Created
July 15, 2015 02:25
-
-
Save Krailon/cf34f555da81b535e039 to your computer and use it in GitHub Desktop.
Python2 CSV Test Data Generator
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 python2 | |
# | |
# CSV Random Test Data Generator | |
# "Allow me to algorithmically test your algorithm with algorithmically-generated test data..." | |
# Written by Kerberos/Krailon | |
# | |
import sys, argparse | |
from random import SystemRandom | |
from datetime import datetime, timedelta | |
parser = argparse.ArgumentParser() | |
parser.add_argument("-r", "--rowcount", help="Row count", type=int, required=True) | |
parser.add_argument("-c", "--columns", help="Columns (format: comma-separated)", required=True) | |
parser.add_argument("-d", "--date", help="Date of first sample (format: YYYY-MM-DD; default: current date)", default=datetime.now().strftime("%Y-%m-%d")) | |
parser.add_argument("-s", "--start", help="Timestamp of first sample (format: H:M:S; default: current time", default=datetime.now().strftime("%H:%M:%S")) | |
parser.add_argument("-i", "--interval", help="Time interval between rows (format: seconds; default: 1)", type=int, default=1) | |
parser.add_argument("-a", "--range", help="Data range (format: low-high: default: 0-255)", default="0-255") | |
parser.add_argument("-o", "--output", help="Output path (default: dustdata.csv)", default="dustdata.csv") | |
args = parser.parse_args() | |
csv = [] | |
sys_rand = SystemRandom() | |
try: | |
row_count = args.rowcount | |
cols = args.columns.split(",") | |
interval = timedelta(seconds=args.interval) | |
sample_date = datetime.strptime(args.date, "%Y-%m-%d") | |
sample_time = datetime.strptime(args.start, "%H:%M:%S") | |
data_range = map(int, args.range.split("-")) | |
except ex: | |
print "- Error: %s" % (ex) | |
sys.exit(1) | |
if data_range[0] > data_range[1]: | |
print "- Error: Invalid data range: %s" % (args.range) | |
sys.exit(1) | |
print "+ Generating %s rows of data..." % (row_count) | |
# Ensure 'date' and 'time' columns are present | |
if "date" not in cols: | |
cols.insert(0, "date") | |
if "time" not in cols: | |
cols.insert(1, "time") | |
# Header | |
header = "" | |
for col in cols: | |
header += col + "," | |
# Data | |
for ri in range(0, row_count): | |
csv.append("") | |
for col in cols: | |
if col == "date": | |
csv[ri] += sample_date.strftime("%Y-%m-%d") | |
elif col == "time": | |
csv[ri] += sample_time.strftime("%H:%M:%S") | |
else: | |
csv[ri] += str(sys_rand.randint(data_range[0], data_range[1])) | |
csv[ri] += "," | |
csv[ri] = csv[ri][:-1] | |
sample_time += interval | |
print "+ Saving to %s..." % (args.output) | |
csv.insert(0, header[:-1]) | |
with open(args.output, 'w') as out_csv: | |
out_csv.write("\n".join(csv)) | |
print "+ Done!" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment