Merge branch 'main' into enh-list-arith

Author: jbrockmendel

doc/source/whatsnew/v3.0.0.rst

@@ -219,6 +219,7 @@ Other enhancements
 - Added support to read and write from and to Apache Iceberg tables with the new :func:`read_iceberg` and :meth:`DataFrame.to_iceberg` functions (:issue:`61383`)
 - Errors occurring during SQL I/O will now throw a generic :class:`.DatabaseError` instead of the raw Exception type from the underlying driver manager library (:issue:`60748`)
 - Implemented :meth:`Series.str.isascii` and :meth:`Series.str.isascii` (:issue:`59091`)
+- Improve error reporting through outputting the first few duplicates when :func:`merge` validation fails (:issue:`62742`)
 - Improve the resulting dtypes in :meth:`DataFrame.where` and :meth:`DataFrame.mask` with :class:`ExtensionDtype` ``other`` (:issue:`62038`)
 - Improved deprecation message for offset aliases (:issue:`60820`)
 - Many type aliases are now exposed in the new submodule :py:mod:`pandas.api.typing.aliases` (:issue:`55231`)
@@ -1015,6 +1016,7 @@ Numeric
 ^^^^^^^
 - Bug in :func:`api.types.infer_dtype` returning "mixed" for complex and ``pd.NA`` mix (:issue:`61976`)
 - Bug in :func:`api.types.infer_dtype` returning "mixed-integer-float" for float and ``pd.NA`` mix (:issue:`61621`)
+- Bug in :meth:`DataFrame.combine_first` where Int64 and UInt64 integers with absolute value greater than ``2**53`` would lose precision after the operation. (:issue:`60128`)
 - Bug in :meth:`DataFrame.corr` where numerical precision errors resulted in correlations above ``1.0`` (:issue:`61120`)
 - Bug in :meth:`DataFrame.cov` raises a ``TypeError`` instead of returning potentially incorrect results or other errors (:issue:`53115`)
 - Bug in :meth:`DataFrame.quantile` where the column type was not preserved when ``numeric_only=True`` with a list-like ``q`` produced an empty result (:issue:`59035`)
@@ -1043,6 +1045,7 @@ Interval
 - :meth:`Index.is_monotonic_decreasing`, :meth:`Index.is_monotonic_increasing`, and :meth:`Index.is_unique` could incorrectly be ``False`` for an ``Index`` created from a slice of another ``Index``. (:issue:`57911`)
 - Bug in :class:`Index`, :class:`Series`, :class:`DataFrame` constructors when given a sequence of :class:`Interval` subclass objects casting them to :class:`Interval` (:issue:`46945`)
 - Bug in :func:`interval_range` where start and end numeric types were always cast to 64 bit (:issue:`57268`)
+- Bug in :meth:`IntervalIndex.get_indexer` and :meth:`IntervalIndex.drop` when one of the sides of the index is non-unique (:issue:`52245`)
 
 Indexing
 ^^^^^^^^

pandas/_libs/index.pyx

@@ -321,6 +321,9 @@ cdef class IndexEngine:
             if is_strict_monotonic:
                 self.unique = 1
                 self.need_unique_check = 0
+            elif self.monotonic_inc == 1 or self.monotonic_dec == 1:
+                self.unique = 0
+                self.need_unique_check = 0
 
     cdef _call_monotonic(self, values):
         return algos.is_monotonic(values, timelike=False)

pandas/core/frame.py

@@ -3293,28 +3293,71 @@ def to_html(
         Examples
         --------
         >>> df = pd.DataFrame(data={"col1": [1, 2], "col2": [4, 3]})
-        >>> html_string = '''<table border="1" class="dataframe">
-        ...   <thead>
-        ...     <tr style="text-align: right;">
-        ...       <th></th>
-        ...       <th>col1</th>
-        ...       <th>col2</th>
-        ...     </tr>
-        ...   </thead>
-        ...   <tbody>
-        ...     <tr>
-        ...       <th>0</th>
-        ...       <td>1</td>
-        ...       <td>4</td>
-        ...     </tr>
-        ...     <tr>
-        ...       <th>1</th>
-        ...       <td>2</td>
-        ...       <td>3</td>
-        ...     </tr>
-        ...   </tbody>
-        ... </table>'''
-        >>> assert html_string == df.to_html()
+        >>> html_string = df.to_html()
+        >>> print(html_string)
+        <table border="1" class="dataframe">
+          <thead>
+            <tr style="text-align: right;">
+              <th></th>
+              <th>col1</th>
+              <th>col2</th>
+            </tr>
+          </thead>
+          <tbody>
+            <tr>
+              <th>0</th>
+              <td>1</td>
+              <td>4</td>
+            </tr>
+            <tr>
+              <th>1</th>
+              <td>2</td>
+              <td>3</td>
+            </tr>
+          </tbody>
+        </table>
+
+        HTML output
+
+        +----+-----+-----+
+        |    |col1 |col2 |
+        +====+=====+=====+
+        |0   |1    |4    |
+        +----+-----+-----+
+        |1   |2    |3    |
+        +----+-----+-----+
+
+        >>> df = pd.DataFrame(data={"col1": [1, 2], "col2": [4, 3]})
+        >>> html_string = df.to_html(index=False)
+        >>> print(html_string)
+        <table border="1" class="dataframe">
+          <thead>
+            <tr style="text-align: right;">
+              <th>col1</th>
+              <th>col2</th>
+            </tr>
+          </thead>
+          <tbody>
+            <tr>
+              <td>1</td>
+              <td>4</td>
+            </tr>
+            <tr>
+              <td>2</td>
+              <td>3</td>
+            </tr>
+          </tbody>
+        </table>
+
+        HTML output
+
+        +-----+-----+
+        |col1 |col2 |
+        +=====+=====+
+        |1    |4    |
+        +-----+-----+
+        |2    |3    |
+        +-----+-----+
         """
         if justify is not None and justify not in fmt.VALID_JUSTIFY_PARAMETERS:
             raise ValueError("Invalid value for justify parameter")
@@ -9165,20 +9208,10 @@ def combine_first(self, other: DataFrame) -> DataFrame:
         1  0.0  3.0  1.0
         2  NaN  3.0  1.0
         """
-        from pandas.core.computation import expressions
 
         def combiner(x: Series, y: Series):
-            mask = x.isna()._values
-
-            x_values = x._values
-            y_values = y._values
-
-            # If the column y in other DataFrame is not in first DataFrame,
-            # just return y_values.
-            if y.name not in self.columns:
-                return y_values
-
-            return expressions.where(mask, y_values, x_values)
+            # GH#60128 The combiner is supposed to preserve EA Dtypes.
+            return y if y.name not in self.columns else y.where(x.isna(), x)
 
         if len(other) == 0:
             combined = self.reindex(

pandas/core/indexes/interval.py

@@ -712,7 +712,10 @@ def _get_indexer(
             # -> at most one match per interval in target
             # want exact matches -> need both left/right to match, so defer to
             # left/right get_indexer, compare elementwise, equality -> match
-            indexer = self._get_indexer_unique_sides(target)
+            if self.left.is_unique and self.right.is_unique:
+                indexer = self._get_indexer_unique_sides(target)
+            else:
+                indexer = self._get_indexer_pointwise(target)[0]
 
         elif not (is_object_dtype(target.dtype) or is_string_dtype(target.dtype)):
             # homogeneous scalar index: use IntervalTree

pandas/core/reshape/merge.py

@@ -1954,42 +1954,62 @@ def _validate_left_right_on(self, left_on, right_on):
     def _validate_validate_kwd(self, validate: str) -> None:
         # Check uniqueness of each
         if self.left_index:
-            left_unique = self.orig_left.index.is_unique
+            left_join_index = self.orig_left.index
+            left_unique = left_join_index.is_unique
         else:
-            left_unique = MultiIndex.from_arrays(self.left_join_keys).is_unique
+            left_join_index = MultiIndex.from_arrays(self.left_join_keys)
+            left_unique = left_join_index.is_unique
 
         if self.right_index:
+            right_join_index = self.orig_right.index
             right_unique = self.orig_right.index.is_unique
         else:
-            right_unique = MultiIndex.from_arrays(self.right_join_keys).is_unique
+            right_join_index = MultiIndex.from_arrays(self.right_join_keys)
+            right_unique = right_join_index.is_unique
+
+        def left_error_msg(x: Index) -> str:
+            name = self.left_on if not self.left_index else lib.no_default
+            msg = x[x.duplicated()][:5].to_frame(name=name).to_string(index=False)
+            return f"\nDuplicates in left:\n {msg} ..."
+
+        def right_error_msg(x: Index) -> str:
+            name = self.right_on if not self.right_index else lib.no_default
+            msg = x[x.duplicated()][:5].to_frame(name=name).to_string(index=False)
+            return f"\nDuplicates in right:\n {msg} ..."
 
         # Check data integrity
         if validate in ["one_to_one", "1:1"]:
             if not left_unique and not right_unique:
                 raise MergeError(
                     "Merge keys are not unique in either left "
-                    "or right dataset; not a one-to-one merge"
+                    "or right dataset; not a one-to-one merge."
+                    f"{left_error_msg(left_join_index)}"
+                    f"{right_error_msg(right_join_index)}"
                 )
             if not left_unique:
                 raise MergeError(
                     "Merge keys are not unique in left dataset; not a one-to-one merge"
+                    f"{left_error_msg(left_join_index)}"
                 )
             if not right_unique:
                 raise MergeError(
                     "Merge keys are not unique in right dataset; not a one-to-one merge"
+                    f"{right_error_msg(right_join_index)}"
                 )
 
         elif validate in ["one_to_many", "1:m"]:
             if not left_unique:
                 raise MergeError(
                     "Merge keys are not unique in left dataset; not a one-to-many merge"
+                    f"{left_error_msg(left_join_index)}"
                 )
 
         elif validate in ["many_to_one", "m:1"]:
             if not right_unique:
                 raise MergeError(
                     "Merge keys are not unique in right dataset; "
-                    "not a many-to-one merge"
+                    "not a many-to-one merge\n"
+                    f"{right_error_msg(right_join_index)}"
                 )
 
         elif validate in ["many_to_many", "m:m"]: