distribution_plot.py

def dist_box(data):
'''
Code will perform univariate analysis for all continuous variables in dataframe.
For each variable, creates plot with spread, central tendency , dispersion and outliers.
'''
    Name=data.name.upper()
    fig,(ax_box,ax_dis)  =plt.subplots(nrows=2,sharex=True,gridspec_kw = {"height_ratios": (.25, .75)},figsize=(8, 5))
    mean=data.mean()
    median=data.median()
    mode=data.mode().tolist()[0]
    sns.set_theme(style="white")
    sns.set_palette(sns.color_palette("Set1", 8))
    fig.suptitle("SPREAD OF DATA FOR "+ Name  , fontsize=18, fontweight='bold')
    sns.boxplot(x=data,showmeans=True, orient='h',ax=ax_box)
    ax_box.set(xlabel='')
     # just trying to make visualisation better. This will set background to white
    sns.despine(top=True,right=True,left=True) # to remove side line from graph
    sns.set_palette(sns.color_palette("Set1", 8))
    sns.distplot(data,kde=False,ax=ax_dis)
    ax_dis.axvline(mean, color='r', linestyle='--',linewidth=2)
    ax_dis.axvline(median, color='g', linestyle='-',linewidth=2)
    ax_dis.axvline(mode, color='y', linestyle='-',linewidth=2)
    plt.legend({'Mean':mean,'Median':median,'Mode':mode})

list_col = data.select_dtypes(include='number').columns.to_list()
for i in range(len(list_col)):
    dist_box(data[list_col[i]])