Raviraj2000

import numpy as np
import pandas as pd

Raviraj2000

finance_news = pd.read_csv('news.csv', encoding = 'ISO-8859-1')
finance_news.head()

Raviraj2000

X = finance_news['headline'].to_list()
y = finance_news['sentiment'].to_list()

Raviraj2000

from transformers import BertTokenizer, BertForSequenceClassification

finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-tone',num_labels=3)
tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-tone')

Raviraj2000

labels = {0:'neutral', 1:'positive',2:'negative'}

Raviraj2000

sent_val = list()
for x in X:
    inputs = tokenizer(x, return_tensors="pt", padding=True)
    outputs = finbert(**inputs)[0]
   
    val = labels[np.argmax(outputs.detach().numpy())]
    print(x, '----', val)
    print('#######################################################')    
    sent_val.append(val)

Raviraj2000

from sklearn.metrics import accuracy_score
print(accuracy_score(y, sent_val))

Raviraj2000

from bs4 import BeautifulSoup
import pandas as pd
from urllib.request import urlopen, Request

Raviraj2000

def get_ticks(url):
    req = Request(url=url,headers={"User-Agent": "Chrome"}) 
    response = urlopen(req)    
    html = BeautifulSoup(response,"html.parser")
    ticks_table = html.find(class_ = 'page')
    
    ticks = list()
    stocks = list()
    for name_box in ticks_table.find_all('a', href = True):
        stocks.append(name_box.text.strip())

Raviraj2000

url = "https://www.tickertape.in/stocks"
tick_df = get_ticks(url)
tick_df.head()