1 导入数据

(1) 文件系统

        ①表格形式的数据:CSV/Excel

import pandas as pd

# 读取 CSV 文件
data = pd.read_csv('sales_data.csv')

# 读取excel
data2 = pd.read_excel('file.xlsx', sheet_name='Sheet2', skiprows=5, nrows=100)

        ②JSON

# 使用 pandas 库
import pandas as pd

data = pd.read_json('file.json')

# 使用 json 库
import json
with open('city_data.json', 'r', encoding='utf - 8') as file:
        data = json.load(file)

(2) 数据库

import mysql.connector
import pandas as pd
conn = mysql.connector.connect(
    host='localhost',
    user='user',
    password='password',
    database='database_name'
)

cursor = conn.cursor()
query = "SELECT * FROM table_name"
cursor.execute(query)

results = cursor.fetchall()
# 将 results转成列表
column_names = []
for desc in cursor.description:
    column_names.append(desc[0])
# 将列表转成 DataFrame
data = pd.DataFrame(results, columns=column_names)

cursor.close()
conn.close()

(3) 网络数据

①API 调用

import requests
# 身份验证
headers = {
    # API 密钥
    'Authorization': 'Bearer your_api_key'
}

response = requests.get('https://api.example.com/data', headers = headers)
if response.status_code == 200:
    data = response.json()

②网页爬虫

# 获取网页内容
import requests
response = requests.get('http://example.com')
if response.status_code == 200:
    content = response.text

# 解析网页内容
from bs4 import BeautifulSoup
soup = BeautifulSoup(content, 'html.parser')
elements = soup.find_all('a') # 查找所有链接

2 导出数据

import csv


# 创建示例数据
data = [
    ['姓名', '年龄', '城市'],
    ['张三', 25, '北京'],
    ['李四', 30, '上海'],
    ['王五', 35, '广州']
]

with open('example.csv', 'w', newline='', encoding='utf - 8') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerows(data)