三个 pandas读取json文件方式
信用盘源码出售搭建q<115.28.8.00.9.9>
from pandas.io.json import json_normalize
import pandas as pd
import json
import time
# 读入数据
data_str = open('AgriculturalDisease_train_annotations.json').read()
#———————————————————— 测试json_normalize ————————————————————
start_time = time.time()
for i in range(0, 300):
data_list = json.loads(data_str)
df = json_normalize(data_list)
end_time = time.time()
print (end_time - start_time)#耗时109秒
#———————————————————— 测试自己构造 ————————————————————
start_time = time.time()
for i in range(0, 300):
data_list = json.loads(data_str)
data = [[d["disease_class"], d["image_id"]] for d in data_list]
df = pd.DataFrame(data, columns=["disease_class", "image_id"])
end_time = time.time()
print (end_time - start_time)#耗时22秒
#———————————————————— 测试read_json ————————————————————
start_time = time.time()
for i in range(0, 300):
df = pd.read_json(data_str, orient='records')
end_time = time.time()
print (end_time - start_time)#耗时36秒
# read_json
df2 = pd.read_json(data_str, orient='records')
# 自己构造
data_list = json.loads(data_str)
data = [[d["disease_class"], d["image_id"]] for d in data_list]
df = pd.DataFrame(data, columns=["disease_class", "image_id"])
df.head(5)
三种代码输出均如下
disease_class image_id
0 1 62fd8bf4d53a1b94fbac16738406f10b.jpg
1 1 0bdec5cccbcade6b6e94087cb5509d98.jpg
2 1 8951e940341f77c8d361c1872c67b16d.jpg
3 1 7ed158da58c451f75fb790530d6f19cc.jpg
4 1 9b7399aa-1c3c-4137-ae4e-196cd23fe573___FREC_Sc...
技巧：将复杂的json串整理成以下格式再读取，再使用data_list = json.loads(data_str)读取即可
{"error_code":40007,"error_msg":"fail to recognize"}
[{"department": "abcdef",
"query_result": {"code": "1000", "description": "1000"},
"is_invoice": 1,
"imageName": "./imgs/8888888.jpeg",
"reco_result": {"total": "", "invoice_no": "123", "create_date": "", "check_code": ""}}]
批量读取 json 文件（中文 json）
./out_file下两个json文件内容如下：
out_01.txt 内容为："{"name_ID":"12343","name":"张三","身份编码":"未知"}"
out_02.txt 内容为："{"name_ID":"12344","name":"李四","身份编码":"98983"}"