Junction 2023 Asia

from sentence_transformers import SentenceTransformer
import numpy as np

def cos_sim(A, B):
    return np.dot(A, B)/(np.linalg.norm(A)*np.linalg.norm(B))
    
with open('database.pkl', 'rb') as f:
    database = pickle.load(f) # database is a datas with festival informations.
    
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2') # SBERT

embedding = model.encode([database['rec'][i]['desc'] for i in range(len(database['rec']))]) # Embedding with datas
inp = model.encode([inp]) # Embedding with input datas
sens = [(i,cos_sim(inp[0],embedding[i])) for i in range(len(database['rec']))] # Calculate  similarity with cosine similarity
sens.sort(key=lambda x:-x[1]) # sort by similarity

from sentence_transformers import SentenceTransformer
from keybert import KeyBERT
import numpy as np

def cos_sim(A, B):
    return np.dot(A, B)/(np.linalg.norm(A)*np.linalg.norm(B))
    
with open('database.pkl', 'rb') as f:
    database = pickle.load(f) # database is a datas with festival informations.
    
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2') # SBERT
kw_model = KeyBERT(model)

input_datas = database['inputs']
if len(input_datas) > 100: # setting input datas as 100 recent input datas
    input_datas.pop(0)
input_datas.append(inp)
    
keywordData = ""
for i in input_datas:
    keywordData += " " + i
keywords = kw_model.extract_keywords(keywordData, keyphrase_ngram_range=(1, 1), stop_words=None, top_n=6) # calculate 6 related keywords