Update app.py

Added the News from NEWAPI + fetching Technical data from yf and then TA from Pandas TA. Integrated this code with the Gradio app for implementation on Huggingface.

app.py

@@ -1,64 +1,104 @@
+import os
+import asyncio
+import logging
+from datetime import datetime, timedelta
+from newsapi.newsapi_client import NewsApiClient
+from textblob import TextBlob
+import yfinance as yf
+import pandas as pd
+import ta
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
+# Set up logging
+logging.basicConfig(level=logging.WARNING, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Retrieve API key from environment variables
+NEWSAPI_KEY = os.getenv("NEWSAPI_KEY")
+
+# Fetch financial news
+def fetch_financial_news(stock_symbol=None, page_size=5, days=2):
+    try:
+        newsapi = NewsApiClient(api_key=NEWSAPI_KEY)
+        query = stock_symbol if stock_symbol else "financial news"
+        end_date = datetime.now()
+        start_date = end_date - timedelta(days=days)
+
+        articles = newsapi.get_everything(
+            q=query,
+            language='en',
+            from_param=start_date.strftime('%Y-%m-%d'),
+            to=end_date.strftime('%Y-%m-%d'),
+            sort_by='publishedAt',
+            page_size=page_size
+        )
+
+        results = []
+        for article in articles.get('articles', []):
+            title = article.get('title', '[Title Unavailable]')
+            description = article.get('description', '[Description Unavailable]')
+            url = article.get('url', 'URL Unavailable')
+            results.append(f"Title: {title}\nDescription: {description}\nURL: {url}")
+
+        return "\n\n".join(results)
+    except Exception as e:
+        return f"Error fetching news: {e}"
+
+# Perform sentiment analysis
+def analyze_sentiment(text):
+    try:
+        analysis = TextBlob(text)
+        polarity = analysis.sentiment.polarity
+        if polarity > 0.1:
+            return "Positive"
+        elif polarity < -0.1:
+            return "Negative"
+        else:
+            return "Neutral"
+    except Exception as e:
+        return f"Error analyzing sentiment: {e}"
+
+# Fetch technical data
+def fetch_technical_data(stock_symbol):
+    try:
+        stock = yf.Ticker(stock_symbol)
+        data = stock.history(period="1y")
+
+        if data.empty:
+            return "No data found for this stock symbol."
+
+        data['RSI'] = ta.momentum.RSIIndicator(data['Close']).rsi()
+        macd = ta.trend.MACD(data['Close'])
+        data['MACD'] = macd.macd()
+        data['MACD_Signal'] = macd.macd_signal()
+        data['SMA_50'] = data['Close'].rolling(window=50).mean()
+        data['SMA_200'] = data['Close'].rolling(window=200).mean()
+
+        latest_technical_data = {
+            "RSI": data['RSI'].iloc[-1],
+            "MACD": data['MACD'].iloc[-1],
+            "MACD Signal": data['MACD_Signal'].iloc[-1],
+            "50 Day SMA": data['SMA_50'].iloc[-1],
+            "200 Day SMA": data['SMA_200'].iloc[-1],
+        }
+
+        return pd.Series(latest_technical_data).to_string()
+    except Exception as e:
+        return f"Error fetching technical data: {e}"
+
+# Define Gradio interface
+def analyze_stock(stock_symbol):
+    news = fetch_financial_news(stock_symbol)
+    technical_data = fetch_technical_data(stock_symbol)
+    return news, technical_data
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Financial News and Technical Analysis Tool")
+    stock_input = gr.Textbox(label="Enter Stock Symbol (e.g., AAPL, TSLA)")
+    news_output = gr.Textbox(label="Financial News", interactive=False)
+    tech_output = gr.Textbox(label="Technical Analysis", interactive=False)
+    analyze_button = gr.Button("Analyze")
+
+    analyze_button.click(analyze_stock, inputs=[stock_input], outputs=[news_output, tech_output])
 
 if __name__ == "__main__":
     demo.launch()