Skip to content
GitLab
Commit 4864ddad authored by Sean Fitzgibbon's avatar Sean Fitzgibbon Committed by Paul McCarthy
Browse files

Initial commit of bokeh examples

parent 21ccc198
Hide whitespace changes
Inline Side-by-side
applications/data_visualisation/Bokeh.ipynb 0 → 100644
View file @ 4864ddad
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# `bokeh`\n",
"\n",
"[`bokeh`](https://docs.bokeh.org/en/latest/index.html) is a Python library for creating interactive visualizations for modern web browsers. `bokeh` allows you to create these interactive web-based plots without having to code in javascript.\n",
"\n",
"`bokeh` has excellent documentation: https://docs.bokeh.org/en/latest/index.html\n",
"\n",
"This notebook is not intended to instruct you how to use `bokeh`. Instead it pulls together interesting examples from the `bokeh` documentation into a single notebook to give you a taster of what can be done with `bokeh`.\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from bokeh.plotting import figure, output_file, show\n",
"from bokeh.io import output_notebook\n",
"output_notebook()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from bokeh import sampledata\n",
"sampledata.download()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Scatter Plots\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/iris.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from bokeh.sampledata.iris import flowers\n",
"\n",
"colormap = {'setosa': 'red', 'versicolor': 'green', 'virginica': 'blue'}\n",
"colors = [colormap[x] for x in flowers['species']]\n",
"\n",
"p = figure(title = \"Iris Morphology\")\n",
"p.xaxis.axis_label = 'Petal Length'\n",
"p.yaxis.axis_label = 'Petal Width'\n",
"\n",
"p.circle(flowers[\"petal_length\"], flowers[\"petal_width\"],\n",
" color=colors, fill_alpha=0.2, size=10)\n",
"\n",
"# output_file(\"iris.html\", title=\"iris.py example\")\n",
"\n",
"show(p)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Line Plots\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/box_annotation.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from bokeh.models import BoxAnnotation\n",
"from bokeh.sampledata.glucose import data\n",
"\n",
"TOOLS = \"pan,wheel_zoom,box_zoom,reset,save\"\n",
"\n",
"data = data.loc['2010-10-04':'2010-10-04']\n",
"\n",
"p = figure(x_axis_type=\"datetime\", tools=TOOLS, title=\"Glocose Readings, Oct 4th (Red = Outside Range)\")\n",
"p.background_fill_color = \"#efefef\"\n",
"p.xgrid.grid_line_color=None\n",
"p.xaxis.axis_label = 'Time'\n",
"p.yaxis.axis_label = 'Value'\n",
"\n",
"p.line(data.index, data.glucose, line_color='grey')\n",
"p.circle(data.index, data.glucose, color='grey', size=1)\n",
"\n",
"p.add_layout(BoxAnnotation(top=80, fill_alpha=0.1, fill_color='red', line_color='red'))\n",
"p.add_layout(BoxAnnotation(bottom=180, fill_alpha=0.1, fill_color='red', line_color='red'))\n",
"\n",
"show(p)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Bar Charts\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/bar_stacked.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from bokeh.palettes import Spectral5\n",
"from bokeh.sampledata.autompg import autompg_clean as df\n",
"from bokeh.transform import factor_cmap\n",
"\n",
"df.cyl = df.cyl.astype(str)\n",
"df.yr = df.yr.astype(str)\n",
"\n",
"group = df.groupby(['cyl', 'mfr'])\n",
"\n",
"index_cmap = factor_cmap('cyl_mfr', palette=Spectral5, factors=sorted(df.cyl.unique()), end=1)\n",
"\n",
"p = figure(plot_width=800, plot_height=500, title=\"Mean MPG by # Cylinders and Manufacturer\",\n",
" x_range=group, toolbar_location=None, tooltips=[(\"MPG\", \"@mpg_mean\"), (\"Cyl, Mfr\", \"@cyl_mfr\")])\n",
"\n",
"p.vbar(x='cyl_mfr', top='mpg_mean', width=1, source=group,\n",
" line_color=\"white\", fill_color=index_cmap, )\n",
"\n",
"p.y_range.start = 0\n",
"p.x_range.range_padding = 0.05\n",
"p.xgrid.grid_line_color = None\n",
"p.xaxis.axis_label = \"Manufacturer grouped by # Cylinders\"\n",
"p.xaxis.major_label_orientation = 1.2\n",
"p.outline_line_color = None\n",
"\n",
"show(p)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Distribution Plots\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/histogram.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import scipy.special\n",
"\n",
"from bokeh.layouts import gridplot\n",
"\n",
"\n",
"def make_plot(title, hist, edges, x, pdf, cdf):\n",
" p = figure(title=title, tools='', background_fill_color=\"#fafafa\")\n",
" p.quad(top=hist, bottom=0, left=edges[:-1], right=edges[1:],\n",
" fill_color=\"navy\", line_color=\"white\", alpha=0.5)\n",
" p.line(x, pdf, line_color=\"#ff8888\", line_width=4, alpha=0.7, legend_label=\"PDF\")\n",
" p.line(x, cdf, line_color=\"orange\", line_width=2, alpha=0.7, legend_label=\"CDF\")\n",
"\n",
" p.y_range.start = 0\n",
" p.legend.location = \"center_right\"\n",
" p.legend.background_fill_color = \"#fefefe\"\n",
" p.xaxis.axis_label = 'x'\n",
" p.yaxis.axis_label = 'Pr(x)'\n",
" p.grid.grid_line_color=\"white\"\n",
" return p\n",
"\n",
"# Normal Distribution\n",
"\n",
"mu, sigma = 0, 0.5\n",
"\n",
"measured = np.random.normal(mu, sigma, 1000)\n",
"hist, edges = np.histogram(measured, density=True, bins=50)\n",
"\n",
"x = np.linspace(-2, 2, 1000)\n",
"pdf = 1/(sigma * np.sqrt(2*np.pi)) * np.exp(-(x-mu)**2 / (2*sigma**2))\n",
"cdf = (1+scipy.special.erf((x-mu)/np.sqrt(2*sigma**2)))/2\n",
"\n",
"p1 = make_plot(\"Normal Distribution (μ=0, σ=0.5)\", hist, edges, x, pdf, cdf)\n",
"\n",
"# Log-Normal Distribution\n",
"\n",
"mu, sigma = 0, 0.5\n",
"\n",
"measured = np.random.lognormal(mu, sigma, 1000)\n",
"hist, edges = np.histogram(measured, density=True, bins=50)\n",
"\n",
"x = np.linspace(0.0001, 8.0, 1000)\n",
"pdf = 1/(x* sigma * np.sqrt(2*np.pi)) * np.exp(-(np.log(x)-mu)**2 / (2*sigma**2))\n",
"cdf = (1+scipy.special.erf((np.log(x)-mu)/(np.sqrt(2)*sigma)))/2\n",
"\n",
"p2 = make_plot(\"Log Normal Distribution (μ=0, σ=0.5)\", hist, edges, x, pdf, cdf)\n",
"\n",
"# Gamma Distribution\n",
"\n",
"k, theta = 7.5, 1.0\n",
"\n",
"measured = np.random.gamma(k, theta, 1000)\n",
"hist, edges = np.histogram(measured, density=True, bins=50)\n",
"\n",
"x = np.linspace(0.0001, 20.0, 1000)\n",
"pdf = x**(k-1) * np.exp(-x/theta) / (theta**k * scipy.special.gamma(k))\n",
"cdf = scipy.special.gammainc(k, x/theta)\n",
"\n",
"p3 = make_plot(\"Gamma Distribution (k=7.5, θ=1)\", hist, edges, x, pdf, cdf)\n",
"\n",
"# Weibull Distribution\n",
"\n",
"lam, k = 1, 1.25\n",
"measured = lam*(-np.log(np.random.uniform(0, 1, 1000)))**(1/k)\n",
"hist, edges = np.histogram(measured, density=True, bins=50)\n",
"\n",
"x = np.linspace(0.0001, 8, 1000)\n",
"pdf = (k/lam)*(x/lam)**(k-1) * np.exp(-(x/lam)**k)\n",
"cdf = 1 - np.exp(-(x/lam)**k)\n",
"\n",
"p4 = make_plot(\"Weibull Distribution (λ=1, k=1.25)\", hist, edges, x, pdf, cdf)\n",
"\n",
"show(gridplot([p1,p2,p3,p4], ncols=2, plot_width=400, plot_height=400, toolbar_location=None))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Boxplot\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/boxplot.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"# generate some synthetic time series for six different categories\n",
"cats = list(\"abcdef\")\n",
"yy = np.random.randn(2000)\n",
"g = np.random.choice(cats, 2000)\n",
"for i, l in enumerate(cats):\n",
" yy[g == l] += i // 2\n",
"df = pd.DataFrame(dict(score=yy, group=g))\n",
"\n",
"# find the quartiles and IQR for each category\n",
"groups = df.groupby('group')\n",
"q1 = groups.quantile(q=0.25)\n",
"q2 = groups.quantile(q=0.5)\n",
"q3 = groups.quantile(q=0.75)\n",
"iqr = q3 - q1\n",
"upper = q3 + 1.5*iqr\n",
"lower = q1 - 1.5*iqr\n",
"\n",
"# find the outliers for each category\n",
"def outliers(group):\n",
" cat = group.name\n",
" return group[(group.score > upper.loc[cat]['score']) | (group.score < lower.loc[cat]['score'])]['score']\n",
"out = groups.apply(outliers).dropna()\n",
"\n",
"# prepare outlier data for plotting, we need coordinates for every outlier.\n",
"if not out.empty:\n",
" outx = list(out.index.get_level_values(0))\n",
" outy = list(out.values)\n",
"\n",
"p = figure(tools=\"\", background_fill_color=\"#efefef\", x_range=cats, toolbar_location=None)\n",
"\n",
"# if no outliers, shrink lengths of stems to be no longer than the minimums or maximums\n",
"qmin = groups.quantile(q=0.00)\n",
"qmax = groups.quantile(q=1.00)\n",
"upper.score = [min([x,y]) for (x,y) in zip(list(qmax.loc[:,'score']),upper.score)]\n",
"lower.score = [max([x,y]) for (x,y) in zip(list(qmin.loc[:,'score']),lower.score)]\n",
"\n",
"# stems\n",
"p.segment(cats, upper.score, cats, q3.score, line_color=\"black\")\n",
"p.segment(cats, lower.score, cats, q1.score, line_color=\"black\")\n",
"\n",
"# boxes\n",
"p.vbar(cats, 0.7, q2.score, q3.score, fill_color=\"#E08E79\", line_color=\"black\")\n",
"p.vbar(cats, 0.7, q1.score, q2.score, fill_color=\"#3B8686\", line_color=\"black\")\n",
"\n",
"# whiskers (almost-0 height rects simpler than segments)\n",
"p.rect(cats, lower.score, 0.2, 0.01, line_color=\"black\")\n",
"p.rect(cats, upper.score, 0.2, 0.01, line_color=\"black\")\n",
"\n",
"# outliers\n",
"if not out.empty:\n",
" p.circle(outx, outy, size=6, color=\"#F38630\", fill_alpha=0.6)\n",
"\n",
"p.xgrid.grid_line_color = None\n",
"p.ygrid.grid_line_color = \"white\"\n",
"p.grid.grid_line_width = 2\n",
"p.xaxis.major_label_text_font_size=\"16px\"\n",
"\n",
"show(p)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Connectivity Matrix\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/les_mis.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"from bokeh.sampledata.les_mis import data\n",
"\n",
"nodes = data['nodes']\n",
"names = [node['name'] for node in sorted(data['nodes'], key=lambda x: x['group'])]\n",
"\n",
"N = len(nodes)\n",
"counts = np.zeros((N, N))\n",
"for link in data['links']:\n",
" counts[link['source'], link['target']] = link['value']\n",
" counts[link['target'], link['source']] = link['value']\n",
"\n",
"colormap = [\"#444444\", \"#a6cee3\", \"#1f78b4\", \"#b2df8a\", \"#33a02c\", \"#fb9a99\",\n",
" \"#e31a1c\", \"#fdbf6f\", \"#ff7f00\", \"#cab2d6\", \"#6a3d9a\"]\n",
"\n",
"xname = []\n",
"yname = []\n",
"color = []\n",
"alpha = []\n",
"for i, node1 in enumerate(nodes):\n",
" for j, node2 in enumerate(nodes):\n",
" xname.append(node1['name'])\n",
" yname.append(node2['name'])\n",
"\n",
" alpha.append(min(counts[i,j]/4.0, 0.9) + 0.1)\n",
"\n",
" if node1['group'] == node2['group']:\n",
" color.append(colormap[node1['group']])\n",
" else:\n",
" color.append('lightgrey')\n",
"\n",
"data=dict(\n",
" xname=xname,\n",
" yname=yname,\n",
" colors=color,\n",
" alphas=alpha,\n",
" count=counts.flatten(),\n",
")\n",
"\n",
"p = figure(title=\"Les Mis Occurrences\",\n",
" x_axis_location=\"above\", tools=\"hover,save\",\n",
" x_range=list(reversed(names)), y_range=names,\n",
" tooltips = [('names', '@yname, @xname'), ('count', '@count')])\n",
"\n",
"p.plot_width = 800\n",
"p.plot_height = 800\n",
"p.grid.grid_line_color = None\n",
"p.axis.axis_line_color = None\n",
"p.axis.major_tick_line_color = None\n",
"p.axis.major_label_text_font_size = \"7px\"\n",
"p.axis.major_label_standoff = 0\n",
"p.xaxis.major_label_orientation = np.pi/3\n",
"\n",
"p.rect('xname', 'yname', 0.9, 0.9, source=data,\n",
" color='colors', alpha='alphas', line_color=None,\n",
" hover_line_color='black', hover_color='colors')\n",
"\n",
"show(p) # show the plot"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Sliders\n",
"\n",
"https://docs.bokeh.org/en/latest/docs/gallery/slider.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"from bokeh.layouts import column, row\n",
"from bokeh.models import CustomJS, Slider\n",
"from bokeh.plotting import ColumnDataSource\n",
"\n",
"x = np.linspace(0, 10, 500)\n",
"y = np.sin(x)\n",
"\n",
"source = ColumnDataSource(data=dict(x=x, y=y))\n",
"\n",
"plot = figure(y_range=(-10, 10), plot_width=400, plot_height=400)\n",
"\n",
"plot.line('x', 'y', source=source, line_width=3, line_alpha=0.6)\n",
"\n",
"amp_slider = Slider(start=0.1, end=10, value=1, step=.1, title=\"Amplitude\")\n",
"freq_slider = Slider(start=0.1, end=10, value=1, step=.1, title=\"Frequency\")\n",
"phase_slider = Slider(start=0, end=6.4, value=0, step=.1, title=\"Phase\")\n",
"offset_slider = Slider(start=-5, end=5, value=0, step=.1, title=\"Offset\")\n",
"\n",
"callback = CustomJS(args=dict(source=source, amp=amp_slider, freq=freq_slider, phase=phase_slider, offset=offset_slider),\n",
" code=\"\"\"\n",
" const data = source.data;\n",
" const A = amp.value;\n",
" const k = freq.value;\n",
" const phi = phase.value;\n",
" const B = offset.value;\n",
" const x = data['x']\n",
" const y = data['y']\n",
" for (var i = 0; i < x.length; i++) {\n",
" y[i] = B + A*Math.sin(k*x[i]+phi);\n",
" }\n",
" source.change.emit();\n",
"\"\"\")\n",
"\n",
"amp_slider.js_on_change('value', callback)\n",
"freq_slider.js_on_change('value', callback)\n",
"phase_slider.js_on_change('value', callback)\n",
"offset_slider.js_on_change('value', callback)\n",
"\n",
"layout = row(\n",
" plot,\n",
" column(amp_slider, freq_slider, phase_slider, offset_slider),\n",
")\n",
"\n",
"show(layout)"
]
}
],
"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": "3.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
%% Cell type:markdown id: tags:
# `bokeh`
[`bokeh`](https://docs.bokeh.org/en/latest/index.html) is a Python library for creating interactive visualizations for modern web browsers. `bokeh` allows you to create these interactive web-based plots without having to code in javascript.
`bokeh` has excellent documentation: https://docs.bokeh.org/en/latest/index.html
This notebook is not intended to instruct you how to use `bokeh`. Instead it pulls together interesting examples from the `bokeh` documentation into a single notebook to give you a taster of what can be done with `bokeh`.
%% Cell type:code id: tags:
``` python
from bokeh.plotting import figure, output_file, show
from bokeh.io import output_notebook
output_notebook()
```
%% Cell type:code id: tags:
``` python
from bokeh import sampledata
sampledata.download()
```
%% Cell type:markdown id: tags:
## Scatter Plots
https://docs.bokeh.org/en/latest/docs/gallery/iris.html
%% Cell type:code id: tags:
``` python
from bokeh.sampledata.iris import flowers
colormap = {'setosa': 'red', 'versicolor': 'green', 'virginica': 'blue'}
colors = [colormap[x] for x in flowers['species']]
p = figure(title = "Iris Morphology")
p.xaxis.axis_label = 'Petal Length'
p.yaxis.axis_label = 'Petal Width'
p.circle(flowers["petal_length"], flowers["petal_width"],
color=colors, fill_alpha=0.2, size=10)
# output_file("iris.html", title="iris.py example")
show(p)
```
%% Cell type:markdown id: tags:
## Line Plots
https://docs.bokeh.org/en/latest/docs/gallery/box_annotation.html
%% Cell type:code id: tags:
``` python
from bokeh.models import BoxAnnotation
from bokeh.sampledata.glucose import data
TOOLS = "pan,wheel_zoom,box_zoom,reset,save"
data = data.loc['2010-10-04':'2010-10-04']
p = figure(x_axis_type="datetime", tools=TOOLS, title="Glocose Readings, Oct 4th (Red = Outside Range)")
p.background_fill_color = "#efefef"
p.xgrid.grid_line_color=None
p.xaxis.axis_label = 'Time'
p.yaxis.axis_label = 'Value'
p.line(data.index, data.glucose, line_color='grey')
p.circle(data.index, data.glucose, color='grey', size=1)
p.add_layout(BoxAnnotation(top=80, fill_alpha=0.1, fill_color='red', line_color='red'))
p.add_layout(BoxAnnotation(bottom=180, fill_alpha=0.1, fill_color='red', line_color='red'))
show(p)
```
%% Cell type:markdown id: tags:
# Bar Charts
https://docs.bokeh.org/en/latest/docs/gallery/bar_stacked.html
%% Cell type:code id: tags:
``` python
from bokeh.palettes import Spectral5
from bokeh.sampledata.autompg import autompg_clean as df
from bokeh.transform import factor_cmap
df.cyl = df.cyl.astype(str)
df.yr = df.yr.astype(str)
group = df.groupby(['cyl', 'mfr'])
index_cmap = factor_cmap('cyl_mfr', palette=Spectral5, factors=sorted(df.cyl.unique()), end=1)
p = figure(plot_width=800, plot_height=500, title="Mean MPG by # Cylinders and Manufacturer",
x_range=group, toolbar_location=None, tooltips=[("MPG", "@mpg_mean"), ("Cyl, Mfr", "@cyl_mfr")])
p.vbar(x='cyl_mfr', top='mpg_mean', width=1, source=group,
line_color="white", fill_color=index_cmap, )
p.y_range.start = 0
p.x_range.range_padding = 0.05
p.xgrid.grid_line_color = None
p.xaxis.axis_label = "Manufacturer grouped by # Cylinders"
p.xaxis.major_label_orientation = 1.2
p.outline_line_color = None
show(p)
```
%% Cell type:markdown id: tags:
# Distribution Plots
https://docs.bokeh.org/en/latest/docs/gallery/histogram.html
%% Cell type:code id: tags:
``` python
import numpy as np
import scipy.special
from bokeh.layouts import gridplot
def make_plot(title, hist, edges, x, pdf, cdf):
p = figure(title=title, tools='', background_fill_color="#fafafa")
p.quad(top=hist, bottom=0, left=edges[:-1], right=edges[1:],
fill_color="navy", line_color="white", alpha=0.5)
p.line(x, pdf, line_color="#ff8888", line_width=4, alpha=0.7, legend_label="PDF")
p.line(x, cdf, line_color="orange", line_width=2, alpha=0.7, legend_label="CDF")
p.y_range.start = 0
p.legend.location = "center_right"
p.legend.background_fill_color = "#fefefe"
p.xaxis.axis_label = 'x'
p.yaxis.axis_label = 'Pr(x)'
p.grid.grid_line_color="white"
return p
# Normal Distribution
mu, sigma = 0, 0.5
measured = np.random.normal(mu, sigma, 1000)
hist, edges = np.histogram(measured, density=True, bins=50)
x = np.linspace(-2, 2, 1000)
pdf = 1/(sigma * np.sqrt(2*np.pi)) * np.exp(-(x-mu)**2 / (2*sigma**2))
cdf = (1+scipy.special.erf((x-mu)/np.sqrt(2*sigma**2)))/2
p1 = make_plot("Normal Distribution (μ=0, σ=0.5)", hist, edges, x, pdf, cdf)
# Log-Normal Distribution
mu, sigma = 0, 0.5
measured = np.random.lognormal(mu, sigma, 1000)
hist, edges = np.histogram(measured, density=True, bins=50)
x = np.linspace(0.0001, 8.0, 1000)
pdf = 1/(x* sigma * np.sqrt(2*np.pi)) * np.exp(-(np.log(x)-mu)**2 / (2*sigma**2))