Last active
October 22, 2020 09:03
-
-
Save lorenzodisidoro/f23d6df6f1ad0845931bb0e9e7ab4ff4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
from benfordslaw import benfordslaw | |
import pandas as pd | |
import sys | |
import csv | |
csv_path = sys.argv[1] | |
alpha = float(sys.argv[2]) | |
print("CSV Data: " + csv_path) | |
print("alpha: " + str(alpha)) | |
df = pd.read_csv (csv_path) | |
bl = benfordslaw() | |
countries = list(df.columns.values)[2:] | |
results = [] | |
for country in countries: | |
X = df[country].values | |
result = bl.fit(X) | |
P = result['P'] | |
if P <= alpha: | |
element = {'Country': country, 'P': P, 'Alpha': alpha, 'Anomaly': True} | |
results.append(element) | |
else: | |
element = {'Country': country, 'P': P, 'Alpha': alpha, 'Anomaly': False} | |
results.append(element) | |
csv_columns = ['Country', 'P', 'Alpha', 'Anomaly'] | |
csv_file = "covid_benford_results.csv" | |
try: | |
with open(csv_file, 'w') as csvfile: | |
writer = csv.DictWriter(csvfile, fieldnames=csv_columns) | |
writer.writeheader() | |
for data in results: | |
writer.writerow(data) | |
except IOError: | |
print("I/O error") | |
# plot one result using the following code | |
# plot_country = "Italy" | |
# X = df[plot_country].values | |
# results = bl.fit(X) | |
# bl.plot(title=plot_country) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment