Upload 2 files

recommendation_paper.py

@@ -0,0 +1,100 @@
+# -*- coding: utf-8 -*-
+"""Recommendation_paper.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/16l0DYZhK4q7tjYvRqpa1IMyIatp1Gtd1
+"""
+
+!pip install -q -U sentence-transformers
+
+import torch
+import pandas as pd
+
+from  sentence_transformers import SentenceTransformer,util
+
+data=pd.read_csv("/content/arxiv_data.csv")
+
+data.head(10)
+
+titles=data["titles"]
+
+titles.head(5)
+
+model=SentenceTransformer("all-MiniLM-L6-v2")
+
+Encoded_titles=model.encode(titles,device="cuda")
+
+keep_counter=0
+for title,encode in zip(titles,Encoded_titles):
+  print("Titles",title)
+  print("Encoded Data",encode)
+  print("length of Encoded Data",len(encode))
+  if(keep_counter==5):
+    break;
+  keep_counter+=1
+
+type(titles),type(Encoded_titles)
+
+#checking the shape of embeding
+Encoded_titles.shape
+
+!pip install huggingface-cli
+
+!pip install huggingface_hub
+
+from huggingface_hub import notebook_login
+notebook_login()
+
+from google.colab import userdata
+userdata.get('secretName')
+
+
+
+!pip install datasets
+
+model.push_to_hub("1998Shubham007/ModelRecomm")
+
+
+
+#Now save your embedding,Title,model
+import pickle
+
+#saving  embedding
+with open("embedding.pkl","wb") as f:
+  pickle.dump(Encoded_titles,f)
+
+with open("ModelRec.pkl","wb") as f:
+  pickle.dump(model,f)
+
+with open("Titles.pkl","wb") as f:
+  pickle.dump(titles,f)
+
+
+
+#Loading the saved Embedding
+with open("/content/embedding.pkl","rb") as f:
+  Lencode=pickle.load(f)
+
+#Loading the saved Model
+with open("/content/ModelRec.pkl","rb") as f:
+  lModelRec=pickle.load(f)
+
+#Prediction
+
+def recomm(inputPaper):
+  encodePaper=lModelRec.encode(inputPaper)
+  cosine_score=util.cos_sim(Lencode,encodePaper)
+  Top_score=torch.topk(cosine_score,dim=0,k=4)
+  paperList=[]
+  for i in Top_score.indices:
+    paperList.append(titles[i.item()])
+  return paperList
+
+value=input("enter the paper name")
+
+papers=recomm(value)
+
+print(papers)
+