Python常用操作汇总—第1部分（持续更新）

 import pandas as pd

    
  
    
 excel_file = '/文件路径/example.xlsx'     # 要读取的excel文件位置
    
  
    
 sheet_name = 'Sheet1'  # 要读取的excel中的sheet名
    
  
    
 df = pd.read_excel(excel_file, sheet_name = sheet_name)
    
  
    
 print(df)

 import pandas as pd

    
  
    
 df = pd.read_csv('/文件路径/example.csv')  # 要读取的csv文件位置
    
  
    
 print(df)

 import pandas as pd

    
 import json
    
 dict_list = []
    
  
    
 with open('/Users/Desktop/test.txt', 'r', encoding='utf-8') as file:
    
  
    
     for line in file:
    
  
    
     try:
    
  
    
         dict_data = json.loads(line)
    
  
    
         dict_list.append(dict_data)
    
  
    
     except json.JSONDecodeError as e:
    
  
    
         print(f"Error reading line: {line}. Skipping...")
    
  
    
 df = pd.DataFrame(dict_list)
    
  
    
 # 继续将result中的键值对进行拆分成更细的列，如果没有对应的键值对，则为空
    
 result_df = df['result'].apply(pd.Series)
    
  
    
 df = pd.concat([df, result_df], axis=1)
    
  
    
 print(df)

 #例：从df中随机抽取100条记录

    
  
    
 import pandas as pd
    
  
    
 df = pd.read_csv('/文件路径/example.csv')
    
  
    
 # n参数指定要选择的记录数;
    
 # random_state参数用于设置随机种子，以便每次运行代码时都能得到相同的随机抽样结果
    
 df_sample = df.sample(n = 100, random_state = 42)
    
  
    
 # 输出抽样结果
    
 print(df_sample)

 import hashlib

    
  
    
 def md5_encrypt(phone_number):    
    
     # 将电话号码转换为字节串，并使用utf-8编码    
    
     phone_bytes = str(phone_number).encode('utf-8')    
    
     # 使用MD5哈希算法进行加密    
    
     md5_hash = hashlib.md5(phone_bytes)    
    
     # 获取加密后的结果    
    
     encrypted_phone = md5_hash.hexdigest()    
    
     return encrypted_phone
    
  
    
 # 测试
    
  
    
 phone = '1234567890'
    
 encrypted_phone = md5_encrypt(phone)
    
 print(encrypted_phone)

 import os

    
  
    
 import shutil
    
  
    
 # 定义文件夹a和文件夹b的路径
    
 folder_a_path = '/path/to/folder_a'
    
 folder_b_path = '/path/to/folder_b'
    
  
    
 # 获取文件夹a中所有文件的列表
    
 file_list = os.listdir(folder_a_path)
    
  
    
 # 遍历文件列表，找出文件名带有"jianshu"的文件，并将其移动到文件夹b中
    
 for file_name in file_list:    
    
     if 'jianshu' in file_name:        
    
     # 构建文件的完整路径        
    
     source_file = os.path.join(folder_a_path, file_name)        
    
     # 移动文件到文件夹b        
    
     shutil.move(source_file, folder_b_path)

 # 例：修改test文件夹中文件名，在原文件名后添加".jpg"

    
 import os
    
  
    
 directory = '/Users/Desktop/test/'
    
  
    
 for filename in os.listdir(directory):
    
  
    
     # 旧文件路径
    
  
    
     old_path = os.path.join(directory, filename)
    
  
    
     if os.path.isfile(old_path):
    
  
    
     # 获取文件名和扩展名
    
  
    
     file_name, file_ext = os.path.splitext(filename)
    
  
    
     # 构建新文件名
    
  
    
     new_filename = file_name + ".jpg"
    
  
    
     # 构建新文件路径
    
  
    
     new_path = os.path.join(directory, new_filename)
    
  
    
     # 修改文件名
    
  
    
     os.rename(old_path, new_path)

 from geopy.geocoders

    
  
    
 import Nominatim
    
  
    
 # 创建一个Nominatim对象
    
 geolocator = Nominatim(user_agent = "myGeocoder",timeout = 20)
    
  
    
 # 定义经纬度坐标
    
 latitude = 30.55462
    
 longitude = 114.3396969
    
  
    
 # 逆地理编码，将经纬度转换为地址信息
    
 location = geolocator.reverse(f"{latitude}, {longitude}")
    
  
    
 # 打印地址信息
    
 print(location.address)

 import pandas as pd

    
  
    
 from geopy.geocoders import Nominatim
    
  
    
 df = pd.read_csv('/Users/Downloads/df_gps_latitude_longitude.csv')
    
  
    
 # 创建一个Nominatim对象
    
 geolocator = Nominatim(user_agent = "myGeocoder",timeout = 20)
    
  
    
 # 定义一个函数，接收经度和纬度作为参数，并返回对应的地址信息
    
 def get_address(latitude, longitude):
    
     try:
    
     location = geolocator.reverse(f"{latitude}, {longitude}")
    
     if location is not None:
    
         return location.address
    
     else:
    
         return 'Unknown Address'
    
     except Exception as e:
    
     print(f"Error: {e}")
    
     return 'Address Error'
    
  
    
 # 使用apply方法调用函数，并将结果存储在新的"address"列中
    
 df['address'] = df.apply(lambda row:get_address(row['latitude'], row['longitude']), axis = 1)
    
  
    
 df.reset_index(drop = True, inplace = True)
    
  
    
 print(df)