Merge branch 'master' into feature/series-info

pandas/core/frame.py

@@ -200,9 +200,15 @@
     nargsort,
 )
 
-from pandas.io.common import get_filepath_or_buffer
-from pandas.io.formats import console, format as fmt
-from pandas.io.formats.info import BaseInfo, DataFrameInfo
+from pandas.io.common import get_handle
+from pandas.io.formats import (
+    console,
+    format as fmt,
+)
+from pandas.io.formats.info import (
+    BaseInfo,
+    DataFrameInfo,
+)
 import pandas.plotting
 
 if TYPE_CHECKING:
@@ -3041,14 +3047,17 @@ def to_xml(
                 is used. By default, the setting in
                 ``pandas.options.display.max_info_columns`` is used."""
         ),
-        null_counts_sub=dedent(
+        show_counts_sub=dedent(
             """\
-            null_counts : bool, optional
+            show_counts : bool, optional
                 Whether to show the non-null counts. By default, this is shown
                 only if the DataFrame is smaller than
                 ``pandas.options.display.max_info_rows`` and
                 ``pandas.options.display.max_info_columns``. A value of True always
-                shows the counts, and False never shows the counts."""
+                shows the counts, and False never shows the counts.
+            null_counts : bool, optional
+                .. deprecated:: 1.2.0
+                    Use show_counts instead."""
         ),
         examples_sub=dedent(
             """\

pandas/core/series.py

@@ -140,7 +140,10 @@
 from pandas.core.tools.datetimes import to_datetime
 
 import pandas.io.formats.format as fmt
-from pandas.io.formats.info import BaseInfo, SeriesInfo
+from pandas.io.formats.info import (
+    BaseInfo,
+    SeriesInfo,
+)
 import pandas.plotting
 
 if TYPE_CHECKING:
@@ -4890,9 +4893,9 @@ def replace(
         klass="Series",
         type_sub="",
         max_cols_sub="",
-        null_counts_sub=dedent(
+        show_counts_sub=dedent(
             """\
-            null_counts : bool, default True
+            show_counts : bool, default True
                 Whether to show the non-null counts."""
         ),
         examples_sub=dedent(
@@ -4965,20 +4968,20 @@ def replace(
     @doc(BaseInfo.render)
     def info(
         self,
-        verbose: Optional[bool] = None,
-        buf: Optional[IO[str]] = None,
-        max_cols: Optional[int] = None,
-        memory_usage: Optional[Union[bool, str]] = None,
-        null_counts: bool = True,
+        verbose: bool | None = None,
+        buf: IO[str] | None = None,
+        max_cols: int | None = None,
+        memory_usage: bool | str | None = None,
+        show_counts: bool = True,
     ) -> None:
         return SeriesInfo(self, memory_usage).render(
             buf=buf,
             max_cols=max_cols,
             verbose=verbose,
-            show_counts=null_counts,
+            show_counts=show_counts,
         )
 
-    def _replace_single(self, to_replace, method, inplace, limit):
+    def _replace_single(self, to_replace, method: str, inplace: bool, limit):
         """
         Replaces values in a Series using the fill method specified when no
         replacement value is given in the replace method

pandas/io/formats/info.py

@@ -19,7 +19,7 @@
 
 from pandas._config import get_option
 
-from pandas._typing import Dtype, FrameOrSeriesUnion
+from pandas._typing import Dtype
 
 from pandas.core.indexes.api import Index
 
@@ -105,20 +105,22 @@ class BaseInfo(ABC):
 
     Parameters
     ----------
-    data : FrameOrSeriesUnion
+    data : DataFrame or Series
         Either dataframe or series.
     memory_usage : bool or str, optional
         If "deep", introspect the data deeply by interrogating object dtypes
         for system-level memory consumption, and include it in the returned
         values.
     """
 
-    data: FrameOrSeriesUnion
+    data: DataFrame | Series
     memory_usage: Union[bool, str]
 
     @property
+    @abstractmethod
     def dtypes(self) -> Iterable[Dtype]:
-        """Dtypes.
+        """
+        Dtypes.
 
         Returns
         -------
@@ -209,7 +211,7 @@ def render(
             consume the same memory amount for corresponding dtypes. With deep
             memory introspection, a real memory usage calculation is performed
             at the cost of computational resources.
-        %(null_counts_sub)s
+        %(show_counts_sub)s
 
         Returns
         -------
@@ -233,10 +235,10 @@ class DataFrameInfo(BaseInfo):
 
     def __init__(
         self,
-        data: "DataFrame",
-        memory_usage: Optional[Union[bool, str]] = None,
+        data: DataFrame,
+        memory_usage: bool | str | None = None,
     ):
-        self.data: "DataFrame" = data
+        self.data: DataFrame = data
         self.memory_usage = _initialize_memory_usage(memory_usage)
 
     @property
@@ -245,7 +247,8 @@ def dtype_counts(self) -> Mapping[str, int]:
 
     @property
     def dtypes(self) -> Iterable[Dtype]:
-        """Dtypes.
+        """
+        Dtypes.
 
         Returns
         -------
@@ -256,7 +259,8 @@ def dtypes(self) -> Iterable[Dtype]:
 
     @property
     def ids(self) -> Index:
-        """Column names.
+        """
+        Column names.
 
         Returns
         -------
@@ -286,10 +290,10 @@ def memory_usage_bytes(self) -> int:
     def render(
         self,
         *,
-        buf: Optional[IO[str]],
-        max_cols: Optional[int],
-        verbose: Optional[bool],
-        show_counts: Optional[bool],
+        buf: IO[str] | None,
+        max_cols: int | None,
+        verbose: bool | None,
+        show_counts: bool | None,
     ) -> None:
         printer = DataFrameInfoPrinter(
             info=self,
@@ -307,19 +311,19 @@ class SeriesInfo(BaseInfo):
 
     def __init__(
         self,
-        data: "Series",
-        memory_usage: Optional[Union[bool, str]] = None,
+        data: Series,
+        memory_usage: bool | str | None = None,
     ):
-        self.data: "Series" = data
+        self.data: Series = data
         self.memory_usage = _initialize_memory_usage(memory_usage)
 
     def render(
         self,
         *,
-        buf: Optional[IO[str]],
-        max_cols: Optional[int],
-        verbose: Optional[bool],
-        show_counts: Optional[bool],
+        buf: IO[str] | None = None,
+        max_cols: int | None = None,
+        verbose: bool | None = None,
+        show_counts: bool | None = None,
     ) -> None:
         if max_cols is not None:
             raise ValueError(
@@ -368,7 +372,7 @@ class InfoPrinterAbstract:
     Class for printing dataframe or series info.
     """
 
-    def to_buffer(self, buf: Optional[IO[str]] = None) -> None:
+    def to_buffer(self, buf: IO[str] | None = None) -> None:
         """Save dataframe info into buffer."""
         table_builder = self._create_table_builder()
         lines = table_builder.get_lines()
@@ -377,7 +381,7 @@ def to_buffer(self, buf: Optional[IO[str]] = None) -> None:
         fmt.buffer_put_lines(buf, lines)
 
     @abstractmethod
-    def _create_table_builder(self) -> "TableBuilderAbstract":
+    def _create_table_builder(self) -> TableBuilderAbstract:
         """Create instance of table builder."""
 
 
@@ -441,7 +445,7 @@ def _initialize_show_counts(self, show_counts: bool | None) -> bool:
         else:
             return show_counts
 
-    def _create_table_builder(self) -> "DataFrameTableBuilder":
+    def _create_table_builder(self) -> DataFrameTableBuilder:
         """
         Create instance of table builder based on verbosity and display settings.
         """
@@ -478,15 +482,15 @@ class SeriesInfoPrinter(InfoPrinterAbstract):
     def __init__(
         self,
         info: SeriesInfo,
-        verbose: Optional[bool] = None,
-        show_counts: Optional[bool] = None,
+        verbose: bool | None = None,
+        show_counts: bool | None = None,
     ):
         self.info = info
         self.data = info.data
         self.verbose = verbose
         self.show_counts = self._initialize_show_counts(show_counts)
 
-    def _create_table_builder(self) -> "SeriesTableBuilder":
+    def _create_table_builder(self) -> SeriesTableBuilder:
         """
         Create instance of table builder based on verbosity.
         """
@@ -510,15 +514,15 @@ class TableBuilderAbstract(ABC):
     Abstract builder for info table.
     """
 
-    _lines: List[str]
+    _lines: list[str]
     info: BaseInfo
 
     @abstractmethod
     def get_lines(self) -> list[str]:
         """Product in a form of list of lines (strings)."""
 
     @property
-    def data(self) -> FrameOrSeriesUnion:
+    def data(self) -> DataFrame | Series:
         return self.info.data
 
     @property
@@ -571,15 +575,6 @@ class DataFrameTableBuilder(TableBuilderAbstract):
         Instance of DataFrameInfo.
     """
 
-    def __init__(self, *, info: DataFrameInfo):
-        self.info: DataFrameInfo = info
-
-    Parameters
-    ----------
-    info : DataFrameInfo.
-        Instance of DataFrameInfo.
-    """
-
     def __init__(self, *, info: DataFrameInfo):
         self.info: DataFrameInfo = info
 
@@ -673,7 +668,8 @@ def _get_body_column_widths(self) -> Sequence[int]:
         return [max(len(x) for x in col) for col in strcols]
 
     def _gen_rows(self) -> Iterator[Sequence[str]]:
-        """Generator function yielding rows content.
+        """
+        Generator function yielding rows content.
 
         Each element represents a row comprising a sequence of strings.
         """
@@ -893,9 +889,9 @@ def _gen_rows_with_counts(self) -> Iterator[Sequence[str]]:
         )
 
 
-def _get_dataframe_dtype_counts(df: "DataFrame") -> Mapping[str, int]:
+def _get_dataframe_dtype_counts(df: DataFrame) -> Mapping[str, int]:
     """
-    Create mapping between datatypes and their number of occurences.
+    Create mapping between datatypes and their number of occurrences.
     """
     # groupby dtype.name to collect e.g. Categorical columns
     return df.dtypes.value_counts().groupby(lambda x: x.name).sum()