Comment utiliser C++ pour une exploration et une analyse de texte efficaces ?

#include <iostream>
#include <string>
#include <algorithm>
#include <cctype>

std::string preprocessText(const std::string& text) {
    std::string processedText = text;
    
    // 去掉标点符号和特殊字符
    processedText.erase(std::remove_if(processedText.begin(), processedText.end(), [](char c) {
        return !std::isalnum(c) && !std::isspace(c);
    }), processedText.end());
    
    // 转换为小写
    std::transform(processedText.begin(), processedText.end(), processedText.begin(), [](unsigned char c) {
        return std::tolower(c);
    });
    
    // 进行词干化等其他操作
    
    return processedText;
}

int main() {
    std::string text = "Hello, World! This is a sample text.";
    std::string processedText = preprocessText(text);

    std::cout << processedText << std::endl;

    return 0;
}

#include <iostream>
#include <string>
#include <vector>
#include <map>
#include <algorithm>

std::vector<std::string> extractWords(const std::string& text) {
    std::vector<std::string> words;
    
    // 通过空格分割字符串
    std::stringstream ss(text);
    std::string word;
    while (ss >> word) {
        words.push_back(word);
    }
    
    return words;
}

std::map<std::string, int> createWordCount(const std::vector<std::string>& words) {
    std::map<std::string, int> wordCount;
    
    for (const std::string& word : words) {
        wordCount[word]++;
    }
    
    return wordCount;
}

std::map<std::string, double> calculateTFIDF(const std::vector<std::map<std::string, int>>& documentWordCounts, const std::map<std::string, int>& wordCount) {
    std::map<std::string, double> tfidf;
    int numDocuments = documentWordCounts.size();
    
    for (const auto& wordEntry : wordCount) {
        const std::string& word = wordEntry.first;
        int wordDocumentCount = 0;
        
        // 统计包含该词的文档数
        for (const auto& documentWordCount : documentWordCounts) {
            if (documentWordCount.count(word) > 0) {
                wordDocumentCount++;
            }
        }
        
        // 计算TF-IDF值
        double tf = static_cast<double>(wordEntry.second) / wordCount.size();
        double idf = std::log(static_cast<double>(numDocuments) / (wordDocumentCount + 1));
        double tfidfValue = tf * idf;
        
        tfidf[word] = tfidfValue;
    }
    
    return tfidf;
}

int main() {
    std::string text1 = "Hello, World! This is a sample text.";
    std::string text2 = "Another sample text.";
    
    std::vector<std::string> words1 = extractWords(text1);
    std::vector<std::string> words2 = extractWords(text2);
    
    std::map<std::string, int> wordCount1 = createWordCount(words1);
    std::map<std::string, int> wordCount2 = createWordCount(words2);
    
    std::vector<std::map<std::string, int>> documentWordCounts = {wordCount1, wordCount2};
    
    std::map<std::string, double> tfidf1 = calculateTFIDF(documentWordCounts, wordCount1);
    std::map<std::string, double> tfidf2 = calculateTFIDF(documentWordCounts, wordCount2);
    
    // 打印TF-IDF特征向量
    for (const auto& tfidfEntry : tfidf1) {
        std::cout << tfidfEntry.first << ": " << tfidfEntry.second << std::endl;
    }
    
    return 0;
}

#include <iostream>
#include <string>
#include <vector>
#include <map>
#include <cmath>

std::map<std::string, double> trainNaiveBayes(const std::vector<std::map<std::string, int>>& documentWordCounts, const std::vector<int>& labels) {
    std::map<std::string, double> classPriors;
    std::map<std::string, std::map<std::string, double>> featureProbabilities;
    
    int numDocuments = documentWordCounts.size();
    int numFeatures = documentWordCounts[0].size();
    
    std::vector<int> classCounts(numFeatures, 0);
    
    // 统计每个类别的先验概率和特征的条件概率
    for (int i = 0; i < numDocuments; i++) {
        std::string label = std::to_string(labels[i]);
        
        classCounts[labels[i]]++;
        
        for (const auto& wordCount : documentWordCounts[i]) {
            const std::string& word = wordCount.first;
            
            featureProbabilities[label][word] += wordCount.second;
        }
    }
    
    // 计算每个类别的先验概率
    for (int i = 0; i < numFeatures; i++) {
        double classPrior = static_cast<double>(classCounts[i]) / numDocuments;
        classPriors[std::to_string(i)] = classPrior;
    }
    
    // 计算每个特征的条件概率
    for (auto& classEntry : featureProbabilities) {
        std::string label = classEntry.first;
        std::map<std::string, double>& wordProbabilities = classEntry.second;
        
        double totalWords = 0.0;
        for (auto& wordEntry : wordProbabilities) {
            totalWords += wordEntry.second;
        }
        
        for (auto& wordEntry : wordProbabilities) {
            std::string& word = wordEntry.first;
            double& wordCount = wordEntry.second;
            
            wordCount = (wordCount + 1) / (totalWords + numFeatures);  // 拉普拉斯平滑
        }
    }
    
    return classPriors;
}

int predictNaiveBayes(const std::string& text, const std::map<std::string, double>& classPriors, const std::map<std::string, std::map<std::string, double>>& featureProbabilities) {
    std::vector<std::string> words = extractWords(text);
    std::map<std::string, int> wordCount = createWordCount(words);
    
    std::map<std::string, double> logProbabilities;
    
    // 计算每个类别的对数概率
    for (const auto& classEntry : classPriors) {
        std::string label = classEntry.first;
        double classPrior = classEntry.second;
        double logProbability = std::log(classPrior);
        
        for (const auto& wordEntry : wordCount) {
            const std::string& word = wordEntry.first;
            int wordCount = wordEntry.second;
            
            if (featureProbabilities.count(label) > 0 && featureProbabilities.at(label).count(word) > 0) {
                const std::map<std::string, double>& wordProbabilities = featureProbabilities.at(label);
                logProbability += std::log(wordProbabilities.at(word)) * wordCount;
            }
        }
        
        logProbabilities[label] = logProbability;
    }
    
    // 返回概率最大的类别作为预测结果
    int predictedLabel = 0;
    double maxLogProbability = -std::numeric_limits<double>::infinity();
    
    for (const auto& logProbabilityEntry : logProbabilities) {
        std::string label = logProbabilityEntry.first;
        double logProbability = logProbabilityEntry.second;
        
        if (logProbability > maxLogProbability) {
            maxLogProbability = logProbability;
            predictedLabel = std::stoi(label);
        }
    }
    
    return predictedLabel;
}

int main() {
    std::vector<std::string> documents = {
        "This is a positive document.",
        "This is a negative document."
    };
    
    std::vector<int> labels = {
        1, 0
    };
    
    std::vector<std::map<std::string, int>> documentWordCounts;
    for (const std::string& document : documents) {
        std::vector<std::string> words = extractWords(document);
        std::map<std::string, int> wordCount = createWordCount(words);
        documentWordCounts.push_back(wordCount);
    }
    
    std::map<std::string, double> classPriors = trainNaiveBayes(documentWordCounts, labels);
    int predictedLabel = predictNaiveBayes("This is a positive test document.", classPriors, featureProbabilities);
    
    std::cout << "Predicted Label: " << predictedLabel << std::endl;
    
    return 0;
}