Merge branch '33141-pandas-cut' of github.com:mabelvj/pandas into 33141-pandas-cut

Author: mabelvj

README.md

@@ -7,6 +7,7 @@
 # pandas: powerful Python data analysis toolkit
 [![PyPI Latest Release](https://img.shields.io/pypi/v/pandas.svg)](https://pypi.org/project/pandas/)
 [![Conda Latest Release](https://anaconda.org/conda-forge/pandas/badges/version.svg)](https://anaconda.org/anaconda/pandas/)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3509134.svg)](https://doi.org/10.5281/zenodo.3509134)
 [![Package Status](https://img.shields.io/pypi/status/pandas.svg)](https://pypi.org/project/pandas/)
 [![License](https://img.shields.io/pypi/l/pandas.svg)](https://github.com/pandas-dev/pandas/blob/master/LICENSE)
 [![Travis Build Status](https://travis-ci.org/pandas-dev/pandas.svg?branch=master)](https://travis-ci.org/pandas-dev/pandas)

asv_bench/asv.conf.json

@@ -39,7 +39,7 @@
     // followed by the pip installed packages).
     "matrix": {
         "numpy": [],
-        "Cython": [],
+        "Cython": ["0.29.16"],
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],

asv_bench/benchmarks/array.py

@@ -9,6 +9,11 @@ def setup(self):
         self.values_float = np.array([1.0, 0.0, 1.0, 0.0])
         self.values_integer = np.array([1, 0, 1, 0])
         self.values_integer_like = [1, 0, 1, 0]
+        self.data = np.array([True, False, True, False])
+        self.mask = np.array([False, False, True, False])
+
+    def time_constructor(self):
+        pd.arrays.BooleanArray(self.data, self.mask)
 
     def time_from_bool_array(self):
         pd.array(self.values_bool, dtype="boolean")
@@ -21,3 +26,16 @@ def time_from_integer_like(self):
 
     def time_from_float_array(self):
         pd.array(self.values_float, dtype="boolean")
+
+
+class IntegerArray:
+    def setup(self):
+        self.values_integer = np.array([1, 0, 1, 0])
+        self.data = np.array([1, 2, 3, 4], dtype="int64")
+        self.mask = np.array([False, False, True, False])
+
+    def time_constructor(self):
+        pd.arrays.IntegerArray(self.data, self.mask)
+
+    def time_from_integer_array(self):
+        pd.array(self.values_integer, dtype="Int64")

ci/code_checks.sh

@@ -292,10 +292,6 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     pytest -q --doctest-modules pandas/core/generic.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Doctests groupby.py' ; echo $MSG
-    pytest -q --doctest-modules pandas/core/groupby/groupby.py -k"-cumcount -describe -pipe"
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
     MSG='Doctests series.py' ; echo $MSG
     pytest -q --doctest-modules pandas/core/series.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
@@ -318,6 +314,10 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     pytest -q --doctest-modules pandas/core/dtypes/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Doctests groupby' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/groupby/
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     MSG='Doctests indexes' ; echo $MSG
     pytest -q --doctest-modules pandas/core/indexes/
     RET=$(($RET + $?)) ; echo $MSG "DONE"

ci/deps/azure-36-minimum_versions.yaml

@@ -22,7 +22,7 @@ dependencies:
   - numpy=1.13.3
   - openpyxl=2.5.7
   - pytables=3.4.2
-  - python-dateutil=2.6.1
+  - python-dateutil=2.7.3
   - pytz=2017.2
   - scipy=0.19.0
   - xlrd=1.1.0

ci/deps/azure-37-numpydev.yaml

@@ -14,7 +14,8 @@ dependencies:
   - pytz
   - pip
   - pip:
-    - cython>=0.29.16
+    - cython==0.29.16
+    # GH#33507 cython 3.0a1 is causing TypeErrors 2020-04-13
     - "git+git://github.com/dateutil/dateutil.git"
     - "-f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com"
     - "--pre"

ci/deps/azure-macos-36.yaml

@@ -23,7 +23,7 @@ dependencies:
   - openpyxl
   - pyarrow>=0.13.0
   - pytables
-  - python-dateutil==2.6.1
+  - python-dateutil==2.7.3
   - pytz
   - xarray
   - xlrd

doc/source/getting_started/install.rst

@@ -221,7 +221,7 @@ Package                                                          Minimum support
 ================================================================ ==========================
 `setuptools <https://setuptools.readthedocs.io/en/latest/>`__    24.2.0
 `NumPy <https://www.numpy.org>`__                                1.13.3
-`python-dateutil <https://dateutil.readthedocs.io/en/stable/>`__ 2.6.1
+`python-dateutil <https://dateutil.readthedocs.io/en/stable/>`__ 2.7.3
 `pytz <https://pypi.org/project/pytz/>`__                        2017.2
 ================================================================ ==========================
 

doc/source/getting_started/intro_tutorials/03_subset_data.rst

@@ -23,7 +23,7 @@
                     <div class="card-body">
                         <p class="card-text">
 
-This tutorial uses the titanic data set, stored as CSV. The data
+This tutorial uses the Titanic data set, stored as CSV. The data
 consists of the following data columns:
 
 -  PassengerId: Id of every passenger.
@@ -72,7 +72,7 @@ How do I select specific columns from a ``DataFrame``?
     <ul class="task-bullet">
         <li>
 
-I’m interested in the age of the titanic passengers.
+I’m interested in the age of the Titanic passengers.
 
 .. ipython:: python
 
@@ -111,7 +111,7 @@ the number of rows is returned.
     <ul class="task-bullet">
         <li>
 
-I’m interested in the age and sex of the titanic passengers.
+I’m interested in the age and sex of the Titanic passengers.
 
 .. ipython:: python
 
@@ -198,7 +198,7 @@ can be used to filter the ``DataFrame`` by putting it in between the
 selection brackets ``[]``. Only rows for which the value is ``True``
 will be selected.
 
-We now from before that the original titanic ``DataFrame`` consists of
+We know from before that the original Titanic ``DataFrame`` consists of
 891 rows. Let’s have a look at the amount of rows which satisfy the
 condition by checking the ``shape`` attribute of the resulting
 ``DataFrame`` ``above_35``:
@@ -212,7 +212,7 @@ condition by checking the ``shape`` attribute of the resulting
     <ul class="task-bullet">
         <li>
 
-I’m interested in the titanic passengers from cabin class 2 and 3.
+I’m interested in the Titanic passengers from cabin class 2 and 3.
 
 .. ipython:: python
 

doc/source/user_guide/io.rst

@@ -285,14 +285,18 @@ chunksize : int, default ``None``
 Quoting, compression, and file format
 +++++++++++++++++++++++++++++++++++++
 
-compression : {``'infer'``, ``'gzip'``, ``'bz2'``, ``'zip'``, ``'xz'``, ``None``}, default ``'infer'``
+compression : {``'infer'``, ``'gzip'``, ``'bz2'``, ``'zip'``, ``'xz'``, ``None``, ``dict``}, default ``'infer'``
   For on-the-fly decompression of on-disk data. If 'infer', then use gzip,
   bz2, zip, or xz if filepath_or_buffer is a string ending in '.gz', '.bz2',
   '.zip', or '.xz', respectively, and no decompression otherwise. If using 'zip',
   the ZIP file must contain only one data file to be read in.
-  Set to ``None`` for no decompression.
+  Set to ``None`` for no decompression. Can also be a dict with key ``'method'``
+  set to one of {``'zip'``, ``'gzip'``, ``'bz2'``}, and other keys set to
+  compression settings. As an example, the following could be passed for
+  faster compression: ``compression={'method': 'gzip', 'compresslevel': 1}``.
 
   .. versionchanged:: 0.24.0 'infer' option added and set to default.
+  .. versionchanged:: 1.1.0 dict option extended to support ``gzip`` and ``bz2``.
 thousands : str, default ``None``
   Thousands separator.
 decimal : str, default ``'.'``
@@ -3347,6 +3351,12 @@ The compression type can be an explicit parameter or be inferred from the file e
 If 'infer', then use ``gzip``, ``bz2``, ``zip``, or ``xz`` if filename ends in ``'.gz'``, ``'.bz2'``, ``'.zip'``, or
 ``'.xz'``, respectively.
 
+The compression parameter can also be a ``dict`` in order to pass options to the
+compression protocol. It must have a ``'method'`` key set to the name
+of the compression protocol, which must be one of
+{``'zip'``, ``'gzip'``, ``'bz2'``}. All other key-value pairs are passed to
+the underlying compression library.
+
 .. ipython:: python
 
    df = pd.DataFrame({
@@ -3383,6 +3393,15 @@ The default is to 'infer':
    rt = pd.read_pickle("s1.pkl.bz2")
    rt
 
+Passing options to the compression protocol in order to speed up compression:
+
+.. ipython:: python
+
+   df.to_pickle(
+       "data.pkl.gz",
+       compression={"method": "gzip", 'compresslevel': 1}
+   )
+
 .. ipython:: python
    :suppress: