How to make Pareto Chart in python?

Question

Pareto is very popular diagarm in Excel and Tableu. In excel we can easily draw a Pareto diagram but I found no easy way to draw the diagram in Python.

I have a pandas d

Answer 1

You would probably want to create a new column with the percentage in it and plot one column as bar chart and the other as a line chart in a twin axes.

import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.ticker import PercentFormatter

df = pd.DataFrame({'country': [177.0, 7.0, 4.0, 2.0, 2.0, 1.0, 1.0, 1.0]})
df.index = ['USA', 'Canada', 'Russia', 'UK', 'Belgium', 'Mexico', 'Germany', 'Denmark']
df = df.sort_values(by='country',ascending=False)
df["cumpercentage"] = df["country"].cumsum()/df["country"].sum()*100


fig, ax = plt.subplots()
ax.bar(df.index, df["country"], color="C0")
ax2 = ax.twinx()
ax2.plot(df.index, df["cumpercentage"], color="C1", marker="D", ms=7)
ax2.yaxis.set_major_formatter(PercentFormatter())

ax.tick_params(axis="y", colors="C0")
ax2.tick_params(axis="y", colors="C1")
plt.show()

Answer 2

pareto chart for pandas.dataframe

import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.ticker import PercentFormatter


def _plot_pareto_by(df_, group_by, column):

    df = df_.groupby(group_by)[column].sum().reset_index()
    df = df.sort_values(by=column,ascending=False)

    df["cumpercentage"] = df[column].cumsum()/df[column].sum()*100


    fig, ax = plt.subplots(figsize=(20,5))
    ax.bar(df[group_by], df[column], color="C0")
    ax2 = ax.twinx()
    ax2.plot(df[group_by], df["cumpercentage"], color="C1", marker="D", ms=7)
    ax2.yaxis.set_major_formatter(PercentFormatter())

    ax.tick_params(axis="y", colors="C0")
    ax2.tick_params(axis="y", colors="C1")

    for tick in ax.get_xticklabels():
        tick.set_rotation(45)
    plt.show()

Answer 3

Another way is using the secondary_y parameter without using twinx():

df['pareto'] = 100 *df.country.cumsum() / df.country.sum()
fig, axes = plt.subplots()
ax1 = df.plot(use_index=True, y='country',  kind='bar', ax=axes)
ax2 = df.plot(use_index=True, y='pareto', marker='D', color="C1", kind='line', ax=axes, secondary_y=True)
ax2.set_ylim([0,110])

The parameter use_index=True is needed because your index is your x axis in this case. Otherwise you could've used x='x_Variable'.

Answer 4

More generalized version of ImportanceOfBeingErnest's code:

def create_pareto_chart(df, by_variable, quant_variable):
    df.index = by_variable
    df["cumpercentage"] = quant_variable.cumsum()/quant_variable.sum()*100

    fig, ax = plt.subplots()
    ax.bar(df.index, quant_variable, color="C0")
    ax2 = ax.twinx()
    ax2.plot(df.index, df["cumpercentage"], color="C1", marker="D", ms=7)
    ax2.yaxis.set_major_formatter(PercentFormatter())

    ax.tick_params(axis="y", colors="C0")
    ax2.tick_params(axis="y", colors="C1")
    plt.show()

And this one includes Pareto by grouping according to a threshold, too. For example: If you set it to 70, it will group minorities beyond 70 into one group called "Other".

def create_pareto_chart(by_variable, quant_variable, threshold):

    total=quant_variable.sum()
    df = pd.DataFrame({'by_var':by_variable, 'quant_var':quant_variable})
    df["cumpercentage"] = quant_variable.cumsum()/quant_variable.sum()*100
    df = df.sort_values(by='quant_var',ascending=False)
    df_above_threshold = df[df['cumpercentage'] < threshold]
    df=df_above_threshold
    df_below_threshold = df[df['cumpercentage'] >= threshold]
    sum = total - df['quant_var'].sum()
    restbarcumsum = 100 - df_above_threshold['cumpercentage'].max()
    rest = pd.Series(['OTHERS', sum, restbarcumsum],index=['by_var','quant_var', 'cumpercentage'])
    df = df.append(rest,ignore_index=True)
    df.index = df['by_var']
    df = df.sort_values(by='cumpercentage',ascending=True)

    fig, ax = plt.subplots()
    ax.bar(df.index, df["quant_var"], color="C0")
    ax2 = ax.twinx()
    ax2.plot(df.index, df["cumpercentage"], color="C1", marker="D", ms=7)
    ax2.yaxis.set_major_formatter(PercentFormatter())

    ax.tick_params(axis="x", colors="C0", labelrotation=70)
    ax.tick_params(axis="y", colors="C0")
    ax2.tick_params(axis="y", colors="C1")

    plt.show()