From 727d4e57a87c2f03e3572e21a7ac9ccfb8f87698 Mon Sep 17 00:00:00 2001
From: mxr612 <work@mxr612.top>
Date: Tue, 14 May 2024 04:50:01 +0800
Subject: [PATCH] sorted similarity of item link

---
 ItemRelate.py      | 50 ++++++++++++++++++++++++++++++++++++++++++++++
 TestFile/adhd.json | 36 +++++++++++++++++++++++++++++++++
 embedding.py       | 25 -----------------------
 main.py            | 10 ++++++++++
 4 files changed, 96 insertions(+), 25 deletions(-)
 create mode 100644 ItemRelate.py
 create mode 100644 TestFile/adhd.json
 delete mode 100644 embedding.py
 create mode 100644 main.py

diff --git a/ItemRelate.py b/ItemRelate.py
new file mode 100644
index 0000000..e44b7c0
--- /dev/null
+++ b/ItemRelate.py
@@ -0,0 +1,50 @@
+import os
+os.environ["OPENAI_API_KEY"]= "sk-PRJ811XeKzEy20Ug3dA98a34Af8b40B5816dE15503D33599"
+os.environ["OPENAI_BASE_URL"]= "http://154.9.28.247:3000/v1/"
+
+from openai import OpenAI
+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="text-embedding-3-small" # nomic-embed-text text-embedding-3-small
+			).data[0].embedding
+
+class edge:
+	a:str
+	b:str
+	sim:float
+	def __init__(self, a:str, b:str, sim:float):
+		self.a=a
+		self.b=b
+		self.sim=sim
+
+def main(scale:json):
+
+	item=[]
+	vec=[]
+
+	for i in scale["item"]:
+		item.append(i)
+		vec.append(embedding(scale["item"][i]))
+
+	simi=cosine_similarity(vec)
+
+	que=[]
+
+	for i,v in enumerate(simi):
+		for j in range(0,i):
+			# print(simi[i][j],',',item[i],',',item[j])
+			que.append(edge(item[i], item[j], simi[i][j]))
+		# print("\n")
+
+	sorted(que,key= lambda t : t.sim)
+
+	return que
\ No newline at end of file
diff --git a/TestFile/adhd.json b/TestFile/adhd.json
new file mode 100644
index 0000000..117c728
--- /dev/null
+++ b/TestFile/adhd.json
@@ -0,0 +1,36 @@
+{
+    "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
+            }
+        }
+    ]
+}
\ No newline at end of file
diff --git a/embedding.py b/embedding.py
deleted file mode 100644
index 5306bfd..0000000
--- a/embedding.py
+++ /dev/null
@@ -1,25 +0,0 @@
-import os
-os.environ["OPENAI_API_KEY"]= "sk-PRJ811XeKzEy20Ug3dA98a34Af8b40B5816dE15503D33599"
-os.environ["OPENAI_BASE_URL"]= "http://154.9.28.247:3000/v1/"
-
-from openai import OpenAI
-client = OpenAI()
-
-from sklearn.metrics.pairwise import cosine_similarity
-
-def embedding(s:str):
-	if len(s)==0:
-		return
-	else:
-		return client.embeddings.create(
-    		input=s, model="text-embedding-3-large" # nomic-embed-text text-embedding-3-small
-			).data[0].embedding
-
-a=embedding("I tend to draw fine distinctions between similar feelings (e.g., depressed and blue; annoyed and irritated).")
-# b=embedding("我喜欢界定两种相似的情绪（如沮丧和忧伤，烦恼和被激怒）。")
-# c=embedding("I like to define two similar emotions (e.g., frustration and sadness, annoyance and irritation).")
-
-print(a,"\n",len(a))
-
-# s = cosine_similarity([a, b, c])
-# print(s)
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..20b89bd
--- /dev/null
+++ b/main.py
@@ -0,0 +1,10 @@
+from ItemRelate import main as relate
+import json
+
+with open("TestFile/adhd.json") as json_file:
+	scale = json.load(json_file)
+
+que=relate(scale)
+
+for i in que:
+	print(i.a, i.b, i.sim)