From 7e461a18d9f6928132afec6f48ce968b3e989ba6 Mon Sep 17 00:00:00 2001 From: Kaiqi Dong Date: Mon, 3 Dec 2018 17:43:52 +0100 Subject: [PATCH 1/7] remove \n from docstring --- pandas/core/arrays/datetimes.py | 26 +++++++++++++------------- pandas/core/arrays/timedeltas.py | 16 ++++++++-------- 2 files changed, 21 insertions(+), 21 deletions(-) diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py index cfe3afcf3730a..b3df505d56d78 100644 --- a/pandas/core/arrays/datetimes.py +++ b/pandas/core/arrays/datetimes.py @@ -82,7 +82,7 @@ def f(self): return result f.__name__ = name - f.__doc__ = docstring + f.__doc__ = "\n{}\n".format(docstring) return property(f) @@ -1072,19 +1072,19 @@ def date(self): return tslib.ints_to_pydatetime(timestamps, box="date") - year = _field_accessor('year', 'Y', "\n The year of the datetime\n") + year = _field_accessor('year', 'Y', "The year of the datetime") month = _field_accessor('month', 'M', - "\n The month as January=1, December=12 \n") - day = _field_accessor('day', 'D', "\nThe days of the datetime\n") - hour = _field_accessor('hour', 'h', "\nThe hours of the datetime\n") - minute = _field_accessor('minute', 'm', "\nThe minutes of the datetime\n") - second = _field_accessor('second', 's', "\nThe seconds of the datetime\n") + "The month as January=1, December=12") + day = _field_accessor('day', 'D', "The days of the datetime") + hour = _field_accessor('hour', 'h', "The hours of the datetime") + minute = _field_accessor('minute', 'm', "The minutes of the datetime") + second = _field_accessor('second', 's', "The seconds of the datetime") microsecond = _field_accessor('microsecond', 'us', - "\nThe microseconds of the datetime\n") + "The microseconds of the datetime") nanosecond = _field_accessor('nanosecond', 'ns', - "\nThe nanoseconds of the datetime\n") + "The nanoseconds of the datetime") weekofyear = _field_accessor('weekofyear', 'woy', - "\nThe week ordinal of the year\n") + "The week ordinal of the year") week = weekofyear _dayofweek_doc = """ The day of the week with Monday=0, Sunday=6. @@ -1129,12 +1129,12 @@ def date(self): "The name of day in a week (ex: Friday)\n\n.. deprecated:: 0.23.0") dayofyear = _field_accessor('dayofyear', 'doy', - "\nThe ordinal day of the year\n") - quarter = _field_accessor('quarter', 'q', "\nThe quarter of the date\n") + "The ordinal day of the year") + quarter = _field_accessor('quarter', 'q', "The quarter of the date") days_in_month = _field_accessor( 'days_in_month', 'dim', - "\nThe number of days in the month\n") + "The number of days in the month") daysinmonth = days_in_month _is_month_doc = """ Indicates whether the date is the {first_or_last} day of the month. diff --git a/pandas/core/arrays/timedeltas.py b/pandas/core/arrays/timedeltas.py index 830283d31a929..4afc9f5483c2a 100644 --- a/pandas/core/arrays/timedeltas.py +++ b/pandas/core/arrays/timedeltas.py @@ -59,7 +59,7 @@ def f(self): return result f.__name__ = name - f.__doc__ = docstring + f.__doc__ = "\n{}\n".format(docstring) return property(f) @@ -684,16 +684,16 @@ def to_pytimedelta(self): return tslibs.ints_to_pytimedelta(self.asi8) days = _field_accessor("days", "days", - "\nNumber of days for each element.\n") + "Number of days for each element.") seconds = _field_accessor("seconds", "seconds", - "\nNumber of seconds (>= 0 and less than 1 day) " - "for each element.\n") + "Number of seconds (>= 0 and less than 1 day) " + "for each element.") microseconds = _field_accessor("microseconds", "microseconds", - "\nNumber of microseconds (>= 0 and less " - "than 1 second) for each element.\n") + "Number of microseconds (>= 0 and less " + "than 1 second) for each element.") nanoseconds = _field_accessor("nanoseconds", "nanoseconds", - "\nNumber of nanoseconds (>= 0 and less " - "than 1 microsecond) for each element.\n") + "Number of nanoseconds (>= 0 and less " + "than 1 microsecond) for each element.") @property def components(self): From dea38f24c0067ae3fe9484b837c9649714213bba Mon Sep 17 00:00:00 2001 From: Kaiqi Date: Tue, 14 Jan 2020 21:26:31 +0100 Subject: [PATCH 2/7] fix issue 17038 --- pandas/core/reshape/pivot.py | 4 +++- pandas/tests/reshape/test_pivot.py | 20 ++++++++++++++------ 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/pandas/core/reshape/pivot.py b/pandas/core/reshape/pivot.py index b443ba142369c..9743d90f4dd04 100644 --- a/pandas/core/reshape/pivot.py +++ b/pandas/core/reshape/pivot.py @@ -117,7 +117,9 @@ def pivot_table( agged[v] = maybe_downcast_to_dtype(agged[v], data[v].dtype) table = agged - if table.index.nlevels > 1: + + # GH 17038, this check should only happen if index is specified + if table.index.nlevels > 1 and index: # Related GH #17123 # If index_names are integers, determine whether the integers refer # to the level position or name. diff --git a/pandas/tests/reshape/test_pivot.py b/pandas/tests/reshape/test_pivot.py index 743fc50c87e96..46a05123c9fdd 100644 --- a/pandas/tests/reshape/test_pivot.py +++ b/pandas/tests/reshape/test_pivot.py @@ -896,12 +896,6 @@ def _check_output( totals = table.loc[("All", ""), value_col] assert totals == self.data[value_col].mean() - # no rows - rtable = self.data.pivot_table( - columns=["AA", "BB"], margins=True, aggfunc=np.mean - ) - assert isinstance(rtable, Series) - table = self.data.pivot_table(index=["AA", "BB"], margins=True, aggfunc="mean") for item in ["DD", "EE", "FF"]: totals = table.loc[("All", ""), item] @@ -972,6 +966,20 @@ def test_pivot_integer_columns(self): tm.assert_frame_equal(table, table2, check_names=False) + @pytest.mark.parametrize("cols", [(1, 2), ("a", "b"), (1, "b"), ("a", 1)]) + def test_pivot_table_multiindex_only(self, cols): + # GH 17038 + df2 = DataFrame({cols[0]: [1, 2, 3], cols[1]: [1, 2, 3], "v": [4, 5, 6]}) + + result = df2.pivot_table(values="v", columns=cols) + expected = DataFrame( + [[4, 5, 6]], + columns=MultiIndex.from_tuples([(1, 1), (2, 2), (3, 3)], names=cols), + index=Index(["v"]), + ) + + tm.assert_frame_equal(result, expected) + def test_pivot_no_level_overlap(self): # GH #1181 From cd9e7ac3f31ffaf95cd628863df911dea9fa1248 Mon Sep 17 00:00:00 2001 From: Kaiqi Date: Tue, 14 Jan 2020 21:29:43 +0100 Subject: [PATCH 3/7] revert change --- pandas/core/reshape/pivot.py | 3 +-- pandas/tests/reshape/test_pivot.py | 20 ++++++-------------- 2 files changed, 7 insertions(+), 16 deletions(-) diff --git a/pandas/core/reshape/pivot.py b/pandas/core/reshape/pivot.py index 9743d90f4dd04..a7cdbb0da7a4e 100644 --- a/pandas/core/reshape/pivot.py +++ b/pandas/core/reshape/pivot.py @@ -118,8 +118,7 @@ def pivot_table( table = agged - # GH 17038, this check should only happen if index is specified - if table.index.nlevels > 1 and index: + if table.index.nlevels > 1: # Related GH #17123 # If index_names are integers, determine whether the integers refer # to the level position or name. diff --git a/pandas/tests/reshape/test_pivot.py b/pandas/tests/reshape/test_pivot.py index 46a05123c9fdd..743fc50c87e96 100644 --- a/pandas/tests/reshape/test_pivot.py +++ b/pandas/tests/reshape/test_pivot.py @@ -896,6 +896,12 @@ def _check_output( totals = table.loc[("All", ""), value_col] assert totals == self.data[value_col].mean() + # no rows + rtable = self.data.pivot_table( + columns=["AA", "BB"], margins=True, aggfunc=np.mean + ) + assert isinstance(rtable, Series) + table = self.data.pivot_table(index=["AA", "BB"], margins=True, aggfunc="mean") for item in ["DD", "EE", "FF"]: totals = table.loc[("All", ""), item] @@ -966,20 +972,6 @@ def test_pivot_integer_columns(self): tm.assert_frame_equal(table, table2, check_names=False) - @pytest.mark.parametrize("cols", [(1, 2), ("a", "b"), (1, "b"), ("a", 1)]) - def test_pivot_table_multiindex_only(self, cols): - # GH 17038 - df2 = DataFrame({cols[0]: [1, 2, 3], cols[1]: [1, 2, 3], "v": [4, 5, 6]}) - - result = df2.pivot_table(values="v", columns=cols) - expected = DataFrame( - [[4, 5, 6]], - columns=MultiIndex.from_tuples([(1, 1), (2, 2), (3, 3)], names=cols), - index=Index(["v"]), - ) - - tm.assert_frame_equal(result, expected) - def test_pivot_no_level_overlap(self): # GH #1181 From e5e912be0f596943067a7df812442764d311a086 Mon Sep 17 00:00:00 2001 From: Kaiqi Date: Tue, 14 Jan 2020 21:30:16 +0100 Subject: [PATCH 4/7] revert change --- pandas/core/reshape/pivot.py | 1 - 1 file changed, 1 deletion(-) diff --git a/pandas/core/reshape/pivot.py b/pandas/core/reshape/pivot.py index a7cdbb0da7a4e..b443ba142369c 100644 --- a/pandas/core/reshape/pivot.py +++ b/pandas/core/reshape/pivot.py @@ -117,7 +117,6 @@ def pivot_table( agged[v] = maybe_downcast_to_dtype(agged[v], data[v].dtype) table = agged - if table.index.nlevels > 1: # Related GH #17123 # If index_names are integers, determine whether the integers refer From 4eaea14f89cefd5c558167d9adfb17c93a298f06 Mon Sep 17 00:00:00 2001 From: kaiqi Dong Date: Tue, 13 Jul 2021 20:31:14 +0200 Subject: [PATCH 5/7] add examples in user guide and docstring for box --- doc/source/user_guide/visualization.rst | 51 +++++++++++++++++++++++++ pandas/plotting/_core.py | 10 +++++ 2 files changed, 61 insertions(+) diff --git a/doc/source/user_guide/visualization.rst b/doc/source/user_guide/visualization.rst index 1c02be989eeeb..7ab038dc05139 100644 --- a/doc/source/user_guide/visualization.rst +++ b/doc/source/user_guide/visualization.rst @@ -316,6 +316,33 @@ The ``by`` keyword can be specified to plot grouped histograms: @savefig grouped_hist.png data.hist(by=np.random.randint(0, 4, 1000), figsize=(6, 4)); +.. ipython:: python + :suppress: + + plt.close("all") + np.random.seed(123456) + +In addition, the ``by`` keyword can also be specified in :meth:`DataFrame.plot.hist`. + +.. ipython:: python + + data = pd.DataFrame( + { + "a": np.random.choice(["x", "y", "z"], 1000), + "b": np.random.choice(["e", "f", "g"], 1000), + "c": np.random.randn(1000), + "d": np.random.randn(1000) - 1, + }, + columns=["a", "b", "c", "d"], + ) + + @savefig grouped_hist_by.png + data.plot.hist(by=["a", "b"], figsize=(10, 5)); + +.. ipython:: python + :suppress: + + plt.close("all") .. _visualization.box: @@ -448,6 +475,30 @@ columns: plt.close("all") +You could also create groupings with :meth:`DataFrame.plot.box`, for instance, + +.. ipython:: python + :suppress: + + plt.close("all") + np.random.seed(123456) + +.. ipython:: python + :okwarning: + + df = pd.DataFrame(np.random.rand(10, 3), columns=["Col1", "Col2", "Col3"]) + df["X"] = pd.Series(["A", "A", "A", "A", "A", "B", "B", "B", "B", "B"]) + + plt.figure(); + + @savefig box_plot_ex4.png + bp = df.plot.box(column=["Col1", "Col2"], by="X") + +.. ipython:: python + :suppress: + + plt.close("all") + .. _visualization.box.return: In ``boxplot``, the return type can be controlled by the ``return_type``, keyword. The valid choices are ``{"axes", "dict", "both", None}``. diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py index 990ccbc2a015b..d0581c51d0546 100644 --- a/pandas/plotting/_core.py +++ b/pandas/plotting/_core.py @@ -1267,6 +1267,16 @@ def box(self, by=None, **kwargs): >>> data = np.random.randn(25, 4) >>> df = pd.DataFrame(data, columns=list('ABCD')) >>> ax = df.plot.box() + + You can also generate groupings if you specify the `by` parameter (which + can take a column name, or a list or tuple of column names): + + .. plot:: + :context: close-figs + + >>> age_list = [8, 10, 12, 14, 72, 74, 76, 78, 20, 25, 30, 35, 60, 85] + >>> df = pd.DataFrame({"gender": list("MMMMMMMMFFFFFF"), "age": age_list}) + >>> ax = df.plot.box(column="age", by="gender", figsize=(10, 8)) """ return self(kind="box", by=by, **kwargs) From d6a5bbd0e29d1b3f545813a44c06813444eeee30 Mon Sep 17 00:00:00 2001 From: kaiqi Dong Date: Tue, 13 Jul 2021 20:34:58 +0200 Subject: [PATCH 6/7] update --- doc/source/user_guide/visualization.rst | 1 - 1 file changed, 1 deletion(-) diff --git a/doc/source/user_guide/visualization.rst b/doc/source/user_guide/visualization.rst index 7ab038dc05139..1dd560b8cee27 100644 --- a/doc/source/user_guide/visualization.rst +++ b/doc/source/user_guide/visualization.rst @@ -333,7 +333,6 @@ In addition, the ``by`` keyword can also be specified in :meth:`DataFrame.plot.h "c": np.random.randn(1000), "d": np.random.randn(1000) - 1, }, - columns=["a", "b", "c", "d"], ) @savefig grouped_hist_by.png From 09060c546af9dd3bce09568f80cdbb9f75b98107 Mon Sep 17 00:00:00 2001 From: kaiqi Dong Date: Thu, 15 Jul 2021 21:39:17 +0200 Subject: [PATCH 7/7] add version changed --- doc/source/user_guide/visualization.rst | 6 +++++- pandas/plotting/_core.py | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/doc/source/user_guide/visualization.rst b/doc/source/user_guide/visualization.rst index 1dd560b8cee27..4edf32e2a1e5f 100644 --- a/doc/source/user_guide/visualization.rst +++ b/doc/source/user_guide/visualization.rst @@ -324,6 +324,8 @@ The ``by`` keyword can be specified to plot grouped histograms: In addition, the ``by`` keyword can also be specified in :meth:`DataFrame.plot.hist`. +.. versionchanged:: 1.4.0 + .. ipython:: python data = pd.DataFrame( @@ -474,7 +476,9 @@ columns: plt.close("all") -You could also create groupings with :meth:`DataFrame.plot.box`, for instance, +You could also create groupings with :meth:`DataFrame.plot.box`, for instance: + +.. versionchanged:: 1.4.0 .. ipython:: python :suppress: diff --git a/pandas/plotting/_core.py b/pandas/plotting/_core.py index d0581c51d0546..456b10dd55726 100644 --- a/pandas/plotting/_core.py +++ b/pandas/plotting/_core.py @@ -1271,6 +1271,8 @@ def box(self, by=None, **kwargs): You can also generate groupings if you specify the `by` parameter (which can take a column name, or a list or tuple of column names): + .. versionchanged:: 1.4.0 + .. plot:: :context: close-figs