我寫了一個（新手）python 函數（如下）來繪制一個按主要維度和可能的次要維度劃分的條形圖。例如，下圖顯示了每種性別中獲得特定教育水平的人數百分比。問題：如何在每個條形上疊加該子組的家庭規模中位數，例如在大學/女性條形上放置一個表示值“3”的點。我見過的例子都沒有準確地將點覆蓋在正確的欄上。我對此非常陌生，所以非常感謝您的幫助！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到目前為止我所取得的成就的圖片
1 回答
陪伴而非守候
TA貢獻1757條經驗 獲得超8個贊
您將必須使用軸級函數sns.barplot()和sns.stripplot()而不是catplot()，它會創建一個新圖形和FacetGrid。
像這樣的東西：
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')
添加回答
舉報
0/150
提交
取消