Update app.py

app.py

@@ -8,6 +8,9 @@ from bs4 import BeautifulSoup
 import requests
 import os
 from datetime import date, timedelta
+from transformers import pipeline
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
 # App title
 st.markdown('''
@@ -84,9 +87,6 @@ if tickerSymbol:
 
 
 
-
-
-
     d0 = start_date
     d1 = datetime.date(2008, 1, 1)
     delta = d0 - d1
@@ -94,11 +94,6 @@ if tickerSymbol:
     st.write(delta)
 
     Begindatestring = start_date
-
-
-    #Begindatestring = datetime.strptime(Begindatestring, "%Y-%m-%d").date()
-
-
     val = 39448 + int(delta.days)
     url = 'https://economictimes.indiatimes.com/archivelist/year-'+str(Begindatestring.year)+',month-'+str(Begindatestring.month)+',starttime-'+str(val)+'.cms'  # Replace with your URL
 
@@ -108,7 +103,7 @@ if tickerSymbol:
         html_text = response.text
         soup = BeautifulSoup(html_text, "lxml")
     else:
-        st.write(f"Failed to fetch the page. Status code: {response.status_code}")
+        gg=0
     jobs = soup.find_all("li")
     headlines = []
     for job in jobs:
@@ -126,20 +121,13 @@ if tickerSymbol:
     del headlines[index:]
     news = pd.DataFrame({"News": headlines})
     news.insert(0, 'Date', Begindatestring)
-    #st.dataframe(df[0:1])
 
 
     news = news.drop_duplicates()
     news = news.dropna(how='any')
     news = news.reset_index(drop=True)
 
-    import pandas as pd
-    import numpy as np
-
 
-    from transformers import pipeline
-    import torch
-    from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
@@ -148,14 +136,6 @@ if tickerSymbol:
     model = AutoModelForSequenceClassification.from_pretrained("nickmuchi/sec-bert-finetuned-finance-classification")
 
 
-
-
-
-
-
-
-
-
     nlp = pipeline("text-classification", model=model, tokenizer=tokenizer, device=device)
 
     length = len(news[ 'News'].to_list())
@@ -169,32 +149,23 @@ if tickerSymbol:
         df.loc[i, "News"] = news_list[i]
         df.loc[i , 'label'] = results[0]["label"]
         df.loc[i , 'score'] = results[0]["score"]
+        if(i%100 ==0): st.write("Articles Processed Number "+ str(i))
 
 
-
-    #st.dataframe(df)
-
-    # Filter the DataFrame to get rows with "neutral" sentiment
     bullish_rows = df[df['label'] == 'bullish']
 
-    # Calculate the sum of the 'Score' column for "neutral" rows
     bullish_score_sum = bullish_rows['score'].sum()
 
     num_bullish_rows = len(bullish_rows)
-    # Calculate the average score for "neutral" sentiment
-    average_score_for_bullish = bullish_score_sum / num_bullish_rows
 
+    average_score_for_bullish = bullish_score_sum / num_bullish_rows
 
-    # Filter the DataFrame to get rows with "neutral" sentiment
     bearish_rows = df[df['label'] == 'bearish']
 
-    # Calculate the sum of the 'Score' column for "neutral" rows
     bearish_score_sum = bearish_rows['score'].sum()
 
-    # Cabearishlculate the number of "neutral" rows
     num_bearish_rows = len(bearish_rows)
 
-    # Calculate the average score for "neutral" sentiment
     average_score_for_bearish = bearish_score_sum / num_bearish_rows