Upload 3 files

data_processor.py

@@ -0,0 +1,41 @@
+import pandas as pd
+import os
+from dotenv import load_dotenv  
+load_dotenv()
+import groq
+groq.api_key = os.getenv("GROQ_API_KEY")
+from agno.agent import Agent
+from agno.models.groq import Groq
+from agno.tools.yfinance import YFinanceTools
+from agno.tools.duckduckgo import DuckDuckGoTools
+from agents.finance_agent import FinanceAgent
+from agents.web_search_agent import WebSearchAgent
+from agents.multi_agent import MultiAgent
+import matplotlib.pyplot as plt
+from textblob import TextBlob
+from agents.finance_agent import FinanceAgent   
+def fetch_financial_data(ticker_symbol):
+    import yfinance as yf
+    ticker = yf.Ticker(ticker_symbol)
+    return ticker
+
+def clean_data(data):
+    if isinstance(data, pd.DataFrame):
+        return data.dropna()
+    return data
+
+def fetch_and_clean_news(ticker_symbol):
+    ticker = fetch_financial_data(ticker_symbol)
+    news_items = ticker.news
+    cleaned_news = [item for item in news_items if item.get('content')]
+    return cleaned_news
+
+def extract_fundamentals(ticker_symbol):
+    ticker = fetch_financial_data(ticker_symbol)
+    fundamentals = {
+        "longName": ticker.info.get('longName', ticker_symbol),
+        "marketCap": ticker.info.get('marketCap'),
+        "peRatio": ticker.info.get('forwardPE'),
+        "dividendYield": ticker.info.get('dividendYield')
+    }
+    return clean_data(fundamentals)

sentiment_analyzer.py

@@ -0,0 +1,48 @@
+from transformers import pipeline
+from rapidfuzz.fuzz import partial_ratio
+import yfinance as yf
+import pandas as pd
+
+def analyze_headline_sentiment(headlines):
+    sentiment_pipeline = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment-latest")
+    results = []
+    for headline in headlines:
+        sentiment = sentiment_pipeline(headline)[0]
+        results.append({
+            "headline": headline,
+            "sentiment": sentiment['label'],
+            "score": sentiment['score']
+        })
+    return pd.DataFrame(results)
+
+def filter_news_by_sentiment(ticker_symbol, news_items, fuzzy_threshold=60):
+    ticker = yf.Ticker(ticker_symbol)
+    company_name = ticker.info.get('longName', ticker_symbol)
+    
+    def extract_text(item):
+        content = item.get('content', '')
+        if isinstance(content, dict):
+            return content.get('title', str(content))
+        elif isinstance(content, str):
+            return content
+        else:
+            return str(content)
+
+    filtered_news = []
+    for item in news_items:
+        text = extract_text(item)
+        text_lower = text.lower()
+        ticker_present = ticker_symbol.lower() in text_lower
+        similarity = partial_ratio(company_name.lower(), text_lower)
+        if ticker_present or similarity >= fuzzy_threshold:
+            filtered_news.append(text)
+
+    if len(filtered_news) < 5:
+        for item in news_items:
+            text = extract_text(item)
+            if text not in filtered_news:
+                filtered_news.append(text)
+            if len(filtered_news) >= 5:
+                break
+
+    return filtered_news[:7]  # Return top 7 headlines

visualization.py

@@ -0,0 +1,26 @@
+def plot_historical_prices(hist_data, ticker_symbol):
+    import matplotlib.pyplot as plt
+
+    plt.figure(figsize=(10, 5))
+    plt.plot(hist_data.index, hist_data['Close'], label=f"{ticker_symbol} Close Price", color="blue")
+    plt.title(f"{ticker_symbol} Historical Closing Prices (Last 6 Months)")
+    plt.xlabel("Date")
+    plt.ylabel("Price (USD)")
+    plt.legend()
+    plt.grid(True)
+    plt.tight_layout()
+    plt.show()
+
+def plot_sentiment_analysis(sentiment_df):
+    import matplotlib.pyplot as plt
+
+    sentiment_counts = sentiment_df['sentiment'].value_counts()
+    plt.figure(figsize=(8, 5))
+    sentiment_counts.plot(kind='bar', color=['green', 'red', 'gray'])
+    plt.title("Sentiment Analysis of News Headlines")
+    plt.xlabel("Sentiment")
+    plt.ylabel("Count")
+    plt.xticks(rotation=0)
+    plt.grid(axis='y')
+    plt.tight_layout()
+    plt.show()