tsa2

Author: bbcho

README.md

@@ -32,12 +32,13 @@ ggplot(df, aes(x='x', y='y')) + geom_point() + facet_wrap('group')
 
 ## ggplot2 Function Coverage
 
-### Geoms (34)
+### Geoms (44)
 
 | Function | Description |
 |----------|-------------|
 | `geom_point` | Scatter plots |
 | `geom_line` | Line plots (sorted by x) |
+| `geom_lines` | Multi-series line plots |
 | `geom_path` | Path plots (unsorted) |
 | `geom_bar` | Bar charts |
 | `geom_col` | Column charts (pre-computed heights) |
@@ -61,18 +62,26 @@ ggplot(df, aes(x='x', y='y')) + geom_point() + facet_wrap('group')
 | `geom_contour` | Contour lines |
 | `geom_contour_filled` | Filled contours |
 | `geom_map` | Choropleth maps |
-| `geom_point_map` | Points on maps |
+| `geom_sf` | Simple features (geographic) |
 | `geom_range` | Range plots (min/max/avg) |
 | `geom_edgebundle` | Edge bundling for networks |
-| `geom_sf` | Simple features (geographic) |
 | `geom_searoute` | Maritime shipping routes |
 | `geom_point_3d` | 3D scatter plots |
 | `geom_surface` | 3D surface plots |
 | `geom_wireframe` | 3D wireframe plots |
 | `geom_candlestick` | Candlestick charts (financial) |
 | `geom_ohlc` | OHLC charts (financial) |
-
-### Stats (7)
+| `geom_waterfall` | Waterfall charts (financial) |
+| `geom_sankey` | Sankey flow diagrams |
+| `geom_fanchart` | Fan charts for uncertainty |
+| `geom_stl` | STL decomposition plots |
+| `geom_acf` | Autocorrelation function plots |
+| `geom_pacf` | Partial autocorrelation plots |
+| `geom_norm` | Normal distribution overlay |
+| `geom_qq` | Q-Q plots (theoretical vs sample quantiles) |
+| `geom_qq_line` | Q-Q reference line through Q1/Q3 |
+
+### Stats (13)
 
 | Function | Description |
 |----------|-------------|
@@ -83,6 +92,12 @@ ggplot(df, aes(x='x', y='y')) + geom_point() + facet_wrap('group')
 | `stat_ecdf` | Empirical CDF |
 | `stat_smooth` | Smoothing with CI |
 | `stat_summary` | Summary statistics |
+| `stat_contour` | Contour computation |
+| `stat_fanchart` | Fan chart percentiles |
+| `stat_function` | Apply function to data range |
+| `stat_stl` | STL time series decomposition |
+| `stat_qq` | Compute Q-Q quantiles |
+| `stat_qq_line` | Compute Q-Q reference line |
 
 ### Scales (17)
 
@@ -166,4 +181,4 @@ ggplot(df, aes(x='x', y='y')) + geom_point() + facet_wrap('group')
 | `ggsave` | Save plots to file |
 | `ggsize` | Set plot dimensions |
 
-## Total: ~97 ggplot2-equivalent functions
+## Total: ~113 ggplot2-equivalent functions

docs/api/geoms.md

@@ -176,6 +176,10 @@ Geometric objects (geoms) are the visual elements used to represent data in a pl
     options:
       show_root_heading: true
 
+::: ggplotly.geoms.geom_waterfall.geom_waterfall
+    options:
+      show_root_heading: true
+
 ## Time Series Geoms
 
 ::: ggplotly.geoms.geom_stl.geom_stl
@@ -199,3 +203,9 @@ Geometric objects (geoms) are the visual elements used to represent data in a pl
 ::: ggplotly.geoms.geom_searoute.geom_searoute
     options:
       show_root_heading: true
+
+## Flow Geoms
+
+::: ggplotly.geoms.geom_sankey.geom_sankey
+    options:
+      show_root_heading: true

docs/gallery/networks.ipynb

@@ -333,6 +333,54 @@
     "- Edge weights (if provided)\n",
     "- All algorithm parameters (K, E, C, P, S, etc.)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6nj4t32vklf",
+   "source": "## Sankey Diagrams\n\nSankey diagrams visualize flows between nodes, where the width of each link is proportional to the flow quantity.\n\n### Basic Sankey",
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "id": "zvld5kwh3o",
+   "source": "# Simple flow from sources to targets\nflow_df = pd.DataFrame({\n    'source': ['A', 'A', 'B', 'B', 'C'],\n    'target': ['X', 'Y', 'X', 'Y', 'Y'],\n    'value': [10, 20, 15, 25, 5]\n})\n\n(ggplot(flow_df, aes(source='source', target='target', value='value'))\n + geom_sankey()\n + labs(title='Basic Sankey Diagram'))",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "hcarax6s7vu",
+   "source": "### Multi-Stage Sankey\n\nFor multi-stage flows (e.g., budget allocation):",
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "id": "nfornzgzfb",
+   "source": "# Multi-stage budget flow\nbudget_df = pd.DataFrame({\n    'source': ['Budget', 'Budget', 'Sales', 'Sales', 'Marketing', 'Marketing', 'R&D'],\n    'target': ['Sales', 'Marketing', 'Revenue', 'Costs', 'Revenue', 'Costs', 'Revenue'],\n    'value': [100, 80, 90, 10, 60, 20, 50]\n})\n\n(ggplot(budget_df, aes(source='source', target='target', value='value'))\n + geom_sankey(node_pad=20, node_thickness=25)\n + labs(title='Budget Allocation Flow'))",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "oi2t776yfqq",
+   "source": "### Custom Colors",
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "id": "0nrov454s3bk",
+   "source": "# Custom node colors\n(ggplot(flow_df, aes(source='source', target='target', value='value'))\n + geom_sankey(\n     node_color=['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd'],\n     link_alpha=0.5\n )\n + labs(title='Sankey with Custom Colors'))",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "sg25xx2i7v",
+   "source": "### Sankey Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `node_pad` | 15 | Padding between nodes |\n| `node_thickness` | 20 | Thickness of nodes |\n| `node_color` | auto | Color(s) for nodes |\n| `link_color` | auto | Color for links (uses source node color) |\n| `link_alpha` | 0.4 | Transparency of links |\n| `orientation` | 'h' | 'h' (horizontal) or 'v' (vertical) |\n| `arrangement` | 'snap' | Node arrangement: 'snap', 'perpendicular', 'freeform', 'fixed' |",
+   "metadata": {}
   }
  ],
  "metadata": {
@@ -348,4 +396,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

docs/gallery/statistical.ipynb

@@ -21516,6 +21516,54 @@
     " + labs(title='Residuals vs Fitted', x='Fitted Values', y='Residuals'))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5bi0xmpz20y",
+   "source": "## Waterfall Charts\n\nWaterfall charts show how an initial value is affected by intermediate positive or negative values.\n\n### Basic Waterfall",
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "id": "5s0e0inllcn",
+   "source": "# Basic waterfall showing quarterly changes\nwaterfall_df = pd.DataFrame({\n    'category': ['Q1 Sales', 'Q2 Growth', 'Q3 Decline', 'Q4 Recovery', 'Year Total'],\n    'value': [100, 50, -30, 20, 0],\n    'measure': ['absolute', 'relative', 'relative', 'relative', 'total']\n})\n\n(ggplot(waterfall_df, aes(x='category', y='value', measure='measure'))\n + geom_waterfall()\n + labs(title='Quarterly Sales Waterfall'))",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "hk7c8dkqt45",
+   "source": "### Financial Statement Waterfall\n\nCommon use case for income statement analysis:",
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "id": "0rim3tnjs79n",
+   "source": "# Income statement waterfall\nincome_df = pd.DataFrame({\n    'item': ['Revenue', 'COGS', 'Gross Profit', 'Operating Expenses', 'Operating Income', 'Taxes', 'Net Income'],\n    'amount': [1000, -400, 0, -300, 0, -75, 0],\n    'type': ['absolute', 'relative', 'total', 'relative', 'total', 'relative', 'total']\n})\n\n(ggplot(income_df, aes(x='item', y='amount', measure='type'))\n + geom_waterfall()\n + labs(title='Income Statement Breakdown', y='Amount ($K)'))",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "obo7mbmzdfl",
+   "source": "### Custom Colors",
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "id": "9286z3430xc",
+   "source": "# Custom colors for different bar types\n(ggplot(waterfall_df, aes(x='category', y='value', measure='measure'))\n + geom_waterfall(\n     increasing_color='#17becf',  # Cyan for increases\n     decreasing_color='#ff7f0e',  # Orange for decreases\n     total_color='#1f77b4'        # Blue for totals\n )\n + labs(title='Waterfall with Custom Colors'))",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "mpqwz5818w",
+   "source": "### Waterfall Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `increasing_color` | '#2ca02c' | Color for positive changes (green) |\n| `decreasing_color` | '#d62728' | Color for negative changes (red) |\n| `total_color` | '#1f77b4' | Color for totals (blue) |\n| `connector_visible` | True | Show connector lines |\n| `connector_color` | gray | Color of connectors |\n| `text_position` | 'outside' | Position of value labels |\n| `orientation` | 'v' | 'v' (vertical) or 'h' (horizontal) |\n\nThe `measure` aesthetic controls bar types:\n- `'absolute'`: Starting value (resets running total)\n- `'relative'`: Change from previous value (default)\n- `'total'`: Shows cumulative total at this point",
+   "metadata": {}
+  },
   {
    "cell_type": "markdown",
    "id": "4b17be7b",

ggplotly/__init__.py

@@ -35,6 +35,7 @@
     geom_range,
     geom_ribbon,
     geom_rug,
+    geom_sankey,
     geom_searoute,
     geom_segment,
     geom_sf,
@@ -46,6 +47,7 @@
     geom_tile,
     geom_violin,
     geom_vline,
+    geom_waterfall,
     geom_wireframe,
 )
 from .ggplot import ggplot
@@ -189,6 +191,8 @@
     "geom_norm",
     "geom_qq",
     "geom_qq_line",
+    "geom_sankey",
+    "geom_waterfall",
     "scale_x_continuous",
     "scale_y_continuous",
     "scale_color_manual",

ggplotly/geoms/__init__.py

@@ -23,13 +23,14 @@
 from .geom_norm import geom_norm
 from .geom_pacf import geom_pacf
 from .geom_path import geom_path
-from .geom_qq import geom_qq
-from .geom_qq_line import geom_qq_line
 from .geom_point import geom_point
 from .geom_point_3d import geom_point_3d
+from .geom_qq import geom_qq
+from .geom_qq_line import geom_qq_line
 from .geom_range import geom_range
 from .geom_ribbon import geom_ribbon
 from .geom_rug import geom_rug
+from .geom_sankey import geom_sankey
 from .geom_searoute import geom_searoute
 from .geom_segment import geom_segment
 from .geom_smooth import geom_smooth
@@ -40,6 +41,7 @@
 from .geom_tile import geom_tile
 from .geom_violin import geom_violin
 from .geom_vline import geom_vline
+from .geom_waterfall import geom_waterfall
 
 __all__ = [
     "Geom",
@@ -85,4 +87,6 @@
     "geom_norm",
     "geom_qq",
     "geom_qq_line",
+    "geom_sankey",
+    "geom_waterfall",
 ]

ggplotly/geoms/geom_acf.py

@@ -60,7 +60,6 @@ def _draw_impl(self, fig, data, row, col):
         nlags = self.params.get("nlags", 40)
         alpha = self.params.get("alpha", 0.05)
         color = self.params.get("color", "steelblue")
-        ci_color = self.params.get("ci_color", "lightblue")
         ci_alpha = self.params.get("ci_alpha", 0.3)
         bar_width = self.params.get("bar_width", 0.3)
 

ggplotly/geoms/geom_fanchart.py

@@ -2,8 +2,8 @@
 
 import plotly.graph_objects as go
 
-from .geom_base import Geom
 from ..stats.stat_fanchart import stat_fanchart
+from .geom_base import Geom
 
 
 class geom_fanchart(Geom):

ggplotly/geoms/geom_pacf.py

@@ -66,7 +66,6 @@ def _draw_impl(self, fig, data, row, col):
         alpha = self.params.get("alpha", 0.05)
         method = self.params.get("method", "ywm")
         color = self.params.get("color", "steelblue")
-        ci_color = self.params.get("ci_color", "lightblue")
         ci_alpha = self.params.get("ci_alpha", 0.3)
         bar_width = self.params.get("bar_width", 0.3)