Spaces:
Build error
Build error
File size: 4,686 Bytes
c188624 cd22fcf c188624 3285b2f c188624 c8e2bd5 fb4de31 3a6124d c188624 a17b65d c188624 3a6124d 083cdef c188624 aa06dc2 c46cd83 bc5855e 699c8d1 4b58234 c188624 0bb7e36 c188624 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
import pandas as pd
import streamlit as st
from transformers import *
from carga_articulos import cargar_articulos
from preprocesamiento_articulos import limpieza_articulos
from entrenamiento_modelo import term_document_matrix, tf_idf_score
from resultados_consulta import resultados_consulta, detalles_resultados
import tensorflow as tf
def crear_indice():
df=cargar_articulos()
vocab = limpieza_articulos(df)
td_matrix=term_document_matrix(df, vocab, 'ID', 'titulo')
td_idf_matrix=tf_idf_score(td_matrix, df.ID.values)
td_idf_matrix.to_csv('articulos_indexados.csv')
def load_qa_model():
tokenizer = AutoTokenizer.from_pretrained('mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es', use_fast="false")
model = TFDistilBertForQuestionAnswering.from_pretrained("mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es", from_pt=True)
return tokenizer, model
# 4. Use streamlit to create a web app
def main():
#crear_indice()
with st.expander("About the #30DaysOfStreamlit"):
st.markdown(
"""
The **#30DaysOfStreamlit** is a coding challenge designed to help you get started in building Streamlit apps.
Particularly, you'll be able to:
- Set up a coding environment for building Streamlit apps
- Build your first Streamlit app
- Learn about all the awesome input/output widgets to use for your Streamlit app
"""
)
# Sidebar
st.sidebar.header("About")
st.sidebar.markdown(
"[Streamlit](https://streamlit.io) is a Python library that allows the creation of interactive, data-driven web applications in Python."
)
st.sidebar.header("Resources")
st.sidebar.markdown(
"""
- [Streamlit Documentation](https://docs.streamlit.io/)
- [Cheat sheet](https://docs.streamlit.io/library/cheatsheet)
- [Book](https://www.amazon.com/dp/180056550X) (Getting Started with Streamlit for Data Science)
- [Blog](https://blog.streamlit.io/how-to-master-streamlit-for-data-science/) (How to master Streamlit for data science)
"""
)
st.sidebar.header("Deploy")
st.sidebar.markdown(
"You can quickly deploy Streamlit apps using [Streamlit Community Cloud](https://streamlit.io/cloud) in just a few clicks."
)
st.set_page_config(page_title="Buscador de noticias periodicos dominicanos", page_icon="📰")
st.header('El Repartidor Dominicano')
st.image('repartidor_periodicos.jpeg', width=150)
df=cargar_articulos()
articulos_indexados = pd.read_csv('articulos_indexados.csv')
articulos_indexados = articulos_indexados.set_index('Unnamed: 0')
tokenizer, qa_model = load_qa_model()
query = st.text_input(
"Escribe tus términos de búsqueda o haz una pregunta terminando con el caracter ?:"
)
if query:
if ('?' in query):
st.write("Contestando a: ", query)
text='Un texto es una composición de signos codificados en un sistema de escritura que forma una unidad de sentido.'
inputs = tokenizer(query, text, return_tensors='tf')
outputs = qa_model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])
answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0])
answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])
predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
answer=tokenizer.decode(predict_answer_tokens)
st.info(answer)
else:
st.write("Buscando: ", query)
result = resultados_consulta(df,articulos_indexados, query)
if result.empty:
st.info("No se encontraron artículos para la búsqueda solicitada")
else:
df_results=detalles_resultados(df,result)
N_cards_per_row = 1
for n_row, row in df_results.reset_index().iterrows():
i = n_row%N_cards_per_row
if i==0:
st.write("---")
cols = st.columns(N_cards_per_row, gap="large")
# draw the card
with cols[n_row%N_cards_per_row]:
st.caption(f"{row['feed'].strip()} - {row['seccion'].strip()} - {row['fecha'].strip()} ")
st.markdown(f"**{row['titulo'].strip()}**")
st.markdown(f"{row['resumen'].strip()}")
st.markdown(f"{row['link']}")
if __name__ == "__main__":
main()
|