Seaborn plot pandas dataframe by multiple groupby

Question

I have pandas dataframe where I have nested 4 categories (50,60,70,80) within two categories (positive, negative) and I would like to plot with seaborn kdeplot of a column (eg., A_mean...) based on groupby. What I want to achieve is this picture (this was done by splitting the pandas to a list). I went over several posts, this code (Multiple single plots in seaborn with pandas groupby data) works for one level but not for the two if I want to plot this for each Game_RS:

for i, group in df_hb_SLR.groupby('Condition'):
 sns.kdeplot(data=group['A_mean_per_subject'], shade=True, color='blue', label = 'label name')

I tried to use this one (Seaborn groupby pandas Series) but the first answer did not work for me:

sns.kdeplot(df_hb_SLR.A_mean_per_subject, groupby=df_hb_SLR.Game_RS)
AttributeError: 'Line2D' object has no property 'groupby'

and the pivot answer I was not able to make work. Is there a direct way from seaborn or any better way directly from pandas Dataframe?

My data are accessible in csv format under this link -- data and I load them as usual:

df_hb_SLR = pd.read_csv('data.csv')

Thank you for help.

Answer 1

Here is a solution using seaborn's FacetGrid, which makes this kind of things really easy

g = sns.FacetGrid(data=df_hb_SLR, col="Condition", hue='Game_RS', height=5, aspect=0.5)
g = g.map(sns.kdeplot, 'A_mean_per_subject', shade=True)
g.add_legend()

enter image description here

The downside of FacetGrid is that it creates a new figure, so If you'd like to integrate those plots into a larger ensemble of subplots, you could achieve the same result using groupby() and some looping:

group1 = "Condition"
N1 = len(df_hb_SLR[group1].unique())
group2 = 'Game_RS'
target = 'A_mean_per_subject'
height = 5
aspect = 0.5
colour = ['gray', 'blue', 'green', 'darkorange']
fig, axs = plt.subplots(1,N1, figsize=(N1*height*aspect,N1*height*aspect), sharey=True)
for (group1Name,df1),ax in zip(df_hb_SLR.groupby(group1),axs):
 ax.set_title(group1Name)
 for (group2Name,df2),c in zip(df1.groupby(group2), colour): 
 sns.kdeplot(df2[target], shade=True, label=group2Name, ax=ax, color = c) 

enter image description here

• My Work: Hi Diziet, thank you very much for your answer. I have two small questions to the 2nd, for loop solution. 1) could you please describe how the looping over groupby objects work? Because 2) I wanted to add custom colour to each game, I tried to generalize your solution to: ``` colour = ['gray', 'blue', 'green', 'darkorange'] ... for (group1Name,df1),ax in zip(df_hb_SLR.groupby(group1),axs): ax.set_title(group1Name) for (group2Name,df2),colour in zip(df1.groupby(group2), colour): sns.kdeplot(df2[target], shade=True, label=group2Name, ax=ax, color = colour) ```
• Diziet Asahi: Your code was almost correct, except that you were using the same name colour twice in the for-loop. I've amended my answer.
• My Work: One more question. If I change the groups, ie. group1 = 'Game_RS'; group2 = 'Condition' and then I want to use 2 rows, 2 cols, fig, axs = plt.subplots(2,2, figsize=(N1*height*aspect,N1*height*aspect), sharey=True) I get this error: AttributeError: 'numpy.ndarray' object has no attribute 'set_title'. Do you know why and how to fix it? If I use (1,N1), it works. Thanks
• Diziet Asahi: There are many posts about that error. For instance see here. Basically, if you're doing more that 1 row or 1 column, then the returned object is a 2D numpy array. You can loop using for (...),ax in zip(..., axs.flat):