Merge branch 'master' into 27453-right-merge-order

Author: Nico Cernek

asv_bench/benchmarks/categoricals.py

@@ -282,4 +282,18 @@ def time_sort_values(self):
         self.index.sort_values(ascending=False)
 
 
+class SearchSorted:
+    def setup(self):
+        N = 10 ** 5
+        self.ci = tm.makeCategoricalIndex(N).sort_values()
+        self.c = self.ci.values
+        self.key = self.ci.categories[1]
+
+    def time_categorical_index_contains(self):
+        self.ci.searchsorted(self.key)
+
+    def time_categorical_contains(self):
+        self.c.searchsorted(self.key)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/ctors.py

@@ -67,7 +67,7 @@ class SeriesConstructors:
     def setup(self, data_fmt, with_index, dtype):
         if data_fmt in (gen_of_str, gen_of_tuples) and with_index:
             raise NotImplementedError(
-                "Series constructors do not support " "using generators with indexes"
+                "Series constructors do not support using generators with indexes"
             )
         N = 10 ** 4
         if dtype == "float":

asv_bench/benchmarks/eval.py

@@ -27,7 +27,7 @@ def time_add(self, engine, threads):
 
     def time_and(self, engine, threads):
         pd.eval(
-            "(self.df > 0) & (self.df2 > 0) & " "(self.df3 > 0) & (self.df4 > 0)",
+            "(self.df > 0) & (self.df2 > 0) & (self.df3 > 0) & (self.df4 > 0)",
             engine=engine,
         )
 

asv_bench/benchmarks/io/hdf.py

@@ -88,11 +88,11 @@ def time_write_store_table_dc(self):
 
     def time_query_store_table_wide(self):
         self.store.select(
-            "table_wide", where="index > self.start_wide and " "index < self.stop_wide"
+            "table_wide", where="index > self.start_wide and index < self.stop_wide"
         )
 
     def time_query_store_table(self):
-        self.store.select("table", where="index > self.start and " "index < self.stop")
+        self.store.select("table", where="index > self.start and index < self.stop")
 
     def time_store_repr(self):
         repr(self.store)

asv_bench/benchmarks/rolling.py

@@ -25,6 +25,25 @@ def peakmem_rolling(self, constructor, window, dtype, method):
         getattr(self.roll, method)()
 
 
+class Apply:
+    params = (
+        ["DataFrame", "Series"],
+        [10, 1000],
+        ["int", "float"],
+        [sum, np.sum, lambda x: np.sum(x) + 5],
+        [True, False],
+    )
+    param_names = ["contructor", "window", "dtype", "function", "raw"]
+
+    def setup(self, constructor, window, dtype, function, raw):
+        N = 10 ** 5
+        arr = (100 * np.random.random(N)).astype(dtype)
+        self.roll = getattr(pd, constructor)(arr).rolling(window)
+
+    def time_rolling(self, constructor, window, dtype, function, raw):
+        self.roll.apply(function, raw=raw)
+
+
 class ExpandingMethods:
 
     params = (

ci/code_checks.sh

@@ -122,7 +122,11 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     MSG='Check for non-standard imports' ; echo $MSG
     invgrep -R --include="*.py*" -E "from pandas.core.common import " pandas
     invgrep -R --include="*.py*" -E "from collections.abc import " pandas
-    # invgrep -R --include="*.py*" -E "from numpy import nan " pandas  # GH#24822 not yet implemented since the offending imports have not all been removed
+    invgrep -R --include="*.py*" -E "from numpy import nan " pandas
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
+    MSG='Check for use of exec' ; echo $MSG
+    invgrep -R --include="*.py*" -E "[^a-zA-Z0-9_]exec\(" pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for pytest warns' ; echo $MSG
@@ -184,7 +188,7 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     invgrep -R --include="*.rst" ".. ipython ::" doc/source
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Check that no file in the repo contains tailing whitespaces' ; echo $MSG
+    MSG='Check that no file in the repo contains trailing whitespaces' ; echo $MSG
     set -o pipefail
     if [[ "$AZURE" == "true" ]]; then
         # we exclude all c/cpp files as the c/cpp files of pandas code base are tested when Linting .c and .h files
@@ -262,13 +266,17 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
         -k"-from_arrays -from_breaks -from_intervals -from_tuples -set_closed -to_tuples -interval_range"
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Doctests arrays/string_.py' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/arrays/string_.py
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
 fi
 
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA05
+    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA01, SA02, SA03, SA05)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA01,SA02,SA03,SA05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/deps/azure-36-32bit.yaml

@@ -3,6 +3,7 @@ channels:
   - defaults
   - conda-forge
 dependencies:
+  - attrs=19.1.0
   - gcc_linux-32
   - gcc_linux-32
   - gxx_linux-32
@@ -11,7 +12,7 @@ dependencies:
   - python=3.6.*
   - pytz=2017.2
   # universal
-  - pytest>=4.0.2,<5.0.0
+  - pytest
   - pytest-xdist
   - pytest-mock
   - pytest-azurepipelines

ci/deps/travis-36-cov.yaml

@@ -29,7 +29,7 @@ dependencies:
   - python-snappy
   - python=3.6.*
   - pytz
-  - s3fs
+  - s3fs<0.3
   - scikit-learn
   - scipy
   - sqlalchemy

ci/deps/travis-36-slow.yaml

@@ -18,7 +18,7 @@ dependencies:
   - python-dateutil
   - python=3.6.*
   - pytz
-  - s3fs
+  - s3fs<0.3
   - scipy
   - sqlalchemy
   - xlrd

ci/deps/travis-37.yaml

@@ -17,7 +17,7 @@ dependencies:
   - pytest-xdist>=1.29.0
   - pytest-mock
   - hypothesis>=3.58.0
-  - s3fs
+  - s3fs<0.3
   - pip
   - pyreadstat
   - pip:

ci/run_tests.sh

@@ -43,10 +43,9 @@ do
     # if no tests are found (the case of "single and slow"), pytest exits with code 5, and would make the script fail, if not for the below code
     sh -c "$PYTEST_CMD; ret=\$?; [ \$ret = 5 ] && exit 0 || exit \$ret"
 
-    # 2019-08-21 disabling because this is hitting HTTP 400 errors GH#27602
-    # if [[ "$COVERAGE" && $? == 0 && "$TRAVIS_BRANCH" == "master" ]]; then
-    #    echo "uploading coverage for $TYPE tests"
-    #    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 $COVERAGE_FNAME
-    # fi
+    if [[ "$COVERAGE" && $? == 0 && "$TRAVIS_BRANCH" == "master" ]]; then
+        echo "uploading coverage for $TYPE tests"
+        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
 done

doc/.gitignore

@@ -0,0 +1,4 @@
+data/
+timeseries.csv
+timeseries.parquet
+timeseries_wide.parquet

doc/redirects.csv

@@ -6,6 +6,7 @@ whatsnew,whatsnew/index
 release,whatsnew/index
 
 # getting started
+install,getting_started/install
 10min,getting_started/10min
 basics,getting_started/basics
 comparison_with_r,getting_started/comparison/comparison_with_r
@@ -1577,3 +1578,6 @@ generated/pandas.unique,../reference/api/pandas.unique
 generated/pandas.util.hash_array,../reference/api/pandas.util.hash_array
 generated/pandas.util.hash_pandas_object,../reference/api/pandas.util.hash_pandas_object
 generated/pandas.wide_to_long,../reference/api/pandas.wide_to_long
+
+# Cached searches
+reference/api/pandas.DataFrame.from_csv,pandas.read_csv

doc/source/conf.py

@@ -120,6 +120,9 @@
 plot_pre_code = """import numpy as np
 import pandas as pd"""
 
+# nbsphinx do not use requirejs (breaks bootstrap)
+nbsphinx_requirejs_path = ""
+
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ["../_templates"]
 
@@ -191,7 +194,7 @@
 
 # The theme to use for HTML and HTML Help pages.  Major themes that come with
 # Sphinx are currently 'default' and 'sphinxdoc'.
-html_theme = "nature_with_gtoc"
+html_theme = "pandas_sphinx_theme"
 
 # The style sheet to use for HTML and HTML Help pages. A file of that name
 # must exist either in Sphinx' static/ path, or in one of the custom paths
@@ -204,7 +207,7 @@
 # html_theme_options = {}
 
 # Add any paths that contain custom themes here, relative to this directory.
-html_theme_path = ["themes"]
+# html_theme_path = ["themes"]
 
 # The name for this set of Sphinx documents.  If None, it defaults to
 # "<project> v<release> documentation".
@@ -628,11 +631,11 @@ def linkcode_resolve(domain, info):
     fn = os.path.relpath(fn, start=os.path.dirname(pandas.__file__))
 
     if "+" in pandas.__version__:
-        return "http://github.com/pandas-dev/pandas/blob/master/pandas/" "{}{}".format(
+        return "http://github.com/pandas-dev/pandas/blob/master/pandas/{}{}".format(
             fn, linespec
         )
     else:
-        return "http://github.com/pandas-dev/pandas/blob/" "v{}/pandas/{}{}".format(
+        return "http://github.com/pandas-dev/pandas/blob/v{}/pandas/{}{}".format(
             pandas.__version__, fn, linespec
         )
 

doc/source/development/contributing.rst

@@ -172,7 +172,7 @@ installed (or you wish to install a newer version) you can install a compiler
     yum groupinstall "Development Tools"
 
 For other Linux distributions, consult your favourite search engine for
-commpiler installation instructions.
+compiler installation instructions.
 
 Let us know if you have any difficulties by opening an issue or reaching out on
 `Gitter`_.
@@ -949,10 +949,13 @@ the expected correct result::
 
         assert_frame_equal(pivoted, expected)
 
+Please remember to add the Github Issue Number as a comment to a new test.
+E.g. "# brief comment, see GH#28907"
+
 Transitioning to ``pytest``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-*pandas* existing test structure is *mostly* classed based, meaning that you will typically find tests wrapped in a class.
+*pandas* existing test structure is *mostly* class-based, meaning that you will typically find tests wrapped in a class.
 
 .. code-block:: python
 

doc/source/ecosystem.rst

@@ -1,3 +1,5 @@
+:orphan:
+
 .. _ecosystem:
 
 {{ header }}

doc/source/getting_started/basics.rst

@@ -986,7 +986,7 @@ not noted for a particular column will be ``NaN``:
 
    tsdf.agg({'A': ['mean', 'min'], 'B': 'sum'})
 
-.. _basics.aggregation.mixed_dtypes:
+.. _basics.aggregation.mixed_string:
 
 Mixed dtypes
 ++++++++++++
@@ -1704,14 +1704,21 @@ built-in string methods. For example:
 
  .. ipython:: python
 
-  s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
+  s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'],
+                dtype="string")
   s.str.lower()
 
 Powerful pattern-matching methods are provided as well, but note that
 pattern-matching generally uses `regular expressions
 <https://docs.python.org/3/library/re.html>`__ by default (and in some cases
 always uses them).
 
+.. note::
+
+   Prior to pandas 1.0, string methods were only available on ``object`` -dtype
+   ``Series``. Pandas 1.0 added the :class:`StringDtype` which is dedicated
+   to strings. See :ref:`text.types` for more.
+
 Please see :ref:`Vectorized String Methods <text.string_methods>` for a complete
 description.
 
@@ -1925,9 +1932,15 @@ period (time spans) :class:`PeriodDtype`      :class:`Period`    :class:`arrays.
 sparse              :class:`SparseDtype`      (none)             :class:`arrays.SparseArray`   :ref:`sparse`
 intervals           :class:`IntervalDtype`    :class:`Interval`  :class:`arrays.IntervalArray` :ref:`advanced.intervalindex`
 nullable integer    :class:`Int64Dtype`, ...  (none)             :class:`arrays.IntegerArray`  :ref:`integer_na`
+Strings             :class:`StringDtype`      :class:`str`       :class:`arrays.StringArray`   :ref:`text`
 =================== ========================= ================== ============================= =============================
 
-Pandas uses the ``object`` dtype for storing strings.
+Pandas has two ways to store strings.
+
+1. ``object`` dtype, which can hold any Python object, including strings.
+2. :class:`StringDtype`, which is dedicated to strings.
+
+Generally, we recommend using :class:`StringDtype`. See :ref:`text.types` fore more.
 
 Finally, arbitrary objects may be stored using the ``object`` dtype, but should
 be avoided to the extent possible (for performance and interoperability with

doc/source/getting_started/index.rst

@@ -12,6 +12,7 @@ Getting started
 .. toctree::
     :maxdepth: 2
 
+    install
     overview
     10min
     basics

doc/source/install.rst renamed to doc/source/getting_started/install.rst

@@ -40,10 +40,8 @@ See the :ref:`overview` for more detail about what's in the library.
 {% endif %}
 {% if not single_doc %}
     What's New in 1.0.0 <whatsnew/v1.0.0>
-    install
     getting_started/index
     user_guide/index
-    ecosystem
     {% endif -%}
     {% if include_api -%}
     reference/index
@@ -54,9 +52,9 @@ See the :ref:`overview` for more detail about what's in the library.
 {% endif %}
 
 * :doc:`whatsnew/v1.0.0`
-* :doc:`install`
 * :doc:`getting_started/index`
 
+  * :doc:`getting_started/install`
   * :doc:`getting_started/overview`
   * :doc:`getting_started/10min`
   * :doc:`getting_started/basics`
@@ -83,6 +81,7 @@ See the :ref:`overview` for more detail about what's in the library.
   * :doc:`user_guide/style`
   * :doc:`user_guide/options`
   * :doc:`user_guide/enhancingperf`
+  * :doc:`user_guide/scale`
   * :doc:`user_guide/sparse`
   * :doc:`user_guide/gotchas`
   * :doc:`user_guide/cookbook`