main.py:

- 添加了读取整个文件夹内scale json
- 可以从我们旧的json格式转换为新的

ItemRelate.py:
- 修复错误的变量名
- 简化Embedding调用
- 转为读取item list
- 修复了排序
This commit is contained in:
mxr612 2024-05-14 13:04:54 +08:00
parent 8717b81bbc
commit 82b958122b
4 changed files with 38 additions and 62 deletions

2
.gitignore vendored
View File

@ -1 +1,3 @@
__pycache__/*
Temp/
Scales/

View File

@ -7,24 +7,16 @@ client = OpenAI()
from sklearn.metrics.pairwise import cosine_similarity
import json
def embedding(s:str):
if len(s)==0:
return
else:
return client.embeddings.create(
input=s, model="nomic-embed-text" # nomic-embed-text text-embedding-3-small
).data[0].embedding
def main(scale:json):
def main(scale):
item=[]
vec=[]
for i in scale["item"]:
for i in scale:
item.append(i)
vec.append(embedding(scale["item"][i]))
vec.append(client.embeddings.create(
input=scale[i], model="text-embedding-3-small" # nomic-embed-text text-embedding-3-small
).data[0].embedding)
simi=cosine_similarity(vec)
@ -32,10 +24,6 @@ def main(scale:json):
for i,v in enumerate(simi):
for j in range(0,i):
# print(simi[i][j],',',item[i],',',item[j])
que.append({"from":item[j], "i":item[i], "similarity":simi[i][j]})
# print("\n")
que.append({"from":item[j], "to":item[i], "similarity":simi[i][j]})
sorted(que,key= lambda t : t["similarity"])
return que
return sorted(que, key = lambda t : t["similarity"], reverse=True)

View File

@ -1,36 +0,0 @@
{
"name":"成人多动症自筛表 (6 itmes)",
"introduction":1,
"item":{
"asrs1": "当一项工作最有挑战性的部分完成后,你经常难以做到对细节部分更精益求精吗?",
"asrs2": "你经常很难把有组织性的任务、事情布置得井井有条吗? ",
"asrs3": "当你从事一项需要脑力的工作的时候,你经常回避或者延长开始的时间吗?",
"asrs4": "你经常很难记住约会或者一些必须完成的事情吗?",
"asrs5": "当您必须安静地坐很长时间时,是否经常表现得坐立不安,手脚动作多?",
"asrs6": "你是否在自觉做事情时表现得极度活跃,非完成某项事情不可,好像在被发动机所驱使一样?"
},
"value": {
"从不":0,
"很少":1,
"有时":2,
"经常":3,
"总是":4
},
"result":[
{
"name": "ADHD",
"sum": [
"asrs1",
"asrs2",
"asrs3",
"asrs4",
"asrs5",
"asrs6"
],
"re_sum": [],
"result": {
"0": 2
}
}
]
}

36
main.py
View File

@ -2,14 +2,36 @@ from ItemRelate import main as relate
import json
import os
if os.path.getsize("TestFile/items.json") == 0:
with open("TestFile/adhd.json","r") as json_file:
scale = json.load(json_file)
que=relate(scale)
with open("TestFile/items.json","w") as items:
def batch():
scales = os.listdir("Scales")
items={}
for i in scales:
with open("Scales/"+i,"r") as scale:
tmp = json.load(scale)
for i in tmp["item"]:
items[i]=tmp["item"][i]
# print(items)
return items
def old_type(str):
with open(str,"r") as file:
scale=json.load(file)
new={"item":{}}
for i in scale:
new["item"][i["name"]]=i["label"]
# print(i["name"],i["label"])
with open(str,"w") as file:
file.write(json.dumps(new))
# old_type("Scales/ceE.json")
if os.path.getsize("Temp/items.json") == 0:
que=relate(batch())
with open("Temp/items.json","w") as items:
items.write(json.dumps(que))
else:
with open("TestFile/items.json","r") as items:
with open("Temp/items.json","r") as items:
que = json.load(items)
print(que)
for i in que:
print(i)