BUG: Patch Checked Add Method

.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)
 

asv_bench/benchmarks/algorithms.py

@@ -15,6 +15,14 @@ def setup(self):
         self.int = pd.Int64Index(np.arange(N).repeat(5))
         self.float = pd.Float64Index(np.random.randn(N).repeat(5))
 
+        # Convenience naming.
+        self.checked_add = pd.core.nanops._checked_add_with_arr
+
+        self.arr = np.arange(1000000)
+        self.arrpos = np.arange(1000000)
+        self.arrneg = np.arange(-1000000, 0)
+        self.arrmixed = np.array([1, -1]).repeat(500000)
+
     def time_int_factorize(self):
         self.int.factorize()
 
@@ -29,3 +37,21 @@ def time_int_duplicated(self):
 
     def time_float_duplicated(self):
         self.float.duplicated()
+
+    def time_add_overflow_pos_scalar(self):
+        self.checked_add(self.arr, 1)
+
+    def time_add_overflow_neg_scalar(self):
+        self.checked_add(self.arr, -1)
+
+    def time_add_overflow_zero_scalar(self):
+        self.checked_add(self.arr, 0)
+
+    def time_add_overflow_pos_arr(self):
+        self.checked_add(self.arr, self.arrpos)
+
+    def time_add_overflow_neg_arr(self):
+        self.checked_add(self.arr, self.arrneg)
+
+    def time_add_overflow_mixed_arr(self):
+        self.checked_add(self.arr, self.arrmixed)

asv_bench/benchmarks/attrs_caching.py

@@ -20,4 +20,4 @@ def setup(self):
         self.cur_index = self.df.index
 
     def time_setattr_dataframe_index(self):
-        self.df.index = self.cur_index
+        self.df.index = self.cur_index

asv_bench/benchmarks/ctors.py

@@ -49,4 +49,4 @@ def setup(self):
         self.s = Series(([Timestamp('20110101'), Timestamp('20120101'), Timestamp('20130101')] * 1000))
 
     def time_index_from_series_ctor(self):
-        Index(self.s)
+        Index(self.s)

asv_bench/benchmarks/frame_ctor.py

@@ -1703,4 +1703,4 @@ def setup(self):
         self.dict_list = [dict(zip(self.columns, row)) for row in self.frame.values]
 
     def time_series_ctor_from_dict(self):
-        Series(self.some_dict)
+        Series(self.some_dict)

asv_bench/benchmarks/groupby.py

@@ -548,6 +548,32 @@ def time_groupby_sum(self):
         self.df.groupby(['a'])['b'].sum()
 
 
+class groupby_period(object):
+    # GH 14338
+    goal_time = 0.2
+
+    def make_grouper(self, N):
+        return pd.period_range('1900-01-01', freq='D', periods=N)
+
+    def setup(self):
+        N = 10000
+        self.grouper = self.make_grouper(N)
+        self.df = pd.DataFrame(np.random.randn(N, 2))
+
+    def time_groupby_sum(self):
+        self.df.groupby(self.grouper).sum()
+
+
+class groupby_datetime(groupby_period):
+    def make_grouper(self, N):
+        return pd.date_range('1900-01-01', freq='D', periods=N)
+
+
+class groupby_datetimetz(groupby_period):
+    def make_grouper(self, N):
+        return pd.date_range('1900-01-01', freq='D', periods=N,
+                             tz='US/Central')
+
 #----------------------------------------------------------------------
 # Series.value_counts
 

asv_bench/benchmarks/hdfstore_bench.py

@@ -348,4 +348,4 @@ def remove(self, f):
         try:
             os.remove(self.f)
         except:
-            pass
+            pass

asv_bench/benchmarks/index_object.py

@@ -344,4 +344,4 @@ def setup(self):
         self.mi = MultiIndex.from_product([self.level1, self.level2])
 
     def time_multiindex_with_datetime_level_sliced(self):
-        self.mi[:10].values
+        self.mi[:10].values

asv_bench/benchmarks/io_sql.py

@@ -212,4 +212,4 @@ def setup(self):
         self.df = DataFrame({'float1': randn(10000), 'float2': randn(10000), 'string1': (['foo'] * 10000), 'bool1': ([True] * 10000), 'int1': np.random.randint(0, 100000, size=10000), }, index=self.index)
 
     def time_sql_write_sqlalchemy(self):
-        self.df.to_sql('test1', self.engine, if_exists='replace')
+        self.df.to_sql('test1', self.engine, if_exists='replace')

asv_bench/benchmarks/packers.py

@@ -547,6 +547,31 @@ def remove(self, f):
             pass
 
 
+class packers_write_json_lines(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.f = '__test__.msg'
+        self.N = 100000
+        self.C = 5
+        self.index = date_range('20000101', periods=self.N, freq='H')
+        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]), index=self.index)
+        self.remove(self.f)
+        self.df.index = np.arange(self.N)
+
+    def time_packers_write_json_lines(self):
+        self.df.to_json(self.f, orient="records", lines=True)
+
+    def teardown(self):
+        self.remove(self.f)
+
+    def remove(self, f):
+        try:
+            os.remove(self.f)
+        except:
+            pass
+
+
 class packers_write_json_T(object):
     goal_time = 0.2
 

asv_bench/benchmarks/panel_ctor.py

@@ -61,4 +61,4 @@ def setup(self):
             self.data_frames[x] = self.df
 
     def time_panel_from_dict_two_different_indexes(self):
-        Panel.from_dict(self.data_frames)
+        Panel.from_dict(self.data_frames)

asv_bench/benchmarks/panel_methods.py

@@ -53,4 +53,4 @@ def setup(self):
         self.panel = Panel(np.random.randn(100, len(self.index), 1000))
 
     def time_panel_shift_minor(self):
-        self.panel.shift(1, axis='minor')
+        self.panel.shift(1, axis='minor')

asv_bench/benchmarks/replace.py

@@ -45,4 +45,4 @@ def setup(self):
         self.ts = Series(np.random.randn(self.N), index=self.rng)
 
     def time_replace_replacena(self):
-        self.ts.replace(np.nan, 0.0, inplace=True)
+        self.ts.replace(np.nan, 0.0, inplace=True)

asv_bench/benchmarks/reshape.py

@@ -73,4 +73,4 @@ def setup(self):
                 break
 
     def time_unstack_sparse_keyspace(self):
-        self.idf.unstack()
+        self.idf.unstack()

asv_bench/benchmarks/stat_ops.py

@@ -258,4 +258,4 @@ def time_rolling_skew(self):
         rolling_skew(self.arr, self.win)
 
     def time_rolling_kurt(self):
-        rolling_kurt(self.arr, self.win)
+        rolling_kurt(self.arr, self.win)

asv_bench/benchmarks/strings.py

@@ -390,4 +390,4 @@ def time_strings_upper(self):
         self.many.str.upper()
 
     def make_series(self, letters, strlen, size):
-        return Series([str(x) for x in np.fromiter(IT.cycle(letters), count=(size * strlen), dtype='|S1').view('|S{}'.format(strlen))])
+        return Series([str(x) for x in np.fromiter(IT.cycle(letters), count=(size * strlen), dtype='|S1').view('|S{}'.format(strlen))])

asv_bench/benchmarks/timedelta.py

@@ -1,5 +1,5 @@
 from .pandas_vb_common import *
-from pandas import to_timedelta
+from pandas import to_timedelta, Timestamp
 
 
 class timedelta_convert_int(object):
@@ -47,3 +47,14 @@ def time_timedelta_convert_coerce(self):
 
     def time_timedelta_convert_ignore(self):
         to_timedelta(self.arr, errors='ignore')
+
+
+class timedelta_add_overflow(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.td = to_timedelta(np.arange(1000000))
+        self.ts = Timestamp('2000')
+
+    def test_add_td_ts(self):
+        self.td + self.ts

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/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

doc/README.rst

@@ -155,9 +155,9 @@ Where to start?
 ---------------
 
 There are a number of issues listed under `Docs
-<https://github.com/pydata/pandas/issues?labels=Docs&sort=updated&state=open>`_
+<https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open>`_
 and `Good as first PR
-<https://github.com/pydata/pandas/issues?labels=Good+as+first+PR&sort=updated&state=open>`_
+<https://github.com/pandas-dev/pandas/issues?labels=Good+as+first+PR&sort=updated&state=open>`_
 where you could start out.
 
 Or maybe you have an idea of your own, by using pandas, looking for something

doc/_templates/autosummary/accessor_attribute.rst

@@ -3,4 +3,4 @@
 
 .. currentmodule:: {{ module.split('.')[0] }}
 
-.. autoaccessorattribute:: {{ [module.split('.')[1], objname]|join('.') }}
+.. autoaccessorattribute:: {{ [module.split('.')[1], objname]|join('.') }}

doc/_templates/autosummary/accessor_method.rst

@@ -3,4 +3,4 @@
 
 .. currentmodule:: {{ module.split('.')[0] }}
 
-.. autoaccessormethod:: {{ [module.split('.')[1], objname]|join('.') }}
+.. autoaccessormethod:: {{ [module.split('.')[1], objname]|join('.') }}

doc/source/basics.rst

@@ -1794,18 +1794,18 @@ The following functions are available for one dimensional object arrays or scala
 
 - :meth:`~pandas.to_datetime` (conversion to datetime objects)
 
-   .. ipython:: python
+  .. ipython:: python
 
-      import datetime
-      m = ['2016-07-09', datetime.datetime(2016, 3, 2)]
-      pd.to_datetime(m)
+     import datetime
+     m = ['2016-07-09', datetime.datetime(2016, 3, 2)]
+     pd.to_datetime(m)
 
 - :meth:`~pandas.to_timedelta` (conversion to timedelta objects)
 
-   .. ipython:: python
+  .. ipython:: python
 
-      m = ['5us', pd.Timedelta('1day')]
-      pd.to_timedelta(m)
+     m = ['5us', pd.Timedelta('1day')]
+     pd.to_timedelta(m)
 
 To force a conversion, we can pass in an ``errors`` argument, which specifies how pandas should deal with elements
 that cannot be converted to desired dtype or object. By default, ``errors='raise'``, meaning that any errors encountered

doc/source/categorical.rst

@@ -973,7 +973,7 @@ are not numeric data (even in the case that ``.categories`` is numeric).
          print("TypeError: " + str(e))
 
 .. note::
-    If such a function works, please file a bug at https://github.com/pydata/pandas!
+    If such a function works, please file a bug at https://github.com/pandas-dev/pandas!
 
 dtype in apply
 ~~~~~~~~~~~~~~

doc/source/comparison_with_sas.rst

@@ -116,7 +116,7 @@ Reading External Data
 
 Like SAS, pandas provides utilities for reading in data from
 many formats.  The ``tips`` dataset, found within the pandas
-tests (`csv <https://raw.github.com/pydata/pandas/master/pandas/tests/data/tips.csv>`_)
+tests (`csv <https://raw.github.com/pandas-dev/pandas/master/pandas/tests/data/tips.csv>`_)
 will be used in many of the following examples.
 
 SAS provides ``PROC IMPORT`` to read csv data into a data set.
@@ -131,7 +131,7 @@ The pandas method is :func:`read_csv`, which works similarly.
 
 .. ipython:: python
 
-   url = 'https://raw.github.com/pydata/pandas/master/pandas/tests/data/tips.csv'
+   url = 'https://raw.github.com/pandas-dev/pandas/master/pandas/tests/data/tips.csv'
    tips = pd.read_csv(url)
    tips.head()
 

doc/source/comparison_with_sql.rst

@@ -23,7 +23,7 @@ structure.
 
 .. ipython:: python
 
-    url = 'https://raw.github.com/pydata/pandas/master/pandas/tests/data/tips.csv'
+    url = 'https://raw.github.com/pandas-dev/pandas/master/pandas/tests/data/tips.csv'
     tips = pd.read_csv(url)
     tips.head()
 

doc/source/conf.py

@@ -295,15 +295,15 @@
     'python': ('http://docs.python.org/3', None),
     'numpy': ('http://docs.scipy.org/doc/numpy', None),
     'scipy': ('http://docs.scipy.org/doc/scipy/reference', None),
-    'py': ('http://pylib.readthedocs.org/en/latest/', None)
+    'py': ('https://pylib.readthedocs.io/en/latest/', None)
 }
 import glob
 autosummary_generate = glob.glob("*.rst")
 
 # extlinks alias
-extlinks = {'issue': ('https://github.com/pydata/pandas/issues/%s',
+extlinks = {'issue': ('https://github.com/pandas-dev/pandas/issues/%s',
                       'GH'),
-            'wiki': ('https://github.com/pydata/pandas/wiki/%s',
+            'wiki': ('https://github.com/pandas-dev/pandas/wiki/%s',
                      'wiki ')}
 
 ipython_exec_lines = [
@@ -468,10 +468,10 @@ def linkcode_resolve(domain, info):
     fn = os.path.relpath(fn, start=os.path.dirname(pandas.__file__))
 
     if '+' in pandas.__version__:
-        return "http://github.com/pydata/pandas/blob/master/pandas/%s%s" % (
+        return "http://github.com/pandas-dev/pandas/blob/master/pandas/%s%s" % (
             fn, linespec)
     else:
-        return "http://github.com/pydata/pandas/blob/v%s/pandas/%s%s" % (
+        return "http://github.com/pandas-dev/pandas/blob/v%s/pandas/%s%s" % (
             pandas.__version__, fn, linespec)