cleaning.py

import pandas as pd
import numpy as np
def clean_dataset():
    df = pd.read_csv('CICIDS dataset.csv')

    print(df.shape)
    print(df.head())

    df.columns = df.columns.str.strip()
    print(df["Label"].unique())

    #replace infinite values with NaN and drop rows with NaN values
    df = df.replace([np.inf, -np.inf], np.nan)
    df = df.dropna()

    for col in df.columns:
        if col == "Label":
            continue
        df[col] = pd.to_numeric(df[col], errors="coerce")
    df = df.dropna()  

    cols = ["Flow Bytes/s", "Flow Packets/s"]
    for c in cols:
        if c in df.columns:
            median_val = df[c].median()
            df[c] = df[c].fillna(median_val)

    df = df[df["Flow Duration"].notna() & (df["Flow Duration"] >= 0)]

    print(df.shape)
    print(df.head())

    df.to_csv('CICIDS_cleaned.csv', index=False)
    return df

if __name__ == "__main__":
    clean_dataset()