Plotting multiple seaborn displot

Question

I am trying to create distplot of a dataframe grouped by a column

data_plot = creditcard_df.copy()
amount = data_plot['Amount']
data_plot.drop(labels=['Amount'], axis=1, inplace = True)
data_plot.insert(0, 'Amount', amount)

# Plot the distributions of the features
columns = data_plot.iloc[:,0:30].columns
plt.figure(figsize=(12,30*4))
grids = gridspec.GridSpec(30, 1)
for grid, index in enumerate(data_plot[columns]):
    ax = plt.subplot(grids[grid])
    sns.distplot(data_plot[index][data_plot.Class == 1], hist=False, kde_kws={"shade": True}, bins=20)
    sns.distplot(data_plot[index][data_plot.Class == 0], hist=False, kde_kws={"shade": True}, bins=20)
    ax.set_xlabel("")
    ax.set_title("Distribution of Column: "  + str(index))
    plt.show()

I tried to use a log scale for the y axis, change the gridspec, and the figsize; but all of those only made a mess of the distributions. Is there a way to make the plots uniform?

Answer 1

• seaborn.distplot is deprecated. Use seaborn.kdeplot, which is an axes-level plot. Otherwise use seaborn.displot for a figure-level plot.
• Tested in python 3.11, pandas 1.5.3, matplotlib 3.7.1, seaborn 0.12.2

Imports and Test Data

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

np.random.seed(365)
rows = 10000
data = {'a': np.random.normal(5, 5, rows),
        'b': np.random.normal(20, 5, rows),
        'c': np.random.normal(35, 5, rows),
        'd': np.random.normal(500, 50, rows),
        'e': np.random.normal(6500, 500, rows),
        'class': np.random.choice([0, 1], size=(rows), p=[0.25, 0.75])}
df = pd.DataFrame(data)

# display(df.head(3))
          a          b          c           d            e  class
0  5.839606  20.807027  34.798230  509.328065  6003.228497      0
1  7.617526  21.691519  40.519995  445.724478  7204.039621      0
2  9.086878  27.193222  32.776264  498.254687  6810.960924      1

Plot with seaborn.kdeplot

fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(15, 7), sharex=False, sharey=False)
axes = axes.ravel()  # array to 1D
cols = df.columns[:-1]  # create a list of dataframe columns to use

for col, ax in zip(cols, axes):
    data = df[[col, 'class']]  # select the data
    sns.kdeplot(data=data, x=col, hue='class', fill=True, ax=ax)
    ax.set(title=f'Distribution of Column: {col}', xlabel=None)
    
fig.delaxes(axes[5])  # delete the empty subplot
fig.tight_layout()
plt.show()

Plot with seaborn.displot

# convert the dataframe from wide to long
dfm = df.melt(id_vars='class', var_name='Distribution')

# display(dfm.head(3))
   class Distribution     value
0      0            a  5.839606
1      0            a  7.617526
2      1            a  9.086878

# plot
sns.displot(kind='kde', data=dfm, col='Distribution', col_wrap=3, x='value', hue='class', fill=True, facet_kws={'sharey': False, 'sharex': False})