Merge remote-tracking branch 'upstream/master' into _get_cython_result

Author: rhshadrach

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]

asv_bench/benchmarks/rolling.py

@@ -186,4 +186,27 @@ def peakmem_rolling(self, constructor, window_size, dtype, method):
         getattr(self.roll, method)()
 
 
+class Groupby:
+
+    params = ["sum", "median", "mean", "max", "min", "kurt", "sum"]
+
+    def setup(self, method):
+        N = 1000
+        df = pd.DataFrame(
+            {
+                "A": [str(i) for i in range(N)] * 10,
+                "B": list(range(N)) * 10,
+                "C": pd.date_range(start="1900-01-01", freq="1min", periods=N * 10),
+            }
+        )
+        self.groupby_roll_int = df.groupby("A").rolling(window=2)
+        self.groupby_roll_offset = df.groupby("A").rolling(window="30s", on="C")
+
+    def time_rolling_int(self, method):
+        getattr(self.groupby_roll_int, method)()
+
+    def time_rolling_offset(self, method):
+        getattr(self.groupby_roll_offset, method)()
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

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