Milwaukee_Benford.py

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

data = pd.read_csv("milwaukee_ward_votes.csv")

def GetFirstDigit(num) -> int:
    first_digit = num
    while (first_digit >= 10):
        first_digit = first_digit // 10
    return (1 if first_digit == 0 else first_digit)

biden = [0] * 10
trump = [0] * 10

# get occurance data
for index, row in data.iterrows():
    biden_digit = GetFirstDigit(row['Joseph R. Biden / Kamala D. Harris'])
    trump_digit = GetFirstDigit(row['Donald J. Trump / Michael R. Pence'])

    biden[biden_digit] += 1
    trump[trump_digit] += 1


for index in range(10):
    biden[index] = biden[index] / 478
    trump[index] = trump[index] / 478

fig, ax = plt.subplots()
plt.xlim((1, 9))

benford = [0, .301, .176, .125, .097, .079, .067, .058, .051, 0.046]

ax.plot(biden, label='Biden', color='b')
ax.plot(trump, label='Trump', color='r')
ax.plot(benford, label='True Benford', color='y')

ax.set_ylabel('Probability of Occurance')
ax.set_xlabel('Most Significant Integer')
ax.set_title('2020 Votes for Major Candidates vs Benford\'s Law')
ax.legend()

plt.show()