ted-symbol-elimination.py

# coding: UTF-8
from selenium import webdriver
from bs4 import BeautifulSoup
from datetime import datetime
import time
import pandas
import numpy

# 変数準備
csv = pandas.read_csv('word.csv')
csv_nomalized = [[]]
row = 0
comp_word = 0

word1 = csv['word']
word2 = []
count = csv['count']
file = open('word-dot-eliminated.csv','w')
file.write('word,count\n')

word2 = word1
    
# 同一の単語があるか調べる        
for w in word1:
    print(row)
    
    # ドットを含むか調べる
    if str(w).find('.') != -1:
        
        # ドットを抜いたとき同じ単語がない場合のフラグ
        flag = 0

        # ドットを抜いたとき同じ単語があるか調べる
        for i in range(0,len(word1)-1):
            
            # 単語が同じであればカウント数を足し合わせる
            if w.replace(".","",1000) == word2[i]:
                count[i] = count[i] + count[row]
                word2[row] = "**not valid**"
                flag = 1
                break
        
        if flag == 0:
            word2[row] = w.replace(".","",1000)

    row = row + 1

row = 0
for w in word2:
    # 足し合わせ後の単語は無視する
    if w != "**not valid**":
        file.write(str(w)+","+str(count[row])+"\n")
    row = row + 1
        
file.close()