This script helps uploads the most frequent words to Dynamo. It requires the "put_words" function from https://gist.github.com/ShawnLMP/fe2e355d5af19e17e5a21bcf356b3d45, as well as this data set: https://www.kaggle.com/rtatman/english-word-frequency/data

most_frequent_words.py

import csv
import sys
from dynamo_access import put_words, get_words

def get_frequent_words(dataset , numOfWords):
	pairs = []
	with open(dataset, 'rb') as csvfile:
		reader = csv.reader(csvfile, delimiter=',')
		next(reader, None)
		for row in reader:
			word = row[0]
			freq = int(row[1])
			pairs.append((word, freq))
	pairs.sort(key=lambda x: x[1]) 
	return [p[0] for p in pairs[0 if numOfWords > len(pairs) else len(pairs) - numOfWords:]]


if __name__ == '__main__':
	dataset = 'unigram_freq.csv'
	numOfWords = 10
	frequent_words = get_frequent_words(dataset, numOfWords)
	put_words(frequent_words)