Merge commit 'v0.19.0-14-ga40e185' into debian

* commit 'v0.19.0-14-ga40e185': (37 commits)
  BUG: Bug in localizing an ambiguous timezone when a boolean is passed
  Convert readthedocs links for their .org -> .io migration for hosted projects (pandas-dev#14406)
  DOC: formatting in basics.rst
  BLD/CI: cython cache pxd files (pandas-dev#14363)
  BUG: set_levels set illegal levels. (pandas-dev#14236)
  DOC: add whitespace to v0.19.1 bug fix section
  change impl details slightly for pandas-dev#14292
  BUG: Fix concat key name
  DOC: add 0.19.1 whatsnew file (pandas-dev#14366)
  DOC: to_csv warns regarding quoting behaviour for floats pandas-dev#14195 (pandas-dev#14228)
  DOC: fix formatting issue with msgpack table
  TST: pandas-dev#14345 fixes TestDatetimeIndexOps test_nat AssertionErrors on 32-bit
  docs: Remove old warning from dsintro.rst (pandas-dev#14365)
  DOC: minor v0.19.0 whatsnew corrections
  RLS: v0.19.0
  DOC: update release notes
  DOC: Latest fixes for whatsnew file
  to_latex encoding follows the documentation (py2 ascii, py3 utf8) (pandas-dev#14329)
  DOC: fix some sphinx build issues (pandas-dev#14332)
  TST: fix period tests for numpy 1.9.3 (GH14183) (pandas-dev#14331)
  ...

Author: yarikoptic

.github/CONTRIBUTING.md

@@ -278,7 +278,7 @@ Please try to maintain backward compatibility. *pandas* has lots of users with l
 
 Adding tests is one of the most common requests after code is pushed to *pandas*. Therefore, it is worth getting in the habit of writing tests ahead of time so this is never an issue.
 
-Like many packages, *pandas* uses the [Nose testing system](http://nose.readthedocs.org/en/latest/index.html) and the convenient extensions in [numpy.testing](http://docs.scipy.org/doc/numpy/reference/routines.testing.html).
+Like many packages, *pandas* uses the [Nose testing system](https://nose.readthedocs.io/en/latest/index.html) and the convenient extensions in [numpy.testing](http://docs.scipy.org/doc/numpy/reference/routines.testing.html).
 
 #### Writing tests
 
@@ -323,7 +323,7 @@ Performance matters and it is worth considering whether your code has introduced
 >
 > The asv benchmark suite was translated from the previous framework, vbench, so many stylistic issues are likely a result of automated transformation of the code.
 
-To use asv you will need either `conda` or `virtualenv`. For more details please check the [asv installation webpage](http://asv.readthedocs.org/en/latest/installing.html).
+To use asv you will need either `conda` or `virtualenv`. For more details please check the [asv installation webpage](https://asv.readthedocs.io/en/latest/installing.html).
 
 To install asv:
 
@@ -360,7 +360,7 @@ This command is equivalent to:
 
 This will launch every test only once, display stderr from the benchmarks, and use your local `python` that comes from your `$PATH`.
 
-Information on how to write a benchmark can be found in the [asv documentation](http://asv.readthedocs.org/en/latest/writing_benchmarks.html).
+Information on how to write a benchmark can be found in the [asv documentation](https://asv.readthedocs.io/en/latest/writing_benchmarks.html).
 
 #### Running the vbench performance test suite (phasing out)
 

.github/ISSUE_TEMPLATE.md

@@ -1,6 +1,15 @@
-#### Code Sample, a copy-pastable example if possible
+#### A small, complete example of the issue
+
+```python
+# Your code here
+
+```
 
 #### Expected Output
 
-#### output of ``pd.show_versions()``
+#### Output of ``pd.show_versions()``
+
+<details>
+# Paste the output here
 
+</details>

asv_bench/benchmarks/gil.py

@@ -22,7 +22,7 @@ def wrapper(fname):
         return wrapper
 
 
-class nogil_groupby_count_2(object):
+class nogil_groupby_base(object):
     goal_time = 0.2
 
     def setup(self):
@@ -33,6 +33,9 @@ def setup(self):
         if (not have_real_test_parallel):
             raise NotImplementedError
 
+
+class nogil_groupby_count_2(nogil_groupby_base):
+
     def time_nogil_groupby_count_2(self):
         self.pg2()
 
@@ -41,16 +44,7 @@ def pg2(self):
         self.df.groupby('key')['data'].count()
 
 
-class nogil_groupby_last_2(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_last_2(nogil_groupby_base):
 
     def time_nogil_groupby_last_2(self):
         self.pg2()
@@ -60,16 +54,7 @@ def pg2(self):
         self.df.groupby('key')['data'].last()
 
 
-class nogil_groupby_max_2(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_max_2(nogil_groupby_base):
 
     def time_nogil_groupby_max_2(self):
         self.pg2()
@@ -79,16 +64,7 @@ def pg2(self):
         self.df.groupby('key')['data'].max()
 
 
-class nogil_groupby_mean_2(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_mean_2(nogil_groupby_base):
 
     def time_nogil_groupby_mean_2(self):
         self.pg2()
@@ -98,16 +74,7 @@ def pg2(self):
         self.df.groupby('key')['data'].mean()
 
 
-class nogil_groupby_min_2(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_min_2(nogil_groupby_base):
 
     def time_nogil_groupby_min_2(self):
         self.pg2()
@@ -117,16 +84,7 @@ def pg2(self):
         self.df.groupby('key')['data'].min()
 
 
-class nogil_groupby_prod_2(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_prod_2(nogil_groupby_base):
 
     def time_nogil_groupby_prod_2(self):
         self.pg2()
@@ -136,16 +94,7 @@ def pg2(self):
         self.df.groupby('key')['data'].prod()
 
 
-class nogil_groupby_sum_2(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_sum_2(nogil_groupby_base):
 
     def time_nogil_groupby_sum_2(self):
         self.pg2()
@@ -155,107 +104,93 @@ def pg2(self):
         self.df.groupby('key')['data'].sum()
 
 
-class nogil_groupby_sum_4(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_sum_4(nogil_groupby_base):
 
     def time_nogil_groupby_sum_4(self):
         self.pg4()
 
     def f(self):
         self.df.groupby('key')['data'].sum()
 
-    def g2(self):
-        for i in range(2):
-            self.f()
-
     def g4(self):
         for i in range(4):
             self.f()
 
-    def g8(self):
-        for i in range(8):
-            self.f()
-
-    @test_parallel(num_threads=2)
-    def pg2(self):
-        self.f()
-
     @test_parallel(num_threads=4)
     def pg4(self):
         self.f()
 
-    @test_parallel(num_threads=8)
-    def pg8(self):
-        self.f()
 
-
-class nogil_groupby_sum_8(object):
-    goal_time = 0.2
-
-    def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
-        np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
-        if (not have_real_test_parallel):
-            raise NotImplementedError
+class nogil_groupby_sum_8(nogil_groupby_base):
 
     def time_nogil_groupby_sum_8(self):
         self.pg8()
 
     def f(self):
         self.df.groupby('key')['data'].sum()
 
-    def g2(self):
-        for i in range(2):
-            self.f()
-
-    def g4(self):
-        for i in range(4):
-            self.f()
-
     def g8(self):
         for i in range(8):
             self.f()
 
-    @test_parallel(num_threads=2)
-    def pg2(self):
-        self.f()
-
-    @test_parallel(num_threads=4)
-    def pg4(self):
-        self.f()
-
     @test_parallel(num_threads=8)
     def pg8(self):
         self.f()
 
 
-class nogil_groupby_var_2(object):
+class nogil_groupby_var_2(nogil_groupby_base):
+
+    def time_nogil_groupby_var_2(self):
+        self.pg2()
+
+    @test_parallel(num_threads=2)
+    def pg2(self):
+        self.df.groupby('key')['data'].var()
+
+
+class nogil_groupby_groups(object):
     goal_time = 0.2
 
     def setup(self):
-        self.N = 1000000
-        self.ngroups = 1000
         np.random.seed(1234)
-        self.df = DataFrame({'key': np.random.randint(0, self.ngroups, size=self.N), 'data': np.random.randn(self.N), })
+        self.size = 2**22
+        self.ngroups = 100
+        self.data = Series(np.random.randint(0, self.ngroups, size=self.size))
         if (not have_real_test_parallel):
             raise NotImplementedError
 
-    def time_nogil_groupby_var_2(self):
+    def f(self):
+        self.data.groupby(self.data).groups
+
+
+class nogil_groupby_groups_2(nogil_groupby_groups):
+
+    def time_nogil_groupby_groups(self):
         self.pg2()
 
     @test_parallel(num_threads=2)
     def pg2(self):
-        self.df.groupby('key')['data'].var()
+        self.f()
+
+
+class nogil_groupby_groups_4(nogil_groupby_groups):
+
+    def time_nogil_groupby_groups(self):
+        self.pg4()
+
+    @test_parallel(num_threads=4)
+    def pg4(self):
+        self.f()
+
+
+class nogil_groupby_groups_8(nogil_groupby_groups):
+
+    def time_nogil_groupby_groups(self):
+        self.pg8()
+
+    @test_parallel(num_threads=8)
+    def pg8(self):
+        self.f()
 
 
 class nogil_take1d_float64(object):

asv_bench/benchmarks/groupby.py

@@ -32,6 +32,32 @@ def time_groupby_apply_dict_return(self):
         self.data.groupby(self.labels).apply(self.f)
 
 
+#----------------------------------------------------------------------
+# groups
+
+class groupby_groups(object):
+    goal_time = 0.1
+
+    def setup(self):
+        size = 2**22
+        self.data = Series(np.random.randint(0, 100, size=size))
+        self.data2 = Series(np.random.randint(0, 10000, size=size))
+        self.data3 = Series(tm.makeStringIndex(100).take(np.random.randint(0, 100, size=size)))
+        self.data4 = Series(tm.makeStringIndex(10000).take(np.random.randint(0, 10000, size=size)))
+
+    def time_groupby_groups_int64_small(self):
+        self.data.groupby(self.data).groups
+
+    def time_groupby_groups_int64_large(self):
+        self.data2.groupby(self.data2).groups
+
+    def time_groupby_groups_object_small(self):
+        self.data3.groupby(self.data3).groups
+
+    def time_groupby_groups_object_large(self):
+        self.data4.groupby(self.data4).groups
+
+
 #----------------------------------------------------------------------
 # First / last functions
 

ci/prep_cython_cache.sh

@@ -3,8 +3,8 @@
 ls "$HOME/.cache/"
 
 PYX_CACHE_DIR="$HOME/.cache/pyxfiles"
-pyx_file_list=`find ${TRAVIS_BUILD_DIR} -name "*.pyx"`
-pyx_cache_file_list=`find ${PYX_CACHE_DIR} -name "*.pyx"`
+pyx_file_list=`find ${TRAVIS_BUILD_DIR} -name "*.pyx" -o -name "*.pxd"`
+pyx_cache_file_list=`find ${PYX_CACHE_DIR} -name "*.pyx" -o -name "*.pxd"`
 
 CACHE_File="$HOME/.cache/cython_files.tar"
 

ci/requirements-2.7_DOC_BUILD.run

@@ -18,3 +18,4 @@ sqlalchemy
 numexpr
 bottleneck
 statsmodels
+pyqt=4.11.4

ci/submit_cython_cache.sh

@@ -2,7 +2,7 @@
 
 CACHE_File="$HOME/.cache/cython_files.tar"
 PYX_CACHE_DIR="$HOME/.cache/pyxfiles"
-pyx_file_list=`find ${TRAVIS_BUILD_DIR} -name "*.pyx"`
+pyx_file_list=`find ${TRAVIS_BUILD_DIR} -name "*.pyx" -o -name "*.pxd"`
 
 rm -rf $CACHE_File
 rm -rf $PYX_CACHE_DIR