Merge branch 'master' of https://github.com/pandas-dev/pandas into fuse_kh

Author: jbrockmendel

doc/source/conf.py

@@ -378,7 +378,7 @@
         "index",
         "pandas.tex",
         "pandas: powerful Python data analysis toolkit",
-        r"Wes McKinney\n\& PyData Development Team",
+        "Wes McKinney and the Pandas Development Team",
         "manual",
     )
 ]

doc/source/whatsnew/v1.0.0.rst

@@ -109,6 +109,7 @@ Other enhancements
   (:issue:`28368`)
 - :meth:`DataFrame.to_json` now accepts an ``indent`` integer argument to enable pretty printing of JSON output (:issue:`12004`)
 - :meth:`read_stata` can read Stata 119 dta files. (:issue:`28250`)
+- Added ``encoding`` argument to :meth:`DataFrame.to_string` for non-ascii text (:issue:`28766`)
 - Added ``encoding`` argument to :func:`DataFrame.to_html` for non-ascii text (:issue:`28663`)
 
 Build Changes

pandas/core/frame.py

@@ -754,6 +754,7 @@ def to_string(
         decimal: str = ".",
         line_width: Optional[int] = None,
         max_colwidth: Optional[int] = None,
+        encoding: Optional[str] = None,
     ) -> Optional[str]:
         """
         Render a DataFrame to a console-friendly tabular output.
@@ -764,6 +765,10 @@ def to_string(
             Max width to truncate each column in characters. By default, no limit.
 
             .. versionadded:: 1.0.0
+        encoding : str, default "utf-8"
+            Set character encoding.
+
+            .. versionadded:: 1.0
         %(returns)s
         See Also
         --------
@@ -802,7 +807,7 @@ def to_string(
                 decimal=decimal,
                 line_width=line_width,
             )
-            return formatter.to_string(buf=buf)
+            return formatter.to_string(buf=buf, encoding=encoding)
 
     # ----------------------------------------------------------------------
 

pandas/io/formats/format.py

@@ -486,6 +486,8 @@ def get_buffer(
 
         if encoding is None:
             encoding = "utf-8"
+        elif not isinstance(buf, str):
+            raise ValueError("buf is not a file name and encoding is specified.")
 
         if hasattr(buf, "write"):
             yield buf
@@ -896,8 +898,12 @@ def _join_multiline(self, *args) -> str:
             st = ed
         return "\n\n".join(str_lst)
 
-    def to_string(self, buf: Optional[FilePathOrBuffer[str]] = None) -> Optional[str]:
-        return self.get_result(buf=buf)
+    def to_string(
+        self,
+        buf: Optional[FilePathOrBuffer[str]] = None,
+        encoding: Optional[str] = None,
+    ) -> Optional[str]:
+        return self.get_result(buf=buf, encoding=encoding)
 
     def to_latex(
         self,

pandas/tests/io/formats/test_format.py

@@ -73,17 +73,19 @@ def filepath_or_buffer(filepath_or_buffer_id, tmp_path):
 
 
 @pytest.fixture
-def assert_filepath_or_buffer_equals(filepath_or_buffer, filepath_or_buffer_id):
+def assert_filepath_or_buffer_equals(
+    filepath_or_buffer, filepath_or_buffer_id, encoding
+):
     """
     Assertion helper for checking filepath_or_buffer.
     """
 
     def _assert_filepath_or_buffer_equals(expected):
         if filepath_or_buffer_id == "string":
-            with open(filepath_or_buffer) as f:
+            with open(filepath_or_buffer, encoding=encoding) as f:
                 result = f.read()
         elif filepath_or_buffer_id == "pathlike":
-            result = filepath_or_buffer.read_text()
+            result = filepath_or_buffer.read_text(encoding=encoding)
         elif filepath_or_buffer_id == "buffer":
             result = filepath_or_buffer.getvalue()
         assert result == expected
@@ -3240,14 +3242,32 @@ def test_repr_html_ipython_config(ip):
 
 
 @pytest.mark.parametrize("method", ["to_string", "to_html", "to_latex"])
+@pytest.mark.parametrize(
+    "encoding, data",
+    [(None, "abc"), ("utf-8", "abc"), ("gbk", "造成输出中文显示乱码"), ("foo", "abc")],
+)
 def test_filepath_or_buffer_arg(
-    float_frame, method, filepath_or_buffer, assert_filepath_or_buffer_equals
+    method,
+    filepath_or_buffer,
+    assert_filepath_or_buffer_equals,
+    encoding,
+    data,
+    filepath_or_buffer_id,
 ):
-    df = float_frame
-    expected = getattr(df, method)()
+    df = DataFrame([data])
 
-    getattr(df, method)(buf=filepath_or_buffer)
-    assert_filepath_or_buffer_equals(expected)
+    if filepath_or_buffer_id not in ["string", "pathlike"] and encoding is not None:
+        with pytest.raises(
+            ValueError, match="buf is not a file name and encoding is specified."
+        ):
+            getattr(df, method)(buf=filepath_or_buffer, encoding=encoding)
+    elif encoding == "foo":
+        with pytest.raises(LookupError, match="unknown encoding"):
+            getattr(df, method)(buf=filepath_or_buffer, encoding=encoding)
+    else:
+        expected = getattr(df, method)()
+        getattr(df, method)(buf=filepath_or_buffer, encoding=encoding)
+        assert_filepath_or_buffer_equals(expected)
 
 
 @pytest.mark.parametrize("method", ["to_string", "to_html", "to_latex"])

pandas/tests/series/test_operators.py

@@ -878,6 +878,17 @@ def test_divmod(self):
         assert_series_equal(result[0], expected[0])
         assert_series_equal(result[1], expected[1])
 
+    @pytest.mark.parametrize("index", [None, range(9)])
+    def test_series_integer_mod(self, index):
+        # see gh-24396
+        s1 = Series(range(1, 10))
+        s2 = Series("foo", index=index)
+
+        msg = "not all arguments converted during string formatting"
+
+        with pytest.raises(TypeError, match=msg):
+            s2 % s1
+
 
 class TestSeriesUnaryOps:
     # __neg__, __pos__, __inv__