import numpy as np
import pandas as pd

# Task 01: 创建 100x6 的 DataFrame，数值在 [-3, 3] 之间
df = pd.DataFrame(np.random.uniform(-3, 3, (100, 6)))

# Task 02: 统计汇总
print("数据统计：")
print(df.describe())

# Task 03: 取前六行
print("\n前6行数据：")
print(df.head(6))

# Task 04: 使用 count() 统计异常值
ab_low = df[df < -2].count()
ab_high = df[df > 2].count()

# 每列总异常值
ab_each_column = ab_low + ab_high
# 异常值总数
ab_total = ab_each_column.sum()

print("\n每列异常值数量：")
print(abnormal_each_column)
print(f"\n异常值总数：{abnormal_total}")

# Task 05: 替换
df_clipped = df.clip(lower=-2, upper=2)

# Task 06: 查看替换后的统计汇总
print("\n替换异常值后的数据统计：")
print(df_clipped.describe())

import requests
from lxml import etree
import csv

url = "https://www.cuc.edu.cn/9996/list.htm"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36"
}

response = requests.get(url, headers=headers)
response.encoding = "utf-8"  

html = etree.HTML(response.text)

# 提取“教学科研单位”节点下的部门名称
departments = html.xpath('//li[@class="wp_sublist sublist-4"]//div[contains(@class, "news_title")]/text()')

print("中国传媒大学 教学科研部门名称:")
for dept in departments:
    print(dept)

# 将数据保存到 CSV 文件
if departments:  
    with open("cuc_departments.csv", "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["学院名称"])  # 表头
        for dept in departments:
            writer.writerow([dept])

    print("数据已成功保存到 cuc_departments.csv")
else:
    print("没有提取到任何数据，请检查 XPath 表达式或网页结构。")