main.py

import pandas as pd
import torch
import platform
# data: (67488, 52)  SWaT
# label 0.0: number = 31588，count = 46.81%
# label 1.0: number = 35900，count = 53.19%
# label 0: number = 9711，count = 43.08%
# label 1: number = 12833，count = 56.92%  nsl-kdd
# label 0: number = 12228，count = 98.12%
# label 1: number = 234，count = 1.88%
# csv_path = "./data/24070102_test.csv"
def data_count(csv_path):
    df = pd.read_csv(csv_path)
    df.columns = df.columns.str.strip()
    print("data:", df.shape)
    if 'label' not in df.columns:
        raise ValueError("no 'label' column")

    label_counts = df['label'].value_counts()
    total = label_counts.sum()

    for label_value in sorted(label_counts.index):
        count = label_counts[label_value]
        percent = count / total * 100
        print(f"label {label_value}: number = {count}，count = {percent:.2f}%")


def attck_to_label(path):
    df = pd.read_csv(path)
    if "attack" in df.columns:
        df = df.rename(columns={"attack": "label"})
        print("column name has been modified.")
    else:
        print("no 'attack' column")

    print(df.head(5))
    print(df.shape)
    df.to_csv(path, index=False)


def drop_index(path):
    df = pd.read_csv(path, index_col=0)
    df = df.reset_index(drop=True)
    print(df.head())
    df.to_csv(path, index=False)


if __name__ == '__main__':
    # path = "../datas/SMAP/test_D_1.csv"
    # df = pd.read_csv(path)
    # print("data:", df.shape)
    # data_count(path)
    print("torch:", torch.__version__)
    print("cuda:", torch.version.cuda)
    print("操作系统:", platform.platform())
    print("处理器:", platform.processor())