Raviraj2000

sent = list()
for i in tot_val:
    sent.append(get_sent(i))
    
tick_df['sentiment'] = sent 
tick_df.head(20)

Raviraj2000

def get_sent(val):
    agg = 0
    for i in val:
        if i == 'positive':
            agg = agg + 1
        elif i == 'negative':
            agg = agg - 1

    if agg > 0:
        return('positive')

Raviraj2000

def detect(news):
    tot_val = list()
    for n in news:
        if len(n) == 0:
            tot_val.append(['neutral'])
        else:
            inputs = tokenizer(n, return_tensors="pt", padding=True)
            outputs = finbert(**inputs)[0]
            val = list()
            for idx, sent in enumerate(n):

Raviraj2000

news = list()
for i, tick in enumerate(tick_df['tick']):
    url = "https://www.tickertape.in/stocks/" + tick + "/news?checklist=basic&ref=stock-overview_overview-sections&type=news"
    headlines = get_data(url)
    news.append(headlines)

Raviraj2000

def get_data(url):
    req = Request(url=url,headers={"User-Agent": "Chrome"}) 
    response = urlopen(req).read()    
    html = BeautifulSoup(response,"html.parser")
    news_table = html.find(class_ = 'latest-news-holder')
    
    news = list()
    
    for name_box in news_table.find_all('p', class_='shave-root'):
        news.append(name_box.text.strip())

Raviraj2000

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

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

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

Raviraj2000

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

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)