REF: simplify Categorical.__repr__ (#55391)

* REF: remove unused arguments from private Categorical methods

* REF: remove unused args from CategoricalFormatter

* REF: remove CategoricalFormatter

Author: jbrockmendel

pandas/core/arrays/categorical.py

@@ -2151,21 +2151,6 @@ def _formatter(self, boxed: bool = False):
         # Defer to CategoricalFormatter's formatter.
         return None
 
-    def _tidy_repr(self, max_vals: int = 10, footer: bool = True) -> str:
-        """
-        a short repr displaying only max_vals and an optional (but default
-        footer)
-        """
-        num = max_vals // 2
-        head = self[:num]._get_repr(length=False, footer=False)
-        tail = self[-(max_vals - num) :]._get_repr(length=False, footer=False)
-
-        result = f"{head[:-1]}, ..., {tail[1:]}"
-        if footer:
-            result = f"{result}\n{self._repr_footer()}"
-
-        return str(result)
-
     def _repr_categories(self) -> list[str]:
         """
         return the base repr for the categories
@@ -2221,33 +2206,49 @@ def _repr_categories_info(self) -> str:
         # replace to simple save space by
         return f"{levheader}[{levstring.replace(' < ... < ', ' ... ')}]"
 
-    def _repr_footer(self) -> str:
-        info = self._repr_categories_info()
-        return f"Length: {len(self)}\n{info}"
-
-    def _get_repr(
-        self, length: bool = True, na_rep: str = "NaN", footer: bool = True
-    ) -> str:
+    def _get_values_repr(self) -> str:
         from pandas.io.formats import format as fmt
 
-        formatter = fmt.CategoricalFormatter(
-            self, length=length, na_rep=na_rep, footer=footer
+        assert len(self) > 0
+
+        vals = self._internal_get_values()
+        fmt_values = fmt.format_array(
+            vals,
+            None,
+            float_format=None,
+            na_rep="NaN",
+            quoting=QUOTE_NONNUMERIC,
         )
-        result = formatter.to_string()
-        return str(result)
+
+        fmt_values = [i.strip() for i in fmt_values]
+        joined = ", ".join(fmt_values)
+        result = "[" + joined + "]"
+        return result
 
     def __repr__(self) -> str:
         """
         String representation.
         """
-        _maxlen = 10
-        if len(self._codes) > _maxlen:
-            result = self._tidy_repr(_maxlen)
-        elif len(self._codes) > 0:
-            result = self._get_repr(length=len(self) > _maxlen)
+        footer = self._repr_categories_info()
+        length = len(self)
+        max_len = 10
+        if length > max_len:
+            # In long cases we do not display all entries, so we add Length
+            #  information to the __repr__.
+            num = max_len // 2
+            head = self[:num]._get_values_repr()
+            tail = self[-(max_len - num) :]._get_values_repr()
+            body = f"{head[:-1]}, ..., {tail[1:]}"
+            length_info = f"Length: {len(self)}"
+            result = f"{body}\n{length_info}\n{footer}"
+        elif length > 0:
+            body = self._get_values_repr()
+            result = f"{body}\n{footer}"
         else:
-            msg = self._get_repr(length=False, footer=True).replace("\n", ", ")
-            result = f"[], {msg}"
+            # In the empty case we use a comma instead of newline to get
+            #  a more compact __repr__
+            body = "[]"
+            result = f"{body}, {footer}"
 
         return result
 

pandas/io/formats/format.py

@@ -12,10 +12,7 @@
     Sequence,
 )
 from contextlib import contextmanager
-from csv import (
-    QUOTE_NONE,
-    QUOTE_NONNUMERIC,
-)
+from csv import QUOTE_NONE
 from decimal import Decimal
 from functools import partial
 from io import StringIO
@@ -200,70 +197,6 @@
     """
 
 
-class CategoricalFormatter:
-    def __init__(
-        self,
-        categorical: Categorical,
-        buf: IO[str] | None = None,
-        length: bool = True,
-        na_rep: str = "NaN",
-        footer: bool = True,
-    ) -> None:
-        self.categorical = categorical
-        self.buf = buf if buf is not None else StringIO("")
-        self.na_rep = na_rep
-        self.length = length
-        self.footer = footer
-        self.quoting = QUOTE_NONNUMERIC
-
-    def _get_footer(self) -> str:
-        footer = ""
-
-        if self.length:
-            if footer:
-                footer += ", "
-            footer += f"Length: {len(self.categorical)}"
-
-        level_info = self.categorical._repr_categories_info()
-
-        # Levels are added in a newline
-        if footer:
-            footer += "\n"
-        footer += level_info
-
-        return str(footer)
-
-    def _get_formatted_values(self) -> list[str]:
-        return format_array(
-            self.categorical._internal_get_values(),
-            None,
-            float_format=None,
-            na_rep=self.na_rep,
-            quoting=self.quoting,
-        )
-
-    def to_string(self) -> str:
-        categorical = self.categorical
-
-        if len(categorical) == 0:
-            if self.footer:
-                return self._get_footer()
-            else:
-                return ""
-
-        fmt_values = self._get_formatted_values()
-
-        fmt_values = [i.strip() for i in fmt_values]
-        values = ", ".join(fmt_values)
-        result = ["[" + values + "]"]
-        if self.footer:
-            footer = self._get_footer()
-            if footer:
-                result.append(footer)
-
-        return str("\n".join(result))
-
-
 class SeriesFormatter:
     def __init__(
         self,