Merging

Author: LucasG0

asv_bench/benchmarks/arithmetic.py

@@ -469,4 +469,29 @@ def time_apply_index(self, offset):
         offset.apply_index(self.rng)
 
 
+class BinaryOpsMultiIndex:
+    params = ["sub", "add", "mul", "div"]
+    param_names = ["func"]
+
+    def setup(self, func):
+        date_range = pd.date_range("20200101 00:00", "20200102 0:00", freq="S")
+        level_0_names = [str(i) for i in range(30)]
+
+        index = pd.MultiIndex.from_product([level_0_names, date_range])
+        column_names = ["col_1", "col_2"]
+
+        self.df = pd.DataFrame(
+            np.random.rand(len(index), 2), index=index, columns=column_names
+        )
+
+        self.arg_df = pd.DataFrame(
+            np.random.randint(1, 10, (len(level_0_names), 2)),
+            index=level_0_names,
+            columns=column_names,
+        )
+
+    def time_binary_op_multiindex(self, func):
+        getattr(self.df, func)(self.arg_df, level=0)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/indexing.py

@@ -158,9 +158,9 @@ def time_boolean_rows_boolean(self):
 class DataFrameNumericIndexing:
     def setup(self):
         self.idx_dupe = np.array(range(30)) * 99
-        self.df = DataFrame(np.random.randn(10000, 5))
+        self.df = DataFrame(np.random.randn(100000, 5))
         self.df_dup = concat([self.df, 2 * self.df, 3 * self.df])
-        self.bool_indexer = [True] * 5000 + [False] * 5000
+        self.bool_indexer = [True] * 50000 + [False] * 50000
 
     def time_iloc_dups(self):
         self.df_dup.iloc[self.idx_dupe]

doc/source/development/contributing.rst

@@ -1275,8 +1275,8 @@ Performance matters and it is worth considering whether your code has introduced
 performance regressions. pandas is in the process of migrating to
 `asv benchmarks <https://github.com/spacetelescope/asv>`__
 to enable easy monitoring of the performance of critical pandas operations.
-These benchmarks are all found in the ``pandas/asv_bench`` directory.  asv
-supports both python2 and python3.
+These benchmarks are all found in the ``pandas/asv_bench`` directory, and the
+test results can be found `here <https://pandas.pydata.org/speed/pandas/#/>`__.
 
 To use all features of asv, you will need either ``conda`` or
 ``virtualenv``. For more details please check the `asv installation

doc/source/ecosystem.rst

@@ -153,6 +153,23 @@ A good implementation for Python users is `has2k1/plotnine <https://github.com/h
 Spun off from the main pandas library, the `qtpandas <https://github.com/draperjames/qtpandas>`__
 library enables DataFrame visualization and manipulation in PyQt4 and PySide applications.
 
+`D-Tale <https://github.com/man-group/dtale>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+D-Tale is a lightweight web client for visualizing pandas data structures. It
+provides a rich spreadsheet-style grid which acts as a wrapper for a lot of
+pandas functionality (query, sort, describe, corr...) so users can quickly
+manipulate their data. There is also an interactive chart-builder using Plotly
+Dash allowing users to build nice portable visualizations. D-Tale can be
+invoked with the following command
+
+.. code:: python
+
+    import dtale; dtale.show(df)
+
+D-Tale integrates seamlessly with jupyter notebooks, python terminals, kaggle
+& Google Colab. Here are some demos of the `grid <http://alphatechadmin.pythonanywhere.com/>`__
+and `chart-builder <http://alphatechadmin.pythonanywhere.com/charts/4?chart_type=surface&query=&x=date&z=Col0&agg=raw&cpg=false&y=%5B%22security_id%22%5D>`__.
 
 .. _ecosystem.ide:
 

doc/source/reference/frame.rst

@@ -240,13 +240,14 @@ Reshaping, sorting, transposing
    DataFrame.T
    DataFrame.transpose
 
-Combining / joining / merging
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Combining / comparing / joining / merging
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 .. autosummary::
    :toctree: api/
 
    DataFrame.append
    DataFrame.assign
+   DataFrame.compare
    DataFrame.join
    DataFrame.merge
    DataFrame.update

doc/source/reference/offset_frequency.rst

@@ -59,6 +59,9 @@ Properties
     BusinessDay.normalize
     BusinessDay.rule_code
     BusinessDay.n
+    BusinessDay.weekmask
+    BusinessDay.holidays
+    BusinessDay.calendar
 
 Methods
 ~~~~~~~
@@ -95,6 +98,9 @@ Properties
     BusinessHour.n
     BusinessHour.start
     BusinessHour.end
+    BusinessHour.weekmask
+    BusinessHour.holidays
+    BusinessHour.calendar
 
 Methods
 ~~~~~~~
@@ -128,12 +134,16 @@ Properties
     CustomBusinessDay.normalize
     CustomBusinessDay.rule_code
     CustomBusinessDay.n
+    CustomBusinessDay.weekmask
+    CustomBusinessDay.calendar
+    CustomBusinessDay.holidays
 
 Methods
 ~~~~~~~
 .. autosummary::
    :toctree: api/
 
+    CustomBusinessDay.apply_index
     CustomBusinessDay.apply
     CustomBusinessDay.copy
     CustomBusinessDay.isAnchored
@@ -161,6 +171,9 @@ Properties
     CustomBusinessHour.normalize
     CustomBusinessHour.rule_code
     CustomBusinessHour.n
+    CustomBusinessHour.weekmask
+    CustomBusinessHour.calendar
+    CustomBusinessHour.holidays
     CustomBusinessHour.start
     CustomBusinessHour.end
 
@@ -333,6 +346,9 @@ Properties
     CustomBusinessMonthEnd.normalize
     CustomBusinessMonthEnd.rule_code
     CustomBusinessMonthEnd.n
+    CustomBusinessMonthEnd.weekmask
+    CustomBusinessMonthEnd.calendar
+    CustomBusinessMonthEnd.holidays
 
 Methods
 ~~~~~~~
@@ -367,6 +383,9 @@ Properties
     CustomBusinessMonthBegin.normalize
     CustomBusinessMonthBegin.rule_code
     CustomBusinessMonthBegin.n
+    CustomBusinessMonthBegin.weekmask
+    CustomBusinessMonthBegin.calendar
+    CustomBusinessMonthBegin.holidays
 
 Methods
 ~~~~~~~
@@ -381,40 +400,6 @@ Methods
     CustomBusinessMonthBegin.is_on_offset
     CustomBusinessMonthBegin.__call__
 
-SemiMonthOffset
----------------
-.. autosummary::
-   :toctree: api/
-
-    SemiMonthOffset
-
-Properties
-~~~~~~~~~~
-.. autosummary::
-   :toctree: api/
-
-    SemiMonthOffset.freqstr
-    SemiMonthOffset.kwds
-    SemiMonthOffset.name
-    SemiMonthOffset.nanos
-    SemiMonthOffset.normalize
-    SemiMonthOffset.rule_code
-    SemiMonthOffset.n
-
-Methods
-~~~~~~~
-.. autosummary::
-   :toctree: api/
-
-    SemiMonthOffset.apply
-    SemiMonthOffset.apply_index
-    SemiMonthOffset.copy
-    SemiMonthOffset.isAnchored
-    SemiMonthOffset.onOffset
-    SemiMonthOffset.is_anchored
-    SemiMonthOffset.is_on_offset
-    SemiMonthOffset.__call__
-
 SemiMonthEnd
 ------------
 .. autosummary::
@@ -434,6 +419,7 @@ Properties
     SemiMonthEnd.normalize
     SemiMonthEnd.rule_code
     SemiMonthEnd.n
+    SemiMonthEnd.day_of_month
 
 Methods
 ~~~~~~~
@@ -468,6 +454,7 @@ Properties
     SemiMonthBegin.normalize
     SemiMonthBegin.rule_code
     SemiMonthBegin.n
+    SemiMonthBegin.day_of_month
 
 Methods
 ~~~~~~~
@@ -502,6 +489,7 @@ Properties
     Week.normalize
     Week.rule_code
     Week.n
+    Week.weekday
 
 Methods
 ~~~~~~~
@@ -536,6 +524,7 @@ Properties
     WeekOfMonth.normalize
     WeekOfMonth.rule_code
     WeekOfMonth.n
+    WeekOfMonth.week
 
 Methods
 ~~~~~~~
@@ -571,6 +560,7 @@ Properties
     LastWeekOfMonth.rule_code
     LastWeekOfMonth.n
     LastWeekOfMonth.weekday
+    LastWeekOfMonth.week
 
 Methods
 ~~~~~~~
@@ -922,6 +912,7 @@ Properties
     FY5253Quarter.normalize
     FY5253Quarter.rule_code
     FY5253Quarter.n
+    FY5253Quarter.qtr_with_extra_week
     FY5253Quarter.startingMonth
     FY5253Quarter.variation
     FY5253Quarter.weekday
@@ -1268,6 +1259,9 @@ Properties
     BDay.offset
     BDay.rule_code
     BDay.n
+    BDay.weekmask
+    BDay.holidays
+    BDay.calendar
 
 Methods
 ~~~~~~~
@@ -1383,6 +1377,9 @@ Properties
     CBMonthEnd.offset
     CBMonthEnd.rule_code
     CBMonthEnd.n
+    CBMonthEnd.weekmask
+    CBMonthEnd.holidays
+    CBMonthEnd.calendar
 
 Methods
 ~~~~~~~
@@ -1424,6 +1421,9 @@ Properties
     CBMonthBegin.offset
     CBMonthBegin.rule_code
     CBMonthBegin.n
+    CBMonthBegin.weekmask
+    CBMonthBegin.holidays
+    CBMonthBegin.calendar
 
 Methods
 ~~~~~~~
@@ -1462,6 +1462,9 @@ Properties
     CDay.offset
     CDay.rule_code
     CDay.n
+    CDay.weekmask
+    CDay.calendar
+    CDay.holidays
 
 Methods
 ~~~~~~~
@@ -1479,6 +1482,7 @@ Methods
     CDay.rollforward
     CDay.__call__
 
+
 .. _api.frequencies:
 
 ===========

doc/source/reference/series.rst

@@ -240,12 +240,13 @@ Reshaping, sorting
    Series.squeeze
    Series.view
 
-Combining / joining / merging
------------------------------
+Combining / comparing / joining / merging
+-----------------------------------------
 .. autosummary::
    :toctree: api/
 
    Series.append
+   Series.compare
    Series.replace
    Series.update
 

doc/source/user_guide/gotchas.rst

@@ -321,7 +321,7 @@ Byte-ordering issues
 --------------------
 Occasionally you may have to deal with data that were created on a machine with
 a different byte order than the one on which you are running Python. A common
-symptom of this issue is an error like:::
+symptom of this issue is an error like::
 
     Traceback
         ...

doc/source/user_guide/indexing.rst

@@ -1866,29 +1866,39 @@ A chained assignment can also crop up in setting in a mixed dtype frame.
 
    These setting rules apply to all of ``.loc/.iloc``.
 
-This is the correct access method:
+The following is the recommended access method using ``.loc`` for multiple items (using ``mask``) and a single item using a fixed index:
 
 .. ipython:: python
 
-   dfc = pd.DataFrame({'A': ['aaa', 'bbb', 'ccc'], 'B': [1, 2, 3]})
-   dfc.loc[0, 'A'] = 11
-   dfc
+   dfc = pd.DataFrame({'a': ['one', 'one', 'two',
+                             'three', 'two', 'one', 'six'],
+                       'c': np.arange(7)})
+   dfd = dfc.copy()
+   # Setting multiple items using a mask
+   mask = dfd['a'].str.startswith('o')
+   dfd.loc[mask, 'c'] = 42
+   dfd
+
+   # Setting a single item
+   dfd = dfc.copy()
+   dfd.loc[2, 'a'] = 11
+   dfd
 
-This *can* work at times, but it is not guaranteed to, and therefore should be avoided:
+The following *can* work at times, but it is not guaranteed to, and therefore should be avoided:
 
 .. ipython:: python
    :okwarning:
 
-   dfc = dfc.copy()
-   dfc['A'][0] = 111
-   dfc
+   dfd = dfc.copy()
+   dfd['a'][2] = 111
+   dfd
 
-This will **not** work at all, and so should be avoided:
+Last, the subsequent example will **not** work at all, and so should be avoided:
 
 ::
 
    >>> pd.set_option('mode.chained_assignment','raise')
-   >>> dfc.loc[0]['A'] = 1111
+   >>> dfd.loc[0]['a'] = 1111
    Traceback (most recent call last)
         ...
    SettingWithCopyException: