{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.8.8"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":91844,"databundleVersionId":11361821,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Advanced Data Visualization Techniques for Kaggle Competitions\n\n## Introduction\n\nData visualization is a critical component of any data science project. Effective visualizations not only help in understanding the data better but also in communicating insights to others. In Kaggle competitions, high-quality visualizations can set your notebook apart, increase engagement, and help you earn badges and recognition.\n\nThis notebook demonstrates advanced visualization techniques using various Python libraries, focusing on creating impactful, interactive, and aesthetically pleasing visualizations. We'll use real-world datasets and show how to create visualizations that tell compelling stories about your data.","metadata":{}},{"cell_type":"markdown","source":"## Setup and Environment\n\nLet's start by importing the necessary libraries and setting up our environment.","metadata":{}},{"cell_type":"code","source":"# Import essential libraries\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.express as px\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\nimport plotly.io as pio\nimport matplotlib.colors as mcolors\nfrom matplotlib.colors import LinearSegmentedColormap\nimport matplotlib.patches as mpatches\nfrom matplotlib.gridspec import GridSpec\nimport warnings\nimport random\nfrom IPython.display import display, HTML\n\n# Set visualization styles\nplt.style.use('seaborn-whitegrid')\nsns.set_context(\"notebook\", font_scale=1.2)\nwarnings.filterwarnings('ignore')\n\n# Set random seed for reproducibility\nRANDOM_SEED = 42\nnp.random.seed(RANDOM_SEED)\nrandom.seed(RANDOM_SEED)\n\n# Set default plotly template\npio.templates.default = \"plotly_white\"\n\n# Display settings\npd.set_option('display.max_columns', None)\npd.set_option('display.max_rows', 100)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:48.630329Z","iopub.execute_input":"2025-05-25T23:36:48.630655Z","iopub.status.idle":"2025-05-25T23:36:48.656354Z","shell.execute_reply.started":"2025-05-25T23:36:48.630631Z","shell.execute_reply":"2025-05-25T23:36:48.655048Z"}},"outputs":[],"execution_count":12},{"cell_type":"markdown","source":"## Part 1: Creating Simulated Financial Market Data\n\nFor this notebook, we'll create a simulated financial dataset that includes stock prices, trading volumes, and market indicators. This will allow us to demonstrate various visualization techniques applicable to financial data analysis.","metadata":{}},{"cell_type":"code","source":"# Generate simulated stock market data\ndef generate_stock_data(n_days=1000, n_stocks=5, volatility=0.01, trend=0.0001):\n np.random.seed(RANDOM_SEED)\n \n # Create date range\n end_date = pd.Timestamp.now().floor('D')\n start_date = end_date - pd.Timedelta(days=n_days)\n dates = pd.date_range(start=start_date, end=end_date, freq='B') # Business days\n n_days = len(dates) # Adjust for business days\n \n # Stock names\n stock_names = [f'Stock_{chr(65+i)}' for i in range(n_stocks)]\n \n # Generate initial prices\n initial_prices = np.random.uniform(50, 200, n_stocks)\n \n # Generate price movements\n price_data = {}\n volume_data = {}\n market_cap_data = {}\n pe_ratio_data = {}\n \n for i, stock in enumerate(stock_names):\n # Set stock-specific parameters\n stock_volatility = volatility * (0.8 + 0.4 * np.random.random())\n stock_trend = trend * (-1 if np.random.random() < 0.3 else 1) * (0.5 + np.random.random())\n \n # Generate daily returns\n daily_returns = np.random.normal(stock_trend, stock_volatility, n_days)\n \n # Add some market-wide events\n # Market crash\n crash_idx = np.random.randint(int(n_days/4), int(3*n_days/4))\n crash_duration = np.random.randint(5, 15)\n daily_returns[crash_idx:crash_idx+crash_duration] -= np.linspace(0.03, 0, crash_duration)\n \n # Market rally\n rally_idx = np.random.randint(int(n_days/4), int(3*n_days/4))\n rally_duration = np.random.randint(5, 15)\n daily_returns[rally_idx:rally_idx+rally_duration] += np.linspace(0.02, 0, rally_duration)\n \n # Calculate cumulative returns\n cumulative_returns = np.cumprod(1 + daily_returns)\n \n # Calculate prices\n prices = initial_prices[i] * cumulative_returns\n \n # Generate trading volumes\n base_volume = np.random.randint(100000, 1000000)\n volumes = np.random.normal(base_volume, base_volume * 0.2, n_days)\n volumes = np.maximum(volumes, base_volume * 0.1) # Ensure positive volumes\n \n # Increase volume during high volatility periods\n volatility_periods = np.abs(daily_returns) > 1.5 * stock_volatility\n volumes[volatility_periods] *= 2\n \n # Calculate market cap (price * outstanding shares)\n outstanding_shares = np.random.randint(10000000, 100000000)\n market_caps = prices * outstanding_shares / 1000000 # In millions\n \n # Calculate P/E ratio (price / earnings per share)\n base_eps = initial_prices[i] / np.random.uniform(10, 30) # Base earnings per share\n eps_growth = np.random.uniform(-0.01, 0.02) # EPS growth rate\n eps = base_eps * np.cumprod(1 + np.random.normal(eps_growth, 0.005, n_days))\n pe_ratios = prices / eps\n \n # Store data\n price_data[stock] = prices\n volume_data[stock] = volumes\n market_cap_data[stock] = market_caps\n pe_ratio_data[stock] = pe_ratios\n \n # Create DataFrames\n price_df = pd.DataFrame(price_data, index=dates)\n volume_df = pd.DataFrame(volume_data, index=dates)\n market_cap_df = pd.DataFrame(market_cap_data, index=dates)\n pe_ratio_df = pd.DataFrame(pe_ratio_data, index=dates)\n \n # Create a market index\n market_weights = np.random.dirichlet(np.ones(n_stocks))\n market_index = (price_df * market_weights).sum(axis=1) / (price_df.iloc[0] * market_weights).sum()\n market_index = market_index * 1000 # Scale to start around 1000\n \n # Add market index to price DataFrame\n price_df['Market_Index'] = market_index\n \n return price_df, volume_df, market_cap_df, pe_ratio_df\n\n# Generate the data\nprice_df, volume_df, market_cap_df, pe_ratio_df = generate_stock_data(n_days=1000, n_stocks=5)\n\n# Display the first few rows of each DataFrame\nprint(\"Stock Prices:\")\ndisplay(price_df.head())\n\nprint(\"\\nTrading Volumes:\")\ndisplay(volume_df.head())\n\nprint(\"\\nMarket Capitalizations (in millions):\")\ndisplay(market_cap_df.head())\n\nprint(\"\\nP/E Ratios:\")\ndisplay(pe_ratio_df.head())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:48.658065Z","iopub.execute_input":"2025-05-25T23:36:48.658333Z","iopub.status.idle":"2025-05-25T23:36:48.72736Z","shell.execute_reply.started":"2025-05-25T23:36:48.658314Z","shell.execute_reply":"2025-05-25T23:36:48.726301Z"}},"outputs":[{"name":"stdout","text":"Stock Prices:\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":" Stock_A Stock_B Stock_C Stock_D Stock_E \\\n2022-08-29 107.612601 196.851259 159.804874 140.505234 73.663956 \n2022-08-30 108.310116 196.459142 161.420867 139.859372 74.213279 \n2022-08-31 107.856800 193.663155 159.914510 138.576194 74.992245 \n2022-09-01 108.346730 192.149669 158.623109 138.936771 76.096609 \n2022-09-02 107.898919 194.605383 158.230905 135.588912 76.042790 \n\n Market_Index \n2022-08-29 1000.000000 \n2022-08-30 1005.252029 \n2022-08-31 997.788087 \n2022-09-01 995.175234 \n2022-09-02 989.018191 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Stock_AStock_BStock_CStock_DStock_EMarket_Index
2022-08-29107.612601196.851259159.804874140.50523473.6639561000.000000
2022-08-30108.310116196.459142161.420867139.85937274.2132791005.252029
2022-08-31107.856800193.663155159.914510138.57619474.992245997.788087
2022-09-01108.346730192.149669158.623109138.93677176.096609995.175234
2022-09-02107.898919194.605383158.230905135.58891276.042790989.018191
\n
"},"metadata":{}},{"name":"stdout","text":"\nTrading Volumes:\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":" Stock_A Stock_B Stock_C Stock_D \\\n2022-08-29 327347.456459 215494.961899 593141.371550 8.173774e+05 \n2022-08-30 184654.939031 111831.137884 733500.488606 7.555574e+05 \n2022-08-31 253772.807902 81594.902544 438314.662769 1.439764e+06 \n2022-09-01 167682.467517 81225.052524 636232.068280 6.894729e+05 \n2022-09-02 276212.989461 121084.535734 569988.616449 1.887450e+06 \n\n Stock_E \n2022-08-29 203857.557427 \n2022-08-30 309900.404425 \n2022-08-31 319574.453843 \n2022-09-01 416783.425769 \n2022-09-02 258256.868306 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Stock_AStock_BStock_CStock_DStock_E
2022-08-29327347.456459215494.961899593141.3715508.173774e+05203857.557427
2022-08-30184654.939031111831.137884733500.4886067.555574e+05309900.404425
2022-08-31253772.80790281594.902544438314.6627691.439764e+06319574.453843
2022-09-01167682.46751781225.052524636232.0682806.894729e+05416783.425769
2022-09-02276212.989461121084.535734569988.6164491.887450e+06258256.868306
\n
"},"metadata":{}},{"name":"stdout","text":"\nMarket Capitalizations (in millions):\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":" Stock_A Stock_B Stock_C Stock_D Stock_E\n2022-08-29 2353.783738 16699.685585 11952.449936 6250.217003 848.362741\n2022-08-30 2369.040311 16666.420734 12073.316530 6221.486549 854.689107\n2022-08-31 2359.125038 16429.225898 11960.649998 6164.405812 863.660185\n2022-09-01 2369.841147 16300.830757 11864.060946 6180.445686 876.378769\n2022-09-02 2360.046305 16509.158907 11834.726440 6031.519942 875.758959","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Stock_AStock_BStock_CStock_DStock_E
2022-08-292353.78373816699.68558511952.4499366250.217003848.362741
2022-08-302369.04031116666.42073412073.3165306221.486549854.689107
2022-08-312359.12503816429.22589811960.6499986164.405812863.660185
2022-09-012369.84114716300.83075711864.0609466180.445686876.378769
2022-09-022360.04630516509.15890711834.7264406031.519942875.758959
\n
"},"metadata":{}},{"name":"stdout","text":"\nP/E Ratios:\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":" Stock_A Stock_B Stock_C Stock_D Stock_E\n2022-08-29 15.371392 15.552956 26.891293 19.201932 15.702969\n2022-08-30 15.327739 15.288368 27.362611 19.267715 15.707936\n2022-08-31 15.265835 14.913047 27.162983 19.219205 15.713498\n2022-09-01 15.221154 14.379838 26.781680 19.238995 16.038528\n2022-09-02 15.074047 14.422171 26.559687 18.863847 15.890443","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Stock_AStock_BStock_CStock_DStock_E
2022-08-2915.37139215.55295626.89129319.20193215.702969
2022-08-3015.32773915.28836827.36261119.26771515.707936
2022-08-3115.26583514.91304727.16298319.21920515.713498
2022-09-0115.22115414.37983826.78168019.23899516.038528
2022-09-0215.07404714.42217126.55968718.86384715.890443
\n
"},"metadata":{}}],"execution_count":13},{"cell_type":"markdown","source":"## Part 2: Advanced Time Series Visualization\n\n### 2.1 Interactive Stock Price Chart with Plotly\n\nLet's create an interactive stock price chart using Plotly. This will allow users to zoom, pan, and hover over data points to see detailed information.","metadata":{}},{"cell_type":"code","source":"# Create an interactive stock price chart\ndef plot_interactive_stock_prices(price_df, title=\"Stock Price Performance\"):\n # Reset index to make date a column\n df_reset = price_df.reset_index()\n df_reset = df_reset.rename(columns={'index': 'Date'})\n \n # Melt the DataFrame for Plotly\n df_melted = pd.melt(df_reset, id_vars=['Date'], value_vars=price_df.columns, \n var_name='Stock', value_name='Price')\n \n # Create the figure\n fig = px.line(df_melted, x='Date', y='Price', color='Stock', \n title=title,\n labels={'Price': 'Stock Price ($)', 'Date': 'Date'},\n height=600)\n \n # Customize the layout\n fig.update_layout(\n hovermode=\"x unified\",\n legend=dict(orientation=\"h\", yanchor=\"bottom\", y=1.02, xanchor=\"right\", x=1),\n margin=dict(l=20, r=20, t=60, b=20),\n xaxis=dict(title_font=dict(size=14), tickfont=dict(size=12)),\n yaxis=dict(title_font=dict(size=14), tickfont=dict(size=12)),\n title=dict(font=dict(size=18))\n )\n \n # Add range slider and buttons\n fig.update_xaxes(\n rangeslider_visible=True,\n rangeselector=dict(\n buttons=list([\n dict(count=1, label=\"1m\", step=\"month\", stepmode=\"backward\"),\n dict(count=6, label=\"6m\", step=\"month\", stepmode=\"backward\"),\n dict(count=1, label=\"YTD\", step=\"year\", stepmode=\"todate\"),\n dict(count=1, label=\"1y\", step=\"year\", stepmode=\"backward\"),\n dict(step=\"all\")\n ])\n )\n )\n \n return fig\n\n# Plot the stock prices\nfig_stock_prices = plot_interactive_stock_prices(price_df)\nfig_stock_prices.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:48.728251Z","iopub.execute_input":"2025-05-25T23:36:48.728485Z","iopub.status.idle":"2025-05-25T23:36:48.85922Z","shell.execute_reply.started":"2025-05-25T23:36:48.728469Z","shell.execute_reply":"2025-05-25T23:36:48.858074Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":14},{"cell_type":"markdown","source":"### 2.2 Candlestick Chart with Volume\n\nNow, let's create a candlestick chart with volume bars for a single stock. This is a common visualization in financial analysis.","metadata":{}},{"cell_type":"code","source":"# Create a candlestick chart with volume for a single stock\ndef plot_candlestick_with_volume(price_df, volume_df, stock_name, days=120):\n # Get the data for the selected stock\n stock_prices = price_df[stock_name].iloc[-days:]\n stock_volumes = volume_df[stock_name].iloc[-days:]\n \n # Calculate OHLC (Open, High, Low, Close)\n # For simulation, we'll create synthetic OHLC data from daily prices\n dates = stock_prices.index\n opens = stock_prices.values\n closes = np.roll(stock_prices.values, -1)\n closes[-1] = opens[-1] * (1 + np.random.normal(0, 0.01)) # Last close\n \n # Generate random intraday volatility\n volatility = np.abs(closes - opens) * 1.5\n highs = np.maximum(opens, closes) + volatility * np.random.random(len(opens))\n lows = np.minimum(opens, closes) - volatility * np.random.random(len(opens))\n \n # Create a DataFrame for OHLC data\n ohlc_df = pd.DataFrame({\n 'Date': dates,\n 'Open': opens,\n 'High': highs,\n 'Low': lows,\n 'Close': closes,\n 'Volume': stock_volumes.values\n })\n \n # Create subplots: 1 for candlestick, 1 for volume\n fig = make_subplots(rows=2, cols=1, shared_xaxes=True, \n vertical_spacing=0.02, \n row_heights=[0.7, 0.3])\n \n # Add candlestick chart\n fig.add_trace(\n go.Candlestick(\n x=ohlc_df['Date'],\n open=ohlc_df['Open'],\n high=ohlc_df['High'],\n low=ohlc_df['Low'],\n close=ohlc_df['Close'],\n name=stock_name\n ),\n row=1, col=1\n )\n \n # Add volume bar chart\n colors = ['red' if c < o else 'green' for c, o in zip(ohlc_df['Close'], ohlc_df['Open'])]\n fig.add_trace(\n go.Bar(\n x=ohlc_df['Date'],\n y=ohlc_df['Volume'],\n marker_color=colors,\n name='Volume'\n ),\n row=2, col=1\n )\n \n # Update layout\n fig.update_layout(\n title=f\"{stock_name} Stock Price and Volume (Last {days} Trading Days)\",\n xaxis_title=\"Date\",\n yaxis_title=\"Price ($)\",\n yaxis2_title=\"Volume\",\n height=800,\n xaxis_rangeslider_visible=False,\n hovermode=\"x unified\",\n legend=dict(orientation=\"h\", yanchor=\"bottom\", y=1.02, xanchor=\"right\", x=1),\n margin=dict(l=20, r=20, t=60, b=20),\n )\n \n # Update y-axes\n fig.update_yaxes(title_text=\"Price ($)\", row=1, col=1)\n fig.update_yaxes(title_text=\"Volume\", row=2, col=1)\n \n return fig\n\n# Plot candlestick chart for Stock_A\nfig_candlestick = plot_candlestick_with_volume(price_df, volume_df, 'Stock_A', days=90)\nfig_candlestick.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:48.860916Z","iopub.execute_input":"2025-05-25T23:36:48.861216Z","iopub.status.idle":"2025-05-25T23:36:48.916898Z","shell.execute_reply.started":"2025-05-25T23:36:48.861194Z","shell.execute_reply":"2025-05-25T23:36:48.915854Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":15},{"cell_type":"markdown","source":"### 2.3 Comparative Performance Visualization\n\nLet's create a visualization that shows the relative performance of each stock compared to the market index.","metadata":{}},{"cell_type":"code","source":"# Create a comparative performance chart\ndef plot_relative_performance(price_df, baseline='Market_Index', start_date=None):\n # Make a copy of the DataFrame\n df = price_df.copy()\n \n # Filter by start date if provided\n if start_date:\n df = df.loc[start_date:]\n \n # Calculate relative performance (normalized to 100 at the start)\n relative_df = df.div(df.iloc[0]) * 100\n \n # Reset index to make date a column\n relative_df_reset = relative_df.reset_index()\n relative_df_reset = relative_df_reset.rename(columns={'index': 'Date'})\n \n # Melt the DataFrame for Plotly\n df_melted = pd.melt(relative_df_reset, id_vars=['Date'], value_vars=relative_df.columns, \n var_name='Stock', value_name='Performance')\n \n # Create the figure\n fig = px.line(df_melted, x='Date', y='Performance', color='Stock', \n title=\"Relative Performance (Indexed to 100)\",\n labels={'Performance': 'Performance (Indexed to 100)', 'Date': 'Date'},\n height=600)\n \n # Add a horizontal line at 100\n fig.add_hline(y=100, line_dash=\"dash\", line_color=\"gray\")\n \n # Customize the layout\n fig.update_layout(\n hovermode=\"x unified\",\n legend=dict(orientation=\"h\", yanchor=\"bottom\", y=1.02, xanchor=\"right\", x=1),\n margin=dict(l=20, r=20, t=60, b=20),\n )\n \n # Add range slider and buttons\n fig.update_xaxes(\n rangeslider_visible=True,\n rangeselector=dict(\n buttons=list([\n dict(count=1, label=\"1m\", step=\"month\", stepmode=\"backward\"),\n dict(count=6, label=\"6m\", step=\"month\", stepmode=\"backward\"),\n dict(count=1, label=\"YTD\", step=\"year\", stepmode=\"todate\"),\n dict(count=1, label=\"1y\", step=\"year\", stepmode=\"backward\"),\n dict(step=\"all\")\n ])\n )\n )\n \n return fig\n\n# Plot relative performance\nfig_relative = plot_relative_performance(price_df)\nfig_relative.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:48.917712Z","iopub.execute_input":"2025-05-25T23:36:48.918022Z","iopub.status.idle":"2025-05-25T23:36:49.061101Z","shell.execute_reply.started":"2025-05-25T23:36:48.918002Z","shell.execute_reply":"2025-05-25T23:36:49.059896Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":16},{"cell_type":"markdown","source":"## Part 3: Advanced Statistical Visualizations\n\n### 3.1 Distribution Analysis with Violin Plots\n\nLet's analyze the distribution of daily returns for each stock using violin plots.","metadata":{}},{"cell_type":"code","source":"# Calculate daily returns\nreturns_df = price_df.pct_change().dropna()\n\n# Create a function for plotting return distributions\ndef plot_return_distributions(returns_df):\n # Prepare data for plotting\n returns_reset = returns_df.reset_index()\n returns_reset = returns_reset.rename(columns={'index': 'Date'})\n \n # Melt the DataFrame\n returns_melted = pd.melt(returns_reset, id_vars=['Date'], value_vars=[col for col in returns_df.columns if col != 'Market_Index'], \n var_name='Stock', value_name='Return')\n \n # Convert returns to percentage\n returns_melted['Return'] = returns_melted['Return'] * 100\n \n # Create violin plot\n fig = px.violin(returns_melted, x='Stock', y='Return', color='Stock',\n box=True, points=\"all\", title=\"Distribution of Daily Returns (%)\",\n height=600)\n \n # Add a horizontal line at 0\n fig.add_hline(y=0, line_dash=\"dash\", line_color=\"black\")\n \n # Update layout\n fig.update_layout(\n xaxis_title=\"Stock\",\n yaxis_title=\"Daily Return (%)\",\n legend_title=\"Stock\",\n margin=dict(l=20, r=20, t=60, b=20),\n )\n \n return fig\n\n# Plot return distributions\nfig_returns = plot_return_distributions(returns_df)\nfig_returns.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:49.06221Z","iopub.execute_input":"2025-05-25T23:36:49.062453Z","iopub.status.idle":"2025-05-25T23:36:49.158936Z","shell.execute_reply.started":"2025-05-25T23:36:49.062435Z","shell.execute_reply":"2025-05-25T23:36:49.157068Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":17},{"cell_type":"markdown","source":"### 3.2 Correlation Heatmap with Hierarchical Clustering\n\nLet's create a correlation heatmap with hierarchical clustering to visualize the relationships between different stocks.","metadata":{}},{"cell_type":"code","source":"# Create a correlation heatmap with hierarchical clustering\ndef plot_correlation_heatmap(returns_df):\n # Calculate correlation matrix\n corr_matrix = returns_df.corr()\n \n # Create a mask for the upper triangle\n mask = np.triu(np.ones_like(corr_matrix, dtype=bool))\n \n # Set up the matplotlib figure\n plt.figure(figsize=(12, 10))\n \n # Generate a custom diverging colormap\n cmap = sns.diverging_palette(230, 20, as_cmap=True)\n \n # Draw the heatmap with the mask and correct aspect ratio\n sns.heatmap(corr_matrix, mask=mask, cmap=cmap, vmax=1, vmin=-1, center=0,\n square=True, linewidths=.5, cbar_kws={\"shrink\": .5}, annot=True, fmt=\".2f\")\n \n plt.title('Correlation Matrix of Daily Returns with Hierarchical Clustering', fontsize=16)\n plt.tight_layout()\n plt.show()\n \n # Create a clustermap for hierarchical clustering\n plt.figure(figsize=(12, 10))\n cluster_grid = sns.clustermap(corr_matrix, cmap=cmap, vmax=1, vmin=-1, center=0,\n linewidths=.5, figsize=(12, 10), annot=True, fmt=\".2f\")\n \n plt.title('Hierarchical Clustering of Stock Correlations', fontsize=16)\n plt.tight_layout()\n plt.show()\n\n# Plot correlation heatmap\nplot_correlation_heatmap(returns_df.drop(columns=['Market_Index']))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:49.160278Z","iopub.execute_input":"2025-05-25T23:36:49.160625Z","iopub.status.idle":"2025-05-25T23:36:50.039381Z","shell.execute_reply.started":"2025-05-25T23:36:49.160599Z","shell.execute_reply":"2025-05-25T23:36:50.038291Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":18},{"cell_type":"markdown","source":"### 3.3 Rolling Statistics Visualization\n\nLet's create a visualization of rolling statistics (mean, standard deviation) for stock returns.","metadata":{}},{"cell_type":"code","source":"# Create a function to plot rolling statistics\ndef plot_rolling_statistics(returns_df, stock, window=30):\n # Calculate rolling statistics\n rolling_mean = returns_df[stock].rolling(window=window).mean() * 100 # Convert to percentage\n rolling_std = returns_df[stock].rolling(window=window).std() * 100 # Convert to percentage\n \n # Create a DataFrame for plotting\n rolling_df = pd.DataFrame({\n 'Date': returns_df.index,\n 'Rolling Mean': rolling_mean.values,\n 'Rolling Std': rolling_std.values\n })\n \n # Create subplots\n fig = make_subplots(rows=2, cols=1, shared_xaxes=True, \n vertical_spacing=0.1, \n subplot_titles=(f\"{window}-Day Rolling Mean of Returns (%)\", \n f\"{window}-Day Rolling Standard Deviation of Returns (%)\"))\n \n # Add rolling mean trace\n fig.add_trace(\n go.Scatter(\n x=rolling_df['Date'],\n y=rolling_df['Rolling Mean'],\n mode='lines',\n name='Rolling Mean',\n line=dict(color='blue')\n ),\n row=1, col=1\n )\n \n # Add a horizontal line at 0 for the mean\n fig.add_shape(\n type=\"line\",\n x0=rolling_df['Date'].min(),\n y0=0,\n x1=rolling_df['Date'].max(),\n y1=0,\n line=dict(color=\"red\", width=1, dash=\"dash\"),\n row=1, col=1\n )\n \n # Add rolling standard deviation trace\n fig.add_trace(\n go.Scatter(\n x=rolling_df['Date'],\n y=rolling_df['Rolling Std'],\n mode='lines',\n name='Rolling Std',\n line=dict(color='green')\n ),\n row=2, col=1\n )\n \n # Update layout\n fig.update_layout(\n title=f\"Rolling Statistics for {stock} (Window: {window} Days)\",\n height=800,\n hovermode=\"x unified\",\n showlegend=False,\n margin=dict(l=20, r=20, t=60, b=20),\n )\n \n # Update y-axes\n fig.update_yaxes(title_text=\"Return (%)\", row=1, col=1)\n fig.update_yaxes(title_text=\"Standard Deviation (%)\", row=2, col=1)\n \n # Update x-axis\n fig.update_xaxes(title_text=\"Date\", row=2, col=1)\n \n return fig\n\n# Plot rolling statistics for Stock_A\nfig_rolling = plot_rolling_statistics(returns_df, 'Stock_A', window=30)\nfig_rolling.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:50.042271Z","iopub.execute_input":"2025-05-25T23:36:50.042641Z","iopub.status.idle":"2025-05-25T23:36:50.263616Z","shell.execute_reply.started":"2025-05-25T23:36:50.042606Z","shell.execute_reply":"2025-05-25T23:36:50.262687Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":19},{"cell_type":"markdown","source":"## Part 4: Advanced Comparative Visualizations\n\n### 4.1 Bubble Chart for Market Cap, P/E Ratio, and Returns","metadata":{}},{"cell_type":"code","source":"# Create a bubble chart for market cap, P/E ratio, and returns\ndef plot_bubble_chart(price_df, market_cap_df, pe_ratio_df, date=None):\n # If no date is provided, use the last date\n if date is None:\n date = price_df.index[-1]\n \n # Calculate 1-year returns\n one_year_ago = date - pd.DateOffset(years=1)\n if one_year_ago < price_df.index[0]:\n one_year_ago = price_df.index[0]\n \n # Get the closest dates\n current_date = price_df.index[price_df.index <= date][-1]\n past_date = price_df.index[price_df.index >= one_year_ago][0]\n \n # Calculate returns\n returns = (price_df.loc[current_date] / price_df.loc[past_date] - 1) * 100\n \n # Get market cap and P/E ratio for the current date\n market_cap = market_cap_df.loc[current_date]\n pe_ratio = pe_ratio_df.loc[current_date]\n \n # Create a DataFrame for the bubble chart\n bubble_df = pd.DataFrame({\n 'Stock': [stock for stock in price_df.columns if stock != 'Market_Index'],\n 'Market_Cap': [market_cap[stock] for stock in price_df.columns if stock != 'Market_Index'],\n 'PE_Ratio': [pe_ratio[stock] for stock in price_df.columns if stock != 'Market_Index'],\n 'Return': [returns[stock] for stock in price_df.columns if stock != 'Market_Index']\n })\n \n # Create the bubble chart\n fig = px.scatter(bubble_df, x='PE_Ratio', y='Return', size='Market_Cap', color='Stock',\n hover_name='Stock', size_max=60,\n labels={'PE_Ratio': 'P/E Ratio', 'Return': 'Annual Return (%)', 'Market_Cap': 'Market Cap ($ millions)'},\n title=f\"Stock Comparison: P/E Ratio vs. Return vs. Market Cap (as of {current_date.strftime('%Y-%m-%d')})\",\n height=600)\n \n # Add a horizontal line at 0% return\n fig.add_hline(y=0, line_dash=\"dash\", line_color=\"gray\")\n \n # Update layout\n fig.update_layout(\n xaxis_title=\"P/E Ratio\",\n yaxis_title=\"Annual Return (%)\",\n legend_title=\"Stock\",\n margin=dict(l=20, r=20, t=60, b=20),\n )\n \n return fig\n\n# Plot bubble chart\nfig_bubble = plot_bubble_chart(price_df, market_cap_df, pe_ratio_df)\nfig_bubble.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:50.264717Z","iopub.execute_input":"2025-05-25T23:36:50.265056Z","iopub.status.idle":"2025-05-25T23:36:50.350951Z","shell.execute_reply.started":"2025-05-25T23:36:50.265029Z","shell.execute_reply":"2025-05-25T23:36:50.349738Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":20},{"cell_type":"markdown","source":"### 4.2 Radar Chart for Stock Metrics Comparison","metadata":{}},{"cell_type":"code","source":"# Create a radar chart for comparing stock metrics\ndef plot_radar_chart(price_df, market_cap_df, pe_ratio_df, volume_df, stocks=None, date=None):\n # If no stocks are provided, use all except the market index\n if stocks is None:\n stocks = [col for col in price_df.columns if col != 'Market_Index']\n \n # If no date is provided, use the last date\n if date is None:\n date = price_df.index[-1]\n \n # Get the closest date\n current_date = price_df.index[price_df.index <= date][-1]\n \n # Calculate metrics\n # 1. 1-month return\n one_month_ago = current_date - pd.DateOffset(months=1)\n if one_month_ago < price_df.index[0]:\n one_month_ago = price_df.index[0]\n past_date_1m = price_df.index[price_df.index >= one_month_ago][0]\n returns_1m = (price_df.loc[current_date] / price_df.loc[past_date_1m] - 1) * 100\n \n # 2. 6-month return\n six_months_ago = current_date - pd.DateOffset(months=6)\n if six_months_ago < price_df.index[0]:\n six_months_ago = price_df.index[0]\n past_date_6m = price_df.index[price_df.index >= six_months_ago][0]\n returns_6m = (price_df.loc[current_date] / price_df.loc[past_date_6m] - 1) * 100\n \n # 3. 1-year return\n one_year_ago = current_date - pd.DateOffset(years=1)\n if one_year_ago < price_df.index[0]:\n one_year_ago = price_df.index[0]\n past_date_1y = price_df.index[price_df.index >= one_year_ago][0]\n returns_1y = (price_df.loc[current_date] / price_df.loc[past_date_1y] - 1) * 100\n \n # 4. Volatility (30-day standard deviation of returns)\n returns_df = price_df.pct_change().dropna()\n volatility = returns_df.iloc[-30:].std() * 100 * np.sqrt(252) # Annualized\n \n # 5. Market Cap\n market_cap = market_cap_df.loc[current_date]\n \n # 6. P/E Ratio\n pe_ratio = pe_ratio_df.loc[current_date]\n \n # 7. Average Daily Volume (30 days)\n avg_volume = volume_df.iloc[-30:].mean() / 1000000 # In millions\n \n # Create a DataFrame for the radar chart\n metrics = ['1-Month Return (%)', '6-Month Return (%)', '1-Year Return (%)', \n 'Volatility (%)', 'Market Cap ($M)', 'P/E Ratio', 'Avg Volume (M)']\n \n # Normalize the metrics for better visualization\n # We'll use min-max scaling for each metric\n def min_max_scale(values):\n min_val = min(values)\n max_val = max(values)\n if max_val == min_val:\n return [0.5 for _ in values] # All values are the same\n return [(v - min_val) / (max_val - min_val) for v in values]\n \n # Get the values for each stock\n metric_values = {}\n for stock in stocks:\n metric_values[stock] = [\n returns_1m[stock],\n returns_6m[stock],\n returns_1y[stock],\n volatility[stock],\n market_cap[stock],\n pe_ratio[stock],\n avg_volume[stock]\n ]\n \n # Normalize each metric across stocks\n normalized_values = {}\n for i, metric in enumerate(metrics):\n values = [metric_values[stock][i] for stock in stocks]\n normalized = min_max_scale(values)\n for j, stock in enumerate(stocks):\n if stock not in normalized_values:\n normalized_values[stock] = []\n normalized_values[stock].append(normalized[j])\n \n # Create the radar chart\n fig = go.Figure()\n \n for stock in stocks:\n # Add a trace for each stock\n fig.add_trace(go.Scatterpolar(\n r=normalized_values[stock] + [normalized_values[stock][0]], # Close the loop\n theta=metrics + [metrics[0]], # Close the loop\n fill='toself',\n name=stock\n ))\n \n # Update layout\n fig.update_layout(\n polar=dict(\n radialaxis=dict(\n visible=True,\n range=[0, 1]\n )\n ),\n title=f\"Stock Metrics Comparison (as of {current_date.strftime('%Y-%m-%d')})\",\n height=600,\n margin=dict(l=80, r=80, t=60, b=20),\n )\n \n # Add a table with the actual values\n table_data = [metrics]\n for stock in stocks:\n table_data.append([f\"{metric_values[stock][i]:.2f}\" for i in range(len(metrics))])\n \n table = go.Figure(data=[go.Table(\n header=dict(values=['Metric'] + stocks,\n fill_color='paleturquoise',\n align='left'),\n cells=dict(values=table_data,\n fill_color='lavender',\n align='left'))\n ])\n \n table.update_layout(\n title=\"Actual Metric Values\",\n height=300,\n margin=dict(l=20, r=20, t=40, b=20),\n )\n \n return fig, table\n\n# Plot radar chart\nfig_radar, table_radar = plot_radar_chart(price_df, market_cap_df, pe_ratio_df, volume_df)\nfig_radar.show()\ntable_radar.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:50.352271Z","iopub.execute_input":"2025-05-25T23:36:50.352607Z","iopub.status.idle":"2025-05-25T23:36:50.401208Z","shell.execute_reply.started":"2025-05-25T23:36:50.35258Z","shell.execute_reply":"2025-05-25T23:36:50.399896Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}},{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":21},{"cell_type":"markdown","source":"## Part 5: Interactive Dashboard Components\n\n### 5.1 Stock Performance Dashboard\n\nLet's create a comprehensive dashboard that combines multiple visualizations.","metadata":{}},{"cell_type":"code","source":"# Create a stock performance dashboard\ndef create_stock_dashboard(price_df, volume_df, market_cap_df, pe_ratio_df, stock):\n # Create a subplot grid\n fig = make_subplots(\n rows=3, cols=2,\n specs=[\n [{'colspan': 2}, None],\n [{'colspan': 2}, None],\n [{'type': 'domain'}, {'type': 'xy'}], # Changed second subplot to 'xy' type for bar chart\n ],\n subplot_titles=(\n f\"{stock} Price History\",\n f\"{stock} Trading Volume\",\n \"Market Cap Distribution\",\n \"P/E Ratio Comparison\"\n ),\n vertical_spacing=0.1,\n horizontal_spacing=0.05,\n )\n \n # 1. Stock Price History\n fig.add_trace(\n go.Scatter(\n x=price_df.index,\n y=price_df[stock],\n mode='lines',\n name=f\"{stock} Price\",\n line=dict(color='blue', width=2)\n ),\n row=1, col=1\n )\n \n # Add Market Index for comparison\n # Normalize to the same starting point\n normalized_index = price_df['Market_Index'] * (price_df[stock].iloc[0] / price_df['Market_Index'].iloc[0])\n \n fig.add_trace(\n go.Scatter(\n x=price_df.index,\n y=normalized_index,\n mode='lines',\n name='Market Index (Normalized)',\n line=dict(color='red', width=1, dash='dash')\n ),\n row=1, col=1\n )\n \n # 2. Trading Volume\n fig.add_trace(\n go.Bar(\n x=volume_df.index,\n y=volume_df[stock],\n name=f\"{stock} Volume\",\n marker_color='green'\n ),\n row=2, col=1\n )\n \n # 3. Market Cap Distribution (Pie Chart)\n # Get the latest market caps\n latest_market_caps = market_cap_df.iloc[-1]\n \n fig.add_trace(\n go.Pie(\n labels=[col for col in market_cap_df.columns],\n values=[latest_market_caps[col] for col in market_cap_df.columns],\n name=\"Market Cap\",\n hole=0.4,\n textinfo=\"label+percent\",\n marker=dict(line=dict(color='#000000', width=1))\n ),\n row=3, col=1\n )\n \n # 4. P/E Ratio Comparison (Bar Chart)\n # Get the latest P/E ratios\n latest_pe_ratios = pe_ratio_df.iloc[-1]\n \n fig.add_trace(\n go.Bar(\n x=[col for col in pe_ratio_df.columns],\n y=[latest_pe_ratios[col] for col in pe_ratio_df.columns],\n name=\"P/E Ratio\",\n marker_color='purple'\n ),\n row=3, col=2\n )\n \n # Update layout\n fig.update_layout(\n title=f\"{stock} Performance Dashboard\",\n height=1000,\n showlegend=True,\n legend=dict(orientation=\"h\", yanchor=\"bottom\", y=1.02, xanchor=\"right\", x=1),\n margin=dict(l=20, r=20, t=60, b=20),\n )\n \n # Update axes\n fig.update_xaxes(title_text=\"Date\", row=1, col=1)\n fig.update_yaxes(title_text=\"Price ($)\", row=1, col=1)\n \n fig.update_xaxes(title_text=\"Date\", row=2, col=1)\n fig.update_yaxes(title_text=\"Volume\", row=2, col=1)\n \n fig.update_xaxes(title_text=\"Stock\", row=3, col=2)\n fig.update_yaxes(title_text=\"P/E Ratio\", row=3, col=2)\n \n return fig\n\n# Create dashboard for Stock_A\nfig_dashboard = create_stock_dashboard(price_df, volume_df, market_cap_df, pe_ratio_df, 'Stock_A')\nfig_dashboard.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:50.402229Z","iopub.execute_input":"2025-05-25T23:36:50.402599Z","iopub.status.idle":"2025-05-25T23:36:50.483028Z","shell.execute_reply.started":"2025-05-25T23:36:50.402575Z","shell.execute_reply":"2025-05-25T23:36:50.481727Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":22},{"cell_type":"markdown","source":"## Part 6: Custom Visualization Styles and Themes\n\n### 6.1 Creating a Custom Visualization Theme","metadata":{}},{"cell_type":"code","source":"# Create a custom visualization theme\ndef create_custom_theme():\n # Define custom colors\n colors = {\n 'background': '#f8f9fa',\n 'text': '#343a40',\n 'grid': '#dee2e6',\n 'primary': '#007bff',\n 'secondary': '#6c757d',\n 'success': '#28a745',\n 'danger': '#dc3545',\n 'warning': '#ffc107',\n 'info': '#17a2b8',\n 'light': '#f8f9fa',\n 'dark': '#343a40'\n }\n \n # Create a custom colormap\n custom_cmap = LinearSegmentedColormap.from_list(\n 'custom_cmap',\n [colors['primary'], colors['info'], colors['success']],\n N=256\n )\n \n # Set matplotlib style\n plt.rcParams['figure.facecolor'] = colors['background']\n plt.rcParams['axes.facecolor'] = colors['background']\n plt.rcParams['axes.edgecolor'] = colors['grid']\n plt.rcParams['axes.labelcolor'] = colors['text']\n plt.rcParams['xtick.color'] = colors['text']\n plt.rcParams['ytick.color'] = colors['text']\n plt.rcParams['grid.color'] = colors['grid']\n plt.rcParams['figure.titlesize'] = 16\n plt.rcParams['axes.titlesize'] = 14\n plt.rcParams['axes.labelsize'] = 12\n plt.rcParams['xtick.labelsize'] = 10\n plt.rcParams['ytick.labelsize'] = 10\n \n # Create a custom plotly template\n plotly_template = dict(\n layout=dict(\n font=dict(family=\"Arial, sans-serif\", size=12, color=colors['text']),\n plot_bgcolor=colors['background'],\n paper_bgcolor=colors['background'],\n title=dict(font=dict(size=18, color=colors['text'])),\n xaxis=dict(\n title=dict(font=dict(size=14, color=colors['text'])),\n gridcolor=colors['grid'],\n zerolinecolor=colors['grid']\n ),\n yaxis=dict(\n title=dict(font=dict(size=14, color=colors['text'])),\n gridcolor=colors['grid'],\n zerolinecolor=colors['grid']\n ),\n colorway=[colors['primary'], colors['success'], colors['info'], \n colors['warning'], colors['danger'], colors['secondary']]\n )\n )\n \n # Register the template with plotly\n pio.templates['custom_theme'] = plotly_template\n pio.templates.default = 'custom_theme'\n \n return custom_cmap, colors\n\n# Apply the custom theme\ncustom_cmap, theme_colors = create_custom_theme()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:50.484099Z","iopub.execute_input":"2025-05-25T23:36:50.484368Z","iopub.status.idle":"2025-05-25T23:36:50.509942Z","shell.execute_reply.started":"2025-05-25T23:36:50.484347Z","shell.execute_reply":"2025-05-25T23:36:50.509084Z"}},"outputs":[],"execution_count":23},{"cell_type":"markdown","source":"### 6.2 Applying the Custom Theme to a Visualization","metadata":{}},{"cell_type":"code","source":"# Create a visualization with the custom theme\ndef plot_themed_visualization(price_df, stock='Stock_A'):\n # Calculate daily returns\n returns = price_df[stock].pct_change().dropna() * 100\n \n # Create a figure with subplots\n fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10), gridspec_kw={'height_ratios': [2, 1]})\n \n # Plot stock price\n ax1.plot(price_df.index, price_df[stock], color=theme_colors['primary'], linewidth=2)\n ax1.set_title(f\"{stock} Price History\", fontsize=16)\n ax1.set_ylabel(\"Price ($)\", fontsize=12)\n ax1.grid(True, alpha=0.3)\n \n # Plot returns histogram\n ax2.hist(returns, bins=50, color=theme_colors['info'], alpha=0.7, edgecolor='white')\n ax2.axvline(x=0, color=theme_colors['danger'], linestyle='--', alpha=0.7)\n ax2.set_title(f\"{stock} Daily Returns Distribution\", fontsize=16)\n ax2.set_xlabel(\"Daily Return (%)\", fontsize=12)\n ax2.set_ylabel(\"Frequency\", fontsize=12)\n ax2.grid(True, alpha=0.3)\n \n # Add some statistics to the returns plot\n mean_return = returns.mean()\n std_return = returns.std()\n skew = returns.skew()\n kurtosis = returns.kurtosis()\n \n stats_text = f\"Mean: {mean_return:.2f}%\\nStd Dev: {std_return:.2f}%\\nSkewness: {skew:.2f}\\nKurtosis: {kurtosis:.2f}\"\n ax2.text(0.02, 0.95, stats_text, transform=ax2.transAxes, fontsize=10,\n verticalalignment='top', bbox=dict(boxstyle='round', facecolor=theme_colors['light'], alpha=0.5))\n \n plt.tight_layout()\n plt.show()\n \n # Create a plotly version with the custom theme\n fig = make_subplots(rows=2, cols=1, shared_xaxes=True, \n vertical_spacing=0.1, \n subplot_titles=(f\"{stock} Price History\", f\"{stock} Daily Returns Distribution\"))\n \n # Add price trace\n fig.add_trace(\n go.Scatter(\n x=price_df.index,\n y=price_df[stock],\n mode='lines',\n name=f\"{stock} Price\"\n ),\n row=1, col=1\n )\n \n # Add returns histogram\n fig.add_trace(\n go.Histogram(\n x=returns,\n nbinsx=50,\n name=\"Returns Distribution\"\n ),\n row=2, col=1\n )\n \n # Add a vertical line at 0 for the returns\n fig.add_shape(\n type=\"line\",\n x0=0, y0=0,\n x1=0, y1=1,\n xref=\"x2\", yref=\"paper\",\n line=dict(color=theme_colors['danger'], width=2, dash=\"dash\")\n )\n \n # Update layout\n fig.update_layout(\n title=f\"{stock} Analysis with Custom Theme\",\n height=800,\n showlegend=False,\n )\n \n # Update axes\n fig.update_xaxes(title_text=\"Date\", row=1, col=1)\n fig.update_yaxes(title_text=\"Price ($)\", row=1, col=1)\n \n fig.update_xaxes(title_text=\"Daily Return (%)\", row=2, col=1)\n fig.update_yaxes(title_text=\"Frequency\", row=2, col=1)\n \n # Add annotation with statistics\n fig.add_annotation(\n x=0.02,\n y=0.95,\n xref=\"x2 domain\",\n yref=\"y2 domain\",\n text=stats_text,\n showarrow=False,\n bgcolor=theme_colors['light'],\n bordercolor=theme_colors['grid'],\n borderwidth=1,\n borderpad=4,\n font=dict(size=10)\n )\n \n fig.show()\n\n# Apply the themed visualization\nplot_themed_visualization(price_df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-25T23:36:50.510935Z","iopub.execute_input":"2025-05-25T23:36:50.511154Z","iopub.status.idle":"2025-05-25T23:36:51.217489Z","shell.execute_reply.started":"2025-05-25T23:36:50.511137Z","shell.execute_reply":"2025-05-25T23:36:51.216225Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":24},{"cell_type":"markdown","source":"## Conclusion\n\nIn this notebook, we've demonstrated a wide range of advanced visualization techniques that can be applied to financial data analysis and other domains. These visualizations go beyond basic charts and provide deeper insights into the data through interactive elements, statistical analysis, and comparative views.\n\nKey takeaways:\n\n1. **Interactive visualizations** allow users to explore data more effectively through zooming, panning, and hovering for details.\n2. **Statistical visualizations** like violin plots, correlation heatmaps, and rolling statistics provide deeper analytical insights.\n3. **Comparative visualizations** such as radar charts and bubble charts help in comparing multiple entities across various metrics.\n4. **Dashboards** combine multiple visualizations to tell a comprehensive story about the data.\n5. **Custom themes** enhance the visual appeal and consistency of visualizations.\n\nThese techniques can be applied to various Kaggle competitions and data science projects to create more engaging and insightful notebooks that stand out from the crowd.","metadata":{}}]}