jina financial qa search
1.0.0
Neste exemplo, usamos os transformadores Jina, PyTorch e Hugging Face para construir um sistema de resposta a perguntas financeiras baseado em BERT pronto para produção. Adaptamos uma abordagem de reclassificação de passagens, primeiro recuperando as 50 principais respostas dos candidatos e, em seguida, reclassificando as respostas dos candidatos usando FinBERT-QA, um modelo baseado em BERT ajustado no conjunto de dados FiQA que alcançou os resultados de última geração.
? Consulte este tutorial para obter um guia passo a passo e explicações detalhadas.
Motivados pela procura emergente na indústria financeira pela análise automática de dados estruturados e não estruturados em escala, os sistemas de GQ podem proporcionar vantagens lucrativas e competitivas às empresas, facilitando a tomada de decisões dos consultores financeiros. O objetivo do nosso sistema é procurar uma lista de passagens de respostas relevantes para uma pergunta. Aqui está um exemplo de uma pergunta e uma resposta verdadeira do conjunto de dados FiQA:
https://github.com/yuanbit/jina-financial-qa-search.git
Usaremos jina-financial-qa-search/ como nosso diretório de trabalho.
pip install -r requirements.txt
bash get_data.sh
Queremos indexar um subconjunto de passagens de respostas do conjunto de dados FiQA, dataset/test_answers.csv :
398960 From http://financial-dictionary.thefreedictionary.com/Business+Fundamentals The facts that affect a company's underlying value. Examples of business fundamentals include debt, cash flow, supply of and demand for the company's products, and so forth. For instance, if a company does not have a sufficient supply of products, it will fail. Likewise, demand for the product must remain at a certain level in order for it to be successful. Strong business fundamentals are considered essential for long-term success and stability. See also: Value Investing, Fundamental Analysis. For a stock the basic fundamentals are the second column of numbers you see on the google finance summary page, P/E ratio, div/yeild, EPS, shares, beta. For the company itself it's generally the stuff on the 'financials' link (e.g. things in the quarterly and annual report, debt, liabilities, assets, earnings, profit etc.
19183 If your sole proprietorship losses exceed all other sources of taxable income, then you have what's called a Net Operating Loss (NOL). You will have the option to "carry back" and amend a return you filed in the last 2 years where you owed tax, or you can "carry forward" the losses and decrease your taxes in a future year, up to 20 years in the future. For more information see the IRS links for NOL. Note: it's important to make sure you file the NOL correctly so I'd advise speaking with an accountant. (Especially if the loss is greater than the cost of the accountant...)
327002 To be deductible, a business expense must be both ordinary and necessary. An ordinary expense is one that is common and accepted in your trade or business. A necessary expense is one that is helpful and appropriate for your trade or business. An expense does not have to be indispensable to be considered necessary. (IRS, Deducting Business Expenses) It seems to me you'd have a hard time convincing an auditor that this is the case. Since business don't commonly own cars for the sole purpose of housing $25 computers, you'd have trouble with the "ordinary" test. And since there are lots of other ways to house a computer other than a car, "necessary" seems problematic also.
Você pode alterar o caminho para answer_collection.tsv para indexar com o conjunto de dados completo.
python app.py index
No final você verá o seguinte:
✅ done in ⏱ 1 minute and 54 seconds ? 7.7/s
gateway@18904[S]:terminated
doc_indexer@18903[I]:recv ControlRequest from ctl▸doc_indexer▸⚐
doc_indexer@18903[I]:Terminating loop requested by terminate signal RequestLoopEnd()
doc_indexer@18903[I]:#sent: 56 #recv: 56 sent_size: 1.7 MB recv_size: 1.7 MB
doc_indexer@18903[I]:request loop ended, tearing down ...
doc_indexer@18903[I]:indexer size: 865 physical size: 3.1 MB
doc_indexer@18903[S]:artifacts of this executor (vecidx) is persisted to ./workspace/doc_compound_indexer-0/vecidx.bin
doc_indexer@18903[I]:indexer size: 865 physical size: 3.2 MB
doc_indexer@18903[S]:artifacts of this executor (docidx) is persisted to ./workspace/doc_compound_indexer-0/docidx.bin
Precisamos construir um Executor personalizado para reclassificar as 50 principais respostas dos candidatos. Podemos fazer isso com a API Jina Hub. Vamos ter certeza de que a extensão Jina Hub está instalada:
pip install "jina[hub]"
Podemos construir o Ranker personalizado, FinBertQARanker executando:
jina hub build FinBertQARanker/ --pull --test-uses --timeout-ready 60000
Agora podemos usar nosso mecanismo de pesquisa de controle de qualidade financeiro executando:
python app.py search
O Ranker pode levar algum tempo para calcular as pontuações de relevância, pois está usando um modelo baseado em BERT. Você pode experimentar esta lista de perguntas do conjunto de dados FiQA:
• What does it mean that stocks are “memoryless”?
• What would a stock be worth if dividends did not exist?
• What are the risks of Dividend-yielding stocks?
• Why do financial institutions charge so much to convert currency?
• Is there a candlestick pattern that guarantees any kind of future profit?
• 15 year mortgage vs 30 year paid off in 15
• Why is it rational to pay out a dividend?
• Why do companies have a fiscal year different from the calendar year?
• What should I look at before investing in a start-up?
• Where do large corporations store their massive amounts of cash?
#JinaSearchCopyright (c) 2021 amiga de Jina. Todos os direitos reservados.
