SHOW:
|
|
- or go back to the newest paste.
| 1 | import pandas as pd | |
| 2 | import matplotlib.pyplot as plt | |
| 3 | import numpy as np | |
| 4 | ||
| 5 | data = pd.read_csv("milwaukee_ward_votes.csv")
| |
| 6 | ||
| 7 | def GetFirstDigit(num) -> int: | |
| 8 | first_digit = num | |
| 9 | while (first_digit >= 10): | |
| 10 | first_digit = first_digit // 10 | |
| 11 | return (1 if first_digit == 0 else first_digit) | |
| 12 | ||
| 13 | biden = [0] * 10 | |
| 14 | trump = [0] * 10 | |
| 15 | ||
| 16 | # get occurance data | |
| 17 | for index, row in data.iterrows(): | |
| 18 | biden_digit = GetFirstDigit(row['Joseph R. Biden / Kamala D. Harris']) | |
| 19 | trump_digit = GetFirstDigit(row['Donald J. Trump / Michael R. Pence']) | |
| 20 | ||
| 21 | biden[biden_digit] += 1 | |
| 22 | trump[trump_digit] += 1 | |
| 23 | ||
| 24 | ||
| 25 | for index in range(10): | |
| 26 | biden[index] = biden[index] / 478 | |
| 27 | trump[index] = trump[index] / 478 | |
| 28 | ||
| 29 | fig, ax = plt.subplots() | |
| 30 | plt.xlim((1, 9)) | |
| 31 | ||
| 32 | benford = [0, .301, .176, .125, .097, .079, .067, .058, .051, 0.046] | |
| 33 | ||
| 34 | ax.plot(biden, label='Biden', color='b') | |
| 35 | ax.plot(trump, label='Trump', color='r') | |
| 36 | ax.plot(benford, label='True Benford', color='y') | |
| 37 | ||
| 38 | ax.set_ylabel('Probability of Occurance')
| |
| 39 | ax.set_xlabel('Most Significant Integer')
| |
| 40 | ax.set_title('2020 Votes for Major Candidates vs Benford\'s Law')
| |
| 41 | ax.legend() | |
| 42 | ||
| 43 | plt.show() |
