Python Altair可视化工具入门与实战

参考文章：

python大佬的可视化工具-Altair_qq_21478261的博客-CSDN博客_altair python

官方参考文章：

Example Gallery — Altair 4.2.0 documentation

Overview | Vega-Litepaaas

安装 轮子 ：

$ pip install altair vega_datasets

官网部分案列：

# Altair, datasets are most commonly provided as a Dataframeimport pandas as pdimport altair as alt'''https://altair-viz.github.io/user_guide/encoding.html''''''https://vega.github.io/vega-lite/docs/'''from vega_datasets import dataimport numpy as nppd.set_option('display.max_columns', 10)#显示列数pd.set_option('display.max_rows', 10)#显示行数pd.set_option('display.width',	5000)#显示宽度 df = data.seattle_weather()print(df)scale = alt.Scale(    domain=['sun', 'fog', 'drizzle', 'rain', 'snow'],    range=['#e7ba52', '#c7c7c7', '#aec7e8', '#1f77b4', '#9467bd'])brush = alt.selection(type='interval')points = alt.Chart().mark_point().encode(    alt.X('temp_max:Q', title='Maximum Daily Temperature (C)'),    alt.Y('temp_range:Q', title='Daily Temperature Range (C)'),    color=alt.condition(brush,                        'weather:N',                        alt.value('lightgray'),                        scale=scale),    size=alt.Size('precipitation:Q',                  scale=alt.Scale(range=[1, 200]))).transform_calculate(    "temp_range",    "datum.temp_max - datum.temp_min").properties(    width=600, height=400).add_selection(brush) bars = alt.Chart().mark_bar().encode(    x='count()',    y='weather:N',    color=alt.Color('weather:N', scale=scale),).transform_calculate(    "temp_range",    "datum.temp_max - datum.temp_min").transform_filter(brush).properties(    width=600) chart_w=alt.vconcat(points, bars, data=df)chart_w.save("altair-weather.html") print("-------------- interactive scatter plot--------------")cars = data.cars()print("cars:\n",cars)'''cars: Name Miles_per_Gallon Cylinders Displacement Horsepower Weight_in_lbs Acceleration Year Origin0 chevrolet chevelle malibu 18.0 8 307.0 130.0 3504 12.0 1970-01-01 USA1 buick skylark 320 15.0 8 350.0 165.0 3693 11.5 1970-01-01 USA2 plymouth satellite 18.0 8 318.0 150.0 3436 11.0 1970-01-01 USA3 amc rebel sst 16.0 8 304.0 150.0 3433 12.0 1970-01-01 USA4 ford torino 17.0 8 302.0 140.0 3449 10.5 1970-01-01 USA'''#The key idea is that you are declaring links between data columns# and visual encoding channels, such as the x-axis, y-axis, color, etc.chart_car=alt.Chart(cars).mark_point().encode(    x='Horsepower',#马力    y='Miles_per_Gallon',#油耗    # y='average(Miles_per_Gallon)',#油耗    color='Origin',#来自哪里).interactive()chart_car.save("altair-cars_y=Miles_per_Gallon.html")  print("-------------- mark_bar--------------")data_bar = pd.DataFrame({'a': list('CCCDDDEEE'),                     'b': [2, 7, 4, 1, 2, 6, 8, 4, 7],                     'b_des': [3, 8, 4, 1, 4, 4, 7, 4, 7]                         })chart_bar_xy=alt.Chart(data_bar).mark_bar().encode(    x='a',    y="average(b)")chart_bar_yx=alt.Chart(data_bar).mark_bar(color='firebrick').encode(    alt.X('b', type='quantitative', aggregate='average',title='avg(b) by category'),    alt.Y('a', type='nominal',title='category'))#画目标线tick = alt.Chart(data_bar).mark_tick(    color='red',    thickness=2,    size=20 * 0.9,  # controls width of tick.).encode(    x='a',    y='average(b_des)')(chart_bar_xy+tick).save("chart_bar_xy_tick.html")chart_bar_yx.save("chart_bar_yx.html") source = data.wheat()#画bar图chart_bar_wheat=alt.Chart(source).mark_bar().encode(    y="wheat:Q",    x='year:O',    # The highlight will be set on the result of a conditional statement    #根据条件设定bar的颜色值    color=alt.condition(        alt.datum.year < 1610,  # If the year is 1810 this test returns True,        alt.value('orange'),     # which sets the bar orange.        alt.value('steelblue')   # And if it's not true it sets the bar steelblue.    ))#加上数量text = chart_bar_wheat.mark_text(    align='center',    baseline='middle',    dy=-7  # Nudges text to right so it doesn't appear on top of the bar).encode(    text='wheat:Q')# 增加均值线rule = alt.Chart(source).mark_rule(color='red').encode(    y='mean(wheat):Q') #增加一个变量,同Y坐标line = chart_bar_wheat.mark_line(color='red').encode(    y='wages:Q')#增加平均值的趋势line2= alt.Chart(source).mark_line(color='red').transform_window(    # The field to average    rolling_mean='mean(wheat)',    # The number of values before and after the current value to include.    frame=[-9, 0]).encode(    x='year:O',    y='rolling_mean:Q')chart_bar_wheat_text_rule_line=(chart_bar_wheat+text+rule+line+line2).properties(height=900,width=600)chart_bar_wheat_text_rule_line.save("chart_bar_wheat_text_rule_line.html") print("-------------- mark_bar:叠加图--------------")source = data.seattle_weather()print("source:\n",source[:6])'''source: date precipitation temp_max temp_min wind weather0 2012-01-01 0.0 12.8 5.0 4.7 drizzle1 2012-01-02 10.9 10.6 2.8 4.5 rain2 2012-01-03 0.8 11.7 7.2 2.3 rain'''mark_bar_round=alt.Chart(source).mark_bar(    cornerRadiusTopLeft=3,#矩形倒角    cornerRadiusTopRight=3,#矩形倒角    opacity=0.8).encode(    x='month(date):O',    y='count(weather):Q',#weather的计数，根据color中的属性值计数     color='weather:N')mark_bar_round.save("mark_bar_round.html") print("-------------- mark_tick:标记图--------------")chart_tick=alt.Chart(cars).mark_tick().encode(    x='Horsepower:Q',    y='Cylinders:O'#作为标记 )chart_tick.save("chart_tick.html") print("-------------- mark_bar:joinaggregate transform--------------") source = pd.DataFrame({'Activity': ['Sleeping', 'Eating', 'TV', 'Work', 'Exercise'],                           'Time': [8, 2, 4, 8, 2]}) chart_bar_joinaggregate=alt.Chart(source).transform_joinaggregate(    TotalTime='sum(Time)',).transform_calculate(    PercentOfTotal="datum.Time / datum.TotalTime").mark_bar().encode(    alt.X('PercentOfTotal:Q', axis=alt.Axis(format='.0%')),    y='Activity:N')chart_bar_joinaggregate.save("chart_bar_joinaggregate.html")  print("-------------- mark_bar:mark_bar_sum--------------")source2 = data.barley()print(source2)mark_bar_sum1=alt.Chart(source2).mark_bar().encode(    x=alt.X('sum(yield)',  stack='normalize'),    y='variety',    color=alt.Color('site'))text1 = alt.Chart(source2).mark_text(dx=-15, dy=3, color='white').encode(    x=alt.X('sum(yield):Q', stack='normalize'),    y=alt.Y('variety:N'),    detail='site:N',    text=alt.Text('sum(yield):Q', format='.1f'))mark_bar_sum2=alt.Chart(source2).mark_bar().encode(    column='year',    x='sum(yield):Q',    y=alt.Y('site:N', sort='x'),    color='variety',    order=alt.Order(      # Sort the segments of the bars by this field      'variety',      sort='ascending'    )) text2 = alt.Chart(source2).mark_text(dx=-15, dy=3, color='white').encode(    column='year',    x=alt.X('sum(yield):Q', stack='zero'),    y=alt.Y('site:N'),    detail='variety:N',    text=alt.Text('sum(yield):Q', format='.1f'))mark_bar_sum1_text=mark_bar_sum1+text1mark_bar_sum2_text=mark_bar_sum2mark_bar_sum=(mark_bar_sum1_text & mark_bar_sum2_text)mark_bar_sum.save("mark_bar_sum.html")  print("-------------- mark_line:with Confidence Interval Band--------------")line = alt.Chart(cars).mark_line().encode(    x='Year',    y='mean(Miles_per_Gallon)') band = alt.Chart(cars).mark_errorband(extent='ci').encode(    x='Year',    y=alt.Y('Miles_per_Gallon', title='Miles/Gallon'),) mark_line=band + linemark_line.save("mark_line.html") print("-------------- mark_area--------------")source = data.sp500.urlbrush = alt.selection(type='interval', encodings=['x'])base = alt.Chart(source).mark_area().encode(    x = 'date:T',    y = 'price:Q').properties(    width=600,    height=200) upper = base.encode(    alt.X('date:T', scale=alt.Scale(domain=brush))) lower = base.properties(    height=60).add_selection(brush)mark_area_A=upper & lowermark_area_A.save("mark_area_A.html") source_iowa_electricity = data.iowa_electricity()print("data.iowa_electricity():\n",source_iowa_electricity)mark_area_B=alt.Chart(source_iowa_electricity).mark_area(opacity=0.3).encode(    x="year:T",    y=alt.Y("net_generation:Q", stack=None),    color="source:N")mark_area_B.save("mark_area_B.html") mark_area_B_row=alt.Chart(source_iowa_electricity).mark_area().encode(    x="year:T",    y="net_generation:Q",    color="source:N",    row="source:N").properties(    height=100)mark_area_B_row.save("mark_area_B_row.html") source_iris = data.iris()print("data.iris():\n",source_iris)'''data.iris(): sepalLength sepalWidth petalLength petalWidth species0 5.1 3.5 1.4 0.2 setosa1 4.9 3.0 1.4 0.2 setosa... 146 6.3 2.5 5.0 1.9 virginica147 6.5 3.0 5.2 2.0 virginica'''mark_area_C=alt.Chart(source_iris).transform_fold(    ['petalWidth',     'petalLength',     'sepalWidth',     'sepalLength'],    as_ = ['Measurement_type', 'value']).transform_density(    density='value',    bandwidth=0.3,    groupby=['Measurement_type'],    extent= [0, 8],    counts = True,    steps=200).mark_area().encode(    alt.X('value:Q'),    alt.Y('density:Q', stack='zero'),    alt.Color('Measurement_type:N')).properties(width=400, height=100)mark_area_C.save("mark_area_C.html") source_stocks = data.stocks()print("data.stocks():\n",source_stocks)'''data.stocks(): symbol date price0 MSFT 2000-01-01 39.811 MSFT 2000-02-01 36.35... 557 AAPL 2010-01-01 192.06558 AAPL 2010-02-01 204.62'''mark_area_D=alt.Chart(source_stocks).transform_filter(    alt.datum.symbol != 'GOOG').mark_area().encode(    x='date:T',    y='price:Q',    color='symbol:N',    row=alt.Row('symbol:N', sort=['MSFT', 'AAPL', 'IBM', 'AMZN'])).properties(height=50, width=400)mark_area_D.save("mark_area_D.html")  print("-------------- mark_point+mark_tick--------------")# Configure the options common to all layersbrush = alt.selection(type='interval')base = alt.Chart(cars).add_selection(brush) # Configure the pointspoints = base.mark_point().encode(    x=alt.X('Miles_per_Gallon', title=''),    y=alt.Y('Horsepower', title=''),    color=alt.condition(brush, 'Origin', alt.value('grey'))) # Configure the tickstick_axis = alt.Axis(labels=False, domain=False, ticks=False) x_ticks = base.mark_tick().encode(    alt.X('Miles_per_Gallon', axis=tick_axis),    alt.Y('Origin', title='', axis=tick_axis),    color=alt.condition(brush, 'Origin', alt.value('lightgrey'))) y_ticks = base.mark_tick().encode(    alt.X('Origin', title='', axis=tick_axis),    alt.Y('Horsepower', axis=tick_axis),    color=alt.condition(brush, 'Origin', alt.value('lightgrey'))) # Build the chartcars_tick=y_ticks | (points & x_ticks)cars_tick.save("cars_tick.html") print("-------------- mark_circle--------------")mark_circle_car=alt.Chart(cars).mark_circle().encode(    alt.X(alt.repeat("column"), type='quantitative'),    alt.Y(alt.repeat("row"), type='quantitative'),    color='Origin:N').properties(    width=150,    height=150).repeat(    row=['Horsepower', 'Acceleration', 'Miles_per_Gallon'],    column=['Miles_per_Gallon', 'Acceleration', 'Horsepower']).interactive()mark_circle_car.save("mark_circle_car.html") np.random.seed(1)source_loess = pd.DataFrame({    'x': np.arange(100),    'A': np.random.randn(100).cumsum(),    'B': np.random.randn(100).cumsum(),    'C': np.random.randn(100).cumsum(),}) print("-------------- 趋势线--------------")base1 = alt.Chart(source_loess).mark_circle(opacity=0.5).transform_fold(    fold=['C'],    as_=['category', 'y'],).encode(    alt.X('x:Q'),    alt.Y('y:Q'),    alt.Color('category:N'))base2 = alt.Chart(source_loess).mark_circle(opacity=0.5).transform_fold(    fold=['A', 'B'],    as_=['category2', 'y2'],).encode(    alt.X('x:Q'),    alt.Y('y2:Q'),    alt.Color('category2:N'))mark_circle_loess=base1 + base2+ base2.transform_loess('x', 'y2', groupby=['category2']).mark_line(size=4)mark_circle_loess.save("mark_circle_loess.html") print("-------------- MAPS--------------")# Data generators for the backgroundsphere = alt.sphere()graticule = alt.graticule() # Source of land datasource = alt.topo_feature(data.world_110m.url, 'countries') # Layering and configuring the componentsmaps_world=alt.layer(    alt.Chart(sphere).mark_geoshape(fill='lightblue'),    alt.Chart(graticule).mark_geoshape(stroke='white', strokeWidth=0.5),    alt.Chart(source).mark_geoshape(fill='ForestGreen', stroke='black')).project(    'naturalEarth1').properties(width=600, height=400).configure_view(stroke=None)maps_world.save("maps_world.html")

免责声明：本文系网络转载或改编，未找到原创作者，版权归原作者所有。如涉及版权，请联系删