你会如何在Python中执行等效的预处理程序指令？

import pandas as pd

# 读取数据
data = pd.read_csv("data.csv")

# 数据清洗
data.dropna(inplace=True)

# 数据转换
data['new_column'] = data['old_column'] * 2

# 数据筛选
filtered_data = data[data['column'] > 100]

import numpy as np

# 创建数组
arr = np.array([1, 2, 3, 4, 5])

# 数组操作
arr_squared = arr ** 2
arr_sum = np.sum(arr)

import matplotlib.pyplot as plt

# 绘制折线图
plt.plot(data['column1'], data['column2'])
plt.show()

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 训练模型
model = LinearRegression()
model.fit(X_train, y_train)

# 预测
y_pred = model.predict(X_test)

# 评估模型
mse = mean_squared_error(y_test, y_pred)