Spaces:
Runtime error
Runtime error
File size: 3,070 Bytes
1699569 65ce061 bfdebb5 1699569 b2912c4 1699569 4b2cc15 1699569 4b2cc15 1699569 4b2cc15 1699569 4b2cc15 1699569 4b2cc15 1699569 4b2cc15 1699569 65ce061 b2912c4 2f21339 5ba2c0e 1699569 |
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 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
import streamlit as st
import time
import json
from gensim.models import Word2Vec
import pandas as pd
from datasets import load_dataset
from datasets import Dataset
# Define the HTML and CSS styles
html_temp = """
<div style="background-color:black;padding:10px">
<h1 style="color:white;text-align:center;">My Streamlit App with HTML and CSS</h1>
</div>
"""
# Display the HTML and CSS styles
st.markdown(html_temp, unsafe_allow_html=True)
# Add some text to the app
st.write("This is my Streamlit app with HTML and CSS formatting.")
query = st.text_input("Enter a word")
# query = input ("Enter your keyword(s):")
query = query.lower()
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)
csv = table.head(50).to_csv(index=False).encode('utf-8')
st.download_button(
label=f"Download words similar to {query} in .csv format",
data=csv,
file_name='clotting_sim1.csv',
mime='text/csv'
)
json = table.head(50).to_json(index=True).encode('utf-8')
st.download_button(
label=f"Download words similar to {query} in .js format",
data=json,
file_name='clotting_sim1.js',
mime='json'
)
print(table.head(10))
table.head(50).to_csv("clotting_sim1.csv", index=True)
table.head(50).to_json("clotting_sim1.js", 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)
csv2 = df1.head(50).to_csv(index=False).encode('utf-8')
st.download_button(
label=f"Download genes similar to {query} in .csv format",
data=csv2,
file_name='clotting_sim2.csv',
mime='text/csv'
)
json2 = df1.head(50).to_json(index=True).encode('utf-8')
st.download_button(
label=f"Download words similar to {query} in .js format",
data=json2,
file_name='clotting_sim1.js',
mime='json'
)
print(df1.head(10))
df1.head(50).to_csv("clotting_sim2.csv", index=True)
df1.head(50).to_json("clotting_sim2.js", index=True)
print()
st.header(f"Similar Genes to {query}")
st.write(df1.head(50))
# arrow_dataset = Dataset.from_pandas(df1.head(50))
# arrow_dataset.save_to_disk("https://huggingface.co/datasets/jfataphd/word2vec_dataset/sim2")
# arrow_dataset_reloaded = load_from_disk('sim2.js')
# arrow_dataset_reloaded
|