Spaces:
Sleeping
Sleeping
File size: 1,596 Bytes
e41540d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import streamlit as st
import time
import json
from gensim.models import Word2Vec
import pandas as pd
query = st.text_input("Enter a word")
# query = input ("Enter your keyword(s):")
if query:
model = Word2Vec.load("pubmed_model_clotting") # you can continue training with the loaded model!
words = list(model.wv.key_to_index)
X = model.wv[model.wv.key_to_index]
model2 = model.wv[query]
df = pd.DataFrame(X)
# def findRelationships(query, df):
table = model.wv.most_similar_cosmul(query, topn=10000)
table = (pd.DataFrame(table))
table.index.name = 'Rank'
table.columns = ['Word', 'SIMILARITY']
print()
print("Similarity to " + str(query))
pd.set_option('display.max_rows', None)
print(table.head(100))
table.head(10).to_csv("clotting_sim1.csv", index=True)
st.header(f"Similar Words to {query}")
st.write(table.head(50))
#
print()
print("Human genes similar to " + str(query))
df1 = table
df2 = pd.read_csv('Human_Genes.csv')
m = df1.Word.isin(df2.symbol)
df1 = df1[m]
df1.rename(columns={'Word': 'Human Gene'}, inplace=True)
print(df1.head(10))
print()
df1.head(10).to_csv("clotting_sim2.csv", index=True, header=False)
time.sleep(2)
st.header(f"Similar Genes to {query}")
st.write(table.head(50))
# findRelationships(query, df)
# model = gensim.models.KeyedVectors.load_word2vec_format('pubmed_model_clotting', binary=True)
# similar_words = model.most_similar(word)
# output = json.dumps({"word": word, "similar_words": similar_words})
# st.write(output)
|