Merge remote-tracking branch 'upstream/master' into CI-TestCase-#29886

Author: MomIsBestFriend

ci/run_tests.sh

@@ -37,7 +37,8 @@ echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"
 
 if [[ "$COVERAGE" && $? == 0 && "$TRAVIS_BRANCH" == "master" ]]; then
+    SHA=`git rev-parse HEAD`
     echo "uploading coverage"
-    echo "bash <(curl -s https://codecov.io/bash) -Z -c -F $TYPE -f $COVERAGE_FNAME"
-          bash <(curl -s https://codecov.io/bash) -Z -c -F $TYPE -f $COVERAGE_FNAME
+    echo "bash <(curl -s https://codecov.io/bash) -Z -c -F $TYPE -f $COVERAGE_FNAME -C $SHA"
+          bash <(curl -s https://codecov.io/bash) -Z -c -F $TYPE -f $COVERAGE_FNAME -C `git rev-parse HEAD`
 fi

doc/source/user_guide/io.rst

@@ -4828,7 +4828,6 @@ See also some :ref:`cookbook examples <cookbook.sql>` for some advanced strategi
 The key functions are:
 
 .. autosummary::
-    :toctree: ../reference/api/
 
     read_sql_table
     read_sql_query

doc/source/whatsnew/v1.0.0.rst

@@ -712,7 +712,7 @@ Datetimelike
 - Bug in :func:`pandas.to_datetime` when called with ``None`` raising ``TypeError`` instead of returning ``NaT`` (:issue:`30011`)
 - Bug in :func:`pandas.to_datetime` failing for `deques` when using ``cache=True`` (the default) (:issue:`29403`)
 - Bug in :meth:`Series.item` with ``datetime64`` or ``timedelta64`` dtype, :meth:`DatetimeIndex.item`, and :meth:`TimedeltaIndex.item` returning an integer instead of a :class:`Timestamp` or :class:`Timedelta` (:issue:`30175`)
--
+- Bug in :class:`DatetimeIndex` addition when adding a non-optimized :class:`DateOffset` incorrectly dropping timezone information (:issue:`30336`)
 
 Timedelta
 ^^^^^^^^^

pandas/core/arrays/datetimes.py

@@ -794,16 +794,17 @@ def _add_offset(self, offset):
                 values = self.tz_localize(None)
             else:
                 values = self
-            result = offset.apply_index(values)
-            if self.tz is not None:
-                result = result.tz_localize(self.tz)
+            result = offset.apply_index(values).tz_localize(self.tz)
 
         except NotImplementedError:
             warnings.warn(
                 "Non-vectorized DateOffset being applied to Series or DatetimeIndex",
                 PerformanceWarning,
             )
             result = self.astype("O") + offset
+            if len(self) == 0:
+                # _from_sequence won't be able to infer self.tz
+                return type(self)._from_sequence(result).tz_localize(self.tz)
 
         return type(self)._from_sequence(result, freq="infer")
 

pandas/core/frame.py

@@ -1745,7 +1745,7 @@ def to_records(self, index=True, column_dtypes=None, index_dtypes=None):
         rec.array([(b'a', 1, 0.5 ), (b'b', 2, 0.75)],
                   dtype=[('I', 'S2'), ('A', '<i8'), ('B', '<f8')])
 
-        >>> index_dtypes = "<S{}".format(df.index.str.len().max())
+        >>> index_dtypes = f"<S{df.index.str.len().max()}"
         >>> df.to_records(index_dtypes=index_dtypes)
         rec.array([(b'a', 1, 0.5 ), (b'b', 2, 0.75)],
                   dtype=[('I', 'S1'), ('A', '<i8'), ('B', '<f8')])
@@ -2355,13 +2355,9 @@ def _sizeof_fmt(num, size_qualifier):
             # returns size in human readable format
             for x in ["bytes", "KB", "MB", "GB", "TB"]:
                 if num < 1024.0:
-                    return "{num:3.1f}{size_q} {x}".format(
-                        num=num, size_q=size_qualifier, x=x
-                    )
+                    return f"{num:3.1f}{size_qualifier} {x}"
                 num /= 1024.0
-            return "{num:3.1f}{size_q} {pb}".format(
-                num=num, size_q=size_qualifier, pb="PB"
-            )
+            return f"{num:3.1f}{size_qualifier} PB"
 
         if verbose:
             _verbose_repr()
@@ -2374,7 +2370,7 @@ def _sizeof_fmt(num, size_qualifier):
                 _verbose_repr()
 
         counts = self._data.get_dtype_counts()
-        dtypes = ["{k}({kk:d})".format(k=k[0], kk=k[1]) for k in sorted(counts.items())]
+        dtypes = [f"{k[0]}({k[1]:d})" for k in sorted(counts.items())]
         lines.append(f"dtypes: {', '.join(dtypes)}")
 
         if memory_usage is None:

pandas/core/generic.py

@@ -117,9 +117,8 @@ def _single_replace(self, to_replace, method, inplace, limit):
     """
     if self.ndim != 1:
         raise TypeError(
-            "cannot replace {0} with method {1} on a {2}".format(
-                to_replace, method, type(self).__name__
-            )
+            f"cannot replace {to_replace} with method {method} on a "
+            f"{type(self).__name__}"
         )
 
     orig_dtype = self.dtype
@@ -254,7 +253,7 @@ def _validate_dtype(self, dtype):
             if dtype.kind == "V":
                 raise NotImplementedError(
                     "compound dtypes are not implemented"
-                    " in the {0} constructor".format(type(self).__name__)
+                    f" in the {type(self).__name__} constructor"
                 )
 
         return dtype
@@ -396,7 +395,7 @@ def _get_axis_number(cls, axis):
                 return cls._AXIS_NUMBERS[axis]
             except KeyError:
                 pass
-        raise ValueError("No axis named {0} for object type {1}".format(axis, cls))
+        raise ValueError(f"No axis named {axis} for object type {cls}")
 
     @classmethod
     def _get_axis_name(cls, axis):
@@ -409,7 +408,7 @@ def _get_axis_name(cls, axis):
                 return cls._AXIS_NAMES[axis]
             except KeyError:
                 pass
-        raise ValueError("No axis named {0} for object type {1}".format(axis, cls))
+        raise ValueError(f"No axis named {axis} for object type {cls}")
 
     def _get_axis(self, axis):
         name = self._get_axis_name(axis)
@@ -437,7 +436,7 @@ def _get_axis_resolvers(self, axis):
                 # prefix with 'i' or 'c' depending on the input axis
                 # e.g., you must do ilevel_0 for the 0th level of an unnamed
                 # multiiindex
-                key = "{prefix}level_{i}".format(prefix=prefix, i=i)
+                key = f"{prefix}level_{i}"
                 level = i
 
             level_values = axis_index.get_level_values(level)
@@ -1082,7 +1081,7 @@ def rename(self, *args, **kwargs):
         if kwargs:
             raise TypeError(
                 "rename() got an unexpected keyword "
-                'argument "{0}"'.format(list(kwargs.keys())[0])
+                f'argument "{list(kwargs.keys())[0]}"'
             )
 
         if com.count_not_none(*axes.values()) == 0:
@@ -1108,7 +1107,7 @@ def rename(self, *args, **kwargs):
                     missing_labels = [
                         label for index, label in enumerate(v) if indexer[index] == -1
                     ]
-                    raise KeyError("{} not found in axis".format(missing_labels))
+                    raise KeyError(f"{missing_labels} not found in axis")
 
             result._data = result._data.rename_axis(
                 f, axis=baxis, copy=copy, level=level
@@ -1257,7 +1256,7 @@ class  name
         if kwargs:
             raise TypeError(
                 "rename_axis() got an unexpected keyword "
-                'argument "{0}"'.format(list(kwargs.keys())[0])
+                f'argument "{list(kwargs.keys())[0]}"'
             )
 
         inplace = validate_bool_kwarg(inplace, "inplace")
@@ -1461,9 +1460,7 @@ def __neg__(self):
         ):
             arr = operator.neg(values)
         else:
-            raise TypeError(
-                "Unary negative expects numeric dtype, not {}".format(values.dtype)
-            )
+            raise TypeError(f"Unary negative expects numeric dtype, not {values.dtype}")
         return self.__array_wrap__(arr)
 
     def __pos__(self):
@@ -1477,9 +1474,7 @@ def __pos__(self):
         ):
             arr = operator.pos(values)
         else:
-            raise TypeError(
-                "Unary plus expects numeric dtype, not {}".format(values.dtype)
-            )
+            raise TypeError(f"Unary plus expects numeric dtype, not {values.dtype}")
         return self.__array_wrap__(arr)
 
     def __invert__(self):
@@ -1492,10 +1487,8 @@ def __invert__(self):
 
     def __nonzero__(self):
         raise ValueError(
-            "The truth value of a {0} is ambiguous. "
-            "Use a.empty, a.bool(), a.item(), a.any() or a.all().".format(
-                type(self).__name__
-            )
+            f"The truth value of a {type(self).__name__} is ambiguous. "
+            "Use a.empty, a.bool(), a.item(), a.any() or a.all()."
         )
 
     __bool__ = __nonzero__
@@ -1519,7 +1512,7 @@ def bool(self):
         elif is_scalar(v):
             raise ValueError(
                 "bool cannot act on a non-boolean single element "
-                "{0}".format(type(self).__name__)
+                f"{type(self).__name__}"
             )
 
         self.__nonzero__()
@@ -1659,14 +1652,8 @@ def _check_label_or_level_ambiguity(self, key, axis: int = 0) -> None:
             )
 
             msg = (
-                "'{key}' is both {level_article} {level_type} level and "
-                "{label_article} {label_type} label, which is ambiguous."
-            ).format(
-                key=key,
-                level_article=level_article,
-                level_type=level_type,
-                label_article=label_article,
-                label_type=label_type,
+                f"'{key}' is both {level_article} {level_type} level and "
+                f"{label_article} {label_type} label, which is ambiguous."
             )
             raise ValueError(msg)
 
@@ -1731,12 +1718,8 @@ def _get_label_or_level_values(self, key: str, axis: int = 0) -> np.ndarray:
             label_axis_name = "column" if axis == 0 else "index"
             raise ValueError(
                 (
-                    "The {label_axis_name} label '{key}' "
-                    "is not unique.{multi_message}"
-                ).format(
-                    key=key,
-                    label_axis_name=label_axis_name,
-                    multi_message=multi_message,
+                    f"The {label_axis_name} label '{key}' "
+                    f"is not unique.{multi_message}"
                 )
             )
 
@@ -1780,8 +1763,8 @@ def _drop_labels_or_levels(self, keys, axis: int = 0):
             raise ValueError(
                 (
                     "The following keys are not valid labels or "
-                    "levels for axis {axis}: {invalid_keys}"
-                ).format(axis=axis, invalid_keys=invalid_keys)
+                    f"levels for axis {axis}: {invalid_keys}"
+                )
             )
 
         # Compute levels and labels to drop
@@ -1998,7 +1981,7 @@ def __setstate__(self, state):
     def __repr__(self) -> str:
         # string representation based upon iterating over self
         # (since, by definition, `PandasContainers` are iterable)
-        prepr = "[%s]" % ",".join(map(pprint_thing, self))
+        prepr = f"[{','.join(map(pprint_thing, self))}]"
         return f"{type(self).__name__}({prepr})"
 
     def _repr_latex_(self):
@@ -3946,13 +3929,13 @@ def _drop_axis(self, labels, axis, level=None, errors: str = "raise"):
 
                 # GH 18561 MultiIndex.drop should raise if label is absent
                 if errors == "raise" and indexer.all():
-                    raise KeyError("{} not found in axis".format(labels))
+                    raise KeyError(f"{labels} not found in axis")
             else:
                 indexer = ~axis.isin(labels)
                 # Check if label doesn't exist along axis
                 labels_missing = (axis.get_indexer_for(labels) == -1).any()
                 if errors == "raise" and labels_missing:
-                    raise KeyError("{} not found in axis".format(labels))
+                    raise KeyError(f"{labels} not found in axis")
 
             slicer = [slice(None)] * self.ndim
             slicer[self._get_axis_number(axis_name)] = indexer
@@ -4476,7 +4459,7 @@ def reindex(self, *args, **kwargs):
         if kwargs:
             raise TypeError(
                 "reindex() got an unexpected keyword "
-                'argument "{0}"'.format(list(kwargs.keys())[0])
+                f'argument "{list(kwargs.keys())[0]}"'
             )
 
         self._consolidate_inplace()
@@ -5997,7 +5980,7 @@ def fillna(
                     raise TypeError(
                         '"value" parameter must be a scalar, dict '
                         "or Series, but you passed a "
-                        '"{0}"'.format(type(value).__name__)
+                        f'"{type(value).__name__}"'
                     )
 
                 new_data = self._data.fillna(
@@ -6781,9 +6764,9 @@ def interpolate(
             if method not in methods and not is_numeric_or_datetime:
                 raise ValueError(
                     "Index column must be numeric or datetime type when "
-                    "using {method} method other than linear. "
+                    f"using {method} method other than linear. "
                     "Try setting a numeric or datetime index column before "
-                    "interpolating.".format(method=method)
+                    "interpolating."
                 )
 
         if isna(index).any():
@@ -9205,7 +9188,7 @@ def _tz_convert(ax, tz):
             ax = ax.set_levels(new_level, level=level)
         else:
             if level not in (None, 0, ax.name):
-                raise ValueError("The level {0} is not valid".format(level))
+                raise ValueError(f"The level {level} is not valid")
             ax = _tz_convert(ax, tz)
 
         result = self._constructor(self._data, copy=copy)
@@ -9375,7 +9358,7 @@ def _tz_localize(ax, tz, ambiguous, nonexistent):
             ax = ax.set_levels(new_level, level=level)
         else:
             if level not in (None, 0, ax.name):
-                raise ValueError("The level {0} is not valid".format(level))
+                raise ValueError(f"The level {level} is not valid")
             ax = _tz_localize(ax, tz, ambiguous, nonexistent)
 
         result = self._constructor(self._data, copy=copy)
@@ -10357,8 +10340,8 @@ def last_valid_index(self):
 
 def _doc_parms(cls):
     """Return a tuple of the doc parms."""
-    axis_descr = "{%s}" % ", ".join(
-        "{0} ({1})".format(a, i) for i, a in enumerate(cls._AXIS_ORDERS)
+    axis_descr = (
+        f"{{{', '.join(f'{a} ({i})' for i, a in enumerate(cls._AXIS_ORDERS))}}}"
     )
     name = cls._constructor_sliced.__name__ if cls._AXIS_LEN > 1 else "scalar"
     name2 = cls.__name__

pandas/core/indexers.py

@@ -144,9 +144,7 @@ def validate_indices(indices: np.ndarray, n: int) -> None:
     if len(indices):
         min_idx = indices.min()
         if min_idx < -1:
-            msg = "'indices' contains values less than allowed ({} < {})".format(
-                min_idx, -1
-            )
+            msg = f"'indices' contains values less than allowed ({min_idx} < -1)"
             raise ValueError(msg)
 
         max_idx = indices.max()

pandas/core/strings.py

@@ -113,7 +113,7 @@ def cat_safe(list_of_columns: List, sep: str):
                 raise TypeError(
                     "Concatenation requires list-likes containing only "
                     "strings (or missing values). Offending values found in "
-                    "column {}".format(dtype)
+                    f"column {dtype}"
                 ) from None
     return result
 
@@ -1355,8 +1355,8 @@ def str_find(arr, sub, start=0, end=None, side="left"):
     """
 
     if not isinstance(sub, str):
-        msg = "expected a string object, not {0}"
-        raise TypeError(msg.format(type(sub).__name__))
+        msg = f"expected a string object, not {type(sub).__name__}"
+        raise TypeError(msg)
 
     if side == "left":
         method = "find"
@@ -1375,8 +1375,8 @@ def str_find(arr, sub, start=0, end=None, side="left"):
 
 def str_index(arr, sub, start=0, end=None, side="left"):
     if not isinstance(sub, str):
-        msg = "expected a string object, not {0}"
-        raise TypeError(msg.format(type(sub).__name__))
+        msg = f"expected a string object, not {type(sub).__name__}"
+        raise TypeError(msg)
 
     if side == "left":
         method = "index"
@@ -1447,15 +1447,15 @@ def str_pad(arr, width, side="left", fillchar=" "):
     dtype: object
     """
     if not isinstance(fillchar, str):
-        msg = "fillchar must be a character, not {0}"
-        raise TypeError(msg.format(type(fillchar).__name__))
+        msg = f"fillchar must be a character, not {type(fillchar).__name__}"
+        raise TypeError(msg)
 
     if len(fillchar) != 1:
         raise TypeError("fillchar must be a character, not str")
 
     if not is_integer(width):
-        msg = "width must be of integer type, not {0}"
-        raise TypeError(msg.format(type(width).__name__))
+        msg = f"width must be of integer type, not {type(width).__name__}"
+        raise TypeError(msg)
 
     if side == "left":
         f = lambda x: x.rjust(width, fillchar)