CSV数据异常值检测与可视化分析工具：支持Z-Score/IQR/3σ三种检测方法、异常行红色高亮标记、统计面板展示均值与标准差、一键导出检测报告CSV

🖥️ 运行效果

🚀 实例简介

一款基于Python Tkinter开发的桌面版CSV数据异常值检测工具。支持IQR（四分位距）、Z-Score（标准分数）、3σ（三倍标准差）三种经典统计学检测方法，自动识别数值列中的异常数据并以红色高亮标记，同时展示每列的均值、标准差等统计信息，支持一键导出带异常标记的检测报告CSV文件。适用于数据分析师、运营人员、财务人员等需要快速发现数据异常的场景。

💻 核心代码

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
CSV数据异常值检测与可视化分析工具
支持Z-Score/IQR/3σ三种检测方法，异常行红色高亮，一键导出报告
作者：好例子网 (haolizi.com)
"""
import tkinter as tk
from tkinter import ttk, filedialog, messagebox
import csv, math, os, platform, random

CHINESE_FONT = "WenQuanYi Zen Hei" if platform.system() == "Linux" else "Microsoft YaHei"

class OutlierApp:
    def __init__(self, root):
        self.root = root
        self.root.title("CSV数据异常值检测与可视化分析工具")
        self.root.geometry("920x680")
        self.data, self.headers, self.num_cols = [], [], []
        self._build_ui()
        self._load_demo()

    def _build_ui(self):
        tk.Label(self.root, text="📊 CSV数据异常值检测与可视化分析",
                 font=(CHINESE_FONT, 16, "bold"), fg="#2c3e50").pack(pady=8)
        bar = tk.Frame(self.root); bar.pack(fill=tk.X, padx=10)
        tk.Button(bar, text="📂 加载CSV", command=self._load_file,
                  font=(CHINESE_FONT, 11), bg="#3498db", fg="white").pack(side=tk.LEFT, padx=3)
        self.method = tk.StringVar(value="IQR")
        tk.Label(bar, text="检测方法:", font=(CHINESE_FONT, 11)).pack(side=tk.LEFT, padx=5)
        ttk.Combobox(bar, textvariable=self.method, values=["IQR", "Z-Score", "3σ"],
                     width=8, state="readonly").pack(side=tk.LEFT)
        tk.Button(bar, text="🔍 检测异常", command=self._detect,
                  font=(CHINESE_FONT, 11), bg="#e74c3c", fg="white").pack(side=tk.LEFT, padx=5)
        tk.Button(bar, text="📥 导出报告", command=self._export,
                  font=(CHINESE_FONT, 11), bg="#27ae60", fg="white").pack(side=tk.LEFT, padx=3)
        self.stats = tk.Label(self.root, text="", font=(CHINESE_FONT, 10),
                              fg="#34495e", bg="#ecf0f1", anchor="w", justify="left")
        self.stats.pack(fill=tk.X, padx=10, pady=5, ipady=4)
        tf = tk.Frame(self.root); tf.pack(fill=tk.BOTH, expand=True, padx=10)
        self.tree = ttk.Treeview(tf, show="headings", height=18)
        vsb = ttk.Scrollbar(tf, orient=tk.VERTICAL, command=self.tree.yview)
        self.tree.configure(yscrollcommand=vsb.set)
        self.tree.pack(side=tk.LEFT, fill=tk.BOTH, expand=True)
        vsb.pack(side=tk.RIGHT, fill=tk.Y)
        self.tree.tag_configure("outlier", background="#ffcccc")
        self.status = tk.Label(self.root, text="就绪 | 提示：点击[加载CSV]选择文件，或查看自动加载的示例数据",
                               font=(CHINESE_FONT, 9), fg="#95a5a6", anchor="w")
        self.status.pack(fill=tk.X, padx=10, pady=3)

    def _load_demo(self):
        """加载内置示例数据（含故意插入的异常值）"""
        self.headers = ["产品ID", "销量", "单价", "库存", "评分"]
        random.seed(42)
        self.data = []
        for i in range(1, 31):
            sales = random.randint(50, 500)
            price = round(random.uniform(10, 200), 1)
            stock = random.randint(10, 300)
            rating = round(random.uniform(3.0, 5.0), 1)
            if i == 5:  sales = 9999
            if i == 12: price = 8888.0
            if i == 18: stock = 0
            if i == 23: rating = 0.1
            if i == 27: sales = 8500
            self.data.append([f"P{i:03d}", str(sales), str(price), str(stock), str(rating)])
        self.num_cols = [1, 2, 3, 4]
        self._refresh_tree()
        self._detect()

    def _load_file(self):
        path = filedialog.askopenfilename(filetypes=[("CSV文件", "*.csv")])
        if not path: return
        try:
            with open(path, 'r', encoding='utf-8') as f:
                reader = csv.reader(f)
                self.headers = next(reader)
                self.data = [r for r in reader if any(c.strip() for c in r)]
            self.num_cols = []
            for i in range(len(self.headers)):

💡 适用场景

办公自动化、数据分析、快速原型开发