sidetable_pareto

plot_pareto

# Refer code develop by Tyler Marrs
# https://tylermarrs.com/posts/pareto-plot-with-matplotlib/

def pareto_plot(df, x, y="Count", title=None, show_pct_y=True, pct_format='{0:.0%}'):
    xlabel = x
    ylabel = y
    df=df.stb.freq([x]) # use sidetable
    if len(x) >1:
      df['MergCol'] = df[df.columns[:2]].apply(
      lambda x: ','.join(x.astype(str)),
      axis=1)
    tmp = df.sort_values(y, ascending=False)
    x = tmp[x].values
    y = tmp[y].values
    # weights = y / y.sum()
    # cumsum = weights.cumsum()
    cumsum=tmp["Cumulative Percent"].values 

    fig, ax1 = plt.subplots()
    ax1.bar(x, y)
    ax1.set_xlabel(xlabel)
    ax1.set_ylabel(ylabel)

    ax2 = ax1.twinx()
    ax2.plot(x, cumsum, '-ro', alpha=0.5)
    ax2.set_ylabel('', color='r')
    ax2.tick_params('y', colors='r')
    
    vals = ax2.get_yticks()
    ax2.set_yticklabels(['{:,.2%}'.format(x) for x in vals])

    # hide y-labels on right side
    if not show_pct_y:
        ax2.set_yticks([])
    
    formatted_weights = [pct_format.format(x) for x in cumsum]
    for i, txt in enumerate(formatted_weights):
        ax2.annotate(txt, (x[i], cumsum[i]), fontweight='heavy')    
    
    if title:
        plt.title(title)
    
    plt.tight_layout()
    plt.show()

import matplotlib.pyplot as plt
import seaborn as sns
import sidetable as stb
df=sns.load_dataset("diamonds")


pareto_plot(df,x="cut",title="Cost value by Diamond types")