Update app.py

app.py

@@ -6,6 +6,17 @@ from transformers import pipeline
 import plotly.express as px
 from datetime import datetime, timedelta
 
+# Load the Excel file with company names and symbols
+file_path = '/Top 2000 Valued Companies with Ticker Symbols.xlsx'
+companies_df = pd.read_excel(file_path)
+
+# Function to get stock symbol for a company name
+def get_stock_symbol(company_name):
+    match = companies_df[companies_df['Name'].str.contains(company_name, case=False, na=False)]
+    if not match.empty:
+        return match.iloc[0]['Symbol']
+    return None
+
 # Sentiment Analysis Model
 sentiment_model = pipeline(model="finiteautomata/bertweet-base-sentiment-analysis")
 
@@ -52,31 +63,24 @@ def analyze_sentiment(text):
     result = sentiment_model(text)[0]
     return result['label'], result['score']
 
-# Function to fetch stock data from Alpha Vantage API
-def fetch_stock_data(company_name):
+# Function to fetch stock data
+def fetch_stock_data(symbol):
     url = "https://alpha-vantage.p.rapidapi.com/query"
-    querystring = {"function": "TIME_SERIES_DAILY", "symbol": company_name, "outputsize": "compact", "datatype": "json"}
+    querystring = {"function":"TIME_SERIES_DAILY", "symbol":symbol, "outputsize":"compact", "datatype":"json"}
     headers = {
         "x-rapidapi-key": "e078dae417mshb13ddc2d8149768p1608e9jsn888ce49e8554",
         "x-rapidapi-host": "alpha-vantage.p.rapidapi.com"
     }
-    
-    try:
-        response = requests.get(url, headers=headers, params=querystring)
-        response.raise_for_status()
-        data = response.json()
-    except requests.RequestException as e:
-        print(f"Error fetching stock data: {e}")
-        return None
+    response = requests.get(url, headers=headers, params=querystring)
+    data = response.json()
     
     if "Time Series (Daily)" not in data:
-        return None
+        return pd.DataFrame()
     
-    stock_data = data["Time Series (Daily)"]
-    df = pd.DataFrame.from_dict(stock_data, orient='index')
-    df.index = pd.to_datetime(df.index)
-    df = df.astype(float)
-    return df
+    stock_data = pd.DataFrame(data["Time Series (Daily)"]).T
+    stock_data.index = pd.to_datetime(stock_data.index)
+    stock_data.columns = ["Open", "High", "Low", "Close", "Volume"]
+    return stock_data
 
 # Main function to process news and perform analysis
 def news_and_analysis(query):
@@ -100,18 +104,14 @@ def news_and_analysis(query):
         labels={'Time': 'Publication Time', 'Sentiment_Score': 'Sentiment Score'}
     )
     
-    # Check if the input query is a company name (heuristic: if it's more than one word)
-    if len(query.split()) > 1:
-        stock_df = fetch_stock_data(query)
-        if stock_df is not None:
-            stock_fig = px.line(
-                stock_df,
-                x=stock_df.index,
-                y='4. close',
-                title=f'{query} Stock Price Over Time',
-                labels={'index': 'Date', '4. close': 'Closing Price'}
-            )
+    # Check if query is a company name and fetch stock data
+    stock_symbol = get_stock_symbol(query)
+    if stock_symbol:
+        stock_data = fetch_stock_data(stock_symbol)
+        if not stock_data.empty:
+            stock_fig = px.line(stock_data, x=stock_data.index, y='Close', title=f'{stock_symbol} Stock Price')
             return news_df, sentiment_fig, stock_fig
+    
     return news_df, sentiment_fig, None
 
 # Gradio interface
@@ -133,7 +133,7 @@ with gr.Blocks() as demo:
         with gr.Column():
             news_output = gr.DataFrame(label="News and Sentiment Analysis")
             sentiment_plot = gr.Plot(label="Sentiment Analysis")
-            stock_plot = gr.Plot(label="Stock Price Analysis")
+            stock_plot = gr.Plot(label="Stock Price Movement")
     
     analyze_btn.click(
         news_and_analysis,