完善了运算

.gitignore

@@ -1,3 +1,4 @@
 __pycache__/*
 Temp/
 Scales/
+Work/

file_load.py

@@ -40,7 +40,7 @@ def calc_similarity(scale):
 	for i in scale:
 		item.append(i)
 		vec.append(client.embeddings.create(
-    		input=scale[i], model="text-embedding-3-small" # nomic-embed-text text-embedding-3-small
+    		input=scale[i], model="text-embedding-3-large" # nomic-embed-text text-embedding-3-small
 			).data[0].embedding)
 	simi=cosine_similarity(vec)
 	que=[]
@@ -73,24 +73,17 @@ def make_data():
 		for j in range(1,20):
 			s += ',' + str(random.randint(0,4))
 		s+='\n'
-	with open("Temp/data.csv","w") as data:
+	with open("data.csv","w") as data:
 		data.write(s)
 
-def corelation(sort:bool=True):
-	data = pandas.read_csv("data.csv")
-	que=[]
+def corelation():
+	data = pandas.read_csv("Work/data.csv")
+	que={}
 	for i in data:
 		for j in data:
 			try:
-				if(i != j):
-					# que[i,j]["psr"]=data[i].corr(data[j])
-					que.append({"from":j,"to":i,"psr":data[i].corr(data[j])})
-				else:
-					pass
+				que[i,j]=data[i].corr(data[j])
 			except:
 				pass
-	if sort:
-		return sorted(que,key = lambda t : abs(t["psr"]), reverse=True)
-	else:
 	return que
 

main.py

@@ -10,23 +10,21 @@ import numpy
 similarity = file_load.similarity()
 corelation = file_load.corelation()
 
-table = {}
-
-for i in corelation:
-	table[i["from"],i["to"]]=i["psr"]
-
 x=[]
 y=[]
 
+s="similarity, corelation\n"
+
 for i in similarity:
-	x.append(abs(table[i["from"],i["to"]]))
-	y.append(i["similarity"])
+	try:
+		s+=str(i["similarity"])+','+str(corelation[i["from"],i["to"]])+'\n'
+		x.append(i["similarity"])
+		y.append(corelation[i["from"],i["to"]])
+	except:
+		pass
 
 print(numpy.corrcoef(x,y)[0,1])
 
-s="similarity, corelation\n"
-for i in similarity:
-	s+=str(i["similarity"])+','+str(table[i["from"],i["to"]])+'\n'
-with open("Temp/point.csv","w") as point:
+with open("Work/point.csv","w") as point:
 	point.write(s)