Update app (3).py

app (3).py

@@ -2,47 +2,44 @@ import streamlit as st
 from urllib.request import urlopen, Request
 from bs4 import BeautifulSoup
 import pandas as pd
-import plotly
 import plotly.express as px
-import json # for graph plotting in website
-# NLTK VADER for sentiment analysis
 from dateutil import parser
 import nltk
 nltk.downloader.download('vader_lexicon')
 from nltk.sentiment.vader import SentimentIntensityAnalyzer
-
-import subprocess
-import os
-
 import datetime
+import requests
 
-st.set_page_config(page_title = "Stock News Sentiment Analyzer", layout = "wide")
+st.set_page_config(page_title="Stock News Sentiment Analyzer", layout="wide")
 
+def verify_link(url, timeout=10, retries=3):
+    for _ in range(retries):
+        try:
+            response = requests.head(url, timeout=timeout, allow_redirects=True)
+            if 200 <= response.status_code < 300:
+                return True
+        except requests.RequestException:
+            continue
+    return False
 
 def get_news(ticker):
+    finviz_url = 'https://finviz.com/quote.ashx?t='
     url = finviz_url + ticker
-    req = Request(url=url,headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:20.0) Gecko/20100101 Firefox/20.0'}) 
+    req = Request(url=url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:20.0) Gecko/20100101 Firefox/20.0'}) 
     response = urlopen(req)    
-    # Read the contents of the file into 'html'
-    html = BeautifulSoup(response)
-    # Find 'news-table' in the Soup and load it into 'news_table'
+    html = BeautifulSoup(response, 'html.parser')
     news_table = html.find(id='news-table')
     return news_table
-	
-# parse news into dataframe
-
 
 def parse_news(news_table):
     parsed_news = []
     
     for x in news_table.findAll('tr'):
         try:
-            # Get the headline text
             text = x.a.get_text()
-            # Get the date and time from the first <td> tag
+            link = x.a['href']
             date_scrape = x.td.text.strip().split()
             
-            # Handle cases where only time is present
             if len(date_scrape) == 1:
                 date = datetime.datetime.today().strftime('%Y-%m-%d')
                 time = date_scrape[0]
@@ -50,103 +47,122 @@ def parse_news(news_table):
                 date = date_scrape[0]
                 time = date_scrape[1]
 
-            # Parse the date and time using dateutil.parser
             datetime_str = f"{date} {time}"
             datetime_parsed = parser.parse(datetime_str)
 
-            # Append the parsed news to the list
-            parsed_news.append([datetime_parsed, text])
+            is_valid = verify_link(link)
+            
+            parsed_news.append([datetime_parsed, text, link, is_valid])
             
         except Exception as e:
             print("Error parsing news:", e)
             continue
     
-    # Convert the list to a DataFrame
-    columns = ['datetime', 'headline']
+    columns = ['datetime', 'headline', 'link', 'is_valid']
     parsed_news_df = pd.DataFrame(parsed_news, columns=columns)
     
     return parsed_news_df
-        
-    
-        
+
 def score_news(parsed_news_df):
-    # Instantiate the sentiment intensity analyzer
     vader = SentimentIntensityAnalyzer()
     
-    # Iterate through the headlines and get the polarity scores using vader
     scores = parsed_news_df['headline'].apply(vader.polarity_scores).tolist()
-
-    # Convert the 'scores' list of dicts into a DataFrame
     scores_df = pd.DataFrame(scores)
-
-    # Join the DataFrames of the news and the list of dicts
     parsed_and_scored_news = parsed_news_df.join(scores_df, rsuffix='_right')        
     parsed_and_scored_news = parsed_and_scored_news.set_index('datetime')    
     parsed_and_scored_news = parsed_and_scored_news.rename(columns={"compound": "sentiment_score"})
 
     return parsed_and_scored_news
 
-
-
 def plot_hourly_sentiment(parsed_and_scored_news, ticker):
-    # Ensure that only numeric columns are resampled
     numeric_cols = parsed_and_scored_news.select_dtypes(include=['float64', 'int64'])
-    
-    # Group by date and ticker columns from scored_news and calculate the mean
     mean_scores = numeric_cols.resample('h').mean()
-
-    # Plot a bar chart with Plotly 
-    fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', title=ticker + ' Hourly Sentiment Scores')
-    return fig  # Return the figure to display in the Streamlit app
+    
+    fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', 
+                 title=f'{ticker} Hourly Sentiment Scores',
+                 color='sentiment_score',
+                 color_continuous_scale=['red', 'yellow', 'green'],
+                 range_color=[-1, 1])
+    
+    fig.update_layout(coloraxis_colorbar=dict(
+        title="Sentiment",
+        tickvals=[-1, 0, 1],
+        ticktext=["Negative", "Neutral", "Positive"],
+    ))
+    
+    return fig
 
 def plot_daily_sentiment(parsed_and_scored_news, ticker):
-    # Ensure that only numeric columns are resampled
     numeric_cols = parsed_and_scored_news.select_dtypes(include=['float64', 'int64'])
-
-    # Group by date and ticker columns from scored_news and calculate the mean
     mean_scores = numeric_cols.resample('D').mean()
+    
+    fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', 
+                 title=f'{ticker} Daily Sentiment Scores',
+                 color='sentiment_score',
+                 color_continuous_scale=['red', 'yellow', 'green'],
+                 range_color=[-1, 1])
+    
+    fig.update_layout(coloraxis_colorbar=dict(
+        title="Sentiment",
+        tickvals=[-1, 0, 1],
+        ticktext=["Negative", "Neutral", "Positive"],
+    ))
+    
+    return fig
 
-    # Plot a bar chart with Plotly
-    fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', title=ticker + ' Daily Sentiment Scores')
-    return fig  # Return the figure to display in the Streamlit app
-
-
-# for extracting data from finviz
-finviz_url = 'https://finviz.com/quote.ashx?t='
-
+def get_recommendation(sentiment_scores):
+    avg_sentiment = sentiment_scores['sentiment_score'].mean()
+    
+    if avg_sentiment >= 0.05:
+        return f"Positive sentiment (Score: {avg_sentiment:.2f}). The recent news suggests a favorable outlook for this stock. Consider buying or holding if you already own it."
+    elif avg_sentiment <= -0.05:
+        return f"Negative sentiment (Score: {avg_sentiment:.2f}). The recent news suggests caution. Consider selling or avoiding this stock for now."
+    else:
+        return f"Neutral sentiment (Score: {avg_sentiment:.2f}). The recent news doesn't show a strong bias. Consider holding if you own the stock, or watch for more definitive trends before making a decision."
 
 st.header("Stock News Sentiment Analyzer")
 
 ticker = st.text_input('Enter Stock Ticker', '').upper()
 
-df = pd.DataFrame({'datetime': datetime.datetime.now(), 'ticker': ticker}, index = [0])
-
-
 try:
-	st.subheader("Hourly and Daily Sentiment of {} Stock".format(ticker))
-	news_table = get_news(ticker)
-	parsed_news_df = parse_news(news_table)
-	print(parsed_news_df)
-	parsed_and_scored_news = score_news(parsed_news_df)
-	fig_hourly = plot_hourly_sentiment(parsed_and_scored_news, ticker)
-	fig_daily = plot_daily_sentiment(parsed_and_scored_news, ticker) 
-	 
-	st.plotly_chart(fig_hourly)
-	st.plotly_chart(fig_daily)
-
-	description = """
-		The above chart averages the sentiment scores of {} stock hourly and daily.
-		The table below gives each of the most recent headlines of the stock and the negative, neutral, positive and an aggregated sentiment score.
-		The news headlines are obtained from the FinViz website.
-		Sentiments are given by the nltk.sentiment.vader Python library.
-		""".format(ticker)
-		
-	st.write(description)	 
-	st.table(parsed_and_scored_news)
-	
+    st.subheader(f"Sentiment Analysis and Recommendation for {ticker} Stock")
+    news_table = get_news(ticker)
+    parsed_news_df = parse_news(news_table)
+    parsed_and_scored_news = score_news(parsed_news_df)
+    
+    # Generate and display recommendation
+    recommendation = get_recommendation(parsed_and_scored_news)
+    st.write(recommendation)
+    
+    # Display a disclaimer
+    st.warning("Disclaimer: This recommendation is based solely on recent news sentiment and should not be considered as financial advice. Always do your own research and consult with a qualified financial advisor before making investment decisions.")
+    
+    fig_hourly = plot_hourly_sentiment(parsed_and_scored_news, ticker)
+    fig_daily = plot_daily_sentiment(parsed_and_scored_news, ticker) 
+     
+    st.plotly_chart(fig_hourly)
+    st.plotly_chart(fig_daily)
+
+    description = f"""
+        The above charts average the sentiment scores of {ticker} stock hourly and daily.
+        The table below gives each of the most recent headlines of the stock and the negative, neutral, positive and an aggregated sentiment score.
+        The news headlines are obtained from the FinViz website.
+        Sentiments are given by the nltk.sentiment.vader Python library.
+        Links have been verified for validity.
+        """
+        
+    st.write(description)     
+    
+    parsed_and_scored_news['link'] = parsed_and_scored_news.apply(
+        lambda row: f'<a href="{row["link"]}" target="_blank">{"Valid✅" if row["is_valid"] else "Invalid❌"} Link</a>', 
+        axis=1
+    )
+    
+    st.write(parsed_and_scored_news.drop(columns=['is_valid']).to_html(escape=False), unsafe_allow_html=True)
+    
 except Exception as e:
-	print(str(e))
-	st.write("Enter a correct stock ticker, e.g. 'AAPL' above and hit Enter.")	
+    print(str(e))
+    st.write("Enter a correct stock ticker, e.g. 'AAPL' above and hit Enter.")    
 
 hide_streamlit_style = """
 <style>
@@ -154,4 +170,4 @@ hide_streamlit_style = """
 footer {visibility: hidden;}
 </style>
 """
-st.markdown(hide_streamlit_style, unsafe_allow_html=True) 
+st.markdown(hide_streamlit_style, unsafe_allow_html=True)