pareto chart python 3, thanks for https://tylermarrs.com/posts/pareto-plot-with-matplotlib/

pareto.py

import pandas as pd
import seaborn as sns

import matplotlib.pyplot as plt
%matplotlib inline

st = {2: 1478515,
        3: 449113,
        4: 646495,
        5: 166796,
        6: 21064,
        7: 11003,
        8: 131289,
        9: 20193,
        10: 24,
        12: 4483,
        13: 1621,
        14: 2,
        16: 3064,
        17: 1454,
        18: 6,
        19: 1,
        24: 1}

df = pd.DataFrame({'Alias Length': list(st.keys()),
                   'Alias Counts': list(st.values())})



def pareto_plot(df, x=None, y=None, title=None, show_pct_y=False, pct_format='{0:.0%}'):
    xlabel = x
    ylabel = y
    tmp = df.sort_values(x)
    x = tmp[x].values
    y = tmp[y].values
    weights = y / y.sum()
    cumsum = weights.cumsum()
    
    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.show()

pareto_plot(df, x='Alias Length', y='Alias Counts', title='Alias Pareto Distribution')