opinionTokenizer.py 文件源码

def positive_and_negative_to_full():
    fpos = open('positive.csv')
    positive_units = [row for row in csv.reader(fpos)]
    fneg = open('negative.csv')
    negative_units = [row for row in csv.reader(fneg)]
    for item in positive_units:
        item.append('positive')
    for item in negative_units:
        item.append('negative')
    del negative_units[0]
    positive_units[0][0] = 'review_content'
    positive_units[0][1] = 'sentiment'
    full = positive_units
    full.extend(negative_units)
    with open('positiveandnegative.csv', 'wb') as csvfile:
        writer = csv.writer(csvfile, dialect='excel')
        writer.writerows(full)



#this will open the review scraped data and write two files from that info:
#positive.csv, containing positive opinion units
#negative.csv, containing negative opinion units