Question

这是我的代码中运行REALLY SLOW的两个函数。基本上我在文档名称中读取，打开文档，然后一次处理一个单词。我需要将文档拆分成句子，并给每个句子一个哈希表，表示单词出现在句子中的次数。我还需要跟踪所有新单词，以及总文档的哈希表。

当我现在在10个文档上运行我的代码时，总共有8000个单词，2100个uniq单词需要大约8000+秒才能运行...每个单词差不多1秒。

你能告诉我if(istream.good())应该花多长时间？

或者，如果你能告诉我什么时候延迟我的代码。如果某个部分不清楚，请告诉我，我会帮忙。

P.S。您可以在代码中看到我有start = clock()和end = clock()注释，它会不断返回＆lt; 1毫秒。这就是思维障碍

void  DocProcess::indexString(string sentenceString, hash * sent){

stringstream iss;

string word;
iss.clear();
iss << sentenceString;

while(iss.good())
{

    iss >> word;
    word = formatWord(word);

    std::unordered_map<std::string,int>::const_iterator IsNewWord = words.find(word);

    if(IsNewWord == words.end())
    {
        std::pair<std::string,int> newWordPair (word,0);
        std::pair<std::string,int> newWordPairPlusOne (word,1);

        words.insert(newWordPair);
        sent->insert(newWordPairPlusOne);
    }
    else
    {
        std::pair<std::string,int> newWordPairPlusOne (word,1);
        sent->insert(newWordPairPlusOne);
    }
}

} void DocProcess :: indexFile（string iFileName）{

hash newDocHash;
hash newSentHash;
scoreAndInfo sentenceScore;
scoreAndInfo dummy;

fstream iFile;
fstream dFile;
string word;
string newDoc;
string fullDoc;
int minSentenceLength = 5;
int docNumber = 1;
int runningLength = 0;
int ProcessedWords = 0;
stringstream iss;

iFile.open(iFileName.c_str());

if(iFile.is_open())
{
    while(iFile.good())
    {
        iFile >> newDoc;
        dFile.open(newDoc.c_str());
        DocNames.push_back(newDoc);

        if(dFile.is_open())
        {
            scoreAndInfo documentScore;
            //iss << dFile.rdbuf();
            while(dFile.good())
            {
                //start = clock();
                dFile >> word;
                ++ProcessedWords;

                std::unordered_map<std::string,int>::const_iterator IsStopWord = stopWords.find(word);


                if(runningLength >= minSentenceLength && IsStopWord != stopWords.end() || word[word.length()-1] == '.')
                {

                    /* word is in the stop list, process the string*/
                    documentScore.second.second.append(" "+word);
                    sentenceScore.second.second.append(" "+word);

                    indexString(sentenceScore.second.second, &sentenceScore.second.first);

                    sentenceScore.first=0.0;
                    SentList.push_back(sentenceScore);
                    sentenceScore.second.first.clear(); //Clear hash
                    sentenceScore.second.second.clear(); // clear string
                    //sentenceScore = dummy;
                    runningLength = 0;
                }
                else
                {
                    ++runningLength;
                    sentenceScore.second.second.append(" "+word);
                    documentScore.second.second.append(" "+word);

                }
                //end = clock();
                    system("cls");
                    cout    << "Processing doc number: " << docNumber << endl
                        << "New Word count: " << words.size() << endl
                        << "Total words: " << ProcessedWords << endl;
                        //<< "Last process time****: " << double(diffclock(end,start)) << " ms"<< endl;

            }
            indexString(documentScore.second.second, &documentScore.second.first);
            documentScore.first=0.0;
            DocList.push_back(documentScore);
            dFile.close();
            //iss.clear();
            //documentScore = dummy;
            ++docNumber;
            //end = clock();
            system("cls");
            cout    << "Processing doc number: " << docNumber << endl
                << "Word count: " << words.size();
                //<< "Last process time: " << double(diffclock(end,start)) << " ms"<< endl;

        }
    }

    iFile.close();
}
else{ cout << "Unable to open index file: "<<endl <<iFileName << endl;}

} `

Answer 1

你能否在没有

的情况下尝试

                system("cls");

在任何循环中？这肯定没有帮助，这是一个昂贵的电话。

Answer 2

要快速清除屏幕，而不是system("cls");，请尝试cout << '\f';。

字符串和unordered_map运行缓慢

2 个答案: