Spaces:
Runtime error
Runtime error
File size: 5,317 Bytes
48eb4b5 eae396a 48eb4b5 eae396a 48eb4b5 eae396a 48eb4b5 eae396a 48eb4b5 eae396a 48eb4b5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 |
from flask import Flask, render_template, request
import plotly.graph_objs as go
from transformers import pipeline
import yfinance as yf
import requests
from newspaper import Article
from newspaper import Config
from bs4 import BeautifulSoup
from datetime import datetime, timedelta
from transformers import BertTokenizer, BertForSequenceClassification
from transformers import BartForConditionalGeneration, BartTokenizer
app = Flask(__name__)
# Set up sentiment analysis and summarization pipelines
finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-tone',num_labels=3)
sentiment_tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-tone')
summarization_model = BartForConditionalGeneration.from_pretrained("facebook/bart-large", forced_bos_token_id=0)
summarization_tokenizer = BartTokenizer.from_pretrained("facebook/bart-large")
sentiment_analysis_pipeline = pipeline("sentiment-analysis",model=finbert,tokenizer=sentiment_tokenizer,truncation = True,max_length = 512)
summarization_pipeline = pipeline("summarization",model=summarization_model,tokenizer=summarization_tokenizer,max_length = 512,truncation=True)
# News API setup
def get_news_articles_info(ticker_name):
# URL of the search results page
url = "https://www.marketwatch.com/search?q=" + ticker_name + "&ts=0&tab=All%20News"
# Send an HTTP GET request to the URL
response = requests.get(url)
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, "html.parser")
article_links = []
for content in soup.find_all("h3",class_="article__headline"):
for link in content.find_all("a"):
if link['href'] != "#":
article_links.append(link['href'])
article_links = article_links[18:36]
ticker_news_extracted = []
count = 0
for link in article_links:
article_info = {}
article_info['text'] = ''
article_info['url'] = link
try:
url = article_info['url']
url = requests.head(url, allow_redirects=True).url
user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36'
config = Config()
config.browser_user_agent = user_agent
article = Article(url, config=config)
article.download()
article.parse()
article_info['title'] = article.title
article_info['text'] = article.text
article_info['url'] = url
count = count + 1
print(count,url)
except Exception as error:
print("Error",url,error)
continue
if article_info['text'] == '':
print('No text',url)
continue
if count > 5:
break
ticker_news_extracted.append(article_info)
return ticker_news_extracted
@app.route("/", methods=["GET", "POST"])
def index():
if request.method == "POST":
ticker = request.form["ticker"]
# Get top 5 news articles for the given ticker
search_results = get_news_articles_info(ticker_name=ticker)
articles = search_results[:5]
print("Getting the info finished")
news_data = []
for article in articles:
title = article['title']
link = article['url']
content = article['text']
# Perform sentiment analysis on article content
sentiment = sentiment_analysis_pipeline(content)[0]
# Summarize article content
summary = summarization_pipeline(content, max_length=100, min_length=30, do_sample=False)[0]["summary_text"]
news_data.append({
"title": title,
"link": link,
"sentiment": sentiment["label"],
"sentiment_score": round(sentiment["score"],3),
"summary": summary,
"Ticker": ticker
})
print(link)
# Define the stock ticker symbol and the date range
ticker_symbol = ticker # Example: Apple Inc.
end_date = datetime.today()
start_date = end_date - timedelta(days=90)
# Fetch historical data using yfinance
data = yf.download(ticker_symbol, start=start_date, end=end_date)
# Create a candlestick graph using Plotly
fig = go.Figure(data=[go.Candlestick(x=data.index,
open=data['Open'],
high=data['High'],
low=data['Low'],
close=data['Close'])])
# Customize the layout
fig.update_layout(title=f'Candlestick Chart for {ticker_symbol} in the Last 90 Days',
xaxis_title='Date',
yaxis_title='Price',
xaxis_rangeslider_visible=False)
# convert the fig to HTML DIV element
graph_html = fig.to_html(full_html=False)
return render_template("index.html", news_data=news_data, candlestick_graph=graph_html,ticker = ticker)
return render_template("index.html")
if __name__ == "__main__":
app.run(host='0.0.0.0',port=7860) |