How do generate a boxplot for every numerical features by a binary target from a Spark dataframe please?
I am not able to extend this to consider the binary target stratification.
age_lst=final_sdf.select('Age','Recommended IND').collect()
counts=[row['Age'] for row in age_lst]
fig, ax = plt.subplots(1,3)
ax[0].set_title('Age',fontsize=15)
ax[0].boxplot(counts,showmeans=True,notch=True)
ax[0].set_ylabel('years')