add_numbers.py

import csv
import json

INPUTFILE = "History_Journal_Articles_KW.csv"

OUTPUTFILE = INPUTFILE[:-4] + "_numbered.csv"

in_file = open(INPUTFILE, "r")  # "r" == Open file for reading
out_file = open(OUTPUTFILE, "w") # "w" for writing

# csv

rows_in = csv.reader(in_file)

rows_out = csv.writer(out_file)

# little function to get or generate a number for a word

topwords = {}
journals = {}

def get_or_set_number(word, words, counter):
  if word not in words:
    counter += 1
    words[word] = counter
    return counter, counter
  else:
    return words[word], counter

headers = rows_in.next()
rows_out.writerow(headers)

numberofrows = 0

counter = 0
for row in rows_in:
  # Which column is the word in? (Computer counting very often starts at zero, not one!)
  topword_number, counter = get_or_set_number(row[0], topwords, counter)
  row[1] = topword_number

  journal_number, counter = get_or_set_number(row[6], journals, counter)
  row[7] = journal_number
  rows_out.writerow(row)
  numberofrows += 1

out_file.close()
in_file.close()

print("Number of ids: {0}".format(counter))
print("Number of rows: {0}".format(numberofrows))