Update app.py

app.py

@@ -1,21 +1,58 @@
 import streamlit as st
+import yfinance as yf
+import matplotlib.pyplot as plt
+import pandas as pd
+import numpy as np
 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
 import nltk
 nltk.downloader.download('vader_lexicon')
 from nltk.sentiment.vader import SentimentIntensityAnalyzer
-
-import subprocess
 from datetime import datetime
-import os
+from sklearn.preprocessing import MinMaxScaler
 
-st.set_page_config(page_title = "Stock News Sentiment Analyzer", layout = "wide")
+finviz_url = 'https://finviz.com/quote.ashx?t='
 
+sector_etf_mapping = {
+    'Consumer Durables': 'XLY',
+    'Consumer Discretionary': 'XLY',
+    'Consumer Staples': 'XLP',
+    'Energy': 'XLE',
+    'Financials': 'XLF',
+    'Health Care': 'XLV',
+    'Industrials': 'XLI',
+    'Materials': 'XLB',
+    'Real Estate': 'XLRE',
+    'Technology': 'XLK',
+    'Utilities': 'XLU',
+    'Communication Services': 'XLC'
+}
+
+# Function to get the trend of a given stock or ETF
+def get_trend(ticker, period='1mo'):
+    stock = yf.Ticker(ticker)
+    hist = stock.history(period=period)
+    return hist['Close']
+
+# Function to normalize a pandas series
+def normalize(series):
+    if len(series.unique()) > 1:  # Check if the series has more than one unique value
+        scaler = MinMaxScaler(feature_range=(0, 1))
+        scaled_values = scaler.fit_transform(series.values.reshape(-1,1))
+        return pd.Series(scaled_values.flatten(), index=series.index)
+    else:
+        return series  # If the series has only one unique value, return it as is
+
+
+# Function to get the trend of a given sector or industry
+def get_trend_from_csv(df, column, value, period='1mo'):
+    # Filter the dataframe by the given sector or industry
+    df_filtered = df[df[column] == value]
+    # Calculate the mean of the closing prices of all stocks in the sector or industry
+    trend = df_filtered.resample(period).mean()
+    return trend
 
 def get_news(ticker):
     url = finviz_url + ticker
@@ -103,43 +140,103 @@ def plot_daily_sentiment(parsed_and_scored_news, ticker):
     fig = px.bar(mean_scores, x=mean_scores.index, y='sentiment_score', title = ticker + ' Daily Sentiment Scores')
     return fig # instead of using fig.show(), we return fig and turn it into a graphjson object for displaying in web page later
 
-# for extracting data from finviz
-finviz_url = 'https://finviz.com/quote.ashx?t='
-
+# Streamlit app
+st.set_page_config(page_title = "Stock Trend and News Sentiment Analyzer", layout = "wide")
 
 st.header("Stock News Sentiment Analyzer")
 
 ticker = st.text_input('Enter Stock Ticker', '').upper()
 
-df = pd.DataFrame({'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.
-        Adapted from https://github.com/damianboh/stock_sentiment_streamlit
-		""".format(ticker)
-		
-	st.write(description)	 
-	st.table(parsed_and_scored_news)
-	
-except Exception as e:
-	print(str(e))
-	st.write("Enter a stock ticker, e.g. 'AAPL' above and hit Enter.")	
+uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+if uploaded_file is not None:
+    data = pd.read_csv(uploaded_file)
+
+    try:
+        # Display company name, last close, and sector from CSV
+        company_name = data.loc[data['Ticker'] == ticker, 'Description'].values[0]
+        last_close = data.loc[data['Ticker'] == ticker, 'Price'].values[0]
+        csv_sector = data.loc[data['Ticker'] == ticker, 'Sector'].values[0]
+        st.write(f"Company: {company_name} ({csv_sector})")
+        st.write(f"Last Close: {last_close}")
+
+
+        # Define a list of all possible sectors and their corresponding ETFs
+        all_sectors = ['XLY', 'XLP', 'XLE', 'XLF', 'XLV', 'XLI', 'XLB', 'XLRE', 'XLK', 'XLU', 'XLC']
+        sector_mapping = {
+            'XLY': 'Consumer Discretionary',
+            'XLP': 'Consumer Staples',
+            'XLE': 'Energy',
+            'XLF': 'Financials',
+            'XLV': 'Health Care',
+            'XLI': 'Industrials',
+            'XLB': 'Materials',
+            'XLRE': 'Real Estate',
+            'XLK': 'Technology',
+            'XLU': 'Utilities',
+            'XLC': 'Communication Services'
+        }
+
+        # Get sector from CSV
+        sector = data.loc[data['Ticker'] == ticker, 'Sector'].values[0]
+
+        # If the sector is not found in the list of all sectors, set it to '--Not Found--'
+        if sector not in sector_mapping.values():
+            sector = '--Not Found--'
+        else:
+            # Convert the sector to its corresponding ETF
+            sector = list(sector_mapping.keys())[list(sector_mapping.values()).index(sector)]
+
+        # Display a dropdown menu for the sector with the current sector selected by default
+        sector = st.selectbox('Sector', options=all_sectors, index=all_sectors.index(sector) if sector in all_sectors else 0)
+
+        # Display the sector mapping table
+        st.table(pd.DataFrame(list(sector_mapping.items()), columns=['ETF', 'Sector']))
+
+        if st.button('Submit'):
+            # Get trends
+            stock_trend = get_trend(ticker)
+            sector_trend = get_trend(sector)
+
+            # Normalize trends
+            scaler = MinMaxScaler()
+            stock_trend = pd.DataFrame(scaler.fit_transform(stock_trend.values.reshape(-1,1)), index=stock_trend.index, columns=['Close'])
+            sector_trend = pd.DataFrame(scaler.fit_transform(sector_trend.values.reshape(-1,1)), index=sector_trend.index, columns=['Close'])
+
+            # Plot trends
+            plt.figure(figsize=(12,6))
+            plt.plot(stock_trend.index, stock_trend.values, label=ticker)
+            plt.plot(sector_trend.index, sector_trend.values, label=sector)
+            plt.legend()
+            plt.grid(True)
+            plt.title('Stock and Sector Trend over the past 30 days')
+            st.pyplot(plt)
+
+            st.subheader("Hourly and Daily Sentiment of {} Stock".format(ticker))
+            news_table = get_news(ticker)
+            parsed_news_df = parse_news(news_table)
+            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.
+                Adapted from https://github.com/damianboh/stock_sentiment_streamlit
+                """.format(ticker)
+                
+            st.write(description)     
+            st.table(parsed_and_scored_news)
+        
+    except Exception as e:
+        print(str(e))
+        st.write("Enter a stock ticker, e.g. 'AAPL' above and hit Enter.")  
+else:
+    st.write("Please upload a CSV file.")
 
 hide_streamlit_style = """
 <style>
@@ -150,4 +247,5 @@ footer {visibility: hidden;}
 st.markdown(hide_streamlit_style, unsafe_allow_html=True) 
 
 
-# streamlit run "c:/Dropbox/BIMWERX/_work/YouTube/elephant/230711 - Stock Sentiment/src/stock_sentiment_streamlit/app.py"
+
+# streamlit run "c:/Dropbox/BIMWERX/_work/YouTube/elephant/230701-10 - ML Predict/src/trend_sentiment.py"