Python 如何将第二个轴添加到matplotlib/seaborn条形图,并使辅助点与正确的条形图对齐?
我编写了一个(新手)python函数(如下)来绘制一个由主维度和可能的辅助维度组成的条形图。例如,下图显示了达到特定教育水平的男女比例 问题:我如何在每个栏上覆盖该分组的家庭规模中值,例如,在大学/女性栏上放置一个表示值“3”的点。我所看到的例子中没有一个能准确地将点覆盖在正确的条上 我对这个非常陌生,所以非常感谢你的帮助Python 如何将第二个轴添加到matplotlib/seaborn条形图,并使辅助点与正确的条形图对齐?,python,matplotlib,charts,seaborn,axes,Python,Matplotlib,Charts,Seaborn,Axes,我编写了一个(新手)python函数(如下)来绘制一个由主维度和可能的辅助维度组成的条形图。例如,下图显示了达到特定教育水平的男女比例 问题:我如何在每个栏上覆盖该分组的家庭规模中值,例如,在大学/女性栏上放置一个表示值“3”的点。我所看到的例子中没有一个能准确地将点覆盖在正确的条上 我对这个非常陌生,所以非常感谢你的帮助 df = pd.DataFrame({'Student' : ['Alice', 'Bob', 'Chris', 'Dave', 'Edna', '
df = pd.DataFrame({'Student' : ['Alice', 'Bob', 'Chris', 'Dave', 'Edna', 'Frank'],
'Education' : ['HS', 'HS', 'HS', 'College', 'College', 'HS' ],
'Household Size': [4, 4, 3, 3, 3, 6 ],
'Gender' : ['F', 'M', 'M', 'M', 'F', 'M' ]});
def MakePercentageFrequencyTable(dataFrame, primaryDimension, secondaryDimension=None, extraAggregatedField=None):
lod = dataFrame.groupby([secondaryDimension]) if secondaryDimension is not None else dataFrame
primaryDimensionPercent = lod[primaryDimension].value_counts(normalize=True) \
.rename('percentage') \
.mul(100) \
.reset_index(drop=False);
if secondaryDimension is not None:
primaryDimensionPercent = primaryDimensionPercent.sort_values(secondaryDimension)
g = sns.catplot(x="percentage", y=secondaryDimension, hue=primaryDimension, kind='bar', data=primaryDimensionPercent)
else:
sns.catplot(x="percentage", y='index', kind='bar', data=primaryDimensionPercent)
MakePercentageFrequencyTable(dataFrame=df,primaryDimension='Education', secondaryDimension='Gender')
# Question: I want to send in extraAggregatedField='Household Size' when I call the function such that
# it creates a secondary 'Household Size' axis at the top of the figure
# and aggregates/integrates the 'Household Size' column such that the following points are plotted
# against the secondary axis and positioned over the given bars:
#
# Female/College => 3
# Female/High School => 4
# Male/College => 3
# Male/High School => 4
您必须使用轴级函数
sns.barplot()
和sns.stripplot()
,而不是catplot()
,这将创建一个新图形和一个FaceGrid
大概是这样的:
df = pd.DataFrame({'Student' : ['Alice', 'Bob', 'Chris', 'Dave', 'Edna', 'Frank'],
'Education' : ['HS', 'HS', 'HS', 'College', 'College', 'HS' ],
'Household Size': [4, 4, 3, 3, 3, 6 ],
'Gender' : ['F', 'M', 'M', 'M', 'F', 'M' ]});
def MakePercentageFrequencyTable(dataFrame, primaryDimension, secondaryDimension=None, extraAggregatedField=None, ax=None):
ax = plt.gca() if ax is None else ax
lod = dataFrame.groupby([secondaryDimension]) if secondaryDimension is not None else dataFrame
primaryDimensionPercent = lod[primaryDimension].value_counts(normalize=True) \
.rename('percentage') \
.mul(100) \
.reset_index(drop=False);
if secondaryDimension is not None:
primaryDimensionPercent = primaryDimensionPercent.sort_values(secondaryDimension)
ax = sns.barplot(x="percentage", y=secondaryDimension, hue=primaryDimension, data=primaryDimensionPercent, ax=ax)
else:
ax = sns.barplot(x="percentage", y='index', data=primaryDimensionPercent, ax=ax)
if extraAggregatedField is not None:
ax2 = ax.twiny()
extraDimension = dataFrame.groupby([primaryDimension, secondaryDimension]).mean().reset_index(drop=False)
ax2 = sns.stripplot(data=extraDimension, x=extraAggregatedField, y=secondaryDimension, hue=primaryDimension,
ax=ax2,dodge=True, edgecolors='k', linewidth=1, size=10)
plt.figure()
MakePercentageFrequencyTable(dataFrame=df,primaryDimension='Education', secondaryDimension='Gender', extraAggregatedField='Household Size')
欢迎使用堆栈溢出!请花点时间阅读。您需要提供一个包含玩具数据集(请参阅)Thank You@DizietAsahi的。我重写了这个问题,希望能在本地重现,并且更清晰。