Geoms¶

Geoms (geometric objects) are the visual elements that represent your data. ggplotly provides 46 geoms for different visualization types.

In [1]:

import pandas as pd
import numpy as np
from ggplotly import *

# Sample data
np.random.seed(42)
df = pd.DataFrame({
    'x': np.random.randn(100),
    'y': np.random.randn(100),
    'category': np.random.choice(['A', 'B', 'C'], 100),
    'value': np.random.rand(100) * 10
})

# Time series data
ts_df = pd.DataFrame({
    'date': pd.date_range('2024-01-01', periods=100, freq='D'),
    'value': np.cumsum(np.random.randn(100)) + 50,
    'series': np.tile(['A', 'B'], 50)
})

# Bar data
bar_df = pd.DataFrame({
    'category': ['A', 'B', 'C', 'D'],
    'count': [25, 40, 35, 30]
})

# Distribution data
dist_df = pd.DataFrame({
    'category': np.repeat(['A', 'B', 'C'], 50),
    'value': np.concatenate([
        np.random.normal(0, 1, 50),
        np.random.normal(2, 1.5, 50),
        np.random.normal(-1, 0.8, 50)
    ])
})

import pandas as pd import numpy as np from ggplotly import * # Sample data np.random.seed(42) df = pd.DataFrame({ 'x': np.random.randn(100), 'y': np.random.randn(100), 'category': np.random.choice(['A', 'B', 'C'], 100), 'value': np.random.rand(100) * 10 }) # Time series data ts_df = pd.DataFrame({ 'date': pd.date_range('2024-01-01', periods=100, freq='D'), 'value': np.cumsum(np.random.randn(100)) + 50, 'series': np.tile(['A', 'B'], 50) }) # Bar data bar_df = pd.DataFrame({ 'category': ['A', 'B', 'C', 'D'], 'count': [25, 40, 35, 30] }) # Distribution data dist_df = pd.DataFrame({ 'category': np.repeat(['A', 'B', 'C'], 50), 'value': np.concatenate([ np.random.normal(0, 1, 50), np.random.normal(2, 1.5, 50), np.random.normal(-1, 0.8, 50) ]) })

Basic Geoms¶

geom_point¶

Scatter plots for showing individual observations.

In [2]:

ggplot(df, aes(x='x', y='y')) + geom_point()

ggplot(df, aes(x='x', y='y')) + geom_point()

Out[2]:

In [3]:

# With aesthetics
ggplot(df, aes(x='x', y='y', color='category', size='value')) + geom_point()

# With aesthetics ggplot(df, aes(x='x', y='y', color='category', size='value')) + geom_point()

Out[3]:

In [4]:

# Parameters
ggplot(df, aes(x='x', y='y')) + geom_point(size=5, alpha=0.7, shape='diamond')

# Parameters ggplot(df, aes(x='x', y='y')) + geom_point(size=5, alpha=0.7, shape='diamond')

Out[4]:

geom_line¶

Line plots connecting points in order of x values.

In [5]:

ggplot(ts_df, aes(x='date', y='value')) + geom_line()

ggplot(ts_df, aes(x='date', y='value')) + geom_line()

Out[5]:

In [6]:

# Multiple lines
ggplot(ts_df, aes(x='date', y='value', color='series')) + geom_line()

# Multiple lines ggplot(ts_df, aes(x='date', y='value', color='series')) + geom_line()

Out[6]:

geom_path¶

Like geom_line, but connects points in data order (not sorted by x).

In [7]:

ggplot(df, aes(x='x', y='y')) + geom_path()

ggplot(df, aes(x='x', y='y')) + geom_path()

Out[7]:

geom_bar¶

Bar charts for categorical data.

In [8]:

# Count occurrences
ggplot(df, aes(x='category')) + geom_bar()

# Count occurrences ggplot(df, aes(x='category')) + geom_bar()

Out[8]:

In [9]:

# Pre-computed heights
ggplot(bar_df, aes(x='category', y='count')) + geom_bar(stat='identity')

# Pre-computed heights ggplot(bar_df, aes(x='category', y='count')) + geom_bar(stat='identity')

Out[9]:

geom_col¶

Alias for geom_bar(stat='identity').

In [10]:

ggplot(bar_df, aes(x='category', y='count')) + geom_col()

ggplot(bar_df, aes(x='category', y='count')) + geom_col()

Out[10]:

Distribution Geoms¶

geom_histogram¶

In [11]:

ggplot(df, aes(x='value')) + geom_histogram()

ggplot(df, aes(x='value')) + geom_histogram()

Out[11]:

In [12]:

# Control bins
ggplot(df, aes(x='value')) + geom_histogram(bins=30)

# Control bins ggplot(df, aes(x='value')) + geom_histogram(bins=30)

Out[12]:

geom_density¶

Kernel density estimation.

In [13]:

ggplot(dist_df, aes(x='value')) + geom_density()

ggplot(dist_df, aes(x='value')) + geom_density()

Out[13]:

In [14]:

# Filled density
ggplot(dist_df, aes(x='value', fill='category')) + geom_density(alpha=0.5)

# Filled density ggplot(dist_df, aes(x='value', fill='category')) + geom_density(alpha=0.5)

Out[14]:

geom_boxplot¶

Box-and-whisker plots.

In [15]:

ggplot(dist_df, aes(x='category', y='value')) + geom_boxplot()

ggplot(dist_df, aes(x='category', y='value')) + geom_boxplot()

Out[15]:

geom_violin¶

Violin plots showing distribution shape.

In [16]:

ggplot(dist_df, aes(x='category', y='value')) + geom_violin()

ggplot(dist_df, aes(x='category', y='value')) + geom_violin()

Out[16]:

Area Geoms¶

geom_area¶

Filled area under a line.

In [17]:

ggplot(ts_df[ts_df['series'] == 'A'], aes(x='date', y='value')) + geom_area()

ggplot(ts_df[ts_df['series'] == 'A'], aes(x='date', y='value')) + geom_area()

Out[17]:

geom_ribbon¶

Area between ymin and ymax.

In [18]:

# Create data with error bounds
ribbon_df = ts_df[ts_df['series'] == 'A'].copy()
ribbon_df['lower'] = ribbon_df['value'] - 5
ribbon_df['upper'] = ribbon_df['value'] + 5

ggplot(ribbon_df, aes(x='date', ymin='lower', ymax='upper')) + geom_ribbon(alpha=0.3)

# Create data with error bounds ribbon_df = ts_df[ts_df['series'] == 'A'].copy() ribbon_df['lower'] = ribbon_df['value'] - 5 ribbon_df['upper'] = ribbon_df['value'] + 5 ggplot(ribbon_df, aes(x='date', ymin='lower', ymax='upper')) + geom_ribbon(alpha=0.3)

Out[18]:

geom_rect¶

Rectangles defined by xmin, xmax, ymin, ymax.

In [19]:

# Rectangle data
rect_df = pd.DataFrame({
    'xmin': [0, 2, 4],
    'xmax': [1, 3, 5],
    'ymin': [0, 1, 0.5],
    'ymax': [2, 3, 2.5],
    'category': ['A', 'B', 'C']
})

ggplot(rect_df, aes(xmin='xmin', xmax='xmax', ymin='ymin', ymax='ymax', fill='category')) + geom_rect(alpha=0.7)

# Rectangle data rect_df = pd.DataFrame({ 'xmin': [0, 2, 4], 'xmax': [1, 3, 5], 'ymin': [0, 1, 0.5], 'ymax': [2, 3, 2.5], 'category': ['A', 'B', 'C'] }) ggplot(rect_df, aes(xmin='xmin', xmax='xmax', ymin='ymin', ymax='ymax', fill='category')) + geom_rect(alpha=0.7)

Out[19]:

Statistical Geoms¶

geom_smooth¶

Smoothed conditional means with confidence intervals.

In [20]:

ggplot(df, aes(x='x', y='y')) + geom_point() + geom_smooth()

ggplot(df, aes(x='x', y='y')) + geom_point() + geom_smooth()

Out[20]:

In [21]:

# Linear regression
ggplot(df, aes(x='x', y='y')) + geom_point() + geom_smooth(method='lm')

# Linear regression ggplot(df, aes(x='x', y='y')) + geom_point() + geom_smooth(method='lm')

Out[21]:

Text Geoms¶

geom_text¶

Add text labels to points.

In [22]:

ggplot(bar_df, aes(x='category', y='count', label='count')) + geom_col() + geom_text()

ggplot(bar_df, aes(x='category', y='count', label='count')) + geom_col() + geom_text()

Out[22]:

geom_label¶

Text labels with a background box.

In [23]:

ggplot(bar_df, aes(x='category', y='count', label='count')) + geom_col() + geom_label()

ggplot(bar_df, aes(x='category', y='count', label='count')) + geom_col() + geom_label()

Out[23]:

Reference Lines¶

geom_hline / geom_vline / geom_abline¶

In [24]:

# Horizontal line
ggplot(df, aes(x='x', y='y')) + geom_point() + geom_hline(yintercept=0)

# Horizontal line ggplot(df, aes(x='x', y='y')) + geom_point() + geom_hline(yintercept=0)

Out[24]:

In [25]:

# Vertical line
ggplot(df, aes(x='x', y='y')) + geom_point() + geom_vline(xintercept=0)

# Vertical line ggplot(df, aes(x='x', y='y')) + geom_point() + geom_vline(xintercept=0)

Out[25]:

In [26]:

# Diagonal line
ggplot(df, aes(x='x', y='y')) + geom_point() + geom_abline(slope=1, intercept=0)

# Diagonal line ggplot(df, aes(x='x', y='y')) + geom_point() + geom_abline(slope=1, intercept=0)

Out[26]:

Specialty Geoms¶

geom_tile¶

Heatmaps and tile plots.

In [27]:

# Heatmap data
x_grid = np.arange(10)
y_grid = np.arange(10)
X, Y = np.meshgrid(x_grid, y_grid)
Z = np.sin(X / 2) * np.cos(Y / 2)
tile_df = pd.DataFrame({'x': X.flatten(), 'y': Y.flatten(), 'z': Z.flatten()})

ggplot(tile_df, aes(x='x', y='y', fill='z')) + geom_tile()

# Heatmap data x_grid = np.arange(10) y_grid = np.arange(10) X, Y = np.meshgrid(x_grid, y_grid) Z = np.sin(X / 2) * np.cos(Y / 2) tile_df = pd.DataFrame({'x': X.flatten(), 'y': Y.flatten(), 'z': Z.flatten()}) ggplot(tile_df, aes(x='x', y='y', fill='z')) + geom_tile()

Out[27]:

geom_contour / geom_contour_filled¶

Contour plots for 3D data on 2D.

In [28]:

ggplot(tile_df, aes(x='x', y='y', z='z')) + geom_contour()

ggplot(tile_df, aes(x='x', y='y', z='z')) + geom_contour()

Out[28]:

In [29]:

ggplot(tile_df, aes(x='x', y='y', z='z')) + geom_contour_filled()

ggplot(tile_df, aes(x='x', y='y', z='z')) + geom_contour_filled()

Out[29]:

geom_segment¶

Line segments between two points.

In [30]:

# Segment data
seg_df = pd.DataFrame({
    'x': [0, 1, 2],
    'y': [0, 1, 0],
    'xend': [1, 2, 3],
    'yend': [1, 0, 1]
})

ggplot(seg_df, aes(x='x', y='y', xend='xend', yend='yend')) + geom_segment()

# Segment data seg_df = pd.DataFrame({ 'x': [0, 1, 2], 'y': [0, 1, 0], 'xend': [1, 2, 3], 'yend': [1, 0, 1] }) ggplot(seg_df, aes(x='x', y='y', xend='xend', yend='yend')) + geom_segment()

Out[30]:

geom_errorbar¶

Error bars.

In [31]:

# Error bar data
err_df = pd.DataFrame({
    'x': ['A', 'B', 'C'],
    'y': [10, 15, 12],
    'ymin': [8, 12, 10],
    'ymax': [12, 18, 14]
})

ggplot(err_df, aes(x='x', y='y', ymin='ymin', ymax='ymax')) + geom_col() + geom_errorbar()

# Error bar data err_df = pd.DataFrame({ 'x': ['A', 'B', 'C'], 'y': [10, 15, 12], 'ymin': [8, 12, 10], 'ymax': [12, 18, 14] }) ggplot(err_df, aes(x='x', y='y', ymin='ymin', ymax='ymax')) + geom_col() + geom_errorbar()

Out[31]:

3D Geoms¶

geom_point_3d¶

3D scatter plots.

In [32]:

# 3D data
df_3d = pd.DataFrame({
    'x': np.random.randn(50),
    'y': np.random.randn(50),
    'z': np.random.randn(50)
})

ggplot(df_3d, aes(x='x', y='y', z='z')) + geom_point_3d()

# 3D data df_3d = pd.DataFrame({ 'x': np.random.randn(50), 'y': np.random.randn(50), 'z': np.random.randn(50) }) ggplot(df_3d, aes(x='x', y='y', z='z')) + geom_point_3d()

Out[32]:

geom_surface¶

3D surface plots.

In [33]:

ggplot(tile_df, aes(x='x', y='y', z='z')) + geom_surface()

ggplot(tile_df, aes(x='x', y='y', z='z')) + geom_surface()

Out[33]:

Complete Geom List¶

Geom	Description
geom_point	Scatter plots
geom_line	Line plots (sorted by x)
geom_lines	Multi-series line plots
geom_path	Path plots (data order)
geom_bar	Bar charts
geom_col	Column charts
geom_histogram	Histograms
geom_boxplot	Box plots
geom_violin	Violin plots
geom_density	Density plots
geom_area	Area plots
geom_ribbon	Ribbon plots
geom_rect	Rectangles
geom_smooth	Smoothed lines
geom_tile	Heatmaps
geom_text	Text labels
geom_label	Text labels with background
geom_errorbar	Error bars
geom_segment	Line segments
geom_step	Step plots
geom_rug	Rug plots
geom_jitter	Jittered points
geom_vline	Vertical lines
geom_hline	Horizontal lines
geom_abline	Diagonal lines
geom_contour	Contour lines
geom_contour_filled	Filled contours
geom_map	Choropleth maps
geom_sf	Simple features
geom_range	Range plots
geom_edgebundle	Edge bundling
geom_searoute	Sea routes
geom_fanchart	Fan charts for uncertainty
geom_point_3d	3D points
geom_surface	3D surfaces
geom_wireframe	3D wireframes
geom_candlestick	Candlestick charts
geom_ohlc	OHLC charts
geom_waterfall	Waterfall charts
geom_sankey	Sankey flow diagrams
geom_stl	STL decomposition plots
geom_acf	Autocorrelation plots
geom_pacf	Partial autocorrelation plots
geom_norm	Normal distribution overlay
geom_qq	Q-Q plots
geom_qq_line	Q-Q reference line