import tkinter as tkfrom tkinter import filedialog messageboximport pandas as pdimport numpy as npclass DataPreprocessingdef initselfselfcolumns = Noneselfdf = None # 创建主窗口 selfmaster = tkTk

缺少了一级缩进，需要在class定义处添加一个缩进。完整代码如下：

import tkinter as tk from tkinter import filedialog, messagebox import pandas as pd import numpy as np

class DataPreprocessing: def init(self): self.columns = None self.df = None

    # 创建主窗口
    self.master = tk.Tk()
    self.master.title("数据预处理")
    self.master.geometry("800x400")

    # 设置标题
    label_title = tk.Label(self.master, text="数据预处理", font=("Arial", 16), pady=30)
    label_title.grid(row=0, column=0, columnspan=3)

    # 设置打开文件按钮
    button_open = tk.Button(self.master, text="打开文件", command=self.open_file)
    button_open.grid(row=1, column=0, padx=50)

    # 设置处理空值按钮
    button_fillna = tk.Button(self.master, text="处理空值", state="disabled", command=self.fill_na)
    button_fillna.grid(row=1, column=1, padx=50)

    # 设置去重按钮
    button_drop_duplicates = tk.Button(self.master, text="去重", state="disabled", command=self.drop_duplicates)
    button_drop_duplicates.grid(row=1, column=2, padx=50)

    # 设置处理异常值按钮
    button_handle_outliers = tk.Button(self.master, text="处理异常值", state="disabled", command=self.handle_outliers)
    button_handle_outliers.grid(row=1, column=3, padx=50)

    # 设置输出缺失值数目的按钮
    button_missing_value = tk.Button(self.master, text="缺失值数量", state="disabled", command=self.missing_value_count)
    button_missing_value.grid(row=1, column=4, padx=50)

    # 设置treeview
    self.tree = tk.StringVar(value="")
    treeview = tk.Listbox(self.master, listvariable=self.tree, height=10)
    treeview.grid(row=2, column=0, columnspan=4, padx=10, pady=10)
    self.treeview = treeview

    # 设置保存文件按钮
    button_save = tk.Button(self.master, text="保存文件", state="disabled", command=self.save_file)
    button_save.grid(row=3, column=0, padx=50)

    # 设置退出按钮
    button_exit = tk.Button(self.master, text="退出", command=self.master.destroy)
    button_exit.grid(row=3, column=1, padx=50)

# 打开文件
def open_file(self):
    file_path = filedialog.askopenfilename(defaultextension=".csv",
                                           filetypes=(("CSV files", "*.csv"), ("All Files", "*.*")))
    if file_path:
        try:
            self.df = pd.read_csv(file_path)
            self.columns = list(self.df.columns)
            self.tree.set(self.columns)
            messagebox.showinfo("提示", "数据已导入成功！", parent=self.master)
            self.enable_buttons()
        except Exception as e:
            messagebox.showerror("错误", "打开文件失败！{}".format(e), parent=self.master)

# 处理空值
def fill_na(self):
    self.df.fillna(method="ffill", inplace=True)
    self.treeview.delete(0, tk.END)
    self.tree.set(list(self.df.isnull().sum()))
    messagebox.showinfo("提示", "空值已填充成功！", parent=self.master)

# 去重
def drop_duplicates(self):
    self.df.drop_duplicates(inplace=True)
    self.treeview.delete(0, tk.END)
    self.tree.set(list(self.df.columns))
    messagebox.showinfo("提示", "重复行已去除成功！", parent=self.master)

# 处理异常值
def handle_outliers(self):
    if "Mileage" in self.df.columns:
        mileage_unit = "km/l"
        if mileage_unit == "mile/l":
            self.df["Mileage"] = self.df["Mileage"].apply(lambda x: 1 / x)
        elif mileage_unit == "km/kg":
            self.df["Mileage"] = self.df["Mileage"].apply(lambda x: x * 0.425)

    if "Engine" in self.df.columns:
        engine_unit = "CC"
        if engine_unit == "L":
            self.df["Engine"] = self.df["Engine"] / 1000

    if "Power" in self.df.columns:
        power_unit = "bhp"
        if power_unit == "kW":
            self.df["Power"] = self.df["Power"] * 0.7457

    self.treeview.delete(0, tk.END)
    self.tree.set(list(self.df.columns))
    messagebox.showinfo("提示", "异常值已处理成功！", parent=self.master)

# 计算缺失值数量
def missing_value_count(self):
    missing_values = self.df.isnull().sum().sum()
    messagebox.showinfo("提示", "缺失值数量为{}".format(missing_values), parent=self.master)

# 保存文件
def save_file(self):
    file_path = filedialog.asksaveasfilename(defaultextension=".csv",
                                             filetypes=(("CSV files", "*.csv"), ("All Files", "*.*")))
    if file_path:
        try:
            self.df.to_csv(file_path, index=False)
            messagebox.showinfo("提示", "数据已保存成功！", parent=self.master)
        except Exception as e:
            messagebox.showerror("错误", "保存文件失败！{}".format(e), parent=self.master)

# 启用处理空值、去重、处理异常值和保存按钮
def enable_buttons(self):
    self.master.children["!button2"].config(state="normal")
    self.master.children["!button3"].config(state="normal")
    self.master.children["!button4"].config(state="normal")
    self.master.children["!button5"].config(state="normal")

# 启动窗口
def run(self):
    self.master.mainloop()

if name == "main": app = DataPreprocessing() app.run(