cleanse stock tweets

data_cleanse.py

ticker_dict = {}
company_list = []
exception_list = []

print "read ticker symbol"
with open("./ticker_symbol.tsv") as ticker_symbol:
    for line in ticker_symbol:
        words = line.split('\t')
        ticker_dict[words[0].strip('"').lower()] = words[1]
        
print "read stock tweets"
with open("./stock_symbol_keywords.tsv") as stock_tweets:
    for line in stock_tweets:
        words = line.split('\t')
        ticker = words[1][1:].strip('.').lower()
        if ticker_dict.has_key(ticker):
            company_list.append(ticker_dict[ticker])
        else:
            exception_list.append(ticker)

print "write company list out"
fo = open("company.txt", "w")
for company in company_list:
    fo.write(company)
fo.close()

print "write exception list out"
fo = open("exception.txt", "w")
for ticker in exception_list:
    fo.write(ticker)
    fo.write('\n')
fo.close()