NLP/Models+K-Means/main/json2csv.py

import json
import csv
import pandas as pd
import re

def process_unicode_escape(text):
    return re.sub(r'\\u([\da-fA-F]{4})', lambda x: chr(int(x.group(1), 16)), text)

def main():
    jsonToCsv()
    dataProcess()
    dataProcess2()
    dataProcess3()

def jsonToCsv():
    with open('../data/SIR_train_set.json', 'r', encoding='UTF-8') as json_file:
        data = json.load(json_file)

        # 如果 data 是列表，遍历每一项
        if isinstance(data, list):
            for item in data:
                if 'description' in item:
                    item['description'] = process_unicode_escape(item['description'])

    # 写入 CSV 文件
    with open('../data_process_cache/SIR_train_set.csv', 'w', newline='', encoding='UTF-8') as csv_file:
        if isinstance(data, list) and len(data) > 0:
            fieldnames = data[0].keys()
            writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(data)

def dataProcess():
    columns_to_keep = ['description', 'vectorString']

    with open('../data_process_cache/SIR_train_set.csv', 'r', encoding='UTF-8') as infile:
        reader = csv.DictReader(infile)
        filtered_rows = [{col: row[col] for col in columns_to_keep} for row in reader]

    with open('../data_process_cache/train_vecStr.csv', 'w', newline='', encoding='utf-8') as outfile:
        if filtered_rows:
            writer = csv.DictWriter(outfile, fieldnames=columns_to_keep)
            writer.writeheader()  # Ensure headers are written
            writer.writerows(filtered_rows)

def dataProcess2():
    df = pd.read_csv('../data_process_cache/train_vecStr.csv', encoding='UTF-8')
    df_expanded = df['vectorString'].str.split('/', expand=True)
    df = pd.concat([df, df_expanded], axis=1)
    df.to_csv('../data_process_cache/output_train.csv', index=False, encoding='UTF-8')

def dataProcess3():
    df = pd.read_csv('../data_process_cache/output_train.csv', encoding='UTF-8')
    df.replace({
        'AV:L': 'LOCAL', 'AV:N': 'NETWORK', 'AV:A': 'ADJACENT', 'AV:P': 'PHYSICAL',
        'AC:L': 'LOW', 'AC:H': 'HIGH',
        'PR:N': 'NONE', 'PR:L': 'LOW', 'PR:H': 'HIGH',
        'UI:N': 'NONE', 'UI:R': 'REQUIRED',
        'S:U': 'UNCHANGED', 'S:C': 'CHANGED',
        'C:N': 'NONE', 'C:L': 'LOW', 'C:H': 'HIGH',
        'I:N': 'NONE', 'I:L': 'LOW', 'I:H': 'HIGH',
        'A:N': 'NONE', 'A:L': 'LOW', 'A:H': 'HIGH'
    }, inplace=True)
    df.to_csv('../dataset/SIR_train_set.csv', index=False, encoding='UTF-8')

if __name__ == '__main__':
    main()