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

Author: hweecat

.github/workflows/ci.yml

@@ -23,53 +23,53 @@ jobs:
 
     - name: Looking for unwanted patterns
       run: ci/code_checks.sh patterns
-      if: true
+      if: always()
 
     - name: Setup environment and build pandas
       run: ci/setup_env.sh
-      if: true
+      if: always()
 
     - name: Linting
       run: |
         source activate pandas-dev
         ci/code_checks.sh lint
-      if: true
+      if: always()
 
     - name: Dependencies consistency
       run: |
         source activate pandas-dev
         ci/code_checks.sh dependencies
-      if: true
+      if: always()
 
     - name: Checks on imported code
       run: |
         source activate pandas-dev
         ci/code_checks.sh code
-      if: true
+      if: always()
 
     - name: Running doctests
       run: |
         source activate pandas-dev
         ci/code_checks.sh doctests
-      if: true
+      if: always()
 
     - name: Docstring validation
       run: |
         source activate pandas-dev
         ci/code_checks.sh docstrings
-      if: true
+      if: always()
 
     - name: Typing validation
       run: |
         source activate pandas-dev
         ci/code_checks.sh typing
-      if: true
+      if: always()
 
     - name: Testing docstring validation script
       run: |
         source activate pandas-dev
         pytest --capture=no --strict scripts
-      if: true
+      if: always()
 
     - name: Running benchmarks
       run: |
@@ -87,11 +87,73 @@ jobs:
         else
             echo "Benchmarks did not run, no changes detected"
         fi
-      if: true
+      if: always()
 
     - name: Publish benchmarks artifact
       uses: actions/upload-artifact@master
       with:
         name: Benchmarks log
         path: asv_bench/benchmarks.log
       if: failure()
+
+  web_and_docs:
+    name: Web and docs
+    runs-on: ubuntu-latest
+    steps:
+
+    - name: Setting conda path
+      run: echo "::set-env name=PATH::${HOME}/miniconda3/bin:${PATH}"
+
+    - name: Checkout
+      uses: actions/checkout@v1
+
+    - name: Setup environment and build pandas
+      run: ci/setup_env.sh
+
+    - name: Build website
+      run: |
+        source activate pandas-dev
+        python web/pandas_web.py web/pandas --target-path=web/build
+
+    - name: Build documentation
+      run: |
+        source activate pandas-dev
+        doc/make.py --warnings-are-errors | tee sphinx.log ; exit ${PIPESTATUS[0]}
+
+    # This can be removed when the ipython directive fails when there are errors,
+    # including the `tee sphinx.log` in te previous step (https://github.com/ipython/ipython/issues/11547)
+    - name: Check ipython directive errors
+      run: "! grep -B1 \"^<<<-------------------------------------------------------------------------$\" sphinx.log"
+
+    - name: Merge website and docs
+      run: |
+        mkdir -p pandas_web/docs
+        cp -r web/build/* pandas_web/
+        cp -r doc/build/html/* pandas_web/docs/
+      if: github.event_name == 'push'
+
+    - name: Install Rclone
+      run: sudo apt install rclone -y
+      if: github.event_name == 'push'
+
+    - name: Set up Rclone
+      run: |
+        RCLONE_CONFIG_PATH=$HOME/.config/rclone/rclone.conf
+        mkdir -p `dirname $RCLONE_CONFIG_PATH`
+        echo "[ovh_cloud_pandas_web]" > $RCLONE_CONFIG_PATH
+        echo "type = swift" >> $RCLONE_CONFIG_PATH
+        echo "env_auth = false" >> $RCLONE_CONFIG_PATH
+        echo "auth_version = 3" >> $RCLONE_CONFIG_PATH
+        echo "auth = https://auth.cloud.ovh.net/v3/" >> $RCLONE_CONFIG_PATH
+        echo "endpoint_type = public" >> $RCLONE_CONFIG_PATH
+        echo "tenant_domain = default" >> $RCLONE_CONFIG_PATH
+        echo "tenant = 2977553886518025" >> $RCLONE_CONFIG_PATH
+        echo "domain = default" >> $RCLONE_CONFIG_PATH
+        echo "user = w4KGs3pmDxpd" >> $RCLONE_CONFIG_PATH
+        echo "key = ${{ secrets.ovh_object_store_key }}" >> $RCLONE_CONFIG_PATH
+        echo "region = BHS" >> $RCLONE_CONFIG_PATH
+      if: github.event_name == 'push'
+
+    - name: Sync web
+      run: rclone sync pandas_web ovh_cloud_pandas_web:dev
+      if: github.event_name == 'push'

.travis.yml

@@ -1,5 +1,5 @@
 language: python
-python: 3.5
+python: 3.7
 
 # To turn off cached cython files and compiler cache
 # set NOCACHE-true

doc/source/user_guide/integer_na.rst

@@ -15,6 +15,10 @@ Nullable integer data type
    IntegerArray is currently experimental. Its API or implementation may
    change without warning.
 
+.. versionchanged:: 1.0.0
+
+   Now uses :attr:`pandas.NA` as the missing value rather
+   than :attr:`numpy.nan`.
 
 In :ref:`missing_data`, we saw that pandas primarily uses ``NaN`` to represent
 missing data. Because ``NaN`` is a float, this forces an array of integers with
@@ -23,6 +27,9 @@ much. But if your integer column is, say, an identifier, casting to float can
 be problematic. Some integers cannot even be represented as floating point
 numbers.
 
+Construction
+------------
+
 Pandas can represent integer data with possibly missing values using
 :class:`arrays.IntegerArray`. This is an :ref:`extension types <extending.extension-types>`
 implemented within pandas.
@@ -39,6 +46,12 @@ NumPy's ``'int64'`` dtype:
 
    pd.array([1, 2, np.nan], dtype="Int64")
 
+All NA-like values are replaced with :attr:`pandas.NA`.
+
+.. ipython:: python
+
+   pd.array([1, 2, np.nan, None, pd.NA], dtype="Int64")
+
 This array can be stored in a :class:`DataFrame` or :class:`Series` like any
 NumPy array.
 
@@ -78,6 +91,9 @@ with the dtype.
    In the future, we may provide an option for :class:`Series` to infer a
    nullable-integer dtype.
 
+Operations
+----------
+
 Operations involving an integer array will behave similar to NumPy arrays.
 Missing values will be propagated, and the data will be coerced to another
 dtype if needed.
@@ -123,3 +139,15 @@ Reduction and groupby operations such as 'sum' work as well.
 
    df.sum()
    df.groupby('B').A.sum()
+
+Scalar NA Value
+---------------
+
+:class:`arrays.IntegerArray` uses :attr:`pandas.NA` as its scalar
+missing value. Slicing a single element that's missing will return
+:attr:`pandas.NA`
+
+.. ipython:: python
+
+   a = pd.array([1, None], dtype="Int64")
+   a[1]

doc/source/whatsnew/v1.0.0.rst

@@ -357,6 +357,64 @@ The following methods now also correctly output values for unobserved categories
 
 As a reminder, you can specify the ``dtype`` to disable all inference.
 
+:class:`arrays.IntegerArray` now uses :attr:`pandas.NA`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+:class:`arrays.IntegerArray` now uses :attr:`pandas.NA` rather than
+:attr:`numpy.nan` as its missing value marker (:issue:`29964`).
+
+*pandas 0.25.x*
+
+.. code-block:: python
+
+   >>> a = pd.array([1, 2, None], dtype="Int64")
+   >>> a
+   <IntegerArray>
+   [1, 2, NaN]
+   Length: 3, dtype: Int64
+
+   >>> a[2]
+   nan
+
+*pandas 1.0.0*
+
+.. ipython:: python
+
+   a = pd.array([1, 2, None], dtype="Int64")
+   a[2]
+
+See :ref:`missing_data.NA` for more on the differences between :attr:`pandas.NA`
+and :attr:`numpy.nan`.
+
+:class:`arrays.IntegerArray` comparisons return :class:`arrays.BooleanArray`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Comparison operations on a :class:`arrays.IntegerArray` now returns a
+:class:`arrays.BooleanArray` rather than a NumPy array (:issue:`29964`).
+
+*pandas 0.25.x*
+
+.. code-block:: python
+
+   >>> a = pd.array([1, 2, None], dtype="Int64")
+   >>> a
+   <IntegerArray>
+   [1, 2, NaN]
+   Length: 3, dtype: Int64
+
+   >>> a > 1
+   array([False,  True, False])
+
+*pandas 1.0.0*
+
+.. ipython:: python
+
+   a = pd.array([1, 2, None], dtype="Int64")
+   a > 1
+
+Note that missing values now propagate, rather than always comparing unequal
+like :attr:`numpy.nan`. See :ref:`missing_data.NA` for more.
+
 By default :meth:`Categorical.min` now returns the minimum instead of np.nan
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -728,6 +786,7 @@ Datetimelike
 - Bug in :class:`DatetimeIndex` addition when adding a non-optimized :class:`DateOffset` incorrectly dropping timezone information (:issue:`30336`)
 - Bug in :meth:`DataFrame.drop` where attempting to drop non-existent values from a DatetimeIndex would yield a confusing error message (:issue:`30399`)
 - Bug in :meth:`DataFrame.append` would remove the timezone-awareness of new data (:issue:`30238`)
+- Bug in :meth:`Series.cummin` and :meth:`Series.cummax` with timezone-aware dtype incorrectly dropping its timezone (:issue:`15553`)
 - Bug in :class:`DatetimeArray`, :class:`TimedeltaArray`, and :class:`PeriodArray` where inplace addition and subtraction did not actually operate inplace (:issue:`24115`)
 
 Timedelta
@@ -757,6 +816,7 @@ Numeric
 - 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`)
 - Bug in :meth:`Series.interpolate` when using method=`index` with an unsorted index, would previously return incorrect results. (:issue:`21037`)
 - Bug in :meth:`DataFrame.round` where a :class:`DataFrame` with a :class:`CategoricalIndex` of :class:`IntervalIndex` columns would incorrectly raise a ``TypeError`` (:issue:`30063`)
+- Bug in :class:`DataFrame` cumulative operations (e.g. cumsum, cummax) incorrect casting to object-dtype (:issue:`19296`)
 
 Conversion
 ^^^^^^^^^^

pandas/_config/config.py

@@ -197,7 +197,7 @@ def __setattr__(self, key, val):
         else:
             raise OptionError("You can only set the value of existing options")
 
-    def __getattr__(self, key):
+    def __getattr__(self, key: str):
         prefix = object.__getattribute__(self, "prefix")
         if prefix:
             prefix += "."

pandas/compat/numpy/function.py

@@ -169,13 +169,6 @@ def validate_clip_with_axis(axis, args, kwargs):
     return axis
 
 
-COMPRESS_DEFAULTS: "OrderedDict[str, Any]" = OrderedDict()
-COMPRESS_DEFAULTS["axis"] = None
-COMPRESS_DEFAULTS["out"] = None
-validate_compress = CompatValidator(
-    COMPRESS_DEFAULTS, fname="compress", method="both", max_fname_arg_count=1
-)
-
 CUM_FUNC_DEFAULTS: "OrderedDict[str, Any]" = OrderedDict()
 CUM_FUNC_DEFAULTS["dtype"] = None
 CUM_FUNC_DEFAULTS["out"] = None

pandas/core/arrays/boolean.py

@@ -524,7 +524,7 @@ def astype(self, dtype, copy=True):
             na_value = np.nan
         # coerce
         data = self._coerce_to_ndarray(na_value=na_value)
-        return astype_nansafe(data, dtype, copy=None)
+        return astype_nansafe(data, dtype, copy=False)
 
     def value_counts(self, dropna=True):
         """
@@ -730,7 +730,6 @@ def all(self, skipna: bool = True, **kwargs):
     @classmethod
     def _create_logical_method(cls, op):
         def logical_method(self, other):
-
             if isinstance(other, (ABCDataFrame, ABCSeries, ABCIndexClass)):
                 # Rely on pandas to unbox and dispatch to us.
                 return NotImplemented
@@ -777,8 +776,11 @@ def logical_method(self, other):
     @classmethod
     def _create_comparison_method(cls, op):
         def cmp_method(self, other):
+            from pandas.arrays import IntegerArray
 
-            if isinstance(other, (ABCDataFrame, ABCSeries, ABCIndexClass)):
+            if isinstance(
+                other, (ABCDataFrame, ABCSeries, ABCIndexClass, IntegerArray)
+            ):
                 # Rely on pandas to unbox and dispatch to us.
                 return NotImplemented