Python可视化库之HoloViews的使用教程

Manda ·

更新时间:2024-09-20

· 186 次阅读

Python-HoloViews库介绍

Python-HoloViews库样例介绍

密度图+箱线图

散点图+横线图

IrisSplom

面积图

直方图系列

RouteChord

小提琴图

总结

参考资料

最近一直在整理统计图表的绘制方法，发现Python中除了经典Seaborn库外，还有一些优秀的可交互的第三方库也能实现一些常见的统计图表绘制，而且其还拥有Matplotlib、Seaborn等库所不具备的交互效果。

当然，同时也能绘制出版级别的图表要求，此外，一些在使用Matplotlib需自定义函数才能绘制的图表在一些第三方库中都集成了，这也大大缩短了绘图时间。

今天我就详细介绍一个优秀的第三方库-HoloViews，内容主要如下：

Python-HoloViews库介绍

Python-HoloViews库样例介绍

Python-HoloViews库介绍

Python-HoloViews库作为一个开源的可视化库，其目的是使数据分析结果和可视化完美衔接，其默认的绘图主题和配色以及较少的绘图代码量，可以使你专注于数据分析本身，同时其统计绘图功能也非常优秀。更多关于HoloViews库的介绍，可参考：Python-HoloViews库官网[1]

Python-HoloViews库样例介绍

这一部分小编重点放在一些统计图表上，其绘制结果不仅可以在网页上交互，同时其默认的绘图结果也完全满足出版界别的要求，主要内容如下(以下图表都是可交互的)：

密度图+箱线图

import pandas as pd
import holoviews as hv
from bokeh.sampledata import autompg
hv.extension('bokeh')
df = autompg.autompg_clean
bw = hv.BoxWhisker(df, kdims=["origin"], vdims=["mpg"])
dist = hv.NdOverlay(
    {origin: hv.Distribution(group, kdims=["mpg"]) 
         for origin, group in df.groupby("origin")}
)
bw + dist

密度图+箱线图

散点图+横线图

scatter = hv.Scatter(df, kdims=["origin"], vdims=["mpg"]).opts(jitter=0.3)
yticks = [(i + 0.25, origin) for i, origin in enumerate(df["origin"].unique())]
spikes = hv.NdOverlay(
    {
        origin: hv.Spikes(group["mpg"]).opts(position=i)
            for i, (origin, group) in enumerate(df.groupby("origin", sort=False))
    }
).opts(hv.opts.Spikes(spike_length=0.5, yticks=yticks, show_legend=False, alpha=0.3))
scatter + spikes

散点图+横线图

Iris Splom

from bokeh.sampledata.iris import flowers
from holoviews.operation import gridmatrix
ds = hv.Dataset(flowers)
grouped_by_species = ds.groupby('species', container_type=hv.NdOverlay)
grid = gridmatrix(grouped_by_species, diagonal_type=hv.Scatter)
grid.opts(opts.Scatter(tools=['hover', 'box_select'], bgcolor='#efe8e2', fill_alpha=0.2, size=4))

Iris Splom

面积图

# create some example data
python=np.array([2, 3, 7, 5, 26, 221, 44, 233, 254, 265, 266, 267, 120, 111])
pypy=np.array([12, 33, 47, 15, 126, 121, 144, 233, 254, 225, 226, 267, 110, 130])
jython=np.array([22, 43, 10, 25, 26, 101, 114, 203, 194, 215, 201, 227, 139, 160])
dims = dict(kdims='time', vdims='memory')
python = hv.Area(python, label='python', **dims)
pypy   = hv.Area(pypy,   label='pypy',   **dims)
jython = hv.Area(jython, label='jython', **dims)
opts.defaults(opts.Area(fill_alpha=0.5))
overlay = (python * pypy * jython)
overlay.relabel("Area Chart") + hv.Area.stack(overlay).relabel("Stacked Area Chart")

面积图

直方图系列

def get_overlay(hist, x, pdf, cdf, label):
    pdf = hv.Curve((x, pdf), label='PDF')
    cdf = hv.Curve((x, cdf), label='CDF')
    return (hv.Histogram(hist, vdims='P(r)') * pdf * cdf).relabel(label)
np.seterr(divide='ignore', invalid='ignore')
label = "Normal Distribution (μ=0, σ=0.5)"
mu, sigma = 0, 0.5
measured = np.random.normal(mu, sigma, 1000)
hist = 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
norm = get_overlay(hist, x, pdf, cdf, label)
label = "Log Normal Distribution (μ=0, σ=0.5)"
mu, sigma = 0, 0.5
measured = np.random.lognormal(mu, sigma, 1000)
hist = np.histogram(measured, density=True, bins=50)
x = np.linspace(0, 8.0, 1000)
pdf = 1/(x* sigma * np.sqrt(2*np.pi)) * np.exp(-(np.log(x)-mu)**2 / (2*sigma**2))
cdf = (1+scipy.special.erf((np.log(x)-mu)/(np.sqrt(2)*sigma)))/2
lognorm = get_overlay(hist, x, pdf, cdf, label)
label = "Gamma Distribution (k=1, θ=2)"
k, theta = 1.0, 2.0
measured = np.random.gamma(k, theta, 1000)
hist = np.histogram(measured, density=True, bins=50)
x = np.linspace(0, 20.0, 1000)
pdf = x**(k-1) * np.exp(-x/theta) / (theta**k * scipy.special.gamma(k))
cdf = scipy.special.gammainc(k, x/theta) / scipy.special.gamma(k)
gamma = get_overlay(hist, x, pdf, cdf, label)
label = "Beta Distribution (α=2, β=2)"
alpha, beta = 2.0, 2.0
measured = np.random.beta(alpha, beta, 1000)
hist = np.histogram(measured, density=True, bins=50)
x = np.linspace(0, 1, 1000)
pdf = x**(alpha-1) * (1-x)**(beta-1) / scipy.special.beta(alpha, beta)
cdf = scipy.special.btdtr(alpha, beta, x)
beta = get_overlay(hist, x, pdf, cdf, label)
label = "Weibull Distribution (λ=1, k=1.25)"
lam, k = 1, 1.25
measured = lam*(-np.log(np.random.uniform(0, 1, 1000)))**(1/k)
hist = np.histogram(measured, density=True, bins=50)
x = np.linspace(0, 8, 1000)
pdf = (k/lam)*(x/lam)**(k-1) * np.exp(-(x/lam)**k)
cdf = 1 - np.exp(-(x/lam)**k)
weibull = get_overlay(hist, x, pdf, cdf, label)

直方图系列

Route Chord

import holoviews as hv
from holoviews import opts, dim
from bokeh.sampledata.airport_routes import routes, airports
hv.extension('bokeh')
# Count the routes between Airports
route_counts = routes.groupby(['SourceID', 'DestinationID']).Stops.count().reset_index()
nodes = hv.Dataset(airports, 'AirportID', 'City')
chord = hv.Chord((route_counts, nodes), ['SourceID', 'DestinationID'], ['Stops'])
# Select the 20 busiest airports
busiest = list(routes.groupby('SourceID').count().sort_values('Stops').iloc[-20:].index.values)
busiest_airports = chord.select(AirportID=busiest, selection_mode='nodes')
busiest_airports.opts(
    opts.Chord(cmap='Category20', edge_color=dim('SourceID').str(), 
               height=800, labels='City', node_color=dim('AirportID').str(), width=800))

Route Chord

小提琴图

import holoviews as hv
from holoviews import dim
from  bokeh.sampledata.autompg import autompg
hv.extension('bokeh')
violin = hv.Violin(autompg, ('yr', 'Year'), ('mpg', 'Miles per Gallon')).redim.range(mpg=(8, 45))
violin.opts(height=500, width=900, violin_fill_color=dim('Year').str(), cmap='Set1')