Created
September 11, 2018 16:29
-
-
Save Niklas9/78f78fbb81aa1a5a3cbcea167db89411 to your computer and use it in GitHub Desktop.
Find most frequent numbers from a Twilio CSV export
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/python3 | |
import csv | |
import operator | |
import sys | |
if len(sys.argv) < 2: | |
print('need csv file as first arg') | |
sys.exit(1) | |
numbers = {} # numbers as keys, occurrences as values | |
no_of_sms = 0 | |
# TODO(niklas9): * create proper class etc for this | |
with open(sys.argv[1], 'r', encoding='utf-8') as f: | |
reader = csv.reader(f) | |
for row in reader: | |
# TODO(niklas9): | |
# * should filter out header row if it exists | |
# * to increase perf for larger csv files, could split in | |
# n threads here where each thread works on part of the file, then | |
# merge the results | |
if not len(row) > 1: continue # some lines might be blank | |
number = row[1] | |
if number in numbers: | |
numbers[number] += 1 | |
else: | |
numbers[number] = 1 | |
no_of_sms += 1 | |
# TODO(niklas9): | |
# * actually just looking for the top ~5 numbers here, instead of sorting this | |
# could be done in O(n*size) runtime complexity instead, where size=5 in this | |
# example.. only beneficial though if size < log(n), using the same numbers if | |
# n>149 (as e^5=148.31..) | |
numbers_sorted = sorted(numbers.items(), key=operator.itemgetter(1), | |
reverse=True) | |
print('unique numbers = {:d}'.format(len(numbers_sorted))) | |
print('sms sent = {:d}\n'.format(no_of_sms)) | |
for item in numbers_sorted[:5]: # print top 5 | |
print(item) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment