Merge remote-tracking branch 'upstream/master' into docfix-multiindex-set_levels

Author: hweecat

.github/workflows/ci.yml

@@ -8,8 +8,6 @@ on:
 
 env:
   ENV_FILE: environment.yml
-  # TODO: remove export PATH=... in each step once this works
-  # PATH: $HOME/miniconda3/bin:$PATH
 
 jobs:
   checks:
@@ -20,68 +18,61 @@ jobs:
     - name: Checkout
       uses: actions/checkout@v1
 
+    - name: Setting conda path
+      run: echo "::set-env name=PATH::${HOME}/miniconda3/bin:${PATH}"
+
     - name: Looking for unwanted patterns
       run: ci/code_checks.sh patterns
       if: true
 
     - name: Setup environment and build pandas
-      run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
-        ci/setup_env.sh
+      run: ci/setup_env.sh
       if: true
 
     - name: Linting
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh lint
       if: true
 
     - name: Dependencies consistency
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh dependencies
       if: true
 
     - name: Checks on imported code
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh code
       if: true
 
     - name: Running doctests
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh doctests
       if: true
 
     - name: Docstring validation
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh docstrings
       if: true
 
     - name: Typing validation
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh typing
       if: true
 
     - name: Testing docstring validation script
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         pytest --capture=no --strict scripts
       if: true
 
     - name: Running benchmarks
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         cd asv_bench
         asv check -E existing

asv_bench/benchmarks/timeseries.py

@@ -113,7 +113,7 @@ class InferFreq:
     def setup(self, freq):
         if freq is None:
             self.idx = date_range(start="1/1/1700", freq="D", periods=10000)
-            self.idx.freq = None
+            self.idx._data._freq = None
         else:
             self.idx = date_range(start="1/1/1700", freq=freq, periods=10000)
 

doc/redirects.csv

@@ -357,10 +357,8 @@ generated/pandas.DataFrame.from_csv,../reference/api/pandas.DataFrame.from_csv
 generated/pandas.DataFrame.from_dict,../reference/api/pandas.DataFrame.from_dict
 generated/pandas.DataFrame.from_items,../reference/api/pandas.DataFrame.from_items
 generated/pandas.DataFrame.from_records,../reference/api/pandas.DataFrame.from_records
-generated/pandas.DataFrame.ftypes,../reference/api/pandas.DataFrame.ftypes
 generated/pandas.DataFrame.ge,../reference/api/pandas.DataFrame.ge
 generated/pandas.DataFrame.get_dtype_counts,../reference/api/pandas.DataFrame.get_dtype_counts
-generated/pandas.DataFrame.get_ftype_counts,../reference/api/pandas.DataFrame.get_ftype_counts
 generated/pandas.DataFrame.get,../reference/api/pandas.DataFrame.get
 generated/pandas.DataFrame.get_value,../reference/api/pandas.DataFrame.get_value
 generated/pandas.DataFrame.get_values,../reference/api/pandas.DataFrame.get_values
@@ -883,10 +881,8 @@ generated/pandas.Panel.first_valid_index,../reference/api/pandas.Panel.first_val
 generated/pandas.Panel.floordiv,../reference/api/pandas.Panel.floordiv
 generated/pandas.Panel.from_dict,../reference/api/pandas.Panel.from_dict
 generated/pandas.Panel.fromDict,../reference/api/pandas.Panel.fromDict
-generated/pandas.Panel.ftypes,../reference/api/pandas.Panel.ftypes
 generated/pandas.Panel.ge,../reference/api/pandas.Panel.ge
 generated/pandas.Panel.get_dtype_counts,../reference/api/pandas.Panel.get_dtype_counts
-generated/pandas.Panel.get_ftype_counts,../reference/api/pandas.Panel.get_ftype_counts
 generated/pandas.Panel.get,../reference/api/pandas.Panel.get
 generated/pandas.Panel.get_value,../reference/api/pandas.Panel.get_value
 generated/pandas.Panel.get_values,../reference/api/pandas.Panel.get_values
@@ -1223,11 +1219,8 @@ generated/pandas.Series.flags,../reference/api/pandas.Series.flags
 generated/pandas.Series.floordiv,../reference/api/pandas.Series.floordiv
 generated/pandas.Series.from_array,../reference/api/pandas.Series.from_array
 generated/pandas.Series.from_csv,../reference/api/pandas.Series.from_csv
-generated/pandas.Series.ftype,../reference/api/pandas.Series.ftype
-generated/pandas.Series.ftypes,../reference/api/pandas.Series.ftypes
 generated/pandas.Series.ge,../reference/api/pandas.Series.ge
 generated/pandas.Series.get_dtype_counts,../reference/api/pandas.Series.get_dtype_counts
-generated/pandas.Series.get_ftype_counts,../reference/api/pandas.Series.get_ftype_counts
 generated/pandas.Series.get,../reference/api/pandas.Series.get
 generated/pandas.Series.get_value,../reference/api/pandas.Series.get_value
 generated/pandas.Series.get_values,../reference/api/pandas.Series.get_values

doc/source/reference/frame.rst

@@ -28,7 +28,6 @@ Attributes and underlying data
    :toctree: api/
 
    DataFrame.dtypes
-   DataFrame.ftypes
    DataFrame.get_dtype_counts
    DataFrame.select_dtypes
    DataFrame.values

doc/source/reference/series.rst

@@ -29,7 +29,6 @@ Attributes
    Series.array
    Series.values
    Series.dtype
-   Series.ftype
    Series.shape
    Series.nbytes
    Series.ndim
@@ -43,7 +42,6 @@ Attributes
    Series.flags
    Series.empty
    Series.dtypes
-   Series.ftypes
    Series.data
    Series.name
    Series.put

doc/source/user_guide/timeseries.rst

@@ -772,7 +772,6 @@ There are several time/date properties that one can access from ``Timestamp`` or
     week,"The week ordinal of the year"
     dayofweek,"The number of the day of the week with Monday=0, Sunday=6"
     weekday,"The number of the day of the week with Monday=0, Sunday=6"
-    weekday_name,"The name of the day in a week (ex: Friday)"
     quarter,"Quarter of the date: Jan-Mar = 1, Apr-Jun = 2, etc."
     days_in_month,"The number of days in the month of the datetime"
     is_month_start,"Logical indicating if first day of month (defined by frequency)"
@@ -1591,18 +1590,18 @@ labels.
 
         s = pd.date_range('2000-01-01', '2000-01-05').to_series()
         s.iloc[2] = pd.NaT
-        s.dt.weekday_name
+        s.dt.day_name()
 
         # default: label='left', closed='left'
-        s.resample('B').last().dt.weekday_name
+        s.resample('B').last().dt.day_name()
 
     Notice how the value for Sunday got pulled back to the previous Friday.
     To get the behavior where the value for Sunday is pushed to Monday, use
     instead
 
     .. ipython:: python
 
-        s.resample('B', label='right', closed='right').last().dt.weekday_name
+        s.resample('B', label='right', closed='right').last().dt.day_name()
 
 The ``axis`` parameter can be set to 0 or 1 and allows you to resample the
 specified axis for a ``DataFrame``.

doc/source/whatsnew/v1.0.0.rst

@@ -394,11 +394,14 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 **Other removals**
 
 - Floordiv of integer-dtyped array by :class:`Timedelta` now raises ``TypeError`` (:issue:`21036`)
+- :func:`pandas.api.types.infer_dtype` argument ``skipna`` defaults to ``True`` instead of ``False`` (:issue:`24050`)
 - Removed the previously deprecated :meth:`Index.summary` (:issue:`18217`)
 - Removed the previously deprecated "fastpath" keyword from the :class:`Index` constructor (:issue:`23110`)
 - Removed the previously deprecated :meth:`Series.get_value`, :meth:`Series.set_value`, :meth:`DataFrame.get_value`, :meth:`DataFrame.set_value` (:issue:`17739`)
 - Changed the the default value of `inplace` in :meth:`DataFrame.set_index` and :meth:`Series.set_axis`. It now defaults to False (:issue:`27600`)
+- Removed the previously deprecated :attr:`Series.cat.categorical`, :attr:`Series.cat.index`, :attr:`Series.cat.name` (:issue:`24751`)
 - Removed support for nested renaming in :meth:`DataFrame.aggregate`, :meth:`Series.aggregate`, :meth:`DataFrameGroupBy.aggregate`, :meth:`SeriesGroupBy.aggregate`, :meth:`Rolling.aggregate` (:issue:`18529`)
+- Passing ``datetime64`` data to :class:`TimedeltaIndex` or ``timedelta64`` data to ``DatetimeIndex`` now raises ``TypeError`` (:issue:`23539`, :issue:`23937`)
 - A tuple passed to :meth:`DataFrame.groupby` is now exclusively treated as a single key (:issue:`18314`)
 - Removed :meth:`Series.from_array` (:issue:`18258`)
 - Removed :meth:`DataFrame.from_items` (:issue:`18458`)
@@ -432,6 +435,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Removed the previously deprecated :meth:`Series.valid`; use :meth:`Series.dropna` instead (:issue:`18800`)
 - Removed the previously properties :attr:`DataFrame.is_copy`, :attr:`Series.is_copy` (:issue:`18812`)
 - Removed the previously deprecated :meth:`DataFrame.get_ftype_counts`, :meth:`Series.get_ftype_counts` (:issue:`18243`)
+- Removed the previously deprecated :meth:`DataFrame.ftypes`, :meth:`Series.ftypes`, :meth:`Series.ftype` (:issue:`26744`)
 - Removed the previously deprecated :meth:`Index.get_duplicated`, use ``idx[idx.duplicated()].unique()`` instead (:issue:`20239`)
 - Removed the previously deprecated :meth:`Series.clip_upper`, :meth:`Series.clip_lower`, :meth:`DataFrame.clip_upper`, :meth:`DataFrame.clip_lower` (:issue:`24203`)
 - Removed the ability to alter :attr:`DatetimeIndex.freq`, :attr:`TimedeltaIndex.freq`, or :attr:`PeriodIndex.freq` (:issue:`20772`)
@@ -445,6 +449,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Removed previously deprecated keyword "n" from :meth:`DatetimeIndex.shift`, :meth:`TimedeltaIndex.shift`, :meth:`PeriodIndex.shift`, use "periods" instead (:issue:`22458`)
 - Changed the default value for the `raw` argument in :func:`Series.rolling().apply() <pandas.core.window.Rolling.apply>`, :func:`DataFrame.rolling().apply() <pandas.core.window.Rolling.apply>`,
 - :func:`Series.expanding().apply() <pandas.core.window.Expanding.apply>`, and :func:`DataFrame.expanding().apply() <pandas.core.window.Expanding.apply>` to ``False`` (:issue:`20584`)
+- Removed previously deprecated :attr:`Timestamp.weekday_name`, :attr:`DatetimeIndex.weekday_name`, and :attr:`Series.dt.weekday_name` (:issue:`18164`)
 -
 
 .. _whatsnew_1000.performance:
@@ -526,7 +531,8 @@ Numeric
 - Improved error message when using `frac` > 1 and `replace` = False (:issue:`27451`)
 - Bug in numeric indexes resulted in it being possible to instantiate an :class:`Int64Index`, :class:`UInt64Index`, or :class:`Float64Index` with an invalid dtype (e.g. datetime-like) (:issue:`29539`)
 - Bug in :class:`UInt64Index` precision loss while constructing from a list with values in the ``np.uint64`` range (:issue:`29526`)
--
+- Bug in :class:`NumericIndex` construction that caused indexing to fail when integers in the ``np.uint64`` range were used (:issue:`28023`)
+- Bug in :class:`NumericIndex` construction that caused :class:`UInt64Index` to be casted to :class:`Float64Index` when integers in the ``np.uint64`` range were used to index a :class:`DataFrame` (:issue:`28279`)
 
 Conversion
 ^^^^^^^^^^

pandas/_libs/internals.pyx

@@ -54,7 +54,7 @@ cdef class BlockPlacement:
         else:
             v = self._as_array
 
-        return f'{self.__class__.__name__}({v})'
+        return f'{type(self).__name__}({v})'
 
     def __repr__(self) -> str:
         return str(self)

pandas/_libs/lib.pyx

@@ -4,7 +4,6 @@ from fractions import Fraction
 from numbers import Number
 
 import sys
-import warnings
 
 import cython
 from cython import Py_ssize_t
@@ -615,7 +614,7 @@ def clean_index_list(obj: list):
 
     # don't force numpy coerce with nan's
     inferred = infer_dtype(obj, skipna=False)
-    if inferred in ['string', 'bytes', 'unicode', 'mixed', 'mixed-integer']:
+    if inferred in ['string', 'bytes', 'mixed', 'mixed-integer']:
         return np.asarray(obj, dtype=object), 0
     elif inferred in ['integer']:
         # TODO: we infer an integer but it *could* be a uint64
@@ -1094,15 +1093,15 @@ cdef _try_infer_map(v):
     return None
 
 
-def infer_dtype(value: object, skipna: object=None) -> str:
+def infer_dtype(value: object, skipna: bool = True) -> str:
     """
     Efficiently infer the type of a passed val, or list-like
     array of values. Return a string describing the type.
 
     Parameters
     ----------
     value : scalar, list, ndarray, or pandas type
-    skipna : bool, default False
+    skipna : bool, default True
         Ignore NaN values when inferring the type.
 
         .. versionadded:: 0.21.0
@@ -1113,7 +1112,6 @@ def infer_dtype(value: object, skipna: object=None) -> str:
     Results can include:
 
     - string
-    - unicode
     - bytes
     - floating
     - integer
@@ -1200,12 +1198,6 @@ def infer_dtype(value: object, skipna: object=None) -> str:
         bint seen_pdnat = False
         bint seen_val = False
 
-    if skipna is None:
-        msg = ('A future version of pandas will default to `skipna=True`. To '
-               'silence this warning, pass `skipna=True|False` explicitly.')
-        warnings.warn(msg, FutureWarning, stacklevel=2)
-        skipna = False
-
     if util.is_array(value):
         values = value
     elif hasattr(value, 'dtype'):

pandas/_libs/tslibs/c_timestamp.pyx

@@ -87,7 +87,7 @@ cdef class _Timestamp(datetime):
                 return PyObject_RichCompareBool(val, other, op)
 
             try:
-                ots = self.__class__(other)
+                ots = type(self)(other)
             except ValueError:
                 return self._compare_outside_nanorange(other, op)
         else:
@@ -96,7 +96,7 @@ cdef class _Timestamp(datetime):
             if ndim != -1:
                 if ndim == 0:
                     if is_datetime64_object(other):
-                        other = self.__class__(other)
+                        other = type(self)(other)
                     elif is_array(other):
                         # zero-dim array, occurs if try comparison with
                         #  datetime64 scalar on the left hand side
@@ -105,7 +105,7 @@ cdef class _Timestamp(datetime):
                         #  the numpy C api to extract it.
                         other = cnp.PyArray_ToScalar(cnp.PyArray_DATA(other),
                                                      other)
-                        other = self.__class__(other)
+                        other = type(self)(other)
                     else:
                         return NotImplemented
                 elif is_array(other):
@@ -226,8 +226,7 @@ cdef class _Timestamp(datetime):
 
         if is_timedelta64_object(other):
             other_int = other.astype('timedelta64[ns]').view('i8')
-            return self.__class__(self.value + other_int,
-                                  tz=self.tzinfo, freq=self.freq)
+            return type(self)(self.value + other_int, tz=self.tzinfo, freq=self.freq)
 
         elif is_integer_object(other):
             maybe_integer_op_deprecated(self)
@@ -238,8 +237,7 @@ cdef class _Timestamp(datetime):
             elif self.freq is None:
                 raise NullFrequencyError(
                     "Cannot add integral value to Timestamp without freq.")
-            return self.__class__((self.freq * other).apply(self),
-                                  freq=self.freq)
+            return type(self)((self.freq * other).apply(self), freq=self.freq)
 
         elif PyDelta_Check(other) or hasattr(other, 'delta'):
             # delta --> offsets.Tick
@@ -253,8 +251,7 @@ cdef class _Timestamp(datetime):
                          other.seconds * 1000000 +
                          other.microseconds) * 1000
 
-            result = self.__class__(self.value + nanos,
-                                    tz=self.tzinfo, freq=self.freq)
+            result = type(self)(self.value + nanos, tz=self.tzinfo, freq=self.freq)
             return result
 
         elif is_array(other):
@@ -272,7 +269,7 @@ cdef class _Timestamp(datetime):
 
         result = datetime.__add__(self, other)
         if PyDateTime_Check(result):
-            result = self.__class__(result)
+            result = type(self)(result)
             result.nanosecond = self.nanosecond
         return result
 
@@ -304,9 +301,9 @@ cdef class _Timestamp(datetime):
         if (PyDateTime_Check(self)
                 and (PyDateTime_Check(other) or is_datetime64_object(other))):
             if isinstance(self, _Timestamp):
-                other = self.__class__(other)
+                other = type(self)(other)
             else:
-                self = other.__class__(self)
+                self = type(other)(self)
 
             # validate tz's
             if not tz_compare(self.tzinfo, other.tzinfo):

pandas/_libs/tslibs/fields.pyx

@@ -90,7 +90,7 @@ def build_field_sarray(const int64_t[:] dtindex):
 def get_date_name_field(const int64_t[:] dtindex, object field, object locale=None):
     """
     Given a int64-based datetime index, return array of strings of date
-    name based on requested field (e.g. weekday_name)
+    name based on requested field (e.g. day_name)
     """
     cdef:
         Py_ssize_t i, count = len(dtindex)
@@ -100,7 +100,7 @@ def get_date_name_field(const int64_t[:] dtindex, object field, object locale=No
 
     out = np.empty(count, dtype=object)
 
-    if field == 'day_name' or field == 'weekday_name':
+    if field == 'day_name':
         if locale is None:
             names = np.array(DAYS_FULL, dtype=np.object_)
         else:

pandas/_libs/tslibs/nattype.pyx

@@ -364,7 +364,6 @@ class NaTType(_NaT):
     days_in_month = property(fget=lambda self: np.nan)
     daysinmonth = property(fget=lambda self: np.nan)
     dayofweek = property(fget=lambda self: np.nan)
-    weekday_name = property(fget=lambda self: np.nan)
 
     # inject Timedelta properties
     days = property(fget=lambda self: np.nan)