Merge remote-tracking branch 'upstream/master' into bug/categorical-i…

…ndexing-1row-df * upstream/master: (32 commits) DEPR: Series.cat.categorical (pandas-dev#29914) DEPR: infer_dtype default for skipna is now True (pandas-dev#29876) Fix broken asv (pandas-dev#29906) DEPR: Remove weekday_name (pandas-dev#29831) Fix mypy errors for pandas\tests\series\test_operators.py (pandas-dev#29826) CI: Setting path only once in GitHub Actions (pandas-dev#29867) DEPR: passing td64 data to DTA or dt64 data to TDA (pandas-dev#29794) CLN: remove unsupported sparse code from io.pytables (pandas-dev#29863) x.__class__ TO type(x) (pandas-dev#29889) DEPR: ftype, ftypes (pandas-dev#29895) REF: use named funcs instead of lambdas (pandas-dev#29841) Correct type inference for UInt64Index during access (pandas-dev#29420) CLN: follow-up to 29725 (pandas-dev#29890) CLN: trim unnecessary code in indexing tests (pandas-dev#29845) TST added test for groupby agg on mulitlevel column (pandas-dev#29772) (pandas-dev#29866) mypy fix (pandas-dev#29891) Typing annotations (pandas-dev#29850) Fix mypy error in pandas/tests.indexes.test_base.py (pandas-dev#29188) CLN: remove never-used kwargs, make kwargs explicit (pandas-dev#29873) TYP: Added typing to __eq__ functions (pandas-dev#29818) ...
keechongtan · Nov 29, 2019 · e5c1420 · e5c1420
2 parents 2b71592 + ea2e26a
commit e5c1420
Show file tree

Hide file tree

Showing 88 changed files with 463 additions and 1,053 deletions.
diff --git a/.github/workflows/ci.yml b/.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

diff --git a/README.md b/README.md
@@ -164,12 +164,11 @@ pip install pandas
 ```
 
 ## Dependencies
-- [NumPy](https://www.numpy.org): 1.13.3 or higher
-- [python-dateutil](https://labix.org/python-dateutil): 2.5.0 or higher
-- [pytz](https://pythonhosted.org/pytz): 2015.4 or higher
+- [NumPy](https://www.numpy.org)
+- [python-dateutil](https://labix.org/python-dateutil)
+- [pytz](https://pythonhosted.org/pytz)
 
-See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies)
-for recommended and optional dependencies.
+See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies.
 
 ## Installation from sources
 To install pandas from source you need Cython in addition to the normal

diff --git a/asv_bench/benchmarks/timeseries.py b/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)
 

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -16,95 +16,6 @@ jobs:
     name: Windows
     vmImage: vs2017-win2016
 
-- job: 'Checks'
-  pool:
-    vmImage: ubuntu-16.04
-  timeoutInMinutes: 90
-  steps:
-  - script: |
-      echo '##vso[task.prependpath]$(HOME)/miniconda3/bin'
-      echo '##vso[task.setvariable variable=ENV_FILE]environment.yml'
-      echo '##vso[task.setvariable variable=AZURE]true'
-    displayName: 'Setting environment variables'
-
-  # Do not require a conda environment
-  - script: ci/code_checks.sh patterns
-    displayName: 'Looking for unwanted patterns'
-    condition: true
-
-  - script: |
-      sudo apt-get update
-      sudo apt-get install -y libc6-dev-i386
-      ci/setup_env.sh
-    displayName: 'Setup environment and build pandas'
-    condition: true
-
-  # Do not require pandas
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh lint
-    displayName: 'Linting'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh dependencies
-    displayName: 'Dependencies consistency'
-    condition: true
-
-  # Require pandas
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh code
-    displayName: 'Checks on imported code'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh doctests
-    displayName: 'Running doctests'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh docstrings
-    displayName: 'Docstring validation'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh typing
-    displayName: 'Typing validation'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      pytest --capture=no --strict scripts
-    displayName: 'Testing docstring validation script'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      cd asv_bench
-      asv check -E existing
-      git remote add upstream https://github.com/pandas-dev/pandas.git
-      git fetch upstream
-      if git diff upstream/master --name-only | grep -q "^asv_bench/"; then
-          asv machine --yes
-          ASV_OUTPUT="$(asv dev)"
-          if [[ $(echo "$ASV_OUTPUT" | grep "failed") ]]; then
-              echo "##vso[task.logissue type=error]Benchmarks run with errors"
-              echo "$ASV_OUTPUT"
-              exit 1
-          else
-              echo "Benchmarks run without errors"
-          fi
-      else
-          echo "Benchmarks did not run, no changes detected"
-      fi
-    displayName: 'Running benchmarks'
-    condition: true
-
 - job: 'Web_and_Docs'
   pool:
     vmImage: ubuntu-16.04

diff --git a/doc/redirects.csv b/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

diff --git a/doc/source/reference/frame.rst b/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

diff --git a/doc/source/reference/series.rst b/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

diff --git a/doc/source/user_guide/scale.rst b/doc/source/user_guide/scale.rst
@@ -94,7 +94,7 @@ Use efficient datatypes
 
 The default pandas data types are not the most memory efficient. This is
 especially true for text data columns with relatively few unique values (commonly
-referred to as "low-cardinality" data). By using more efficient data types you
+referred to as "low-cardinality" data). By using more efficient data types, you
 can store larger datasets in memory.
 
 .. ipython:: python

diff --git a/doc/source/user_guide/timeseries.rst b/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``.

diff --git a/doc/source/whatsnew/v1.0.0.rst b/doc/source/whatsnew/v1.0.0.rst
@@ -402,10 +402,14 @@ 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`)
@@ -439,6 +443,7 @@ 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`)
@@ -452,6 +457,7 @@ 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:
@@ -533,7 +539,8 @@ 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
 ^^^^^^^^^^

diff --git a/environment.yml b/environment.yml
@@ -78,7 +78,7 @@ dependencies:
   - fastparquet>=0.3.2  # pandas.read_parquet, DataFrame.to_parquet
   - html5lib  # pandas.read_html
   - lxml  # pandas.read_html
-  - openpyxl  # pandas.read_excel, DataFrame.to_excel, pandas.ExcelWriter, pandas.ExcelFile
+  - openpyxl<=3.0.1  # pandas.read_excel, DataFrame.to_excel, pandas.ExcelWriter, pandas.ExcelFile
   - pyarrow>=0.13.1  # pandas.read_parquet, DataFrame.to_parquet, pandas.read_feather, DataFrame.to_feather
   - pyqt>=5.9.2  # pandas.read_clipboard
   - pytables>=3.4.2  # pandas.read_hdf, DataFrame.to_hdf

diff --git a/pandas/__init__.py b/pandas/__init__.py
@@ -24,6 +24,7 @@
     _np_version_under1p15,
     _np_version_under1p16,
     _np_version_under1p17,
+    _np_version_under1p18,
 )
 
 try:

diff --git a/pandas/_libs/internals.pyx b/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)