Pandas读存JSON数据操作示例详解

pandas.read_json(
  path_or_buf=None,  # 文件路径
  orient=None,  # 取值：split、records、index、columns、values
  typ='frame',   # 要恢复的对象类型（系列或框架），默认'框架'.
  dtype=None, # boolean或dict，默认为True
  convert_axes=None,
  convert_dates=True,
  keep_default_dates=True,
  numpy=False,
  precise_float=False,
  date_unit=None,
  encoding=None,  # 编码
  lines=False,  # 布尔值，默认为False，每行读取该文件作为json对象
  chunksize=None,  # 分块读取大小
  compression='infer',
  nrows=None,
  storage_options=None)

split' : dict like {index -> [index], columns -> [columns], data -> [values]}

data1 = '{"index":[1,2],"columns":["name","age"],"data":[["xiaoming",28], ["zhouhong",20]]}'

df1 = pd.read_json(data1, orient="split")
df1

‘records' : list like [{column -> value}, … , {column -> value}]

data2 = '[{"name":"Peter","sex":"male","age":20},{"name":"Tom","age":27},{"sex":"male"}]'

df2 = pd.read_json(data2, orient="records")
df2

dict like {index -> {column -> value}}

data3 = '{"id1":{"name":"Mike","age":20,"sex":"male","score":80},"id2":{"name":"Jack","sex":"female","score":90}}'

df3 = pd.read_json(data3, orient="index")
df3

dict like {column -> {index -> value}}

data4 = '{"sex":{"id1":"Peter","id2":"Tom","id3":"Jimmy"},"age":{"id1": 20,"id3":28}}'

df4 = pd.read_json(data4, orient="columns")
df4

‘values' : just the values array

data5 = '[["深圳",2000],["广州",1900],["北京",2500]]'

df5 = pd.read_json(data5, orient="values")
df5

DataFrame.to_json(path_or_buf=None,  # 路径
                  orient=None, # 转换类型
                  date_format=None, # 日期转换类型
                  double_precision=10,  # 小数保留精度
                  force_ascii=True, # 是否显示中文
                  date_unit='ms', # 日期显示最小单位
                  default_handler=None, 
                  lines=False, 
                  compression='infer', 
                  index=True, # 是否保留行索引
                  indent=None, # 空格数
                  storage_options=None)

df.to_json("df_to_json_1.json", force_ascii=True)  # 不显示中文

df.to_json("df_to_json_2.json", force_ascii=False)  # 显示中文

df.to_json("df_to_json_3.json", force_ascii=False, orient="index",indent=4) 
# index + 换行

df.to_json("df_to_json_4.json", force_ascii=False, orient="columns",indent=4)   # columns + 换行