python_pandas

dataframe

• 数据获取

  df = pd.DataFrame(data, index=["a", "b", "c"])
  
  # 获取某一行,类型是series
  first = df.loc['a']  
  
  # 获取某两行,类型是dataframe
  second = df.loc[['a', 'b']]
  
  # 获取某一列,类型是series
  third = df['name'] 
  

• 循环每一行

  data_list = pd.read_excel('test.xlsx')
  
  for index, row in data_list.iterrows():
      print(index)
      print(row)  # 类型是series
  

• 创建

  # 使用字典创建
  data = {
      "total": [420, 380, 390],
      "age": [50, 40, 45]
  }
  df = pd.DataFrame(data)
  
  # 使用列表创建
  data = [['Google', 10], ['Runoob', 12],['Wiki', 13]]
  df = pd.DataFrame(data, columns=['Site', 'Age'])
  print(df)
  
  # 使用字典和列表创建
  data = [
      {"Name": "Alice", "Age": 30, "City": "New York"},
      {"Name": "Bob", "Age": 35, "City": "Los Angeles"},
      {"Name": "Charlie", "Age": 25, "City": "Chicago"}
  ]
  df = pd.DataFrame(data)
  

series

• 循环

  for index, value in seriesList.items():
      print(index)
      print(value)