dfc55a..01e320cdb1b72 100644 --- a/pandas/io/parquet.py +++ b/pandas/io/parquet.py @@ -10,9 +10,11 @@ Literal, ) import warnings -from warnings import catch_warnings +from warnings import ( + catch_warnings, + filterwarnings, +) -from pandas._config import using_string_dtype from pandas._config.config import _get_option from pandas._libs import lib @@ -22,14 +24,13 @@ from pandas.util._exceptions import find_stack_level from pandas.util._validators import check_dtype_backend -import pandas as pd from pandas import ( DataFrame, get_option, ) from pandas.core.shared_docs import _shared_docs -from pandas.io._util import arrow_string_types_mapper +from pandas.io._util import arrow_table_to_pandas from pandas.io.common import ( IOHandles, get_handle, @@ -250,20 +251,10 @@ def read( kwargs["use_pandas_metadata"] = True to_pandas_kwargs = {} - if dtype_backend == "numpy_nullable": - from pandas.io._util import _arrow_dtype_mapping - - mapping = _arrow_dtype_mapping() - to_pandas_kwargs["types_mapper"] = mapping.get - elif dtype_backend == "pyarrow": - to_pandas_kwargs["types_mapper"] = pd.ArrowDtype # type: ignore[assignment] - elif using_string_dtype(): - to_pandas_kwargs["types_mapper"] = arrow_string_types_mapper() manager = _get_option("mode.data_manager", silent=True) if manager == "array": - to_pandas_kwargs["split_blocks"] = True # type: ignore[assignment] - + to_pandas_kwargs["split_blocks"] = True path_or_handle, handles, filesystem = _get_path_or_handle( path, filesystem, @@ -278,7 +269,18 @@ def read( filters=filters, **kwargs, ) - result = pa_table.to_pandas(**to_pandas_kwargs) + + with catch_warnings(): + filterwarnings( + "ignore", + "make_block is deprecated", + DeprecationWarning, + ) + result = arrow_table_to_pandas( + pa_table, + dtype_backend=dtype_backend, + to_pandas_kwargs=to_pandas_kwargs, + ) if manager == "array": result = result._as_manager("array", copy=False) diff --git a/pandas/io/parsers/arrow_parser_wrapper.py b/pandas/io/parsers/arrow_parser_wrapper.py index c774638fd73f7..a7f01e6322755 100644 --- a/pandas/io/parsers/arrow_parser_wrapper.py +++ b/pandas/io/parsers/arrow_parser_wrapper.py @@ -3,8 +3,6 @@ from typing import TYPE_CHECKING import warnings -from pandas._config import using_string_dtype - from pandas._libs import lib from pandas.compat._optional import import_optional_dependency from pandas.errors import ( @@ -16,18 +14,14 @@ from pandas.core.dtypes.common import pandas_dtype from pandas.core.dtypes.inference import is_integer -import pandas as pd -from pandas import DataFrame - -from pandas.io._util import ( - _arrow_dtype_mapping, - arrow_string_types_mapper, -) +from pandas.io._util import arrow_table_to_pandas from pandas.io.parsers.base_parser import ParserBase if TYPE_CHECKING: from pandas._typing import ReadBuffer + from pandas import DataFrame + class ArrowParserWrapper(ParserBase): """ @@ -287,17 +281,14 @@ def read(self) -> DataFrame: table = table.cast(new_schema) - if dtype_backend == "pyarrow": - frame = table.to_pandas(types_mapper=pd.ArrowDtype) - elif dtype_backend == "numpy_nullable": - # Modify the default mapping to also - # map null to Int64 (to match other engines) - dtype_mapping = _arrow_dtype_mapping() - dtype_mapping[pa.null()] = pd.Int64Dtype() - frame = table.to_pandas(types_mapper=dtype_mapping.get) - elif using_string_dtype(): - frame = table.to_pandas(types_mapper=arrow_string_types_mapper()) + with warnings.catch_warnings(): + warnings.filterwarnings( + "ignore", + "make_block is deprecated", + DeprecationWarning, + ) + frame = arrow_table_to_pandas( + table, dtype_backend=dtype_backend, null_to_int64=True + ) - else: - frame = table.to_pandas() return self._finalize_pandas_output(frame) diff --git a/pandas/io/parsers/base_parser.py b/pandas/io/parsers/base_parser.py index 09f0f2af8e5c6..40e3ea6450647 100644 --- a/pandas/io/parsers/base_parser.py +++ b/pandas/io/parsers/base_parser.py @@ -464,7 +464,11 @@ def _agg_index(self, index, try_parse_dates: bool = True) -> Index: arrays = [] converters = self._clean_mapping(self.converters) - for i, arr in enumerate(index): + if self.index_names is not None: + names: Iterable = self.index_names + else: + names = itertools.cycle([None]) + for i, (arr, name) in enumerate(zip(index, names)): if try_parse_dates and self._should_parse_dates(i): arr = self._date_conv( arr, @@ -504,12 +508,17 @@ def _agg_index(self, index, try_parse_dates: bool = True) -> Index: arr, _ = self._infer_types( arr, col_na_values | col_na_fvalues, cast_type is None, try_num_bool ) - arrays.append(arr) - - names = self.index_names - index = ensure_index_from_sequences(arrays, names) + if cast_type is not None: + # Don't perform RangeIndex inference + idx = Index(arr, name=name, dtype=cast_type) + else: + idx = ensure_index_from_sequences([arr], [name]) + arrays.append(idx) - return index + if len(arrays) == 1: + return arrays[0] + else: + return MultiIndex.from_arrays(arrays) @final def _convert_to_ndarrays( @@ -1084,12 +1093,11 @@ def _get_empty_meta(self, columns, dtype: DtypeArg | None = None): dtype_dict: defaultdict[Hashable, Any] if not is_dict_like(dtype): # if dtype == None, default will be object. - default_dtype = dtype or object - dtype_dict = defaultdict(lambda: default_dtype) + dtype_dict = defaultdict(lambda: dtype) else: dtype = cast(dict, dtype) dtype_dict = defaultdict( - lambda: object, + lambda: None, {columns[k] if is_integer(k) else k: v for k, v in dtype.items()}, ) @@ -1106,8 +1114,14 @@ def _get_empty_meta(self, columns, dtype: DtypeArg | None = None): if (index_col is None or index_col is False) or index_names is None: index = default_index(0) else: - data = [Series([], dtype=dtype_dict[name]) for name in index_names] - index = ensure_index_from_sequences(data, names=index_names) + # TODO: We could return default_index(0) if dtype_dict[name] is None + data = [ + Index([], name=name, dtype=dtype_dict[name]) for name in index_names + ] + if len(data) == 1: + index = data[0] + else: + index = MultiIndex.from_arrays(data) index_col.sort() for i, n in enumerate(index_col): diff --git a/pandas/io/sql.py b/pandas/io/sql.py index 03ef1792f1fb8..7027702a696fe 100644 --- a/pandas/io/sql.py +++ b/pandas/io/sql.py @@ -46,11 +46,10 @@ from pandas.core.dtypes.common import ( is_dict_like, is_list_like, + is_object_dtype, + is_string_dtype, ) -from pandas.core.dtypes.dtypes import ( - ArrowDtype, - DatetimeTZDtype, -) +from pandas.core.dtypes.dtypes import DatetimeTZDtype from pandas.core.dtypes.missing import isna from pandas import get_option @@ -59,12 +58,15 @@ Series, ) from pandas.core.arrays import ArrowExtensionArray +from pandas.core.arrays.string_ import StringDtype from pandas.core.base import PandasObject import pandas.core.common as com from pandas.core.common import maybe_make_list from pandas.core.internals.construction import convert_object_array from pandas.core.tools.datetimes import to_datetime +from pandas.io._util import arrow_table_to_pandas + if TYPE_CHECKING: from collections.abc import ( Iterator, @@ -1331,7 +1333,12 @@ def _harmonize_columns( elif dtype_backend == "numpy" and col_type is float: # floats support NA, can always convert! self.frame[col_name] = df_col.astype(col_type, copy=False) - + elif ( + using_string_dtype() + and is_string_dtype(col_type) + and is_object_dtype(self.frame[col_name]) + ): + self.frame[col_name] = df_col.astype(col_type, copy=False) elif dtype_backend == "numpy" and len(df_col) == df_col.count(): # No NA values, can convert ints and bools if col_type is np.dtype("int64") or col_type is bool: @@ -1418,6 +1425,7 @@ def _get_dtype(self, sqltype): DateTime, Float, Integer, + String, ) if isinstance(sqltype, Float): @@ -1437,6 +1445,10 @@ def _get_dtype(self, sqltype): return date elif isinstance(sqltype, Boolean): return bool + elif isinstance(sqltype, String): + if using_string_dtype(): + return StringDtype(na_value=np.nan) + return object @@ -2208,23 +2220,10 @@ def read_table( else: stmt = f"SELECT {select_list} FROM {table_name}" - mapping: type[ArrowDtype] | None | Callable - if dtype_backend == "pyarrow": - mapping = ArrowDtype - elif dtype_backend == "numpy_nullable": - from pandas.io._util import _arrow_dtype_mapping - - mapping = _arrow_dtype_mapping().get - elif using_string_dtype(): - from pandas.io._util import arrow_string_types_mapper - - arrow_string_types_mapper() - else: - mapping = None - with self.con.cursor() as cur: cur.execute(stmt) - df = cur.fetch_arrow_table().to_pandas(types_mapper=mapping) + pa_table = cur.fetch_arrow_table() + df = arrow_table_to_pandas(pa_table, dtype_backend=dtype_backend) return _wrap_result_adbc( df, @@ -2292,19 +2291,10 @@ def read_query( if chunksize: raise NotImplementedError("'chunksize' is not implemented for ADBC drivers") - mapping: type[ArrowDtype] | None | Callable - if dtype_backend == "pyarrow": - mapping = ArrowDtype - elif dtype_backend == "numpy_nullable": - from pandas.io._util import _arrow_dtype_mapping - - mapping = _arrow_dtype_mapping().get - else: - mapping = None - with self.con.cursor() as cur: cur.execute(sql) - df = cur.fetch_arrow_table().to_pandas(types_mapper=mapping) + pa_table = cur.fetch_arrow_table() + df = arrow_table_to_pandas(pa_table, dtype_backend=dtype_backend) return _wrap_result_adbc( df, diff --git a/pandas/plotting/_matplotlib/boxplot.py b/pandas/plotting/_matplotlib/boxplot.py index d2b76decaa75d..80f0349b205e6 100644 --- a/pandas/plotting/_matplotlib/boxplot.py +++ b/pandas/plotting/_matplotlib/boxplot.py @@ -7,6 +7,7 @@ ) import warnings +import matplotlib as mpl from matplotlib.artist import setp import numpy as np @@ -20,6 +21,7 @@ import pandas as pd import pandas.core.common as com +from pandas.util.version import Version from pandas.io.formats.printing import pprint_thing from pandas.plotting._matplotlib.core import ( @@ -54,7 +56,8 @@ def _set_ticklabels(ax: Axes, labels: list[str], is_vertical: bool, **kwargs) -> ticks = ax.get_xticks() if is_vertical else ax.get_yticks() if len(ticks) != len(labels): i, remainder = divmod(len(ticks), len(labels)) - assert remainder == 0, remainder + if Version(mpl.__version__) < Version("3.10"): + assert remainder == 0, remainder labels *= i if is_vertical: ax.set_xticklabels(labels, **kwargs) diff --git a/pandas/plotting/_matplotlib/tools.py b/pandas/plotting/_matplotlib/tools.py index 898b5b25e7b01..98441c5afbaa4 100644 --- a/pandas/plotting/_matplotlib/tools.py +++ b/pandas/plotting/_matplotlib/tools.py @@ -57,7 +57,7 @@ def format_date_labels(ax: Axes, rot) -> None: fig = ax.get_figure() if fig is not None: # should always be a Figure but can technically be None - maybe_adjust_figure(fig, bottom=0.2) + maybe_adjust_figure(fig, bottom=0.2) # type: ignore[arg-type] def table( diff --git a/pandas/tests/apply/test_invalid_arg.py b/pandas/tests/apply/test_invalid_arg.py index 8963265b0a800..68f3fe36546a0 100644 --- a/pandas/tests/apply/test_invalid_arg.py +++ b/pandas/tests/apply/test_invalid_arg.py @@ -218,18 +218,12 @@ def transform(row): def test_agg_cython_table_raises_frame(df, func, expected, axis, using_infer_string): # GH 21224 if using_infer_string: - if df.dtypes.iloc[0].storage == "pyarrow": - import pyarrow as pa - - # TODO(infer_string) - # should raise a proper TypeError instead of propagating the pyarrow error - - expected = (expected, pa.lib.ArrowNotImplementedError) - else: - expected = (expected, NotImplementedError) + expected = (expected, NotImplementedError) msg = ( - "can't multiply sequence by non-int of type 'str'|has no kernel|cannot perform" + "can't multiply sequence by non-int of type 'str'" + "|cannot perform cumprod with type str" # NotImplementedError python backend + "|operation 'cumprod' not supported for dtype 'str'" # TypeError pyarrow ) warn = None if isinstance(func, str) else FutureWarning with pytest.raises(expected, match=msg): @@ -259,16 +253,12 @@ def test_agg_cython_table_raises_series(series, func, expected, using_infer_stri if func == "median" or func is np.nanmedian or func is np.median: msg = r"Cannot convert \['a' 'b' 'c'\] to numeric" - if using_infer_string: - if series.dtype.storage == "pyarrow": - import pyarrow as pa - - # TODO(infer_string) - # should raise a proper TypeError instead of propagating the pyarrow error - expected = (expected, pa.lib.ArrowNotImplementedError) - else: - expected = (expected, NotImplementedError) - msg = msg + "|does not support|has no kernel|Cannot perform|cannot perform" + if using_infer_string and func in ("cumprod", np.cumprod, np.nancumprod): + expected = (expected, NotImplementedError) + + msg = ( + msg + "|does not support|has no kernel|Cannot perform|cannot perform|operation" + ) warn = None if isinstance(func, str) else FutureWarning with pytest.raises(expected, match=msg): diff --git a/pandas/tests/apply/test_str.py b/pandas/tests/apply/test_str.py index 8956aed5e9ceb..f916567c6b883 100644 --- a/pandas/tests/apply/test_str.py +++ b/pandas/tests/apply/test_str.py @@ -4,8 +4,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.core.dtypes.common import is_number from pandas import ( @@ -88,7 +86,6 @@ def test_apply_np_transformer(float_frame, op, how): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize( "series, func, expected", chain( @@ -147,7 +144,6 @@ def test_agg_cython_table_series(series, func, expected): assert result == expected -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize( "series, func, expected", chain( @@ -170,10 +166,17 @@ def test_agg_cython_table_series(series, func, expected): ), ), ) -def test_agg_cython_table_transform_series(series, func, expected): +def test_agg_cython_table_transform_series(request, series, func, expected): # GH21224 # test transforming functions in # pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum) + if series.dtype == "string" and func in ("cumsum", np.cumsum, np.nancumsum): + request.applymarker( + pytest.mark.xfail( + raises=(TypeError, NotImplementedError), + reason="TODO(infer_string) cumsum not yet implemented for string", + ) + ) warn = None if isinstance(func, str) else FutureWarning with tm.assert_produces_warning(warn, match="is currently using Series.*"): result = series.agg(func) diff --git a/pandas/tests/extension/test_arrow.py b/pandas/tests/extension/test_arrow.py index 0ce7a66e0e00c..470ca0673c60e 100644 --- a/pandas/tests/extension/test_arrow.py +++ b/pandas/tests/extension/test_arrow.py @@ -436,7 +436,7 @@ def test_accumulate_series(self, data, all_numeric_accumulations, skipna, reques request.applymarker( pytest.mark.xfail( reason=f"{all_numeric_accumulations} not implemented for {pa_type}", - raises=NotImplementedError, + raises=TypeError, ) ) @@ -1637,7 +1637,7 @@ def test_from_arrow_respecting_given_dtype(): def test_from_arrow_respecting_given_dtype_unsafe(): array = pa.array([1.5, 2.5], type=pa.float64()) - with pytest.raises(pa.ArrowInvalid, match="Float value 1.5 was truncated"): + with tm.external_error_raised(pa.ArrowInvalid): array.to_pandas(types_mapper={pa.float64(): ArrowDtype(pa.int64())}.get) diff --git a/pandas/tests/extension/test_interval.py b/pandas/tests/extension/test_interval.py index 98dd1c5cb615f..6292e6051aa90 100644 --- a/pandas/tests/extension/test_interval.py +++ b/pandas/tests/extension/test_interval.py @@ -90,6 +90,31 @@ def _supports_reduction(self, ser: pd.Series, op_name: str) -> bool: def test_fillna_length_mismatch(self, data_missing): super().test_fillna_length_mismatch(data_missing) + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) + def test_hash_pandas_object(self, data): + super().test_hash_pandas_object(data) + + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) + def test_hash_pandas_object_works(self, data, as_frame): + super().test_hash_pandas_object_works(data, as_frame) + + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) + @pytest.mark.parametrize("engine", ["c", "python"]) + def test_EA_types(self, engine, data, request): + super().test_EA_types(engine, data, request) + + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) + def test_astype_str(self, data): + super().test_astype_str(data) + # TODO: either belongs in tests.arrays.interval or move into base tests. def test_fillna_non_scalar_raises(data_missing): diff --git a/pandas/tests/frame/indexing/test_where.py b/pandas/tests/frame/indexing/test_where.py index 5fd3796d0255a..356257bbfec98 100644 --- a/pandas/tests/frame/indexing/test_where.py +++ b/pandas/tests/frame/indexing/test_where.py @@ -1086,15 +1086,9 @@ def test_where_producing_ea_cond_for_np_dtype(): @pytest.mark.parametrize( "replacement", [0.001, True, "snake", None, datetime(2022, 5, 4)] ) -def test_where_int_overflow(replacement, using_infer_string): +def test_where_int_overflow(replacement): # GH 31687 df = DataFrame([[1.0, 2e25, "nine"], [np.nan, 0.1, None]]) - if using_infer_string and replacement not in (None, "snake"): - with pytest.raises( - TypeError, match=f"Invalid value '{replacement}' for dtype 'str'" - ): - df.where(pd.notnull(df), replacement) - return result = df.where(pd.notnull(df), replacement) expected = DataFrame([[1.0, 2e25, "nine"], [replacement, 0.1, replacement]]) diff --git a/pandas/tests/frame/methods/test_fillna.py b/pandas/tests/frame/methods/test_fillna.py index e2baa2567f5b4..9844122dc4b2d 100644 --- a/pandas/tests/frame/methods/test_fillna.py +++ b/pandas/tests/frame/methods/test_fillna.py @@ -132,21 +132,14 @@ def test_fillna_different_dtype(self, using_infer_string): [["a", "a", np.nan, "a"], ["b", "b", np.nan, "b"], ["c", "c", np.nan, "c"]] ) - if using_infer_string: - with tm.assert_produces_warning(FutureWarning, match="Downcasting"): - result = df.fillna({2: "foo"}) - else: - result = df.fillna({2: "foo"}) + result = df.fillna({2: "foo"}) expected = DataFrame( [["a", "a", "foo", "a"], ["b", "b", "foo", "b"], ["c", "c", "foo", "c"]] ) + expected[2] = expected[2].astype("object") tm.assert_frame_equal(result, expected) - if using_infer_string: - with tm.assert_produces_warning(FutureWarning, match="Downcasting"): - return_value = df.fillna({2: "foo"}, inplace=True) - else: - return_value = df.fillna({2: "foo"}, inplace=True) + return_value = df.fillna({2: "foo"}, inplace=True) tm.assert_frame_equal(df, expected) assert return_value is None @@ -385,12 +378,8 @@ def test_fillna_dtype_conversion(self, using_infer_string): # empty block df = DataFrame(index=range(3), columns=["A", "B"], dtype="float64") - if using_infer_string: - with tm.assert_produces_warning(FutureWarning, match="Downcasting"): - result = df.fillna("nan") - else: - result = df.fillna("nan") - expected = DataFrame("nan", index=range(3), columns=["A", "B"]) + result = df.fillna("nan") + expected = DataFrame("nan", index=range(3), columns=["A", "B"], dtype=object) tm.assert_frame_equal(result, expected) @pytest.mark.parametrize("val", ["", 1, np.nan, 1.0]) diff --git a/pandas/tests/frame/methods/test_replace.py b/pandas/tests/frame/methods/test_replace.py index ccee7ca24bd3d..2ee878893ce70 100644 --- a/pandas/tests/frame/methods/test_replace.py +++ b/pandas/tests/frame/methods/test_replace.py @@ -281,23 +281,14 @@ def test_regex_replace_dict_nested(self, mix_abc): tm.assert_frame_equal(res3, expec) tm.assert_frame_equal(res4, expec) - def test_regex_replace_dict_nested_non_first_character( - self, any_string_dtype, using_infer_string - ): + def test_regex_replace_dict_nested_non_first_character(self, any_string_dtype): # GH 25259 dtype = any_string_dtype df = DataFrame({"first": ["abc", "bca", "cab"]}, dtype=dtype) - if using_infer_string and any_string_dtype == "object": - with tm.assert_produces_warning(FutureWarning, match="Downcasting"): - result = df.replace({"a": "."}, regex=True) - expected = DataFrame({"first": [".bc", "bc.", "c.b"]}) - - else: - result = df.replace({"a": "."}, regex=True) - expected = DataFrame({"first": [".bc", "bc.", "c.b"]}, dtype=dtype) + result = df.replace({"a": "."}, regex=True) + expected = DataFrame({"first": [".bc", "bc.", "c.b"]}, dtype=dtype) tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_regex_replace_dict_nested_gh4115(self): df = DataFrame({"Type": ["Q", "T", "Q", "Q", "T"], "tmp": 2}) expected = DataFrame({"Type": [0, 1, 0, 0, 1], "tmp": 2}) @@ -430,31 +421,12 @@ def test_replace_regex_metachar(self, metachar): ], ) def test_regex_replace_string_types( - self, - data, - to_replace, - expected, - frame_or_series, - any_string_dtype, - using_infer_string, - request, + self, data, to_replace, expected, frame_or_series, any_string_dtype ): # GH-41333, GH-35977 dtype = any_string_dtype obj = frame_or_series(data, dtype=dtype) - if using_infer_string and any_string_dtype == "object": - if len(to_replace) > 1 and isinstance(obj, DataFrame): - request.node.add_marker( - pytest.mark.xfail( - reason="object input array that gets downcasted raises on " - "second pass" - ) - ) - with tm.assert_produces_warning(FutureWarning, match="Downcasting"): - result = obj.replace(to_replace, regex=True) - dtype = "str" - else: - result = obj.replace(to_replace, regex=True) + result = obj.replace(to_replace, regex=True) expected = frame_or_series(expected, dtype=dtype) tm.assert_equal(result, expected) @@ -556,7 +528,6 @@ def test_replace_series_dict(self): result = df.replace(s, df.mean()) tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_replace_convert(self): # gh 3907 df = DataFrame([["foo", "bar", "bah"], ["bar", "foo", "bah"]]) @@ -932,7 +903,6 @@ def test_replace_input_formats_listlike(self): with pytest.raises(ValueError, match=msg): df.replace(to_rep, values[1:]) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_replace_input_formats_scalar(self): df = DataFrame( {"A": [np.nan, 0, np.inf], "B": [0, 2, 5], "C": ["", "asdf", "fd"]} @@ -961,7 +931,6 @@ def test_replace_limit(self): # TODO pass - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_replace_dict_no_regex(self): answer = Series( { @@ -985,7 +954,6 @@ def test_replace_dict_no_regex(self): result = answer.replace(weights) tm.assert_series_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_replace_series_no_regex(self): answer = Series( { @@ -1104,7 +1072,6 @@ def test_replace_swapping_bug(self, using_infer_string): expect = DataFrame({"a": ["Y", "N", "Y"]}) tm.assert_frame_equal(res, expect) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_replace_period(self): d = { "fname": { @@ -1141,7 +1108,6 @@ def test_replace_period(self): result = df.replace(d) tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") def test_replace_datetime(self): d = { "fname": { @@ -1367,7 +1333,6 @@ def test_replace_commutative(self, df, to_replace, exp): result = df.replace(to_replace) tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") @pytest.mark.parametrize( "replacer", [ @@ -1644,7 +1609,6 @@ def test_regex_replace_scalar( expected.loc[expected["a"] == ".", "a"] = expected_replace_val tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="can't set float into string") @pytest.mark.parametrize("regex", [False, True]) def test_replace_regex_dtype_frame(self, regex): # GH-48644 diff --git a/pandas/tests/frame/methods/test_to_numpy.py b/pandas/tests/frame/methods/test_to_numpy.py index bdb9b2c055061..0731750aed0cf 100644 --- a/pandas/tests/frame/methods/test_to_numpy.py +++ b/pandas/tests/frame/methods/test_to_numpy.py @@ -1,4 +1,5 @@ import numpy as np +import pytest import pandas.util._test_decorators as td @@ -41,6 +42,9 @@ def test_to_numpy_copy(self, using_copy_on_write): else: assert df.to_numpy(copy=False, na_value=np.nan).base is arr + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) def test_to_numpy_mixed_dtype_to_str(self): # https://github.com/pandas-dev/pandas/issues/35455 df = DataFrame([[Timestamp("2020-01-01 00:00:00"), 100.0]]) diff --git a/pandas/tests/frame/test_constructors.py b/pandas/tests/frame/test_constructors.py index fd770b368c9da..f16068e0b6538 100644 --- a/pandas/tests/frame/test_constructors.py +++ b/pandas/tests/frame/test_constructors.py @@ -2450,6 +2450,9 @@ def test_construct_with_two_categoricalindex_series(self): ) tm.assert_frame_equal(result, expected) + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) def test_constructor_series_nonexact_categoricalindex(self): # GH 42424 ser = Series(range(100)) diff --git a/pandas/tests/frame/test_reductions.py b/pandas/tests/frame/test_reductions.py index bee95e8295746..84d56864b3219 100644 --- a/pandas/tests/frame/test_reductions.py +++ b/pandas/tests/frame/test_reductions.py @@ -6,8 +6,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.compat import ( IS64, is_platform_windows, @@ -1091,7 +1089,6 @@ def test_idxmin_empty(self, index, skipna, axis): expected = Series(dtype=index.dtype) tm.assert_series_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("numeric_only", [True, False]) def test_idxmin_numeric_only(self, numeric_only): df = DataFrame({"a": [2, 3, 1], "b": [2, 1, 1], "c": list("xyx")}) @@ -1108,8 +1105,6 @@ def test_idxmin_axis_2(self, float_frame): with pytest.raises(ValueError, match=msg): frame.idxmin(axis=2) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) - @pytest.mark.parametrize("skipna", [True, False]) @pytest.mark.parametrize("axis", [0, 1]) def test_idxmax(self, float_frame, int_frame, skipna, axis): frame = float_frame @@ -1142,7 +1137,6 @@ def test_idxmax_empty(self, index, skipna, axis): expected = Series(dtype=index.dtype) tm.assert_series_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("numeric_only", [True, False]) def test_idxmax_numeric_only(self, numeric_only): df = DataFrame({"a": [2, 3, 1], "b": [2, 1, 1], "c": list("xyx")}) diff --git a/pandas/tests/frame/test_stack_unstack.py b/pandas/tests/frame/test_stack_unstack.py index 8bb5eb2d5c57a..af84ee021252f 100644 --- a/pandas/tests/frame/test_stack_unstack.py +++ b/pandas/tests/frame/test_stack_unstack.py @@ -2083,7 +2083,7 @@ def test_unstack_period_frame(self): @pytest.mark.filterwarnings( "ignore:The previous implementation of stack is deprecated" ) - def test_stack_multiple_bug(self, future_stack): + def test_stack_multiple_bug(self, future_stack, using_infer_string): # bug when some uniques are not present in the data GH#3170 id_col = ([1] * 3) + ([2] * 3) name = (["a"] * 3) + (["b"] * 3) @@ -2095,6 +2095,8 @@ def test_stack_multiple_bug(self, future_stack): multi.columns.name = "Params" unst = multi.unstack("ID") msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): unst.resample("W-THU").mean() down = unst.resample("W-THU").mean(numeric_only=True) diff --git a/pandas/tests/groupby/aggregate/test_aggregate.py b/pandas/tests/groupby/aggregate/test_aggregate.py index b267347aaf030..f02a828fe8d17 100644 --- a/pandas/tests/groupby/aggregate/test_aggregate.py +++ b/pandas/tests/groupby/aggregate/test_aggregate.py @@ -9,8 +9,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.errors import SpecificationError from pandas.core.dtypes.common import is_integer_dtype @@ -335,12 +333,11 @@ def aggfun_1(ser): assert len(result) == 0 -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_wrap_agg_out(three_group): grouped = three_group.groupby(["A", "B"]) def func(ser): - if ser.dtype == object: + if ser.dtype in (object, "string"): raise TypeError("Test error message") return ser.sum() @@ -1101,7 +1098,6 @@ def test_lambda_named_agg(func): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_aggregate_mixed_types(): # GH 16916 df = DataFrame( @@ -1113,7 +1109,7 @@ def test_aggregate_mixed_types(): expected = DataFrame( expected_data, index=Index([2, "group 1"], dtype="object", name="grouping"), - columns=Index(["X", "Y", "Z"], dtype="object"), + columns=Index(["X", "Y", "Z"]), ) tm.assert_frame_equal(result, expected) diff --git a/pandas/tests/groupby/aggregate/test_cython.py b/pandas/tests/groupby/aggregate/test_cython.py index fa8a6cb4120b2..0d04af3801dbe 100644 --- a/pandas/tests/groupby/aggregate/test_cython.py +++ b/pandas/tests/groupby/aggregate/test_cython.py @@ -5,8 +5,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.core.dtypes.common import ( is_float_dtype, is_integer_dtype, @@ -95,7 +93,6 @@ def test_cython_agg_boolean(): tm.assert_series_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_cython_agg_nothing_to_agg(): frame = DataFrame( {"a": np.random.default_rng(2).integers(0, 5, 50), "b": ["foo", "bar"] * 25} @@ -111,7 +108,9 @@ def test_cython_agg_nothing_to_agg(): result = frame[["b"]].groupby(frame["a"]).mean(numeric_only=True) expected = DataFrame( - [], index=frame["a"].sort_values().drop_duplicates(), columns=[] + [], + index=frame["a"].sort_values().drop_duplicates(), + columns=Index([], dtype="str"), ) tm.assert_frame_equal(result, expected) @@ -166,14 +165,14 @@ def test_cython_agg_return_dict(): def test_cython_fail_agg(): dr = bdate_range("1/1/2000", periods=50) - ts = Series(["A", "B", "C", "D", "E"] * 10, index=dr) + ts = Series(["A", "B", "C", "D", "E"] * 10, dtype=object, index=dr) grouped = ts.groupby(lambda x: x.month) summed = grouped.sum() msg = "using SeriesGroupBy.sum" with tm.assert_produces_warning(FutureWarning, match=msg): # GH#53425 - expected = grouped.agg(np.sum) + expected = grouped.agg(np.sum).astype(object) tm.assert_series_equal(summed, expected) diff --git a/pandas/tests/groupby/aggregate/test_other.py b/pandas/tests/groupby/aggregate/test_other.py index 5904b2f48359e..213704f31aca5 100644 --- a/pandas/tests/groupby/aggregate/test_other.py +++ b/pandas/tests/groupby/aggregate/test_other.py @@ -8,8 +8,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.errors import SpecificationError import pandas as pd @@ -308,7 +306,6 @@ def test_series_agg_multikey(): tm.assert_series_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_series_agg_multi_pure_python(): data = DataFrame( { @@ -358,7 +355,8 @@ def test_series_agg_multi_pure_python(): ) def bad(x): - assert len(x.values.base) > 0 + if isinstance(x.values, np.ndarray): + assert len(x.values.base) > 0 return "foo" result = data.groupby(["A", "B"]).agg(bad) diff --git a/pandas/tests/groupby/methods/test_quantile.py b/pandas/tests/groupby/methods/test_quantile.py index d3bc815402ade..3943590b069ad 100644 --- a/pandas/tests/groupby/methods/test_quantile.py +++ b/pandas/tests/groupby/methods/test_quantile.py @@ -1,8 +1,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - import pandas as pd from pandas import ( DataFrame, @@ -170,11 +168,11 @@ def test_groupby_quantile_with_arraylike_q_and_int_columns(frame_size, groupby, tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_quantile_raises(): df = DataFrame([["foo", "a"], ["foo", "b"], ["foo", "c"]], columns=["key", "val"]) - with pytest.raises(TypeError, match="cannot be performed against 'object' dtypes"): + msg = "dtype '(object|str)' does not support operation 'quantile'" + with pytest.raises(TypeError, match=msg): df.groupby("key").quantile() @@ -253,7 +251,6 @@ def test_groupby_quantile_nullable_array(values, q): tm.assert_series_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("q", [0.5, [0.0, 0.5, 1.0]]) @pytest.mark.parametrize("numeric_only", [True, False]) def test_groupby_quantile_raises_on_invalid_dtype(q, numeric_only): @@ -263,9 +260,8 @@ def test_groupby_quantile_raises_on_invalid_dtype(q, numeric_only): expected = df.groupby("a")[["b"]].quantile(q) tm.assert_frame_equal(result, expected) else: - with pytest.raises( - TypeError, match="'quantile' cannot be performed against 'object' dtypes!" - ): + msg = "dtype '.*' does not support operation 'quantile'" + with pytest.raises(TypeError, match=msg): df.groupby("a").quantile(q, numeric_only=numeric_only) diff --git a/pandas/tests/groupby/methods/test_size.py b/pandas/tests/groupby/methods/test_size.py index fb834ee2a8799..271802c447024 100644 --- a/pandas/tests/groupby/methods/test_size.py +++ b/pandas/tests/groupby/methods/test_size.py @@ -108,6 +108,8 @@ def test_size_series_masked_type_returns_Int64(dtype): tm.assert_series_equal(result, expected) +# TODO(infer_string) in case the column is object dtype, it should preserve that dtype +# for the result's index @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) def test_size_strings(any_string_dtype): # GH#55627 diff --git a/pandas/tests/groupby/test_categorical.py b/pandas/tests/groupby/test_categorical.py index cded7a71458fa..cba02ae869889 100644 --- a/pandas/tests/groupby/test_categorical.py +++ b/pandas/tests/groupby/test_categorical.py @@ -3,8 +3,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - import pandas as pd from pandas import ( Categorical, @@ -69,6 +67,7 @@ def f(a): } +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") def test_apply_use_categorical_name(df): cats = qcut(df.C, 4) @@ -340,8 +339,8 @@ def test_apply(ordered): tm.assert_series_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) -def test_observed(observed): +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") +def test_observed(request, using_infer_string, observed): # multiple groupers, don't re-expand the output space # of the grouper # gh-14942 (implement) @@ -349,6 +348,10 @@ def test_observed(observed): # gh-8138 (back-compat) # gh-8869 + if using_infer_string and not observed: + # TODO(infer_string) this fails with filling the string column with 0 + request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)")) + cat1 = Categorical(["a", "a", "b", "b"], categories=["a", "b", "z"], ordered=True) cat2 = Categorical(["c", "d", "c", "d"], categories=["c", "d", "y"], ordered=True) df = DataFrame({"A": cat1, "B": cat2, "values": [1, 2, 3, 4]}) @@ -1555,6 +1558,7 @@ def test_dataframe_groupby_on_2_categoricals_when_observed_is_false( assert (res.loc[unobserved_cats] == expected).all().all() +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") def test_series_groupby_categorical_aggregation_getitem(): # GH 8870 d = {"foo": [10, 8, 4, 1], "bar": [10, 20, 30, 40], "baz": ["d", "c", "d", "c"]} diff --git a/pandas/tests/groupby/test_groupby.py b/pandas/tests/groupby/test_groupby.py index 13269ea9c0920..b5588898d4580 100644 --- a/pandas/tests/groupby/test_groupby.py +++ b/pandas/tests/groupby/test_groupby.py @@ -640,7 +640,7 @@ def test_frame_multi_key_function_list(): tm.assert_frame_equal(agged, expected) -def test_frame_multi_key_function_list_partial_failure(): +def test_frame_multi_key_function_list_partial_failure(using_infer_string): data = DataFrame( { "A": [ @@ -691,6 +691,8 @@ def test_frame_multi_key_function_list_partial_failure(): grouped = data.groupby(["A", "B"]) funcs = ["mean", "std"] msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): grouped.agg(funcs) @@ -981,9 +983,11 @@ def test_groupby_multi_corner(df): tm.assert_frame_equal(agged, expected) -def test_raises_on_nuisance(df): +def test_raises_on_nuisance(df, using_infer_string): grouped = df.groupby("A") msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): grouped.agg("mean") with pytest.raises(TypeError, match=msg): @@ -1026,7 +1030,7 @@ def test_keep_nuisance_agg(df, agg_function): ["sum", "mean", "prod", "std", "var", "sem", "median"], ) @pytest.mark.parametrize("numeric_only", [True, False]) -def test_omit_nuisance_agg(df, agg_function, numeric_only): +def test_omit_nuisance_agg(df, agg_function, numeric_only, using_infer_string): # GH 38774, GH 38815 grouped = df.groupby("A") @@ -1034,7 +1038,10 @@ def test_omit_nuisance_agg(df, agg_function, numeric_only): if agg_function in no_drop_nuisance and not numeric_only: # Added numeric_only as part of GH#46560; these do not drop nuisance # columns when numeric_only is False - if agg_function in ("std", "sem"): + if using_infer_string: + msg = f"dtype 'str' does not support operation '{agg_function}'" + klass = TypeError + elif agg_function in ("std", "sem"): klass = ValueError msg = "could not convert string to float: 'one'" else: @@ -1055,16 +1062,24 @@ def test_omit_nuisance_agg(df, agg_function, numeric_only): tm.assert_frame_equal(result, expected) -def test_raise_on_nuisance_python_single(df): +def test_raise_on_nuisance_python_single(df, using_infer_string): # GH 38815 grouped = df.groupby("A") - with pytest.raises(ValueError, match="could not convert"): + + err = ValueError + msg = "could not convert" + if using_infer_string: + err = TypeError + msg = "dtype 'str' does not support operation 'skew'" + with pytest.raises(err, match=msg): grouped.skew() -def test_raise_on_nuisance_python_multiple(three_group): +def test_raise_on_nuisance_python_multiple(three_group, using_infer_string): grouped = three_group.groupby(["A", "B"]) msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): grouped.agg("mean") with pytest.raises(TypeError, match=msg): @@ -1102,12 +1117,16 @@ def test_nonsense_func(): df.groupby(lambda x: x + "foo") -def test_wrap_aggregated_output_multindex(multiindex_dataframe_random_data): +def test_wrap_aggregated_output_multindex( + multiindex_dataframe_random_data, using_infer_string +): df = multiindex_dataframe_random_data.T df["baz", "two"] = "peekaboo" keys = [np.array([0, 0, 1]), np.array([0, 0, 1])] msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): df.groupby(keys).agg("mean") agged = df.drop(columns=("baz", "two")).groupby(keys).agg("mean") @@ -1299,8 +1318,10 @@ def test_groupby_with_hier_columns(): def test_grouping_ndarray(df): grouped = df.groupby(df["A"].values) + grouped2 = df.groupby(df["A"].rename(None)) + result = grouped.sum() - expected = df.groupby(df["A"].rename(None)).sum() + expected = grouped2.sum() tm.assert_frame_equal(result, expected) @@ -1596,7 +1617,6 @@ def test_groupby_two_group_keys_all_nan(): assert result == {} -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_groupby_2d_malformed(): d = DataFrame(index=range(2)) d["group"] = ["g1", "g2"] @@ -1605,7 +1625,7 @@ def test_groupby_2d_malformed(): d["label"] = ["l1", "l2"] tmp = d.groupby(["group"]).mean(numeric_only=True) res_values = np.array([[0.0, 1.0], [0.0, 1.0]]) - tm.assert_index_equal(tmp.columns, Index(["zeros", "ones"])) + tm.assert_index_equal(tmp.columns, Index(["zeros", "ones"], dtype=object)) tm.assert_numpy_array_equal(tmp.values, res_values) @@ -1793,8 +1813,8 @@ def test_no_dummy_key_names(df): result = df.groupby(df["A"].values).sum() assert result.index.name is None - result = df.groupby([df["A"].values, df["B"].values]).sum() - assert result.index.names == (None, None) + result2 = df.groupby([df["A"].values, df["B"].values]).sum() + assert result2.index.names == (None, None) def test_groupby_sort_multiindex_series(): @@ -2099,6 +2119,7 @@ def get_categorical_invalid_expected(): is_per = isinstance(df.dtypes.iloc[0], pd.PeriodDtype) is_dt64 = df.dtypes.iloc[0].kind == "M" is_cat = isinstance(values, Categorical) + is_str = isinstance(df.dtypes.iloc[0], pd.StringDtype) if ( isinstance(values, Categorical) @@ -2123,13 +2144,15 @@ def get_categorical_invalid_expected(): if op in ["prod", "sum", "skew"]: # ops that require more than just ordered-ness - if is_dt64 or is_cat or is_per: + if is_dt64 or is_cat or is_per or (is_str and op != "sum"): # GH#41291 # datetime64 -> prod and sum are invalid if is_dt64: msg = "datetime64 type does not support" elif is_per: msg = "Period type does not support" + elif is_str: + msg = f"dtype 'str' does not support operation '{op}'" else: msg = "category type does not support" if op == "skew": @@ -2687,7 +2710,6 @@ def test_groupby_all_nan_groups_drop(): tm.assert_series_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("numeric_only", [True, False]) def test_groupby_empty_multi_column(as_index, numeric_only): # GH 15106 & GH 41998 @@ -2696,7 +2718,7 @@ def test_groupby_empty_multi_column(as_index, numeric_only): result = gb.sum(numeric_only=numeric_only) if as_index: index = MultiIndex([[], []], [[], []], names=["A", "B"]) - columns = ["C"] if not numeric_only else [] + columns = ["C"] if not numeric_only else Index([], dtype="str") else: index = RangeIndex(0) columns = ["A", "B", "C"] if not numeric_only else ["A", "B"] @@ -2704,7 +2726,6 @@ def test_groupby_empty_multi_column(as_index, numeric_only): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_groupby_aggregation_non_numeric_dtype(): # GH #43108 df = DataFrame( @@ -2715,7 +2736,7 @@ def test_groupby_aggregation_non_numeric_dtype(): { "v": [[1, 1], [10, 20]], }, - index=Index(["M", "W"], dtype="object", name="MW"), + index=Index(["M", "W"], name="MW"), ) gb = df.groupby(by=["MW"]) @@ -3083,7 +3104,7 @@ def test_obj_with_exclusions_duplicate_columns(): def test_groupby_numeric_only_std_no_result(numeric_only): # GH 51080 dicts_non_numeric = [{"a": "foo", "b": "bar"}, {"a": "car", "b": "dar"}] - df = DataFrame(dicts_non_numeric) + df = DataFrame(dicts_non_numeric, dtype=object) dfgb = df.groupby("a", as_index=False, sort=False) if numeric_only: @@ -3097,6 +3118,7 @@ def test_groupby_numeric_only_std_no_result(numeric_only): dfgb.std(numeric_only=numeric_only) +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") def test_grouping_with_categorical_interval_columns(): # GH#34164 df = DataFrame({"x": [0.1, 0.2, 0.3, -0.4, 0.5], "w": ["a", "b", "a", "c", "a"]}) @@ -3142,10 +3164,14 @@ def test_grouping_with_categorical_interval_columns(): def test_groupby_sum_on_nan_should_return_nan(bug_var): # GH 24196 df = DataFrame({"A": [bug_var, bug_var, bug_var, np.nan]}) + if isinstance(bug_var, str): + df = df.astype(object) dfgb = df.groupby(lambda x: x) result = dfgb.sum(min_count=1) - expected_df = DataFrame([bug_var, bug_var, bug_var, None], columns=["A"]) + expected_df = DataFrame( + [bug_var, bug_var, bug_var, None], columns=["A"], dtype=df["A"].dtype + ) tm.assert_frame_equal(result, expected_df) diff --git a/pandas/tests/groupby/test_groupby_dropna.py b/pandas/tests/groupby/test_groupby_dropna.py index 7e65e56abc4c9..2a9b61aa7ebf5 100644 --- a/pandas/tests/groupby/test_groupby_dropna.py +++ b/pandas/tests/groupby/test_groupby_dropna.py @@ -1,8 +1,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.compat.pyarrow import pa_version_under10p1 from pandas.core.dtypes.missing import na_value_for_dtype @@ -99,7 +97,6 @@ def test_groupby_dropna_multi_index_dataframe_nan_in_two_groups( tm.assert_frame_equal(grouped, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize( "dropna, idx, outputs", [ @@ -126,7 +123,7 @@ def test_groupby_dropna_normal_index_dataframe(dropna, idx, outputs): df = pd.DataFrame(df_list, columns=["a", "b", "c", "d"]) grouped = df.groupby("a", dropna=dropna).sum() - expected = pd.DataFrame(outputs, index=pd.Index(idx, dtype="object", name="a")) + expected = pd.DataFrame(outputs, index=pd.Index(idx, name="a")) tm.assert_frame_equal(grouped, expected) diff --git a/pandas/tests/groupby/test_groupby_subclass.py b/pandas/tests/groupby/test_groupby_subclass.py index 1a2acb658ee26..b5523592c3c5c 100644 --- a/pandas/tests/groupby/test_groupby_subclass.py +++ b/pandas/tests/groupby/test_groupby_subclass.py @@ -109,7 +109,7 @@ def test_groupby_resample_preserves_subclass(obj): df = obj( { - "Buyer": "Carl Carl Carl Carl Joe Carl".split(), + "Buyer": Series("Carl Carl Carl Carl Joe Carl".split(), dtype=object), "Quantity": [18, 3, 5, 1, 9, 3], "Date": [ datetime(2013, 9, 1, 13, 0), diff --git a/pandas/tests/groupby/test_grouping.py b/pandas/tests/groupby/test_grouping.py index 7c0a4b78a123d..9a0e67dea532b 100644 --- a/pandas/tests/groupby/test_grouping.py +++ b/pandas/tests/groupby/test_grouping.py @@ -9,8 +9,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - import pandas as pd from pandas import ( CategoricalIndex, @@ -844,7 +842,6 @@ def test_groupby_empty(self): expected = ["name"] assert result == expected - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_groupby_level_index_value_all_na(self): # issue 20519 df = DataFrame( @@ -854,7 +851,7 @@ def test_groupby_level_index_value_all_na(self): expected = DataFrame( data=[], index=MultiIndex( - levels=[Index(["x"], dtype="object"), Index([], dtype="float64")], + levels=[Index(["x"], dtype="str"), Index([], dtype="float64")], codes=[[], []], names=["A", "B"], ), @@ -989,12 +986,13 @@ def test_groupby_with_empty(self): grouped = series.groupby(grouper) assert next(iter(grouped), None) is None - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_groupby_with_single_column(self): df = DataFrame({"a": list("abssbab")}) tm.assert_frame_equal(df.groupby("a").get_group("a"), df.iloc[[0, 5]]) # GH 13530 - exp = DataFrame(index=Index(["a", "b", "s"], name="a"), columns=[]) + exp = DataFrame( + index=Index(["a", "b", "s"], name="a"), columns=Index([], dtype="str") + ) tm.assert_frame_equal(df.groupby("a").count(), exp) tm.assert_frame_equal(df.groupby("a").sum(), exp) diff --git a/pandas/tests/groupby/test_numeric_only.py b/pandas/tests/groupby/test_numeric_only.py index 3b7614347d181..3c1ed20ddcb16 100644 --- a/pandas/tests/groupby/test_numeric_only.py +++ b/pandas/tests/groupby/test_numeric_only.py @@ -29,7 +29,8 @@ def df(self): "group": [1, 1, 2], "int": [1, 2, 3], "float": [4.0, 5.0, 6.0], - "string": list("abc"), + "string": Series(["a", "b", "c"], dtype="str"), + "object": Series(["a", "b", "c"], dtype=object), "category_string": Series(list("abc")).astype("category"), "category_int": [7, 8, 9], "datetime": date_range("20130101", periods=3), @@ -41,6 +42,7 @@ def df(self): "int", "float", "string", + "object", "category_string", "category_int", "datetime", @@ -113,6 +115,7 @@ def test_first_last(self, df, method): "int", "float", "string", + "object", "category_string", "category_int", "datetime", @@ -160,7 +163,9 @@ def _check(self, df, method, expected_columns, expected_columns_numeric): # object dtypes for transformations are not implemented in Cython and # have no Python fallback - exception = NotImplementedError if method.startswith("cum") else TypeError + exception = ( + (NotImplementedError, TypeError) if method.startswith("cum") else TypeError + ) if method in ("min", "max", "cummin", "cummax", "cumsum", "cumprod"): # The methods default to numeric_only=False and raise TypeError @@ -171,6 +176,7 @@ def _check(self, df, method, expected_columns, expected_columns_numeric): re.escape(f"agg function failed [how->{method},dtype->object]"), # cumsum/cummin/cummax/cumprod "function is not implemented for this dtype", + f"dtype 'str' does not support operation '{method}'", ] ) with pytest.raises(exception, match=msg): @@ -181,7 +187,7 @@ def _check(self, df, method, expected_columns, expected_columns_numeric): "category type does not support sum operations", re.escape(f"agg function failed [how->{method},dtype->object]"), re.escape(f"agg function failed [how->{method},dtype->string]"), - re.escape(f"agg function failed [how->{method},dtype->str]"), + f"dtype 'str' does not support operation '{method}'", ] ) with pytest.raises(exception, match=msg): @@ -199,7 +205,7 @@ def _check(self, df, method, expected_columns, expected_columns_numeric): f"Cannot perform {method} with non-ordered Categorical", re.escape(f"agg function failed [how->{method},dtype->object]"), re.escape(f"agg function failed [how->{method},dtype->string]"), - re.escape(f"agg function failed [how->{method},dtype->str]"), + f"dtype 'str' does not support operation '{method}'", ] ) with pytest.raises(exception, match=msg): @@ -384,7 +390,9 @@ def test_numeric_only(kernel, has_arg, numeric_only, keys): re.escape(f"agg function failed [how->{kernel},dtype->object]"), ] ) - if kernel == "idxmin": + if kernel == "quantile": + msg = "dtype 'object' does not support operation 'quantile'" + elif kernel == "idxmin": msg = "'<' not supported between instances of 'type' and 'type'" elif kernel == "idxmax": msg = "'>' not supported between instances of 'type' and 'type'" @@ -458,7 +466,7 @@ def test_deprecate_numeric_only_series(dtype, groupby_func, request): # that succeed should not be allowed to fail (without deprecation, at least) if groupby_func in fails_on_numeric_object and dtype is object: if groupby_func == "quantile": - msg = "cannot be performed against 'object' dtypes" + msg = "dtype 'object' does not support operation 'quantile'" else: msg = "is not supported for object dtype" warn = FutureWarning if groupby_func == "fillna" else None diff --git a/pandas/tests/groupby/test_pipe.py b/pandas/tests/groupby/test_pipe.py index 1044c83e3e56b..ee59a93695bcf 100644 --- a/pandas/tests/groupby/test_pipe.py +++ b/pandas/tests/groupby/test_pipe.py @@ -1,7 +1,4 @@ import numpy as np -import pytest - -from pandas._config import using_string_dtype import pandas as pd from pandas import ( @@ -11,7 +8,6 @@ import pandas._testing as tm -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_pipe(): # Test the pipe method of DataFrameGroupBy. # Issue #17871 @@ -39,7 +35,7 @@ def square(srs): # NDFrame.pipe methods result = df.groupby("A").pipe(f).pipe(square) - index = Index(["bar", "foo"], dtype="object", name="A") + index = Index(["bar", "foo"], name="A") expected = pd.Series([3.749306591013693, 6.717707873081384], name="B", index=index) tm.assert_series_equal(expected, result) diff --git a/pandas/tests/groupby/test_raises.py b/pandas/tests/groupby/test_raises.py index 4ebb26b0289ec..5457f5ba050c6 100644 --- a/pandas/tests/groupby/test_raises.py +++ b/pandas/tests/groupby/test_raises.py @@ -8,8 +8,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas import ( Categorical, DataFrame, @@ -119,10 +117,9 @@ def _call_and_check(klass, msg, how, gb, groupby_func, args, warn_msg=""): gb.transform(groupby_func, *args) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("how", ["method", "agg", "transform"]) def test_groupby_raises_string( - how, by, groupby_series, groupby_func, df_with_string_col + how, by, groupby_series, groupby_func, df_with_string_col, using_infer_string ): df = df_with_string_col args = get_groupby_method_args(groupby_func, df) @@ -182,7 +179,7 @@ def test_groupby_raises_string( TypeError, re.escape("agg function failed [how->prod,dtype->object]"), ), - "quantile": (TypeError, "cannot be performed against 'object' dtypes!"), + "quantile": (TypeError, "dtype 'object' does not support operation 'quantile'"), "rank": (None, ""), "sem": (ValueError, "could not convert string to float"), "shift": (None, ""), @@ -196,6 +193,37 @@ def test_groupby_raises_string( ), }[groupby_func] + if using_infer_string: + if groupby_func in [ + "prod", + "mean", + "median", + "cumsum", + "cumprod", + "std", + "sem", + "var", + "skew", + "quantile", + ]: + msg = f"dtype 'str' does not support operation '{groupby_func}'" + if groupby_func in ["sem", "std", "skew"]: + # The object-dtype raises ValueError when trying to convert to numeric. + klass = TypeError + elif groupby_func == "pct_change" and df["d"].dtype.storage == "pyarrow": + # This doesn't go through EA._groupby_op so the message isn't controlled + # there. + msg = "operation 'truediv' not supported for dtype 'str' with dtype 'str'" + elif groupby_func == "diff" and df["d"].dtype.storage == "pyarrow": + # This doesn't go through EA._groupby_op so the message isn't controlled + # there. + msg = "operation 'sub' not supported for dtype 'str' with dtype 'str'" + + elif groupby_func in ["cummin", "cummax"]: + msg = msg.replace("object", "str") + elif groupby_func == "corrwith": + msg = "Cannot perform reduction 'mean' with string dtype" + if groupby_func == "fillna": kind = "Series" if groupby_series else "DataFrame" warn_msg = f"{kind}GroupBy.fillna is deprecated" @@ -222,7 +250,12 @@ def func(x): @pytest.mark.parametrize("how", ["agg", "transform"]) @pytest.mark.parametrize("groupby_func_np", [np.sum, np.mean]) def test_groupby_raises_string_np( - how, by, groupby_series, groupby_func_np, df_with_string_col + how, + by, + groupby_series, + groupby_func_np, + df_with_string_col, + using_infer_string, ): # GH#50749 df = df_with_string_col @@ -239,6 +272,11 @@ def test_groupby_raises_string_np( ), }[groupby_func_np] + if using_infer_string: + if groupby_func_np is np.mean: + klass = TypeError + msg = "dtype 'str' does not support operation 'mean'" + if groupby_series: warn_msg = "using SeriesGroupBy.[sum|mean]" else: diff --git a/pandas/tests/groupby/test_reductions.py b/pandas/tests/groupby/test_reductions.py index 8e1bbcb43e3f3..599b0aabf85d5 100644 --- a/pandas/tests/groupby/test_reductions.py +++ b/pandas/tests/groupby/test_reductions.py @@ -5,8 +5,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas._libs.tslibs import iNaT from pandas.core.dtypes.common import pandas_dtype @@ -457,8 +455,7 @@ def test_max_min_non_numeric(): assert "ss" in result -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") -def test_max_min_object_multiple_columns(using_array_manager): +def test_max_min_object_multiple_columns(using_array_manager, using_infer_string): # GH#41111 case where the aggregation is valid for some columns but not # others; we split object blocks column-wise, consistent with # DataFrame._reduce @@ -472,7 +469,7 @@ def test_max_min_object_multiple_columns(using_array_manager): ) df._consolidate_inplace() # should already be consolidate, but double-check if not using_array_manager: - assert len(df._mgr.blocks) == 2 + assert len(df._mgr.blocks) == 3 if using_infer_string else 2 gb = df.groupby("A") diff --git a/pandas/tests/groupby/test_timegrouper.py b/pandas/tests/groupby/test_timegrouper.py index 92dfe146bbb54..3bae719e01b73 100644 --- a/pandas/tests/groupby/test_timegrouper.py +++ b/pandas/tests/groupby/test_timegrouper.py @@ -75,6 +75,8 @@ def groupby_with_truncated_bingrouper(frame_for_truncated_bingrouper): class TestGroupBy: + # TODO(infer_string) resample sum introduces 0's + # https://github.com/pandas-dev/pandas/issues/60229 @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_groupby_with_timegrouper(self): # GH 4161 diff --git a/pandas/tests/groupby/transform/test_transform.py b/pandas/tests/groupby/transform/test_transform.py index 2aada753e27f4..18ce6e93de402 100644 --- a/pandas/tests/groupby/transform/test_transform.py +++ b/pandas/tests/groupby/transform/test_transform.py @@ -2,8 +2,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas._libs import lib from pandas.core.dtypes.common import ensure_platform_int @@ -905,6 +903,7 @@ def test_cython_transform_frame_column( ".* is not supported for object dtype", "is not implemented for this dtype", ".* is not supported for str dtype", + "dtype 'str' does not support operation '.*'", ] ) with pytest.raises(TypeError, match=msg): @@ -1228,20 +1227,19 @@ def test_groupby_transform_with_datetimes(func, values): tm.assert_series_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_groupby_transform_dtype(): # GH 22243 df = DataFrame({"a": [1], "val": [1.35]}) result = df["val"].transform(lambda x: x.map(lambda y: f"+{y}")) - expected1 = Series(["+1.35"], name="val", dtype="object") + expected1 = Series(["+1.35"], name="val") tm.assert_series_equal(result, expected1) result = df.groupby("a")["val"].transform(lambda x: x.map(lambda y: f"+{y}")) tm.assert_series_equal(result, expected1) result = df.groupby("a")["val"].transform(lambda x: x.map(lambda y: f"+({y})")) - expected2 = Series(["+(1.35)"], name="val", dtype="object") + expected2 = Series(["+(1.35)"], name="val") tm.assert_series_equal(result, expected2) df["val"] = df["val"].astype(object) diff --git a/pandas/tests/indexes/interval/test_astype.py b/pandas/tests/indexes/interval/test_astype.py index 59c555b9644a1..dde5f38074efb 100644 --- a/pandas/tests/indexes/interval/test_astype.py +++ b/pandas/tests/indexes/interval/test_astype.py @@ -186,6 +186,12 @@ def test_subtype_datetimelike(self, index, subtype): with pytest.raises(TypeError, match=msg): index.astype(dtype) + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) + def test_astype_category(self, index): + super().test_astype_category(index) + class TestDatetimelikeSubtype(AstypeTests): """Tests specific to IntervalIndex with datetime-like subtype""" diff --git a/pandas/tests/indexes/interval/test_formats.py b/pandas/tests/indexes/interval/test_formats.py index f858ae137ca4e..73bbfc91028b3 100644 --- a/pandas/tests/indexes/interval/test_formats.py +++ b/pandas/tests/indexes/interval/test_formats.py @@ -59,6 +59,9 @@ def test_repr_floats(self): expected = "(329.973, 345.137] 1\n(345.137, 360.191] 2\ndtype: int64" assert result == expected + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) @pytest.mark.parametrize( "tuples, closed, expected_data", [ diff --git a/pandas/tests/indexes/interval/test_indexing.py b/pandas/tests/indexes/interval/test_indexing.py index fd03047b2c127..b5be7e0713cdf 100644 --- a/pandas/tests/indexes/interval/test_indexing.py +++ b/pandas/tests/indexes/interval/test_indexing.py @@ -341,6 +341,9 @@ def test_get_indexer_categorical(self, target, ordered): expected = index.get_indexer(target) tm.assert_numpy_array_equal(result, expected) + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) def test_get_indexer_categorical_with_nans(self): # GH#41934 nans in both index and in target ii = IntervalIndex.from_breaks(range(5)) diff --git a/pandas/tests/indexes/object/test_indexing.py b/pandas/tests/indexes/object/test_indexing.py index d3df349027c00..42ef7e7a96f5e 100644 --- a/pandas/tests/indexes/object/test_indexing.py +++ b/pandas/tests/indexes/object/test_indexing.py @@ -62,6 +62,15 @@ def test_get_indexer_with_NA_values( expected = np.array([0, 1, -1], dtype=np.intp) tm.assert_numpy_array_equal(result, expected) + def test_get_indexer_infer_string_missing_values(self): + # ensure the passed list is not cast to string but to object so that + # the None value is matched in the index + # https://github.com/pandas-dev/pandas/issues/55834 + idx = Index(["a", "b", None], dtype="object") + result = idx.get_indexer([None, "x"]) + expected = np.array([2, -1], dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) + class TestGetIndexerNonUnique: def test_get_indexer_non_unique_nas(self, nulls_fixture): diff --git a/pandas/tests/indexes/string/test_indexing.py b/pandas/tests/indexes/string/test_indexing.py index 755b7109a5a04..d1a278af337b7 100644 --- a/pandas/tests/indexes/string/test_indexing.py +++ b/pandas/tests/indexes/string/test_indexing.py @@ -6,6 +6,51 @@ import pandas._testing as tm +def _isnan(val): + try: + return val is not pd.NA and np.isnan(val) + except TypeError: + return False + + +class TestGetLoc: + def test_get_loc(self, any_string_dtype): + index = Index(["a", "b", "c"], dtype=any_string_dtype) + assert index.get_loc("b") == 1 + + def test_get_loc_raises(self, any_string_dtype): + index = Index(["a", "b", "c"], dtype=any_string_dtype) + with pytest.raises(KeyError, match="d"): + index.get_loc("d") + + def test_get_loc_invalid_value(self, any_string_dtype): + index = Index(["a", "b", "c"], dtype=any_string_dtype) + with pytest.raises(KeyError, match="1"): + index.get_loc(1) + + def test_get_loc_non_unique(self, any_string_dtype): + index = Index(["a", "b", "a"], dtype=any_string_dtype) + result = index.get_loc("a") + expected = np.array([True, False, True]) + tm.assert_numpy_array_equal(result, expected) + + def test_get_loc_non_missing(self, any_string_dtype, nulls_fixture): + index = Index(["a", "b", "c"], dtype=any_string_dtype) + with pytest.raises(KeyError): + index.get_loc(nulls_fixture) + + def test_get_loc_missing(self, any_string_dtype, nulls_fixture): + index = Index(["a", "b", nulls_fixture], dtype=any_string_dtype) + if any_string_dtype == "string" and ( + (any_string_dtype.na_value is pd.NA and nulls_fixture is not pd.NA) + or (_isnan(any_string_dtype.na_value) and not _isnan(nulls_fixture)) + ): + with pytest.raises(KeyError): + index.get_loc(nulls_fixture) + else: + assert index.get_loc(nulls_fixture) == 2 + + class TestGetIndexer: @pytest.mark.parametrize( "method,expected", @@ -41,23 +86,60 @@ def test_get_indexer_strings_raises(self, any_string_dtype): ["a", "b", "c", "d"], method="pad", tolerance=[2, 2, 2, 2] ) + @pytest.mark.parametrize("null", [None, np.nan, float("nan"), pd.NA]) + def test_get_indexer_missing(self, any_string_dtype, null, using_infer_string): + # NaT and Decimal("NaN") from null_fixture are not supported for string dtype + index = Index(["a", "b", null], dtype=any_string_dtype) + result = index.get_indexer(["a", null, "c"]) + if using_infer_string: + expected = np.array([0, 2, -1], dtype=np.intp) + elif any_string_dtype == "string" and ( + (any_string_dtype.na_value is pd.NA and null is not pd.NA) + or (_isnan(any_string_dtype.na_value) and not _isnan(null)) + ): + expected = np.array([0, -1, -1], dtype=np.intp) + else: + expected = np.array([0, 2, -1], dtype=np.intp) -class TestGetIndexerNonUnique: - @pytest.mark.xfail(reason="TODO(infer_string)", strict=False) - def test_get_indexer_non_unique_nas(self, any_string_dtype, nulls_fixture): - index = Index(["a", "b", None], dtype=any_string_dtype) - indexer, missing = index.get_indexer_non_unique([nulls_fixture]) + tm.assert_numpy_array_equal(result, expected) - expected_indexer = np.array([2], dtype=np.intp) - expected_missing = np.array([], dtype=np.intp) + +class TestGetIndexerNonUnique: + @pytest.mark.parametrize("null", [None, np.nan, float("nan"), pd.NA]) + def test_get_indexer_non_unique_nas( + self, any_string_dtype, null, using_infer_string + ): + index = Index(["a", "b", null], dtype=any_string_dtype) + indexer, missing = index.get_indexer_non_unique(["a", null]) + + if using_infer_string: + expected_indexer = np.array([0, 2], dtype=np.intp) + expected_missing = np.array([], dtype=np.intp) + elif any_string_dtype == "string" and ( + (any_string_dtype.na_value is pd.NA and null is not pd.NA) + or (_isnan(any_string_dtype.na_value) and not _isnan(null)) + ): + expected_indexer = np.array([0, -1], dtype=np.intp) + expected_missing = np.array([1], dtype=np.intp) + else: + expected_indexer = np.array([0, 2], dtype=np.intp) + expected_missing = np.array([], dtype=np.intp) tm.assert_numpy_array_equal(indexer, expected_indexer) tm.assert_numpy_array_equal(missing, expected_missing) # actually non-unique - index = Index(["a", None, "b", None], dtype=any_string_dtype) - indexer, missing = index.get_indexer_non_unique([nulls_fixture]) - - expected_indexer = np.array([1, 3], dtype=np.intp) + index = Index(["a", null, "b", null], dtype=any_string_dtype) + indexer, missing = index.get_indexer_non_unique(["a", null]) + + if using_infer_string: + expected_indexer = np.array([0, 1, 3], dtype=np.intp) + elif any_string_dtype == "string" and ( + (any_string_dtype.na_value is pd.NA and null is not pd.NA) + or (_isnan(any_string_dtype.na_value) and not _isnan(null)) + ): + pass + else: + expected_indexer = np.array([0, 1, 3], dtype=np.intp) tm.assert_numpy_array_equal(indexer, expected_indexer) tm.assert_numpy_array_equal(missing, expected_missing) diff --git a/pandas/tests/indexes/test_setops.py b/pandas/tests/indexes/test_setops.py index 3845744dc0717..f6a865ccbb3a0 100644 --- a/pandas/tests/indexes/test_setops.py +++ b/pandas/tests/indexes/test_setops.py @@ -519,6 +519,7 @@ def test_intersection_difference_match_empty(self, index, sort): tm.assert_index_equal(inter, diff, exact=True) +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") @pytest.mark.parametrize( "method", ["intersection", "union", "difference", "symmetric_difference"] diff --git a/pandas/tests/indexing/test_coercion.py b/pandas/tests/indexing/test_coercion.py index ac3bfe3a13a44..4e1697eabf734 100644 --- a/pandas/tests/indexing/test_coercion.py +++ b/pandas/tests/indexing/test_coercion.py @@ -831,7 +831,7 @@ def replacer(self, how, from_key, to_key): raise ValueError return replacer - def test_replace_series(self, how, to_key, from_key, replacer): + def test_replace_series(self, how, to_key, from_key, replacer, using_infer_string): index = pd.Index([3, 4], name="xxx") obj = pd.Series(self.rep[from_key], index=index, name="yyy") obj = obj.astype(from_key) @@ -856,6 +856,10 @@ def test_replace_series(self, how, to_key, from_key, replacer): else: exp = pd.Series(self.rep[to_key], index=index, name="yyy") + if using_infer_string and exp.dtype == "string" and obj.dtype == object: + # with infer_string, we disable the deprecated downcasting behavior + exp = exp.astype(object) + msg = "Downcasting behavior in `replace`" warn = FutureWarning if ( diff --git a/pandas/tests/interchange/test_impl.py b/pandas/tests/interchange/test_impl.py index ef94c4c7aff2c..c32b31c297c5d 100644 --- a/pandas/tests/interchange/test_impl.py +++ b/pandas/tests/interchange/test_impl.py @@ -6,8 +6,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas._libs.tslibs import iNaT from pandas.compat import ( is_ci_environment, @@ -412,7 +410,6 @@ def test_interchange_from_corrected_buffer_dtypes(monkeypatch) -> None: pd.api.interchange.from_dataframe(df) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_empty_string_column(): # https://github.com/pandas-dev/pandas/issues/56703 df = pd.DataFrame({"a": []}, dtype=str) @@ -421,13 +418,12 @@ def test_empty_string_column(): tm.assert_frame_equal(df, result) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_large_string(): # GH#56702 pytest.importorskip("pyarrow") df = pd.DataFrame({"a": ["x"]}, dtype="large_string[pyarrow]") result = pd.api.interchange.from_dataframe(df.__dataframe__()) - expected = pd.DataFrame({"a": ["x"]}, dtype="object") + expected = pd.DataFrame({"a": ["x"]}, dtype="str") tm.assert_frame_equal(result, expected) @@ -438,7 +434,6 @@ def test_non_str_names(): assert names == ["0"] -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_non_str_names_w_duplicates(): # https://github.com/pandas-dev/pandas/issues/56701 df = pd.DataFrame({"0": [1, 2, 3], 0: [4, 5, 6]}) @@ -449,7 +444,7 @@ def test_non_str_names_w_duplicates(): "Expected a Series, got a DataFrame. This likely happened because you " "called __dataframe__ on a DataFrame which, after converting column " r"names to string, resulted in duplicated names: Index\(\['0', '0'\], " - r"dtype='object'\). Please rename these columns before using the " + r"dtype='(str|object)'\). Please rename these columns before using the " "interchange protocol." ), ): diff --git a/pandas/tests/io/excel/test_writers.py b/pandas/tests/io/excel/test_writers.py index 57091b268a9db..f133423bc6a85 100644 --- a/pandas/tests/io/excel/test_writers.py +++ b/pandas/tests/io/excel/test_writers.py @@ -755,6 +755,9 @@ def test_excel_date_datetime_format(self, ext, path): # we need to use df_expected to check the result. tm.assert_frame_equal(rs2, df_expected) + @pytest.mark.filterwarnings( + "ignore:invalid value encountered in cast:RuntimeWarning" + ) def test_to_excel_interval_no_labels(self, path, using_infer_string): # see gh-19242 # diff --git a/pandas/tests/io/json/test_json_table_schema.py b/pandas/tests/io/json/test_json_table_schema.py index 1e47b3bc38737..1c7320aa7a083 100644 --- a/pandas/tests/io/json/test_json_table_schema.py +++ b/pandas/tests/io/json/test_json_table_schema.py @@ -6,8 +6,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.core.dtypes.dtypes import ( CategoricalDtype, DatetimeTZDtype, @@ -26,10 +24,6 @@ set_default_names, ) -pytestmark = pytest.mark.xfail( - using_string_dtype(), reason="TODO(infer_string)", strict=False -) - @pytest.fixture def df_schema(): @@ -126,7 +120,7 @@ def test_multiindex(self, df_schema, using_infer_string): expected["fields"][0] = { "name": "level_0", "type": "any", - "extDtype": "string", + "extDtype": "str", } expected["fields"][3] = {"name": "B", "type": "any", "extDtype": "str"} assert result == expected diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py index a8608434be5ee..10f1e7df648f0 100644 --- a/pandas/tests/io/json/test_pandas.py +++ b/pandas/tests/io/json/test_pandas.py @@ -118,7 +118,7 @@ def datetime_frame(self): # since that doesn't round-trip, see GH#33711 df = DataFrame( np.random.default_rng(2).standard_normal((30, 4)), - columns=Index(list("ABCD"), dtype=object), + columns=Index(list("ABCD")), index=date_range("2000-01-01", periods=30, freq="B"), ) df.index = df.index._with_freq(None) @@ -203,7 +203,6 @@ def test_roundtrip_simple(self, orient, convert_axes, dtype, float_frame): assert_json_roundtrip_equal(result, expected, orient) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("dtype", [False, np.int64]) @pytest.mark.parametrize("convert_axes", [True, False]) def test_roundtrip_intframe(self, orient, convert_axes, dtype, int_frame): @@ -281,7 +280,6 @@ def test_roundtrip_empty(self, orient, convert_axes): tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("convert_axes", [True, False]) def test_roundtrip_timestamp(self, orient, convert_axes, datetime_frame): # TODO: improve coverage with date_format parameter @@ -709,7 +707,6 @@ def test_series_roundtrip_simple(self, orient, string_series, using_infer_string tm.assert_series_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @pytest.mark.parametrize("dtype", [False, None]) def test_series_roundtrip_object(self, orient, dtype, object_series): data = StringIO(object_series.to_json(orient=orient)) @@ -721,6 +718,9 @@ def test_series_roundtrip_object(self, orient, dtype, object_series): if orient != "split": expected.name = None + if using_string_dtype(): + expected = expected.astype("str") + tm.assert_series_equal(result, expected) def test_series_roundtrip_empty(self, orient): @@ -814,7 +814,6 @@ def test_path(self, float_frame, int_frame, datetime_frame): df.to_json(path) read_json(path) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_axis_dates(self, datetime_series, datetime_frame): # frame json = StringIO(datetime_frame.to_json()) @@ -827,7 +826,6 @@ def test_axis_dates(self, datetime_series, datetime_frame): tm.assert_series_equal(result, datetime_series, check_names=False) assert result.name is None - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_convert_dates(self, datetime_series, datetime_frame): # frame df = datetime_frame @@ -898,7 +896,6 @@ def test_convert_dates_infer(self, infer_word): result = read_json(StringIO(ujson_dumps(data)))[["id", infer_word]] tm.assert_frame_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @pytest.mark.parametrize( "date,date_unit", [ @@ -959,7 +956,6 @@ def test_date_format_series_raises(self, datetime_series): with pytest.raises(ValueError, match=msg): ts.to_json(date_format="iso", date_unit="foo") - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @pytest.mark.parametrize("unit", ["s", "ms", "us", "ns"]) def test_date_unit(self, unit, datetime_frame): df = datetime_frame @@ -1065,7 +1061,6 @@ def test_round_trip_exception(self, datapath): res = res.fillna(np.nan, downcast=False) tm.assert_frame_equal(res, df) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.network @pytest.mark.single_cpu @pytest.mark.parametrize( @@ -1474,7 +1469,6 @@ def test_data_frame_size_after_to_json(self): assert size_before == size_after - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize( "index", [None, [1, 2], [1.0, 2.0], ["a", "b"], ["1", "2"], ["1.", "2."]] ) diff --git a/pandas/tests/io/parser/common/test_chunksize.py b/pandas/tests/io/parser/common/test_chunksize.py index 7b70601addcad..5226476ef6eac 100644 --- a/pandas/tests/io/parser/common/test_chunksize.py +++ b/pandas/tests/io/parser/common/test_chunksize.py @@ -7,8 +7,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas._libs import parsers as libparsers from pandas.errors import DtypeWarning @@ -230,8 +228,7 @@ def test_chunks_have_consistent_numerical_type(all_parsers, monkeypatch): assert result.a.dtype == float -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) -def test_warn_if_chunks_have_mismatched_type(all_parsers): +def test_warn_if_chunks_have_mismatched_type(all_parsers, using_infer_string): warning_type = None parser = all_parsers size = 10000 @@ -259,8 +256,12 @@ def test_warn_if_chunks_have_mismatched_type(all_parsers): "Specify dtype option on import or set low_memory=False.", buf, ) - - assert df.a.dtype == object + if parser.engine == "c" and parser.low_memory: + assert df.a.dtype == object + elif using_infer_string: + assert df.a.dtype == "str" + else: + assert df.a.dtype == object @pytest.mark.parametrize("iterator", [True, False]) diff --git a/pandas/tests/io/parser/common/test_file_buffer_url.py b/pandas/tests/io/parser/common/test_file_buffer_url.py index c13b77f365496..d573b47bb3279 100644 --- a/pandas/tests/io/parser/common/test_file_buffer_url.py +++ b/pandas/tests/io/parser/common/test_file_buffer_url.py @@ -14,8 +14,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.errors import ( EmptyDataError, ParserError, @@ -69,14 +67,13 @@ def test_local_file(all_parsers, csv_dir_path): pytest.skip("Failing on: " + " ".join(platform.uname())) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @xfail_pyarrow # AssertionError: DataFrame.index are different def test_path_path_lib(all_parsers): parser = all_parsers df = DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=Index(list("ABCD"), dtype=object), - index=Index([f"i-{i}" for i in range(30)], dtype=object), + columns=Index(list("ABCD")), + index=Index([f"i-{i}" for i in range(30)]), ) result = tm.round_trip_pathlib(df.to_csv, lambda p: parser.read_csv(p, index_col=0)) tm.assert_frame_equal(df, result) diff --git a/pandas/tests/io/parser/common/test_index.py b/pandas/tests/io/parser/common/test_index.py index 0121af53f1aa4..cdd65223a9c9f 100644 --- a/pandas/tests/io/parser/common/test_index.py +++ b/pandas/tests/io/parser/common/test_index.py @@ -8,8 +8,6 @@ import pytest -from pandas._config import using_string_dtype - from pandas import ( DataFrame, Index, @@ -87,9 +85,13 @@ def test_pass_names_with_index(all_parsers, data, kwargs, expected): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("index_col", [[0, 1], [1, 0]]) -def test_multi_index_no_level_names(all_parsers, index_col): +def test_multi_index_no_level_names( + request, all_parsers, index_col, using_infer_string +): + if using_infer_string and all_parsers.engine == "pyarrow": + # result should have string columns instead of object dtype + request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)")) data = """index1,index2,A,B,C,D foo,one,2,3,4,5 foo,two,7,8,9,10 diff --git a/pandas/tests/io/parser/dtypes/test_dtypes_basic.py b/pandas/tests/io/parser/dtypes/test_dtypes_basic.py index 787941c5d0376..d28c43c45647a 100644 --- a/pandas/tests/io/parser/dtypes/test_dtypes_basic.py +++ b/pandas/tests/io/parser/dtypes/test_dtypes_basic.py @@ -8,8 +8,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.errors import ParserWarning import pandas as pd @@ -24,6 +22,8 @@ "ignore:Passing a BlockManager to DataFrame:DeprecationWarning" ) +xfail_pyarrow = pytest.mark.usefixtures("pyarrow_xfail") + @pytest.mark.parametrize("dtype", [str, object]) @pytest.mark.parametrize("check_orig", [True, False]) @@ -54,7 +54,6 @@ def test_dtype_all_columns(all_parsers, dtype, check_orig, using_infer_string): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @pytest.mark.usefixtures("pyarrow_xfail") def test_dtype_per_column(all_parsers): parser = all_parsers @@ -68,7 +67,6 @@ def test_dtype_per_column(all_parsers): [[1, "2.5"], [2, "3.5"], [3, "4.5"], [4, "5.5"]], columns=["one", "two"] ) expected["one"] = expected["one"].astype(np.float64) - expected["two"] = expected["two"].astype(object) result = parser.read_csv(StringIO(data), dtype={"one": np.float64, 1: str}) tm.assert_frame_equal(result, expected) @@ -598,6 +596,7 @@ def test_string_inference_object_dtype(all_parsers, dtype, using_infer_string): tm.assert_frame_equal(result, expected) +@xfail_pyarrow def test_accurate_parsing_of_large_integers(all_parsers): # GH#52505 data = """SYMBOL,MOMENT,ID,ID_DEAL @@ -608,7 +607,7 @@ def test_accurate_parsing_of_large_integers(all_parsers): AMZN,20230301181139587,2023552585717889759,2023552585717263360 MSFT,20230301181139587,2023552585717889863,2023552585717263361 NVDA,20230301181139587,2023552585717889827,2023552585717263361""" - orders = pd.read_csv(StringIO(data), dtype={"ID_DEAL": pd.Int64Dtype()}) + orders = all_parsers.read_csv(StringIO(data), dtype={"ID_DEAL": pd.Int64Dtype()}) assert len(orders.loc[orders["ID_DEAL"] == 2023552585717263358, "ID_DEAL"]) == 1 assert len(orders.loc[orders["ID_DEAL"] == 2023552585717263359, "ID_DEAL"]) == 1 assert len(orders.loc[orders["ID_DEAL"] == 2023552585717263360, "ID_DEAL"]) == 2 @@ -630,3 +629,16 @@ def test_dtypes_with_usecols(all_parsers): values = ["1", "4"] expected = DataFrame({"a": pd.Series(values, dtype=object), "c": [3, 6]}) tm.assert_frame_equal(result, expected) + + +def test_index_col_with_dtype_no_rangeindex(all_parsers): + data = StringIO("345.5,519.5,0\n519.5,726.5,1") + result = all_parsers.read_csv( + data, + header=None, + names=["start", "stop", "bin_id"], + dtype={"start": np.float32, "stop": np.float32, "bin_id": np.uint32}, + index_col="bin_id", + ).index + expected = pd.Index([0, 1], dtype=np.uint32, name="bin_id") + tm.assert_index_equal(result, expected) diff --git a/pandas/tests/io/parser/test_c_parser_only.py b/pandas/tests/io/parser/test_c_parser_only.py index 1501479510e17..5b72f76440349 100644 --- a/pandas/tests/io/parser/test_c_parser_only.py +++ b/pandas/tests/io/parser/test_c_parser_only.py @@ -17,8 +17,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.compat.numpy import np_version_gte1p24 from pandas.errors import ( ParserError, @@ -185,8 +183,7 @@ def error(val: float, actual_val: Decimal) -> Decimal: assert max(precise_errors) <= max(normal_errors) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") -def test_usecols_dtypes(c_parser_only): +def test_usecols_dtypes(c_parser_only, using_infer_string): parser = c_parser_only data = """\ 1,2,3 @@ -211,8 +208,12 @@ def test_usecols_dtypes(c_parser_only): dtype={"b": int, "c": float}, ) - assert (result.dtypes == [object, int, float]).all() - assert (result2.dtypes == [object, float]).all() + if using_infer_string: + assert (result.dtypes == ["string", int, float]).all() + assert (result2.dtypes == ["string", float]).all() + else: + assert (result.dtypes == [object, int, float]).all() + assert (result2.dtypes == [object, float]).all() def test_disable_bool_parsing(c_parser_only): diff --git a/pandas/tests/io/parser/test_converters.py b/pandas/tests/io/parser/test_converters.py index a3c6dc8fd0898..1848e1e571fc1 100644 --- a/pandas/tests/io/parser/test_converters.py +++ b/pandas/tests/io/parser/test_converters.py @@ -8,8 +8,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - import pandas as pd from pandas import ( DataFrame, @@ -186,7 +184,6 @@ def convert_score(x): tm.assert_frame_equal(results[0], results[1]) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("conv_f", [lambda x: x, str]) def test_converter_index_col_bug(all_parsers, conv_f): # see gh-1835 , GH#40589 @@ -205,7 +202,7 @@ def test_converter_index_col_bug(all_parsers, conv_f): StringIO(data), sep=";", index_col="A", converters={"A": conv_f} ) - xp = DataFrame({"B": [2, 4]}, index=Index(["1", "3"], name="A", dtype="object")) + xp = DataFrame({"B": [2, 4]}, index=Index(["1", "3"], name="A")) tm.assert_frame_equal(rs, xp) diff --git a/pandas/tests/io/parser/test_index_col.py b/pandas/tests/io/parser/test_index_col.py index 6dbfed2b6ae83..9224b743b8917 100644 --- a/pandas/tests/io/parser/test_index_col.py +++ b/pandas/tests/io/parser/test_index_col.py @@ -8,8 +8,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas import ( DataFrame, Index, @@ -344,7 +342,6 @@ def test_infer_types_boolean_sum(all_parsers): tm.assert_frame_equal(result, expected, check_index_type=False) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("dtype, val", [(object, "01"), ("int64", 1)]) def test_specify_dtype_for_index_col(all_parsers, dtype, val, request): # GH#9435 @@ -355,7 +352,7 @@ def test_specify_dtype_for_index_col(all_parsers, dtype, val, request): pytest.mark.xfail(reason="Cannot disable type-inference for pyarrow engine") ) result = parser.read_csv(StringIO(data), index_col="a", dtype={"a": dtype}) - expected = DataFrame({"b": [2]}, index=Index([val], name="a")) + expected = DataFrame({"b": [2]}, index=Index([val], name="a", dtype=dtype)) tm.assert_frame_equal(result, expected) diff --git a/pandas/tests/io/parser/test_mangle_dupes.py b/pandas/tests/io/parser/test_mangle_dupes.py index 32a8d3b81f470..80c32d3a6262e 100644 --- a/pandas/tests/io/parser/test_mangle_dupes.py +++ b/pandas/tests/io/parser/test_mangle_dupes.py @@ -7,9 +7,10 @@ import pytest -from pandas._config import using_string_dtype - -from pandas import DataFrame +from pandas import ( + DataFrame, + Index, +) import pandas._testing as tm xfail_pyarrow = pytest.mark.usefixtures("pyarrow_xfail") @@ -120,7 +121,6 @@ def test_thorough_mangle_names(all_parsers, data, names, expected): parser.read_csv(StringIO(data), names=names) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @xfail_pyarrow # AssertionError: DataFrame.columns are different def test_mangled_unnamed_placeholders(all_parsers): # xref gh-13017 @@ -132,7 +132,7 @@ def test_mangled_unnamed_placeholders(all_parsers): # This test recursively updates `df`. for i in range(3): - expected = DataFrame() + expected = DataFrame(columns=Index([], dtype="str")) for j in range(i + 1): col_name = "Unnamed: 0" + f".{1*j}" * min(j, 1) diff --git a/pandas/tests/io/parser/test_na_values.py b/pandas/tests/io/parser/test_na_values.py index 5f9823f7225f9..dd168aaa45808 100644 --- a/pandas/tests/io/parser/test_na_values.py +++ b/pandas/tests/io/parser/test_na_values.py @@ -7,8 +7,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas._libs.parsers import STR_NA_VALUES from pandas import ( @@ -260,7 +258,6 @@ def test_na_value_dict_multi_index(all_parsers, index_col, expected): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize( "kwargs,expected", [ @@ -306,7 +303,9 @@ def test_na_value_dict_multi_index(all_parsers, index_col, expected): ), ], ) -def test_na_values_keep_default(all_parsers, kwargs, expected, request): +def test_na_values_keep_default( + all_parsers, kwargs, expected, request, using_infer_string +): data = """\ A,B,C a,1,one @@ -324,8 +323,9 @@ def test_na_values_keep_default(all_parsers, kwargs, expected, request): with pytest.raises(ValueError, match=msg): parser.read_csv(StringIO(data), **kwargs) return - mark = pytest.mark.xfail() - request.applymarker(mark) + if not using_infer_string or "na_values" in kwargs: + mark = pytest.mark.xfail() + request.applymarker(mark) result = parser.read_csv(StringIO(data), **kwargs) tm.assert_frame_equal(result, expected) @@ -435,8 +435,6 @@ def test_no_keep_default_na_dict_na_values_diff_reprs(all_parsers, col_zero_na_v tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) -@xfail_pyarrow # mismatched dtypes in both cases, FutureWarning in the True case @pytest.mark.parametrize( "na_filter,row_data", [ @@ -444,14 +442,21 @@ def test_no_keep_default_na_dict_na_values_diff_reprs(all_parsers, col_zero_na_v (False, [["1", "A"], ["nan", "B"], ["3", "C"]]), ], ) -def test_na_values_na_filter_override(all_parsers, na_filter, row_data): +def test_na_values_na_filter_override( + request, all_parsers, na_filter, row_data, using_infer_string +): + parser = all_parsers + if parser.engine == "pyarrow": + # mismatched dtypes in both cases, FutureWarning in the True case + if not (using_infer_string and na_filter): + mark = pytest.mark.xfail(reason="pyarrow doesn't support this.") + request.applymarker(mark) data = """\ A,B 1,A nan,B 3,C """ - parser = all_parsers result = parser.read_csv(StringIO(data), na_values=["B"], na_filter=na_filter) expected = DataFrame(row_data, columns=["A", "B"]) diff --git a/pandas/tests/io/parser/test_parse_dates.py b/pandas/tests/io/parser/test_parse_dates.py index be2015fca27d1..616fcb81cf055 100644 --- a/pandas/tests/io/parser/test_parse_dates.py +++ b/pandas/tests/io/parser/test_parse_dates.py @@ -16,8 +16,6 @@ import pytest import pytz -from pandas._config import using_string_dtype - from pandas._libs.tslibs import parsing import pandas as pd @@ -1799,7 +1797,6 @@ def test_parse_timezone(all_parsers): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @skip_pyarrow # pandas.errors.ParserError: CSV parse error @pytest.mark.parametrize( "date_string", @@ -1807,7 +1804,7 @@ def test_parse_timezone(all_parsers): ) def test_invalid_parse_delimited_date(all_parsers, date_string): parser = all_parsers - expected = DataFrame({0: [date_string]}, dtype="object") + expected = DataFrame({0: [date_string]}, dtype="str") result = parser.read_csv( StringIO(date_string), header=None, @@ -2054,7 +2051,6 @@ def test_parse_dates_and_keep_original_column(all_parsers): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_dayfirst_warnings(): # GH 12585 @@ -2087,7 +2083,7 @@ def test_dayfirst_warnings(): # first in DD/MM/YYYY, second in MM/DD/YYYY input = "date\n31/12/2014\n03/30/2011" - expected = Index(["31/12/2014", "03/30/2011"], dtype="object", name="date") + expected = Index(["31/12/2014", "03/30/2011"], dtype="str", name="date") # A. use dayfirst=True res5 = read_csv( @@ -2204,7 +2200,6 @@ def test_parse_dates_and_string_dtype(all_parsers): tm.assert_frame_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) def test_parse_dot_separated_dates(all_parsers): # https://github.com/pandas-dev/pandas/issues/2586 parser = all_parsers @@ -2214,7 +2209,7 @@ def test_parse_dot_separated_dates(all_parsers): if parser.engine == "pyarrow": expected_index = Index( ["27.03.2003 14:55:00.000", "03.08.2003 15:20:00.000"], - dtype="object", + dtype="str", name="a", ) warn = None diff --git a/pandas/tests/io/parser/test_upcast.py b/pandas/tests/io/parser/test_upcast.py index 01e576ba40f26..bc4c4c2e24e9c 100644 --- a/pandas/tests/io/parser/test_upcast.py +++ b/pandas/tests/io/parser/test_upcast.py @@ -1,8 +1,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas._libs.parsers import ( _maybe_upcast, na_values, @@ -86,7 +84,6 @@ def test_maybe_upcaste_all_nan(): tm.assert_extension_array_equal(result, expected) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) @pytest.mark.parametrize("val", [na_values[np.object_], "c"]) def test_maybe_upcast_object(val, string_storage): # GH#36712 diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py index 3a52ff5acc0b3..a16c63e8d3d65 100644 --- a/pandas/tests/io/test_clipboard.py +++ b/pandas/tests/io/test_clipboard.py @@ -3,8 +3,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.errors import ( PyperclipException, PyperclipWindowsException, @@ -26,10 +24,6 @@ init_qt_clipboard, ) -pytestmark = pytest.mark.xfail( - using_string_dtype(), reason="TODO(infer_string)", strict=False -) - def build_kwargs(sep, excel): kwargs = {} @@ -351,7 +345,7 @@ def test_raw_roundtrip(self, data): @pytest.mark.parametrize("engine", ["c", "python"]) def test_read_clipboard_dtype_backend( - self, clipboard, string_storage, dtype_backend, engine + self, clipboard, string_storage, dtype_backend, engine, using_infer_string ): # GH#50502 if dtype_backend == "pyarrow": @@ -396,6 +390,11 @@ def test_read_clipboard_dtype_backend( ) expected["g"] = ArrowExtensionArray(pa.array([None, None])) + if using_infer_string: + expected.columns = expected.columns.astype( + pd.StringDtype(string_storage, na_value=np.nan) + ) + tm.assert_frame_equal(result, expected) def test_invalid_dtype_backend(self): diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py index d38f716cf6a98..d1e42b297f143 100644 --- a/pandas/tests/io/test_common.py +++ b/pandas/tests/io/test_common.py @@ -154,7 +154,6 @@ def test_bytesiowrapper_returns_correct_bytes(self): assert result == data.encode("utf-8") # Test that pyarrow can handle a file opened with get_handle - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_get_handle_pyarrow_compat(self): pa_csv = pytest.importorskip("pyarrow.csv") @@ -169,6 +168,8 @@ def test_get_handle_pyarrow_compat(self): s = StringIO(data) with icom.get_handle(s, "rb", is_text=False) as handles: df = pa_csv.read_csv(handles.handle).to_pandas() + # TODO will have to update this when pyarrow' to_pandas() is fixed + expected = expected.astype("object") tm.assert_frame_equal(df, expected) assert not s.closed @@ -352,7 +353,6 @@ def test_read_fspath_all(self, reader, module, path, datapath): ("to_stata", {"time_stamp": pd.to_datetime("2019-01-01 00:00")}, "os"), ], ) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False) def test_write_fspath_all(self, writer_name, writer_kwargs, module): if writer_name in ["to_latex"]: # uses Styler implementation pytest.importorskip("jinja2") @@ -379,7 +379,7 @@ def test_write_fspath_all(self, writer_name, writer_kwargs, module): expected = f_path.read() assert result == expected - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") + @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string) hdf support") def test_write_fspath_hdf5(self): # Same test as write_fspath_all, except HDF5 files aren't # necessarily byte-for-byte identical for a given dataframe, so we'll @@ -450,14 +450,13 @@ def test_unknown_engine(self): with tm.ensure_clean() as path: df = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) df.to_csv(path) with pytest.raises(ValueError, match="Unknown engine"): pd.read_csv(path, engine="pyt") - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_binary_mode(self): """ 'encoding' shouldn't be passed to 'open' in binary mode. @@ -467,8 +466,8 @@ def test_binary_mode(self): with tm.ensure_clean() as path: df = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) df.to_csv(path, mode="w+b") tm.assert_frame_equal(df, pd.read_csv(path, index_col=0)) @@ -485,8 +484,8 @@ def test_warning_missing_utf_bom(self, encoding, compression_): """ df = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) with tm.ensure_clean() as path: with tm.assert_produces_warning(UnicodeWarning): @@ -516,15 +515,14 @@ def test_is_fsspec_url(): assert icom.is_fsspec_url("RFC-3986+compliant.spec://something") -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @pytest.mark.parametrize("encoding", [None, "utf-8"]) @pytest.mark.parametrize("format", ["csv", "json"]) def test_codecs_encoding(encoding, format): # GH39247 expected = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) with tm.ensure_clean() as path: with codecs.open(path, mode="w", encoding=encoding) as handle: @@ -537,13 +535,12 @@ def test_codecs_encoding(encoding, format): tm.assert_frame_equal(expected, df) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_codecs_get_writer_reader(): # GH39247 expected = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) with tm.ensure_clean() as path: with open(path, "wb") as handle: @@ -568,8 +565,8 @@ def test_explicit_encoding(io_class, mode, msg): # wrong mode is requested expected = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) with io_class() as buffer: with pytest.raises(TypeError, match=msg): diff --git a/pandas/tests/io/test_compression.py b/pandas/tests/io/test_compression.py index 25504c7b88fdb..af89f0916355e 100644 --- a/pandas/tests/io/test_compression.py +++ b/pandas/tests/io/test_compression.py @@ -12,8 +12,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.compat import is_platform_windows import pandas as pd @@ -139,7 +137,6 @@ def test_compression_warning(compression_only): df.to_csv(handles.handle, compression=compression_only) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_compression_binary(compression_only): """ Binary file handles support compression. @@ -148,8 +145,8 @@ def test_compression_binary(compression_only): """ df = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) # with a file @@ -180,8 +177,8 @@ def test_gzip_reproducibility_file_name(): """ df = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) compression_options = {"method": "gzip", "mtime": 1} @@ -203,8 +200,8 @@ def test_gzip_reproducibility_file_object(): """ df = pd.DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=pd.Index(list("ABCD"), dtype=object), - index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + columns=pd.Index(list("ABCD")), + index=pd.Index([f"i-{i}" for i in range(30)]), ) compression_options = {"method": "gzip", "mtime": 1} diff --git a/pandas/tests/io/test_feather.py b/pandas/tests/io/test_feather.py index 3b4484e44e155..58a5f78ce3258 100644 --- a/pandas/tests/io/test_feather.py +++ b/pandas/tests/io/test_feather.py @@ -2,6 +2,8 @@ import numpy as np import pytest +from pandas.compat.pyarrow import pa_version_under18p0 + import pandas as pd import pandas._testing as tm @@ -250,3 +252,21 @@ def test_string_inference(self, tmp_path): data={"a": ["x", "y"]}, dtype=pd.StringDtype(na_value=np.nan) ) tm.assert_frame_equal(result, expected) + + @pytest.mark.skipif(pa_version_under18p0, reason="not supported before 18.0") + def test_string_inference_string_view_type(self, tmp_path): + # GH#54798 + import pyarrow as pa + from pyarrow import feather + + path = tmp_path / "string_view.parquet" + table = pa.table({"a": pa.array([None, "b", "c"], pa.string_view())}) + feather.write_feather(table, path) + + with pd.option_context("future.infer_string", True): + result = read_feather(path) + + expected = pd.DataFrame( + data={"a": [None, "b", "c"]}, dtype=pd.StringDtype(na_value=np.nan) + ) + tm.assert_frame_equal(result, expected) diff --git a/pandas/tests/io/test_fsspec.py b/pandas/tests/io/test_fsspec.py index 5ed64e3eb0958..cf59e3e4c4934 100644 --- a/pandas/tests/io/test_fsspec.py +++ b/pandas/tests/io/test_fsspec.py @@ -5,6 +5,8 @@ from pandas._config import using_string_dtype +from pandas.compat import HAS_PYARROW + from pandas import ( DataFrame, date_range, @@ -168,7 +170,9 @@ def test_excel_options(fsspectest): assert fsspectest.test[0] == "read" -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string) fastparquet") +@pytest.mark.xfail( + using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string) fastparquet" +) def test_to_parquet_new_file(cleared_fs, df1): """Regression test for writing to a not-yet-existent GCS Parquet file.""" pytest.importorskip("fastparquet") diff --git a/pandas/tests/io/test_gcs.py b/pandas/tests/io/test_gcs.py index 81f951b3958b0..9fc0f6eb47766 100644 --- a/pandas/tests/io/test_gcs.py +++ b/pandas/tests/io/test_gcs.py @@ -7,8 +7,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - from pandas.compat.pyarrow import pa_version_under17p0 from pandas import ( @@ -147,7 +145,6 @@ def assert_equal_zip_safe(result: bytes, expected: bytes, compression: str): assert result == expected -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") @pytest.mark.parametrize("encoding", ["utf-8", "cp1251"]) def test_to_csv_compression_encoding_gcs( gcs_buffer, compression_only, encoding, compression_to_extension @@ -160,8 +157,8 @@ def test_to_csv_compression_encoding_gcs( """ df = DataFrame( 1.1 * np.arange(120).reshape((30, 4)), - columns=Index(list("ABCD"), dtype=object), - index=Index([f"i-{i}" for i in range(30)], dtype=object), + columns=Index(list("ABCD")), + index=Index([f"i-{i}" for i in range(30)]), ) # reference of compressed and encoded file @@ -197,7 +194,6 @@ def test_to_csv_compression_encoding_gcs( tm.assert_frame_equal(df, read_df) -@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string) fastparquet") def test_to_parquet_gcs_new_file(monkeypatch, tmpdir): """Regression test for writing to a not-yet-existent GCS Parquet file.""" pytest.importorskip("fastparquet") diff --git a/pandas/tests/io/test_parquet.py b/pandas/tests/io/test_parquet.py index e43aae6a2e9e7..87f9b0108402c 100644 --- a/pandas/tests/io/test_parquet.py +++ b/pandas/tests/io/test_parquet.py @@ -1223,11 +1223,17 @@ def test_duplicate_columns(self, fp): msg = "Cannot create parquet dataset with duplicate column names" self.check_error_on_write(df, fp, ValueError, msg) - @pytest.mark.xfail( - Version(np.__version__) >= Version("2.0.0"), - reason="fastparquet uses np.float_ in numpy2", - ) - def test_bool_with_none(self, fp): + def test_bool_with_none(self, fp, request): + import fastparquet + + if Version(fastparquet.__version__) < Version("2024.11.0") and Version( + np.__version__ + ) >= Version("2.0.0"): + request.applymarker( + pytest.mark.xfail( + reason=("fastparquet uses np.float_ in numpy2"), + ) + ) df = pd.DataFrame({"a": [True, None, False]}) expected = pd.DataFrame({"a": [1.0, np.nan, 0.0]}, dtype="float16") # Fastparquet bug in 0.7.1 makes it so that this dtype becomes @@ -1342,12 +1348,21 @@ def test_empty_dataframe(self, fp): expected = df.copy() check_round_trip(df, fp, expected=expected) - @pytest.mark.xfail( - _HAVE_FASTPARQUET and Version(fastparquet.__version__) > Version("2022.12"), - reason="fastparquet bug, see https://github.com/dask/fastparquet/issues/929", - ) - @pytest.mark.skipif(using_copy_on_write(), reason="fastparquet writes into Index") - def test_timezone_aware_index(self, fp, timezone_aware_date_list): + def test_timezone_aware_index(self, fp, timezone_aware_date_list, request): + import fastparquet + + if Version(fastparquet.__version__) > Version("2022.12") and Version( + fastparquet.__version__ + ) < Version("2024.11.0"): + request.applymarker( + pytest.mark.xfail( + reason=( + "fastparquet bug, see " + "https://github.com/dask/fastparquet/issues/929" + ), + ) + ) + idx = 5 * [timezone_aware_date_list] df = pd.DataFrame(index=idx, data={"index_as_col": idx}) diff --git a/pandas/tests/io/test_sql.py b/pandas/tests/io/test_sql.py index 514eaceaccbe6..3676721c5e6b7 100644 --- a/pandas/tests/io/test_sql.py +++ b/pandas/tests/io/test_sql.py @@ -63,7 +63,7 @@ pytest.mark.filterwarnings( "ignore:Passing a BlockManager to DataFrame:DeprecationWarning" ), - pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False), + pytest.mark.single_cpu, ] @@ -685,6 +685,7 @@ def postgresql_psycopg2_conn(postgresql_psycopg2_engine): @pytest.fixture def postgresql_adbc_conn(): + pytest.importorskip("pyarrow") pytest.importorskip("adbc_driver_postgresql") from adbc_driver_postgresql import dbapi @@ -817,6 +818,7 @@ def sqlite_conn_types(sqlite_engine_types): @pytest.fixture def sqlite_adbc_conn(): + pytest.importorskip("pyarrow") pytest.importorskip("adbc_driver_sqlite") from adbc_driver_sqlite import dbapi @@ -957,12 +959,12 @@ def sqlite_buildin_types(sqlite_buildin, types_data): adbc_connectable_iris = [ pytest.param("postgresql_adbc_iris", marks=pytest.mark.db), - pytest.param("sqlite_adbc_iris", marks=pytest.mark.db), + "sqlite_adbc_iris", ] adbc_connectable_types = [ pytest.param("postgresql_adbc_types", marks=pytest.mark.db), - pytest.param("sqlite_adbc_types", marks=pytest.mark.db), + "sqlite_adbc_types", ] @@ -986,13 +988,13 @@ def test_dataframe_to_sql(conn, test_frame1, request): @pytest.mark.parametrize("conn", all_connectable) def test_dataframe_to_sql_empty(conn, test_frame1, request): - if conn == "postgresql_adbc_conn": + if conn == "postgresql_adbc_conn" and not using_string_dtype(): request.node.add_marker( pytest.mark.xfail( - reason="postgres ADBC driver cannot insert index with null type", - strict=True, + reason="postgres ADBC driver < 1.2 cannot insert index with null type", ) ) + # GH 51086 if conn is sqlite_engine conn = request.getfixturevalue(conn) empty_df = test_frame1.iloc[:0] @@ -3571,7 +3573,8 @@ def test_read_sql_dtype_backend( result = getattr(pd, func)( f"Select * from {table}", conn, dtype_backend=dtype_backend ) - expected = dtype_backend_expected(string_storage, dtype_backend, conn_name) + expected = dtype_backend_expected(string_storage, dtype_backend, conn_name) + tm.assert_frame_equal(result, expected) if "adbc" in conn_name: @@ -3621,7 +3624,7 @@ def test_read_sql_dtype_backend_table( with pd.option_context("mode.string_storage", string_storage): result = getattr(pd, func)(table, conn, dtype_backend=dtype_backend) - expected = dtype_backend_expected(string_storage, dtype_backend, conn_name) + expected = dtype_backend_expected(string_storage, dtype_backend, conn_name) tm.assert_frame_equal(result, expected) if "adbc" in conn_name: @@ -4150,7 +4153,7 @@ def tquery(query, con=None): def test_xsqlite_basic(sqlite_buildin): frame = DataFrame( np.random.default_rng(2).standard_normal((10, 4)), - columns=Index(list("ABCD"), dtype=object), + columns=Index(list("ABCD")), index=date_range("2000-01-01", periods=10, freq="B"), ) assert sql.to_sql(frame, name="test_table", con=sqlite_buildin, index=False) == 10 @@ -4177,7 +4180,7 @@ def test_xsqlite_basic(sqlite_buildin): def test_xsqlite_write_row_by_row(sqlite_buildin): frame = DataFrame( np.random.default_rng(2).standard_normal((10, 4)), - columns=Index(list("ABCD"), dtype=object), + columns=Index(list("ABCD")), index=date_range("2000-01-01", periods=10, freq="B"), ) frame.iloc[0, 0] = np.nan @@ -4200,7 +4203,7 @@ def test_xsqlite_write_row_by_row(sqlite_buildin): def test_xsqlite_execute(sqlite_buildin): frame = DataFrame( np.random.default_rng(2).standard_normal((10, 4)), - columns=Index(list("ABCD"), dtype=object), + columns=Index(list("ABCD")), index=date_range("2000-01-01", periods=10, freq="B"), ) create_sql = sql.get_schema(frame, "test") @@ -4221,7 +4224,7 @@ def test_xsqlite_execute(sqlite_buildin): def test_xsqlite_schema(sqlite_buildin): frame = DataFrame( np.random.default_rng(2).standard_normal((10, 4)), - columns=Index(list("ABCD"), dtype=object), + columns=Index(list("ABCD")), index=date_range("2000-01-01", periods=10, freq="B"), ) create_sql = sql.get_schema(frame, "test") diff --git a/pandas/tests/plotting/frame/test_frame.py b/pandas/tests/plotting/frame/test_frame.py index 4ca4067214bbd..33366b4eabba5 100644 --- a/pandas/tests/plotting/frame/test_frame.py +++ b/pandas/tests/plotting/frame/test_frame.py @@ -1059,28 +1059,43 @@ def test_boxplot_series_positions(self, hist_df): tm.assert_numpy_array_equal(ax.xaxis.get_ticklocs(), positions) assert len(ax.lines) == 7 * len(numeric_cols) + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") + @pytest.mark.xfail( + Version(mpl.__version__) >= Version("3.10"), + reason="Fails starting with matplotlib 3.10", + ) def test_boxplot_vertical(self, hist_df): df = hist_df numeric_cols = df._get_numeric_data().columns labels = [pprint_thing(c) for c in numeric_cols] # if horizontal, yticklabels are rotated - ax = df.plot.box(rot=50, fontsize=8, vert=False) + kwargs = ( + {"vert": False} + if Version(mpl.__version__) < Version("3.10") + else {"orientation": "horizontal"} + ) + ax = df.plot.box(rot=50, fontsize=8, **kwargs) _check_ticks_props(ax, xrot=0, yrot=50, ylabelsize=8) _check_text_labels(ax.get_yticklabels(), labels) assert len(ax.lines) == 7 * len(numeric_cols) - @pytest.mark.filterwarnings("ignore:Attempt:UserWarning") + @pytest.mark.filterwarnings("ignore::UserWarning") + @pytest.mark.xfail( + Version(mpl.__version__) >= Version("3.10"), + reason="Fails starting with matplotlib version 3.10", + ) def test_boxplot_vertical_subplots(self, hist_df): df = hist_df numeric_cols = df._get_numeric_data().columns labels = [pprint_thing(c) for c in numeric_cols] + kwargs = ( + {"vert": False} + if Version(mpl.__version__) < Version("3.10") + else {"orientation": "horizontal"} + ) axes = _check_plot_works( - df.plot.box, - default_axes=True, - subplots=True, - vert=False, - logx=True, + df.plot.box, default_axes=True, subplots=True, logx=True, **kwargs ) _check_axes_shape(axes, axes_num=3, layout=(1, 3)) _check_ax_scales(axes, xaxis="log") @@ -1088,12 +1103,22 @@ def test_boxplot_vertical_subplots(self, hist_df): _check_text_labels(ax.get_yticklabels(), [label]) assert len(ax.lines) == 7 + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") + @pytest.mark.xfail( + Version(mpl.__version__) >= Version("3.10"), + reason="Fails starting with matplotlib 3.10", + ) def test_boxplot_vertical_positions(self, hist_df): df = hist_df numeric_cols = df._get_numeric_data().columns labels = [pprint_thing(c) for c in numeric_cols] positions = np.array([3, 2, 8]) - ax = df.plot.box(positions=positions, vert=False) + kwargs = ( + {"vert": False} + if Version(mpl.__version__) < Version("3.10") + else {"orientation": "horizontal"} + ) + ax = df.plot.box(positions=positions, **kwargs) _check_text_labels(ax.get_yticklabels(), labels) tm.assert_numpy_array_equal(ax.yaxis.get_ticklocs(), positions) assert len(ax.lines) == 7 * len(numeric_cols) diff --git a/pandas/tests/plotting/test_boxplot_method.py b/pandas/tests/plotting/test_boxplot_method.py index 76f7fa1f22eec..e1b03a34086c0 100644 --- a/pandas/tests/plotting/test_boxplot_method.py +++ b/pandas/tests/plotting/test_boxplot_method.py @@ -1,5 +1,7 @@ """ Test cases for .boxplot method """ +from __future__ import annotations + import itertools import string @@ -22,6 +24,7 @@ _check_ticks_props, _check_visible, ) +from pandas.util.version import Version from pandas.io.formats.printing import pprint_thing @@ -35,6 +38,17 @@ def _check_ax_limits(col, ax): assert y_max >= col.max() +if Version(mpl.__version__) < Version("3.10"): + verts: list[dict[str, bool | str]] = [{"vert": False}, {"vert": True}] +else: + verts = [{"orientation": "horizontal"}, {"orientation": "vertical"}] + + +@pytest.fixture(params=verts) +def vert(request): + return request.param + + class TestDataFramePlots: def test_stacked_boxplot_set_axis(self): # GH2980 @@ -315,7 +329,7 @@ def test_specified_props_kwd(self, props, expected): assert result[expected][0].get_color() == "C1" - @pytest.mark.parametrize("vert", [True, False]) + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") def test_plot_xlabel_ylabel(self, vert): df = DataFrame( { @@ -325,11 +339,11 @@ def test_plot_xlabel_ylabel(self, vert): } ) xlabel, ylabel = "x", "y" - ax = df.plot(kind="box", vert=vert, xlabel=xlabel, ylabel=ylabel) + ax = df.plot(kind="box", xlabel=xlabel, ylabel=ylabel, **vert) assert ax.get_xlabel() == xlabel assert ax.get_ylabel() == ylabel - @pytest.mark.parametrize("vert", [True, False]) + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") def test_plot_box(self, vert): # GH 54941 rng = np.random.default_rng(2) @@ -338,14 +352,14 @@ def test_plot_box(self, vert): xlabel, ylabel = "x", "y" _, axs = plt.subplots(ncols=2, figsize=(10, 7), sharey=True) - df1.plot.box(ax=axs[0], vert=vert, xlabel=xlabel, ylabel=ylabel) - df2.plot.box(ax=axs[1], vert=vert, xlabel=xlabel, ylabel=ylabel) + df1.plot.box(ax=axs[0], xlabel=xlabel, ylabel=ylabel, **vert) + df2.plot.box(ax=axs[1], xlabel=xlabel, ylabel=ylabel, **vert) for ax in axs: assert ax.get_xlabel() == xlabel assert ax.get_ylabel() == ylabel mpl.pyplot.close() - @pytest.mark.parametrize("vert", [True, False]) + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") def test_boxplot_xlabel_ylabel(self, vert): df = DataFrame( { @@ -355,11 +369,11 @@ def test_boxplot_xlabel_ylabel(self, vert): } ) xlabel, ylabel = "x", "y" - ax = df.boxplot(vert=vert, xlabel=xlabel, ylabel=ylabel) + ax = df.boxplot(xlabel=xlabel, ylabel=ylabel, **vert) assert ax.get_xlabel() == xlabel assert ax.get_ylabel() == ylabel - @pytest.mark.parametrize("vert", [True, False]) + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") def test_boxplot_group_xlabel_ylabel(self, vert): df = DataFrame( { @@ -369,14 +383,20 @@ def test_boxplot_group_xlabel_ylabel(self, vert): } ) xlabel, ylabel = "x", "y" - ax = df.boxplot(by="group", vert=vert, xlabel=xlabel, ylabel=ylabel) + ax = df.boxplot(by="group", xlabel=xlabel, ylabel=ylabel, **vert) for subplot in ax: assert subplot.get_xlabel() == xlabel assert subplot.get_ylabel() == ylabel mpl.pyplot.close() - @pytest.mark.parametrize("vert", [True, False]) - def test_boxplot_group_no_xlabel_ylabel(self, vert): + @pytest.mark.filterwarnings("ignore:set_ticklabels:UserWarning") + def test_boxplot_group_no_xlabel_ylabel(self, vert, request): + if Version(mpl.__version__) >= Version("3.10") and vert == { + "orientation": "horizontal" + }: + request.applymarker( + pytest.mark.xfail(reason=f"{vert} fails starting with matplotlib 3.10") + ) df = DataFrame( { "a": np.random.default_rng(2).standard_normal(10), @@ -384,9 +404,14 @@ def test_boxplot_group_no_xlabel_ylabel(self, vert): "group": np.random.default_rng(2).choice(["group1", "group2"], 10), } ) - ax = df.boxplot(by="group", vert=vert) + ax = df.boxplot(by="group", **vert) for subplot in ax: - target_label = subplot.get_xlabel() if vert else subplot.get_ylabel() + target_label = ( + subplot.get_xlabel() + if vert == {"vert": True} # noqa: PLR1714 + or vert == {"orientation": "vertical"} + else subplot.get_ylabel() + ) assert target_label == pprint_thing(["group"]) mpl.pyplot.close() diff --git a/pandas/tests/reductions/test_reductions.py b/pandas/tests/reductions/test_reductions.py index ed2b01b09bb71..496b00a0547b7 100644 --- a/pandas/tests/reductions/test_reductions.py +++ b/pandas/tests/reductions/test_reductions.py @@ -7,10 +7,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - -from pandas.compat import HAS_PYARROW - import pandas as pd from pandas import ( Categorical, @@ -1246,10 +1242,6 @@ def test_idxminmax_object_dtype(self, using_infer_string): with pytest.raises(TypeError, match=msg): ser3.idxmin(skipna=False) - # TODO(infer_string) implement argmin/max for python string dtype - @pytest.mark.xfail( - using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)" - ) def test_idxminmax_object_frame(self): # GH#4279 df = DataFrame([["zimm", 2.5], ["biff", 1.0], ["bid", 12.0]]) diff --git a/pandas/tests/resample/test_resample_api.py b/pandas/tests/resample/test_resample_api.py index af4cf5d4ebae5..74d06117cbb4a 100644 --- a/pandas/tests/resample/test_resample_api.py +++ b/pandas/tests/resample/test_resample_api.py @@ -188,7 +188,7 @@ def test_api_compat_before_use(attr): getattr(rs, attr) -def tests_raises_on_nuisance(test_frame): +def tests_raises_on_nuisance(test_frame, using_infer_string): df = test_frame df["D"] = "foo" r = df.resample("h") @@ -198,6 +198,8 @@ def tests_raises_on_nuisance(test_frame): expected = r[["A", "B", "C"]].mean() msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): r.mean() result = r.mean(numeric_only=True) @@ -932,7 +934,9 @@ def test_end_and_end_day_origin( ("sem", lib.no_default, "could not convert string to float"), ], ) -def test_frame_downsample_method(method, numeric_only, expected_data): +def test_frame_downsample_method( + method, numeric_only, expected_data, using_infer_string +): # GH#46442 test if `numeric_only` behave as expected for DataFrameGroupBy index = date_range("2018-01-01", periods=2, freq="D") @@ -949,6 +953,11 @@ def test_frame_downsample_method(method, numeric_only, expected_data): if method in ("var", "mean", "median", "prod"): klass = TypeError msg = re.escape(f"agg function failed [how->{method},dtype->") + if using_infer_string: + msg = f"dtype 'str' does not support operation '{method}'" + elif method in ["sum", "std", "sem"] and using_infer_string: + klass = TypeError + msg = f"dtype 'str' does not support operation '{method}'" else: klass = ValueError msg = expected_data @@ -983,7 +992,9 @@ def test_frame_downsample_method(method, numeric_only, expected_data): ("last", lib.no_default, ["cat_2"]), ], ) -def test_series_downsample_method(method, numeric_only, expected_data): +def test_series_downsample_method( + method, numeric_only, expected_data, using_infer_string +): # GH#46442 test if `numeric_only` behave as expected for SeriesGroupBy index = date_range("2018-01-01", periods=2, freq="D") @@ -999,8 +1010,11 @@ def test_series_downsample_method(method, numeric_only, expected_data): func(**kwargs) elif method == "prod": msg = re.escape("agg function failed [how->prod,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'prod'" with pytest.raises(TypeError, match=msg): func(**kwargs) + else: result = func(**kwargs) expected = Series(expected_data, index=expected_index) diff --git a/pandas/tests/reshape/merge/test_join.py b/pandas/tests/reshape/merge/test_join.py index 9188521c71158..4b79860437f72 100644 --- a/pandas/tests/reshape/merge/test_join.py +++ b/pandas/tests/reshape/merge/test_join.py @@ -625,7 +625,7 @@ def test_join_non_unique_period_index(self): ) tm.assert_frame_equal(result, expected) - def test_mixed_type_join_with_suffix(self): + def test_mixed_type_join_with_suffix(self, using_infer_string): # GH #916 df = DataFrame( np.random.default_rng(2).standard_normal((20, 6)), @@ -636,6 +636,8 @@ def test_mixed_type_join_with_suffix(self): grouped = df.groupby("id") msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): grouped.mean() mn = grouped.mean(numeric_only=True) diff --git a/pandas/tests/reshape/test_cut.py b/pandas/tests/reshape/test_cut.py index 0811c69859c0d..cab2302b3d877 100644 --- a/pandas/tests/reshape/test_cut.py +++ b/pandas/tests/reshape/test_cut.py @@ -727,6 +727,7 @@ def test_cut_with_duplicated_index_lowest_included(): tm.assert_series_equal(result, expected) +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") def test_cut_with_nonexact_categorical_indices(): # GH 42424 diff --git a/pandas/tests/reshape/test_pivot.py b/pandas/tests/reshape/test_pivot.py index d0858a0ea5558..75268ccee1d8c 100644 --- a/pandas/tests/reshape/test_pivot.py +++ b/pandas/tests/reshape/test_pivot.py @@ -948,12 +948,14 @@ def test_margins(self, data): for value_col in table.columns.levels[0]: self._check_output(table[value_col], value_col, data) - def test_no_col(self, data): + def test_no_col(self, data, using_infer_string): # no col # to help with a buglet data.columns = [k * 2 for k in data.columns] msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): data.pivot_table(index=["AA", "BB"], margins=True, aggfunc="mean") table = data.drop(columns="CC").pivot_table( @@ -1003,7 +1005,7 @@ def test_no_col(self, data): ], ) def test_margin_with_only_columns_defined( - self, columns, aggfunc, values, expected_columns + self, columns, aggfunc, values, expected_columns, using_infer_string ): # GH 31016 df = DataFrame( @@ -1027,6 +1029,8 @@ def test_margin_with_only_columns_defined( ) if aggfunc != "sum": msg = re.escape("agg function failed [how->mean,dtype->") + if using_infer_string: + msg = "dtype 'str' does not support operation 'mean'" with pytest.raises(TypeError, match=msg): df.pivot_table(columns=columns, margins=True, aggfunc=aggfunc) if "B" not in columns: diff --git a/pandas/tests/series/indexing/test_setitem.py b/pandas/tests/series/indexing/test_setitem.py index d95ee99489076..85558e85494eb 100644 --- a/pandas/tests/series/indexing/test_setitem.py +++ b/pandas/tests/series/indexing/test_setitem.py @@ -34,7 +34,6 @@ concat, date_range, interval_range, - isna, period_range, timedelta_range, ) @@ -865,11 +864,6 @@ def test_series_where(self, obj, key, expected, warn, val, is_inplace): obj = obj.copy() arr = obj._values - if obj.dtype == "string" and not (isinstance(val, str) or isna(val)): - with pytest.raises(TypeError, match="Invalid value"): - obj.where(~mask, val) - return - res = obj.where(~mask, val) if val is NA and res.dtype == object: @@ -886,24 +880,16 @@ def test_index_where(self, obj, key, expected, warn, val): mask = np.zeros(obj.shape, dtype=bool) mask[key] = True - if obj.dtype == "string" and not (isinstance(val, str) or isna(val)): - with pytest.raises(TypeError, match="Invalid value"): - Index(obj, dtype=obj.dtype).where(~mask, val) - else: - res = Index(obj, dtype=obj.dtype).where(~mask, val) - expected_idx = Index(expected, dtype=expected.dtype) - tm.assert_index_equal(res, expected_idx) + res = Index(obj, dtype=obj.dtype).where(~mask, val) + expected_idx = Index(expected, dtype=expected.dtype) + tm.assert_index_equal(res, expected_idx) def test_index_putmask(self, obj, key, expected, warn, val): mask = np.zeros(obj.shape, dtype=bool) mask[key] = True - if obj.dtype == "string" and not (isinstance(val, str) or isna(val)): - with pytest.raises(TypeError, match="Invalid value"): - Index(obj, dtype=obj.dtype).putmask(mask, val) - else: - res = Index(obj, dtype=obj.dtype).putmask(mask, val) - tm.assert_index_equal(res, Index(expected, dtype=expected.dtype)) + res = Index(obj, dtype=obj.dtype).putmask(mask, val) + tm.assert_index_equal(res, Index(expected, dtype=expected.dtype)) @pytest.mark.parametrize( diff --git a/pandas/tests/series/methods/test_replace.py b/pandas/tests/series/methods/test_replace.py index 79a66526a0004..0c2e0fdc2616f 100644 --- a/pandas/tests/series/methods/test_replace.py +++ b/pandas/tests/series/methods/test_replace.py @@ -3,8 +3,6 @@ import numpy as np import pytest -from pandas._config import using_string_dtype - import pandas as pd import pandas._testing as tm from pandas.core.arrays import IntervalArray @@ -403,10 +401,6 @@ def test_replace_categorical(self, categorical, numeric, using_infer_string): ser = pd.Series(categorical) msg = "Downcasting behavior in `replace`" msg = "with CategoricalDtype is deprecated" - if using_infer_string: - with pytest.raises(TypeError, match="Invalid value"): - ser.replace({"A": 1, "B": 2}) - return with tm.assert_produces_warning(FutureWarning, match=msg): result = ser.replace({"A": 1, "B": 2}) expected = pd.Series(numeric).astype("category") @@ -745,13 +739,13 @@ def test_replace_regex_dtype_series(self, regex): tm.assert_series_equal(result, expected) @pytest.mark.parametrize("regex", [False, True]) - def test_replace_regex_dtype_series_string(self, regex, using_infer_string): - if not using_infer_string: - # then this is object dtype which is already tested above - return + def test_replace_regex_dtype_series_string(self, regex): series = pd.Series(["0"], dtype="str") - with pytest.raises(TypeError, match="Invalid value"): - series.replace(to_replace="0", value=1, regex=regex) + expected = pd.Series([1], dtype="int64") + msg = "Downcasting behavior in `replace`" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = series.replace(to_replace="0", value=1, regex=regex) + tm.assert_series_equal(result, expected) def test_replace_different_int_types(self, any_int_numpy_dtype): # GH#45311 @@ -772,7 +766,6 @@ def test_replace_value_none_dtype_numeric(self, val): expected = pd.Series([1, None], dtype=object) tm.assert_series_equal(result, expected) - @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)") def test_replace_change_dtype_series(self): # GH#25797 df = pd.DataFrame({"Test": ["0.5", True, "0.6"]}, dtype=object) diff --git a/pandas/tests/test_algos.py b/pandas/tests/test_algos.py index 97d6415e0de05..d1e69cfa2b4ee 100644 --- a/pandas/tests/test_algos.py +++ b/pandas/tests/test_algos.py @@ -1283,7 +1283,7 @@ def test_value_counts_nat(self): result_dt = algos.value_counts(dt) tm.assert_series_equal(result_dt, exp_dt) - exp_td = Series({np.timedelta64(10000): 1}, name="count") + exp_td = Series([1], index=[np.timedelta64(10000)], name="count") with tm.assert_produces_warning(FutureWarning, match=msg): result_td = algos.value_counts(td) tm.assert_series_equal(result_td, exp_td)