Update app.py

app.py

@@ -11,6 +11,9 @@ import tempfile
 import os
 import spaces
 import pandas as pd
+import numpy as np
+from scipy import stats
+import seaborn as sns
 
 # Configure logging
 logging.basicConfig(filename='debug.log', level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -43,123 +46,71 @@ def fetch_stock_data(ticker='TSLA', start='2010-01-01', end=None, interval='1d')
         data = stock.history(start=start, end=end, interval=interval)
         if data.empty:
             logging.warning(f"No data fetched for {ticker} in the range {start} to {end}")
-            return pd.DataFrame()  # Return empty DataFrame instead of raising an exception
+            return pd.DataFrame()
         logging.debug(f"Fetched data with {len(data)} rows")
         return data
     except Exception as e:
         logging.error(f"Error fetching data: {e}")
-        return pd.DataFrame()  # Return empty DataFrame on any exception
+        return pd.DataFrame()
 
 def create_stock_chart(data, ticker, filename='chart.png', timeframe='1d', indicators=None):
-    try:
-        logging.debug(f"Creating chart for {ticker} with timeframe {timeframe} and saving to {filename}")
-        title = f"{ticker.upper()} Price Data (Timeframe: {timeframe})"
-
-        plt.rcParams["axes.titlesize"] = 10
-        my_style = mpf.make_mpf_style(base_mpf_style='charles')
-
-        # Calculate indicators if selected
-        addplot = []
-        if indicators:
-            if 'RSI' in indicators:
-                delta = data['Close'].diff(1)
-                gain = delta.where(delta > 0, 0)
-                loss = -delta.where(delta < 0, 0)
-                avg_gain = gain.rolling(window=14).mean()
-                avg_loss = loss.rolling(window=14).mean()
-                rs = avg_gain / avg_loss
-                rsi = 100 - (100 / (1 + rs))
-                addplot.append(mpf.make_addplot(rsi, panel=2, color='orange', ylabel='RSI'))
-            if 'SMA21' in indicators:
-                logging.debug("Calculating SMA 21")
-                sma_21 = data['Close'].rolling(window=21).mean()
-                addplot.append(mpf.make_addplot(sma_21, color='purple', linestyle='dashed'))
-            if 'SMA50' in indicators:
-                logging.debug("Calculating SMA 50")
-                sma_50 = data['Close'].rolling(window=50).mean()
-                addplot.append(mpf.make_addplot(sma_50, color='orange', linestyle='dashed'))
-            if 'SMA200' in indicators:
-                logging.debug("Calculating SMA 200")
-                sma_200 = data['Close'].rolling(window=200).mean()
-                addplot.append(mpf.make_addplot(sma_200, color='brown', linestyle='dashed'))
-            if 'VWAP' in indicators:
-                logging.debug("Calculating VWAP")
-                vwap = (data['Volume'] * (data['High'] + data['Low'] + data['Close']) / 3).cumsum() / data['Volume'].cumsum()
-                addplot.append(mpf.make_addplot(vwap, color='blue', linestyle='dashed'))
-            if 'Bollinger Bands' in indicators:
-                logging.debug("Calculating Bollinger Bands")
-                sma = data['Close'].rolling(window=20).mean()
-                std = data['Close'].rolling(window=20).std()
-                upper_band = sma + (std * 2)
-                lower_band = sma - (std * 2)
-                addplot.append(mpf.make_addplot(upper_band, color='green', linestyle='dashed'))
-                addplot.append(mpf.make_addplot(lower_band, color='green', linestyle='dashed'))
-
-        fig, axlist = mpf.plot(data, type='candle', style=my_style, volume=True, addplot=addplot, returnfig=True)
-        fig.suptitle(title, y=0.98)
-
-        # Save chart image
-        fig.savefig(filename, dpi=300)
-        plt.close(fig)
-
-        # Open and add financial data to the image
-        image = Image.open(filename)
-        draw = ImageDraw.Draw(image)
-        font = ImageFont.load_default()  # Use default font, you can also use custom fonts if available
-
-        # Financial metrics to add
-        metrics = {
-            "Ticker": ticker,
-            "Latest Close": f"${data['Close'].iloc[-1]:,.2f}",
-            "Volume": f"{data['Volume'].iloc[-1]:,.0f}"
-        }
-
-        # Add additional metrics if indicators are present
-        if 'SMA21' in indicators:
-            metrics["SMA 21"] = f"${data['Close'].rolling(window=21).mean().iloc[-1]:,.2f}"
-        if 'SMA50' in indicators:
-            metrics["SMA 50"] = f"${data['Close'].rolling(window=50).mean().iloc[-1]:,.2f}"
-        if 'SMA200' in indicators:
-            metrics["SMA 200"] = f"${data['Close'].rolling(window=200).mean().iloc[-1]:,.2f}"
-
-        # Draw metrics on the image
-        y_text = image.height - 50  # Starting y position for text
-        for key, value in metrics.items():
-            text = f"{key}: {value}"
-            draw.text((10, y_text), text, font=font, fill=(255, 255, 255))  # White color text
-            y_text += 20
-
-        # Resize image
-        new_size = (image.width * 3, image.height * 3)
-        resized_image = image.resize(new_size, Image.LANCZOS)
-        resized_image.save(filename)
-
-        logging.debug(f"Resized image with timeframe {timeframe} and ticker {ticker} saved to {filename}")
-    except Exception as e:
-        logging.error(f"Error creating or resizing chart: {e}")
-        raise
+    # ... (keep the existing create_stock_chart function as is) ...
 
 def combine_images(image_paths, output_path='combined_chart.png'):
-    try:
-        logging.debug(f"Combining images {image_paths} into {output_path}")
-        images = [Image.open(path) for path in image_paths]
-
-        # Calculate total width and max height for combined image
-        total_width = sum(img.width for img in images)
-        max_height = max(img.height for img in images)
-
-        combined_image = Image.new('RGB', (total_width, max_height))
-        x_offset = 0
-        for img in images:
-            combined_image.paste(img, (x_offset, 0))
-            x_offset += img.width
-
-        combined_image.save(output_path)
-        logging.debug(f"Combined image saved to {output_path}")
-        return output_path
-    except Exception as e:
-        logging.error(f"Error combining images: {e}")
-        raise
+    # ... (keep the existing combine_images function as is) ...
+
+def perform_trend_analysis(data):
+    # Perform trend analysis
+    close_prices = data['Close']
+    time_index = np.arange(len(close_prices))
+    slope, intercept, r_value, p_value, std_err = stats.linregress(time_index, close_prices)
+    
+    trend_line = slope * time_index + intercept
+    
+    plt.figure(figsize=(12, 6))
+    plt.plot(close_prices.index, close_prices, label='Close Price')
+    plt.plot(close_prices.index, trend_line, color='red', label='Trend Line')
+    plt.title('Trend Analysis')
+    plt.xlabel('Date')
+    plt.ylabel('Price')
+    plt.legend()
+    
+    trend_filename = 'trend_analysis.png'
+    plt.savefig(trend_filename)
+    plt.close()
+    
+    trend_strength = abs(r_value)
+    trend_direction = "upward" if slope > 0 else "downward"
+    
+    analysis_text = f"Trend Analysis:\n"
+    analysis_text += f"The stock shows a {trend_direction} trend.\n"
+    analysis_text += f"Trend strength (R-squared): {trend_strength:.2f}\n"
+    analysis_text += f"Slope: {slope:.4f}\n"
+    
+    return analysis_text, trend_filename
+
+def perform_correlation_analysis(data_dict):
+    # Perform correlation analysis
+    combined_data = pd.DataFrame({ticker: data['Close'] for ticker, data in data_dict.items()})
+    correlation_matrix = combined_data.corr()
+    
+    plt.figure(figsize=(10, 8))
+    sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1, center=0)
+    plt.title('Correlation Analysis')
+    
+    corr_filename = 'correlation_analysis.png'
+    plt.savefig(corr_filename)
+    plt.close()
+    
+    analysis_text = f"Correlation Analysis:\n"
+    for i in range(len(correlation_matrix.columns)):
+        for j in range(i+1, len(correlation_matrix.columns)):
+            ticker1 = correlation_matrix.columns[i]
+            ticker2 = correlation_matrix.columns[j]
+            corr = correlation_matrix.iloc[i, j]
+            analysis_text += f"Correlation between {ticker1} and {ticker2}: {corr:.2f}\n"
+    
+    return analysis_text, corr_filename
 
 def gradio_interface(ticker1, ticker2, ticker3, ticker4, start_date, end_date, query, analysis_type, interval, indicators):
     try:
@@ -167,12 +118,14 @@ def gradio_interface(ticker1, ticker2, ticker3, ticker4, start_date, end_date, q
 
         tickers = [ticker1, ticker2, ticker3, ticker4]
         chart_paths = []
+        data_dict = {}
 
         for i, ticker in enumerate(tickers):
             if ticker:
                 data = fetch_stock_data(ticker, start=start_date, end=end_date, interval=interval)
                 if data.empty:
                     return f"No data available for {ticker} in the specified date range.", None
+                data_dict[ticker] = data
                 with tempfile.NamedTemporaryFile(delete=False, suffix='.png') as temp_chart:
                     chart_path = temp_chart.name
                     create_stock_chart(data, ticker, chart_path, timeframe=interval, indicators=indicators)
@@ -184,13 +137,26 @@ def gradio_interface(ticker1, ticker2, ticker3, ticker4, start_date, end_date, q
                 combine_images(chart_paths, combined_chart_path)
                 insights = predict(Image.open(combined_chart_path), query)
                 return insights, combined_chart_path
-
-        # No comparative analysis, just return the single chart
-        if chart_paths:
-            insights = predict(Image.open(chart_paths[0]), query)
-            return insights, chart_paths[0]
+        elif analysis_type == 'Trend Analysis':
+            if len(data_dict) > 0:
+                first_ticker = list(data_dict.keys())[0]
+                analysis_text, trend_chart = perform_trend_analysis(data_dict[first_ticker])
+                return analysis_text, trend_chart
+            else:
+                return "No data available for trend analysis.", None
+        elif analysis_type == 'Correlation Analysis':
+            if len(data_dict) > 1:
+                analysis_text, corr_chart = perform_correlation_analysis(data_dict)
+                return analysis_text, corr_chart
+            else:
+                return "At least two tickers are required for correlation analysis.", None
         else:
-            return "No tickers provided.", None
+            # Single ticker analysis
+            if chart_paths:
+                insights = predict(Image.open(chart_paths[0]), query)
+                return insights, chart_paths[0]
+            else:
+                return "No tickers provided.", None
     except Exception as e:
         logging.error(f"Error in Gradio interface: {e}")
         return f"Error processing image or query: {e}", None
@@ -198,42 +164,46 @@ def gradio_interface(ticker1, ticker2, ticker3, ticker4, start_date, end_date, q
 def gradio_app():
     with gr.Blocks() as demo:
         gr.Markdown("""
-        ## 📈Stock Analysis Dashboard
+        ## 📈 Advanced Stock Analysis Dashboard
 
         This application provides a comprehensive stock analysis tool that allows users to input up to four stock tickers, specify date ranges, and select various financial indicators. The core functionalities include:
 
         1. **Data Fetching and Chart Creation**: Historical stock data is fetched from Yahoo Finance, and candlestick charts are generated with optional financial indicators like RSI, SMA, VWAP, and Bollinger Bands.
 
-        2. **Text Analysis and Insights Generation**: The application uses a pre-trained model based on the **Paligema** architecture to analyze the input chart and text query, generating insightful analysis based on the provided financial data and context.
+        2. **Text Analysis and Insights Generation**: The application uses a pre-trained model based on the Paligema architecture to analyze the input chart and text query, generating insightful analysis based on the provided financial data and context.
+
+        3. **Trend Analysis**: Performs trend analysis on a single stock, showing the trend line and providing information about the trend strength and direction.
+
+        4. **Correlation Analysis**: Analyzes the correlation between multiple stocks, providing a correlation matrix and heatmap.
 
-        3. **User Interface**: Users can interactively select stocks, date ranges, intervals, and indicators. The app also supports the analysis of single tickers or comparative analysis across multiple tickers.
+        5. **User Interface**: Users can interactively select stocks, date ranges, intervals, and indicators. The app supports single ticker analysis, comparative analysis, trend analysis, and correlation analysis.
 
-        4. **Logging and Debugging**: Detailed logging helps in debugging and tracking the application's processes.
+        6. **Logging and Debugging**: Detailed logging helps in debugging and tracking the application's processes.
 
-        5. **Enhanced Image Processing**: The app adds financial metrics and annotations to the generated charts, ensuring clear presentation of data.
+        7. **Enhanced Image Processing**: The app adds financial metrics and annotations to the generated charts, ensuring clear presentation of data.
 
-        This tool leverages the Paligema model to provide detailed insights into stock market trends, offering an interactive and educational experience for users.
+        This tool leverages various analysis techniques to provide detailed insights into stock market trends, offering an interactive and educational experience for users.
         """)
 
         with gr.Row():
-            ticker1 = gr.Textbox(label="Primary Ticker", value="GC=F")
-            ticker2 = gr.Textbox(label="Secondary Ticker", value="CL=F")
-            ticker3 = gr.Textbox(label="Third Ticker", value="SPY")
-            ticker4 = gr.Textbox(label="Fourth Ticker", value="EURUSD=X")
+            ticker1 = gr.Textbox(label="Primary Ticker", value="AAPL")
+            ticker2 = gr.Textbox(label="Secondary Ticker", value="MSFT")
+            ticker3 = gr.Textbox(label="Third Ticker", value="GOOGL")
+            ticker4 = gr.Textbox(label="Fourth Ticker", value="AMZN")
 
         with gr.Row():
             start_date = gr.Textbox(label="Start Date", value="2022-01-01")
             end_date = gr.Textbox(label="End Date", value=datetime.date.today().isoformat())
-            interval = gr.Dropdown(label="Interval", choices=['1m', '2m', '5m', '15m', '30m', '60m', '90m', '1h', '1d', '5d', '1wk', '1mo', '3mo'], value='1d')
+            interval = gr.Dropdown(label="Interval", choices=['1d', '5d', '1wk', '1mo', '3mo'], value='1d')
 
         with gr.Row():
             indicators = gr.CheckboxGroup(label="Indicators", choices=['RSI', 'SMA21', 'SMA50', 'SMA200', 'VWAP', 'Bollinger Bands'], value=['SMA21', 'SMA50'])
-            analysis_type = gr.Radio(label="Analysis Type", choices=['Single Ticker', 'Comparative Analysis'], value='Single Ticker')
+            analysis_type = gr.Radio(label="Analysis Type", choices=['Single Ticker', 'Comparative Analysis', 'Trend Analysis', 'Correlation Analysis'], value='Single Ticker')
 
         query = gr.Textbox(label="Analysis Query", value="Analyze the price trends.")
         analyze_button = gr.Button("Analyze")
-        output_image = gr.Image(label="Stock Chart")
-        output_text = gr.Textbox(label="Generated Insights", lines=5)
+        output_image = gr.Image(label="Analysis Chart")
+        output_text = gr.Textbox(label="Generated Insights", lines=10)
 
         analyze_button.click(
             fn=gradio_interface,