def run(fileName, n_hashes, n_buckets):
""" Starts the main LSH process.
Args:
fileName (string): path of text file to read
n_hashes (int): number of hash functions to generate
n_buckets (int): number of buckets to use
Returns:
Vector: buckets of minhash values
"""
sc = SparkContext(conf=SparkConf())
hashes = sc.broacast(getHashFunctions(n_hashes))
text = sc.textFile(fileName)
stopWords = sc.textFile('path/to/stopwords') # Test
cleanData = text.map(removePunctuation).subtract(stopWords).cache()
