Revert "merge."

This reverts commit df2671b, reversing
changes made to 104fc11.

ci/run_tests.sh

@@ -38,6 +38,6 @@ sh -c "$PYTEST_CMD"
 
 if [[ "$COVERAGE" && $? == 0 && "$TRAVIS_BRANCH" == "master" ]]; then
     echo "uploading coverage"
-    echo "bash <(curl -s https://codecov.io/bash) -Z -c -f $COVERAGE_FNAME"
-          bash <(curl -s https://codecov.io/bash) -Z -c -f $COVERAGE_FNAME
+    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
 fi

doc/source/conf.py

@@ -204,11 +204,7 @@
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
-html_theme_options = {
-    "external_links": [],
-    "github_url": "https://github.com/pandas-dev/pandas",
-    "twitter_url": "https://twitter.com/pandas_dev",
-}
+# html_theme_options = {}
 
 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = ["themes"]
@@ -232,7 +228,7 @@
 # The name of an image file (within the static path) to use as favicon of the
 # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-html_favicon = "../../web/pandas/static/img/favicon.ico"
+html_favicon = os.path.join(html_static_path[0], "favicon.ico")
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.

doc/source/user_guide/io.rst

@@ -4763,10 +4763,10 @@ Parquet supports partitioning of data based on the values of one or more columns
 .. ipython:: python
 
     df = pd.DataFrame({'a': [0, 0, 1, 1], 'b': [0, 1, 0, 1]})
-    df.to_parquet(path='test', engine='pyarrow',
+    df.to_parquet(fname='test', engine='pyarrow',
                   partition_cols=['a'], compression=None)
 
-The `path` specifies the parent directory to which data will be saved.
+The `fname` specifies the parent directory to which data will be saved.
 The `partition_cols` are the column names by which the dataset will be partitioned.
 Columns are partitioned in the order they are given. The partition splits are
 determined by the unique values in the partition columns.
@@ -4828,6 +4828,7 @@ 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/user_guide/text.rst

@@ -74,7 +74,6 @@ These are places where the behavior of ``StringDtype`` objects differ from
 l. For ``StringDtype``, :ref:`string accessor methods<api.series.str>`
    that return **numeric** output will always return a nullable integer dtype,
    rather than either int or float dtype, depending on the presence of NA values.
-   Methods returning **boolean** output will return a nullable boolean dtype.
 
    .. ipython:: python
 
@@ -90,13 +89,7 @@ l. For ``StringDtype``, :ref:`string accessor methods<api.series.str>`
       s.astype(object).str.count("a")
       s.astype(object).dropna().str.count("a")
 
-   When NA values are present, the output dtype is float64. Similarly for
-   methods returning boolean values.
-
-   .. ipython:: python
-
-      s.str.isdigit()
-      s.str.match("a")
+   When NA values are present, the output dtype is float64.
 
 2. Some string methods, like :meth:`Series.str.decode` are not available
    on ``StringArray`` because ``StringArray`` only holds strings, not

doc/source/whatsnew/v1.0.0.rst

@@ -206,7 +206,6 @@ Other enhancements
   now preserve those data types with pyarrow >= 1.0.0 (:issue:`20612`).
 - The ``partition_cols`` argument in :meth:`DataFrame.to_parquet` now accepts a string (:issue:`27117`)
 - :func:`to_parquet` now appropriately handles the ``schema`` argument for user defined schemas in the pyarrow engine. (:issue: `30270`)
-- DataFrame constructor preserve `ExtensionArray` dtype with `ExtensionArray` (:issue:`11363`)
 
 
 Build Changes
@@ -255,10 +254,10 @@ To update, use ``MultiIndex.set_names``, which returns a new ``MultiIndex``.
    mi2 = mi.set_names("new name", level=0)
    mi2.names
 
-New repr for :class:`~pandas.arrays.IntervalArray`
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+New repr for :class:`pandas.core.arrays.IntervalArray`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-- :class:`pandas.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)
+- :class:`pandas.core.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)
 
 *pandas 0.25.x*
 
@@ -502,7 +501,6 @@ Deprecations
 - :func:`pandas.json_normalize` is now exposed in the top-level namespace.
   Usage of ``json_normalize`` as ``pandas.io.json.json_normalize`` is now deprecated and
   it is recommended to use ``json_normalize`` as :func:`pandas.json_normalize` instead (:issue:`27586`).
-- :meth:`DataFrame.to_stata`, :meth:`DataFrame.to_feather`, and :meth:`DataFrame.to_parquet` argument "fname" is deprecated, use "path" instead (:issue:`23574`)
 - The ``numpy`` argument of :meth:`pandas.read_json` is deprecated (:issue:`28512`).
 -
 
@@ -580,7 +578,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - :meth:`Series.where` with ``Categorical`` dtype (or :meth:`DataFrame.where` with ``Categorical`` column) no longer allows setting new categories (:issue:`24114`)
 - :class:`DatetimeIndex`, :class:`TimedeltaIndex`, and :class:`PeriodIndex` constructors no longer allow ``start``, ``end``, and ``periods`` keywords, use :func:`date_range`, :func:`timedelta_range`, and :func:`period_range` instead (:issue:`23919`)
 - :class:`DatetimeIndex` and :class:`TimedeltaIndex` constructors no longer have a ``verify_integrity`` keyword argument (:issue:`23919`)
-- ``pandas.core.internals.blocks.make_block`` no longer accepts the "fastpath" keyword(:issue:`19265`)
+- :func:`core.internals.blocks.make_block` no longer accepts the "fastpath" keyword(:issue:`19265`)
 - :meth:`Block.make_block_same_class` no longer accepts the "dtype" keyword(:issue:`19434`)
 - Removed the previously deprecated :meth:`ExtensionArray._formatting_values`. Use :attr:`ExtensionArray._formatter` instead. (:issue:`23601`)
 - Removed the previously deprecated :meth:`MultiIndex.to_hierarchical` (:issue:`21613`)
@@ -657,7 +655,7 @@ Performance improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
 - Performance improvement in indexing with a non-unique :class:`IntervalIndex` (:issue:`27489`)
-- Performance improvement in :attr:`MultiIndex.is_monotonic` (:issue:`27495`)
+- Performance improvement in `MultiIndex.is_monotonic` (:issue:`27495`)
 - Performance improvement in :func:`cut` when ``bins`` is an :class:`IntervalIndex` (:issue:`27668`)
 - Performance improvement when initializing a :class:`DataFrame` using a ``range`` (:issue:`30171`)
 - Performance improvement in :meth:`DataFrame.corr` when ``method`` is ``"spearman"`` (:issue:`28139`)
@@ -713,7 +711,7 @@ 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
 ^^^^^^^^^
@@ -760,7 +758,7 @@ Interval
 ^^^^^^^^
 
 - Bug in :meth:`IntervalIndex.get_indexer` where a :class:`Categorical` or :class:`CategoricalIndex` ``target`` would incorrectly raise a ``TypeError`` (:issue:`30063`)
-- Bug in ``pandas.core.dtypes.cast.infer_dtype_from_scalar`` where passing ``pandas_dtype=True`` did not infer :class:`IntervalDtype` (:issue:`30337`)
+-
 
 Indexing
 ^^^^^^^^

pandas/_config/config.py

@@ -57,10 +57,10 @@
 DeprecatedOption = namedtuple("DeprecatedOption", "key msg rkey removal_ver")
 RegisteredOption = namedtuple("RegisteredOption", "key defval doc validator cb")
 
-# holds deprecated option metadata
+# holds deprecated option metdata
 _deprecated_options: Dict[str, DeprecatedOption] = {}
 
-# holds registered option metadata
+# holds registered option metdata
 _registered_options: Dict[str, RegisteredOption] = {}
 
 # holds the current values for registered options

pandas/_libs/groupby.pyx

@@ -791,7 +791,7 @@ def group_quantile(ndarray[float64_t] out,
                 out[i] = NaN
             else:
                 # Calculate where to retrieve the desired value
-                # Casting to int will intentionally truncate result
+                # Casting to int will intentionaly truncate result
                 idx = grp_start + <int64_t>(q * <float64_t>(non_na_sz - 1))
 
                 val = values[sort_arr[idx]]

pandas/_libs/index.pyx

@@ -288,7 +288,7 @@ cdef class IndexEngine:
 
     def get_indexer_non_unique(self, targets):
         """
-        Return an indexer suitable for taking from a non unique index
+        Return an indexer suitable for takng from a non unique index
         return the labels in the same order ast the target
         and a missing indexer into the targets (which correspond
         to the -1 indices in the results

pandas/_libs/lib.pyx

@@ -510,7 +510,7 @@ def maybe_booleans_to_slice(ndarray[uint8_t] mask):
 @cython.boundscheck(False)
 def array_equivalent_object(left: object[:], right: object[:]) -> bool:
     """
-    Perform an element by element comparison on 1-d object arrays
+    Perform an element by element comparion on 1-d object arrays
     taking into account nan positions.
     """
     cdef:

pandas/_libs/parsers.pyx

@@ -1367,26 +1367,7 @@ def _ensure_encoded(list lst):
 # common NA values
 # no longer excluding inf representations
 # '1.#INF','-1.#INF', '1.#INF000000',
-STR_NA_VALUES = {
-    "-1.#IND",
-    "1.#QNAN",
-    "1.#IND",
-    "-1.#QNAN",
-    "#N/A N/A",
-    "#N/A",
-    "N/A",
-    "n/a",
-    "NA",
-    "#NA",
-    "NULL",
-    "null",
-    "NaN",
-    "-NaN",
-    "nan",
-    "-nan",
-    "",
-}
-_NA_VALUES = _ensure_encoded(list(STR_NA_VALUES))
+_NA_VALUES = _ensure_encoded(list(icom._NA_VALUES))
 
 
 def _maybe_upcast(arr):

pandas/_libs/src/klib/khash.h

@@ -498,7 +498,7 @@ PANDAS_INLINE khint_t __ac_Wang_hash(khint_t key)
  */
 #define kh_n_buckets(h) ((h)->n_buckets)
 
-/* More convenient interfaces */
+/* More conenient interfaces */
 
 /*! @function
   @abstract     Instantiate a hash set containing integer keys

pandas/_libs/src/ujson/lib/ultrajsondec.c

@@ -150,7 +150,7 @@ FASTCALL_ATTR JSOBJ FASTCALL_MSVC decode_numeric(struct DecoderState *ds) {
             case '7':
             case '8':
             case '9': {
-                // FIXME: Check for arithmetic overflow here
+                // FIXME: Check for arithemtic overflow here
                 // PERF: Don't do 64-bit arithmetic here unless we know we have
                 // to
                 intValue = intValue * 10ULL + (JSLONG)(chr - 48);
@@ -235,7 +235,7 @@ FASTCALL_ATTR JSOBJ FASTCALL_MSVC decode_numeric(struct DecoderState *ds) {
     }
 
 BREAK_FRC_LOOP:
-    // FIXME: Check for arithmetic overflow here
+    // FIXME: Check for arithemtic overflow here
     ds->lastType = JT_DOUBLE;
     ds->start = offset;
     return ds->dec->newDouble(
@@ -282,7 +282,7 @@ FASTCALL_ATTR JSOBJ FASTCALL_MSVC decode_numeric(struct DecoderState *ds) {
     }
 
 BREAK_EXP_LOOP:
-    // FIXME: Check for arithmetic overflow here
+    // FIXME: Check for arithemtic overflow here
     ds->lastType = JT_DOUBLE;
     ds->start = offset;
     return ds->dec->newDouble(

pandas/_libs/src/ujson/python/objToJSON.c

@@ -1632,7 +1632,7 @@ char **NpyArr_encodeLabels(PyArrayObject *labels, PyObjectEncoder *enc,
                 sprintf(buf, "%" NPY_INT64_FMT, value);
                 len = strlen(cLabel);
             }
-        } else { // Fallback to string representation
+        } else { // Fallack to string representation
             PyObject *str = PyObject_Str(item);
             if (str == NULL) {
                 Py_DECREF(item);

pandas/_libs/tslibs/timestamps.pyx

@@ -324,7 +324,7 @@ class Timestamp(_Timestamp):
 
         Function is not implemented. Use pd.to_datetime().
         """
-        raise NotImplementedError("Timestamp.strptime() is not implemented."
+        raise NotImplementedError("Timestamp.strptime() is not implmented."
                                   "Use to_datetime() to parse date strings.")
 
     @classmethod
@@ -336,22 +336,11 @@ class Timestamp(_Timestamp):
         """
         return cls(datetime.combine(date, time))
 
-    def __new__(
-        cls,
-        object ts_input=_no_input,
-        object freq=None,
-        tz=None,
-        unit=None,
-        year=None,
-        month=None,
-        day=None,
-        hour=None,
-        minute=None,
-        second=None,
-        microsecond=None,
-        nanosecond=None,
-        tzinfo=None
-    ):
+    def __new__(cls, object ts_input=_no_input,
+                object freq=None, tz=None, unit=None,
+                year=None, month=None, day=None,
+                hour=None, minute=None, second=None, microsecond=None,
+                nanosecond=None, tzinfo=None):
         # The parameter list folds together legacy parameter names (the first
         # four) and positional and keyword parameter names from pydatetime.
         #
@@ -412,8 +401,8 @@ class Timestamp(_Timestamp):
             freq = None
 
         if getattr(ts_input, 'tzinfo', None) is not None and tz is not None:
-            raise ValueError("Cannot pass a datetime or Timestamp with tzinfo with "
-                             "the tz parameter. Use tz_convert instead.")
+            raise ValueError("Cannot pass a datetime or Timestamp with tzinfo with the"
+                             " tz parameter. Use tz_convert instead.")
 
         ts = convert_to_tsobject(ts_input, tz, unit, 0, 0, nanosecond or 0)
 

pandas/core/arrays/datetimes.py

@@ -794,17 +794,16 @@ def _add_offset(self, offset):
                 values = self.tz_localize(None)
             else:
                 values = self
-            result = offset.apply_index(values).tz_localize(self.tz)
+            result = offset.apply_index(values)
+            if self.tz is not None:
+                result = result.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/arrays/sparse/dtype.py

@@ -290,7 +290,7 @@ def update_dtype(self, dtype):
         Returns
         -------
         SparseDtype
-            A new SparseDtype with the correct `dtype` and fill value
+            A new SparseDtype with the corret `dtype` and fill value
             for that `dtype`.
 
         Raises

pandas/core/arrays/string_.py

@@ -86,7 +86,7 @@ def __from_arrow__(self, array):
 
         results = []
         for arr in chunks:
-            # using _from_sequence to ensure None is converted to NA
+            # using _from_sequence to ensure None is convered to NA
             str_arr = StringArray._from_sequence(np.array(arr))
             results.append(str_arr)
 
@@ -153,7 +153,7 @@ class StringArray(PandasArray):
     ...
     ValueError: StringArray requires an object-dtype ndarray of strings.
 
-    For comparison methods, this returns a :class:`pandas.BooleanArray`
+    For comparision methods, this returns a :class:`pandas.BooleanArray`
 
     >>> pd.array(["a", None, "c"], dtype="string") == "a"
     <BooleanArray>

pandas/core/dtypes/cast.py

@@ -41,7 +41,7 @@
     is_unsigned_integer_dtype,
     pandas_dtype,
 )
-from .dtypes import DatetimeTZDtype, ExtensionDtype, IntervalDtype, PeriodDtype
+from .dtypes import DatetimeTZDtype, ExtensionDtype, PeriodDtype
 from .generic import (
     ABCDataFrame,
     ABCDatetimeArray,
@@ -601,9 +601,6 @@ def infer_dtype_from_scalar(val, pandas_dtype: bool = False):
         if lib.is_period(val):
             dtype = PeriodDtype(freq=val.freq)
             val = val.ordinal
-        elif lib.is_interval(val):
-            subtype = infer_dtype_from_scalar(val.left, pandas_dtype=True)[0]
-            dtype = IntervalDtype(subtype=subtype)
 
     return dtype, val