Simple data generator with skew

dgen.py

import random

numRecords = 10000000

numProds = 100
numCust = 1000

# probability that a parameter combination is in each class
freqProb = 0.1
medProb = freqProb + 0.35
rareProb = 1 - medProb

# ratio of records in the table for each class
freqRatio = 0.5
medRatio = 0.35
rareRatio = 1 - freqRatio - medRatio

# number of records to generate for each distinct combination per class
freqCnt = int((numRecords * freqRatio) / (numProds * numCust * freqProb))
medCnt = int((numRecords * medRatio) / (numProds * numCust * medProb))
rareCnt = int((numRecords * rareRatio) / (numProds * numCust * rareProb))

tid = 0

for p in range(0, numProds):
	for c in range(0, numCust):
		r = random.uniform(0, 1.0)
		if r < freqProb:
			# frequent
			for i in range(0, freqCnt):
				print "{} {} {}".format(p, c, tid)
				tid += 1
		elif r < medProb:
			# medium
			for i in range(0, medCnt):
				print "{} {} {}".format(p, c, tid)
				tid += 1
		else:
			#rare
			for i in range(0, rareCnt):
				print "{} {} {}".format(p, c, tid)
				tid += 1