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

import json
import csv
import pandas as pd
import re


def main():
    jsonToCsv()
    dataProcess()
    dataProcess2()
    dataProcess3()
def jsonToCsv():
    with open('../data/SIR_validation_set.json', 'r', encoding='UTF-8') as json_file:
        data = json.load(json_file)

    with open('../data_process_cache/SIR_validation_set.csv', 'w', newline='', encoding='UTF-8') as csv_file:

        if data:

            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_validation_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]

    # 将选择的列写入到新 CSV 文件
    with open('../data_process_cache/validation_vecStr.csv', 'w', newline='', encoding='utf-8') as outfile:
        if filtered_rows:
            writer = csv.DictWriter(outfile, fieldnames=columns_to_keep)
            writer.writerows(filtered_rows)  # 写入选择的列

def dataProcess2():
    import pandas as pd
    df = pd.read_csv('../data_process_cache/validation_vecStr.csv', header=None, encoding='UTF-8')
    df_expanded = df[1].str.split('/', expand=True)
    df = pd.concat([df, df_expanded], axis=1)
    print(df.head())
    df.to_csv('../data_process_cache/output_validation.csv', index=False, header=False, encoding='UTF-8')

    df = pd.read_csv('../data_process_cache/output_validation.csv', header=None, encoding='UTF-8')
    df = df.drop(columns=[1, 2])
    df.to_csv('../data_process_cache/output_validation.csv',index=False, header=False, encoding='UTF-8')
def dataProcess3():

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


if __name__ == '__main__':
    main()