{"spec_id":"biplot-pca","library":"bokeh","language":"python","code":"\"\"\" anyplot.ai\nbiplot-pca: PCA Biplot with Scores and Loading Vectors\nLibrary: bokeh 3.9.0 | Python 3.13.13\nQuality: 95/100 | Updated: 2026-05-17\n\"\"\"\n\nimport os\nimport sys\nimport time\nfrom pathlib import Path\n\n\n# Prevent local bokeh.py from shadowing bokeh package\nif \"\" in sys.path:\n    sys.path.remove(\"\")\nif \".\" in sys.path:\n    sys.path.remove(\".\")\n\nimport numpy as np\nfrom bokeh.io import output_file, save\nfrom bokeh.models import Arrow, ColumnDataSource, Label, VeeHead\nfrom bokeh.plotting import figure\nfrom selenium import webdriver\nfrom selenium.webdriver.chrome.options import Options\nfrom sklearn.datasets import load_iris\nfrom sklearn.decomposition import PCA\nfrom sklearn.preprocessing import StandardScaler\n\n\n# Theme tokens\nTHEME = os.getenv(\"ANYPLOT_THEME\", \"light\")\nPAGE_BG = \"#FAF8F1\" if THEME == \"light\" else \"#1A1A17\"\nELEVATED_BG = \"#FFFDF6\" if THEME == \"light\" else \"#242420\"\nINK = \"#1A1A17\" if THEME == \"light\" else \"#F0EFE8\"\nINK_SOFT = \"#4A4A44\" if THEME == \"light\" else \"#B8B7B0\"\n\n# Okabe-Ito palette - first series is ALWAYS #009E73 (brand)\nIMPRINT = [\"#009E73\", \"#C475FD\", \"#4467A3\"]\n\n# Data - Iris dataset\niris = load_iris()\nX = iris.data\ny = iris.target\nfeature_names = [\"sepal length\", \"sepal width\", \"petal length\", \"petal width\"]\ntarget_names = iris.target_names\n\n# Standardize features\nscaler = StandardScaler()\nX_scaled = scaler.fit_transform(X)\n\n# PCA\npca = PCA(n_components=2)\nscores = pca.fit_transform(X_scaled)\nloadings = pca.components_.T\nexplained_var = pca.explained_variance_ratio_ * 100\n\n# Scale loadings for visibility\nscore_max = np.abs(scores).max()\nloading_scale = score_max * 0.9 / np.abs(loadings).max()\nloadings_scaled = loadings * loading_scale\n\n# Create figure with appropriate range\nmargin = 1.5\nx_range = (scores[:, 0].min() - margin, scores[:, 0].max() + margin)\ny_range = (scores[:, 1].min() - margin, scores[:, 1].max() + margin)\n\np = figure(\n    width=4800,\n    height=2700,\n    title=\"biplot-pca · bokeh · anyplot.ai\",\n    x_axis_label=f\"PC1 ({explained_var[0]:.1f}%)\",\n    y_axis_label=f\"PC2 ({explained_var[1]:.1f}%)\",\n    x_range=x_range,\n    y_range=y_range,\n)\n\n# Style title and axes\np.title.text_font_size = \"28pt\"\np.title.text_color = INK\np.xaxis.axis_label_text_font_size = \"22pt\"\np.yaxis.axis_label_text_font_size = \"22pt\"\np.xaxis.axis_label_text_color = INK\np.yaxis.axis_label_text_color = INK\np.xaxis.major_label_text_font_size = \"18pt\"\np.yaxis.major_label_text_font_size = \"18pt\"\np.xaxis.major_label_text_color = INK_SOFT\np.yaxis.major_label_text_color = INK_SOFT\n\n# Theme-adaptive styling\np.background_fill_color = PAGE_BG\np.border_fill_color = PAGE_BG\np.outline_line_color = INK_SOFT\np.xaxis.axis_line_color = INK_SOFT\np.yaxis.axis_line_color = INK_SOFT\np.xaxis.major_tick_line_color = INK_SOFT\np.yaxis.major_tick_line_color = INK_SOFT\np.xgrid.grid_line_color = INK\np.ygrid.grid_line_color = INK\np.xgrid.grid_line_alpha = 0.10\np.ygrid.grid_line_alpha = 0.10\n\n# Plot observation scores by group\nfor i, name in enumerate(target_names):\n    mask = y == i\n    source = ColumnDataSource(data={\"x\": scores[mask, 0], \"y\": scores[mask, 1]})\n    p.scatter(x=\"x\", y=\"y\", source=source, size=20, alpha=0.7, color=IMPRINT[i], legend_label=name)\n\n# Style legend\nif p.legend:\n    p.legend.location = \"top_left\"\n    p.legend.label_text_font_size = \"16pt\"\n    p.legend.label_text_color = INK_SOFT\n    p.legend.background_fill_color = ELEVATED_BG\n    p.legend.background_fill_alpha = 0.9\n    p.legend.border_line_color = INK_SOFT\n    p.legend.border_line_alpha = 0.5\n\n# Draw loading arrows\narrow_color = INK_SOFT\n\n# Custom label offsets for each feature to avoid overlap\nlabel_offsets = {\n    \"sepal length\": (0.4, 0.5),\n    \"sepal width\": (-0.3, 0.4),\n    \"petal length\": (0.5, -0.4),\n    \"petal width\": (0.3, 0.5),\n}\n\nfor i, name in enumerate(feature_names):\n    x_end = loadings_scaled[i, 0]\n    y_end = loadings_scaled[i, 1]\n\n    # Add arrow\n    p.add_layout(\n        Arrow(\n            end=VeeHead(size=30, fill_color=arrow_color, line_color=arrow_color),\n            x_start=0,\n            y_start=0,\n            x_end=x_end,\n            y_end=y_end,\n            line_width=3,\n            line_color=arrow_color,\n        )\n    )\n\n    # Add label with custom offset\n    offset_x, offset_y = label_offsets[name]\n    label = Label(\n        x=x_end + offset_x,\n        y=y_end + offset_y,\n        text=name,\n        text_font_size=\"16pt\",\n        text_color=INK_SOFT,\n        text_align=\"center\",\n    )\n    p.add_layout(label)\n\n# Add origin reference lines\np.line(x=[x_range[0], x_range[1]], y=[0, 0], line_width=2, line_color=INK_SOFT, line_alpha=0.3, line_dash=\"dashed\")\np.line(x=[0, 0], y=[y_range[0], y_range[1]], line_width=2, line_color=INK_SOFT, line_alpha=0.3, line_dash=\"dashed\")\n\n# Save HTML\noutput_file(f\"plot-{THEME}.html\")\nsave(p)\n\n# Screenshot with headless Chrome via Selenium\nW, H = 4800, 2700\nopts = Options()\nfor arg in (\n    \"--headless=new\",\n    \"--no-sandbox\",\n    \"--disable-dev-shm-usage\",\n    \"--disable-gpu\",\n    f\"--window-size={W},{H}\",\n    \"--hide-scrollbars\",\n):\n    opts.add_argument(arg)\n\ndriver = webdriver.Chrome(options=opts)\ndriver.set_window_size(W, H)\ndriver.get(f\"file://{Path(f'plot-{THEME}.html').resolve()}\")\ntime.sleep(3)\ndriver.save_screenshot(f\"plot-{THEME}.png\")\ndriver.quit()\n"}