Created
August 12, 2022 19:53
-
-
Save lucasmenendez/ff9f98f3a64378263d85a3cca037148b to your computer and use it in GitHub Desktop.
Python script to generate 2 uuid's datasets with the 2.5% of records in common to test lucasmenendez/goPSI project. Usage: python generate_datasets.py <number_of_records>
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
import sys | |
import random | |
import uuid | |
numOfUUIDS = int(sys.argv[1]) | |
def main(): | |
numCommons = int(numOfUUIDS * 0.025) | |
numRandom = numOfUUIDS - numCommons | |
print("Generating 2 datasets with %d random UUID's (%d in both)..." % (numOfUUIDS, numCommons)) | |
print("Generating unique datasets records...") | |
dataA = [] | |
dataB = [] | |
for x in range(numRandom): | |
dataA.append(str(uuid.uuid4()) + "\n") | |
dataB.append(str(uuid.uuid4()) + "\n") | |
print("Generating common datasets records...") | |
for x in range(numCommons): | |
common = str(uuid.uuid4()) + "\n" | |
dataA.append(common) | |
dataB.append(common) | |
print("Shuffleling first dataset...") | |
random.shuffle(dataA) | |
print("Storing first dataset...") | |
with open("dataA", "w") as fd: | |
fd.writelines(dataA) | |
print("Shuffleling second dataset...") | |
random.shuffle(dataB) | |
print("Storing second dataset...") | |
with open("dataB", "w") as fd: | |
fd.writelines(dataB) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment