Python数据可视化的五种方法小结

import holoviews as hv
from holoviews import opts
import pandas as pd
import numpy as np
hv.extension('bokeh')
 
# 代表5个国家之间出口量的示例矩阵
export_data = np.array([[0, 50, 30, 20, 10],   
                        [10, 0, 40, 30, 20],   
                        [20, 10, 0, 35, 25],   
                        [30, 20, 10, 0, 40],   
                        [25, 15, 30, 20, 0]]) 
 
labels = ['美国', '中国', '德国', '日本', '印度']
 
# 创建一个pandas DataFrame
df = pd.DataFrame(export_data, index=labels, columns=labels)
df = df.stack().reset_index()
df.columns = ['来源', '目标', '数值']
 
# 创建一个Chord对象
chord = hv.Chord(df)
 
# 对和弦图进行样式设置
chord.opts(
    opts.Chord(
        cmap='Category20', edge_cmap='Category20', 
        labels='source', label_text_font_size='10pt',  
        edge_color='source', node_color='index', 
        width=700, height=700
    )
).select(value=(5, None)) 
 
# 显示图表
chord

import plotly.express as px
import numpy as np
 
df = px.data.gapminder().query("year == 2007")
 
fig = px.sunburst(df, path=['continent', 'country'], 
                  values='pop',
                  color='lifeExp', 
                  hover_data=['iso_alpha'],
                  color_continuous_scale='RdBu',
                  color_continuous_midpoint=np.average(df['lifeExp'], weights=df['pop']))
fig.show()

import numpy as np
import matplotlib.pyplot as plt
from mplhexbin import HexBin
 
# 模拟数据
np.random.seed(0)  # 确保结果可复现
n_points = 10000
x = np.random.rand(n_points) * 100# 空气质量指数（AQI）取值范围为0到100
y = 5 * np.sin(x * np.pi / 50) + np.random.randn(n_points) * 15# 模拟的医院就诊人数，与AQI相关但存在噪声
 
# 创建一个新的图形
fig, ax = plt.subplots(figsize=(10, 8))
 
# 使用HexBin创建六边形分箱图
hb = HexBin(ax, gridsize=20, cmap='viridis', extent=[0, 100, -30, 50])  # 设置网格大小、颜色映射和范围
hb.hexbin(x, y, mincnt=1)  # 绘制六边形分箱图，mincnt设置最小计数阈值
 
# 添加标题和轴标签
ax.set_title('空气质量指数（AQI）与医院就诊人数之间的关系')
ax.set_xlabel('空气质量指数（AQI）')
ax.set_ylabel('医院就诊人数')
 
# 显示图形
plt.colorbar(hb.cmap, ax=ax, label='数据点数量')  # 添加颜色条并设置标签
plt.show()

import plotly.graph_objects as go
 
labels = ["煤炭", "太阳能", "风能", "核能", "居民", "工业", "商业"]
 
source = [0, 1, 2, 3, 0, 1, 2, 3] 
target = [4, 4, 4, 4, 5, 5, 5, 5] 
value = [25, 10, 40, 20, 30, 15, 25, 35] 
 
# 创建桑基图对象
fig = go.Figure(data=[go.Sankey(
    node=dict(
        pad=15,  
        thickness=20, 
        line=dict(color="black", width=0.5),
        label=labels 
    ),
    link=dict(
        source=source,  
        target=target, 
        value=value  
    ))])
 
fig.update_layout(title_text="模范城市的能源流动", font_size=12)
fig.show()

import altair as alt
from vega_datasets import data
 
source = data.unemployment_across_industries.url
 
alt.Chart(source).mark_area().encode(
    alt.X('yearmonth(date):T',
        axis=alt.Axis(format='%Y', domain=False, tickSize=0)
    ),
    alt.Y('sum(count):Q', stack='center', axis=None),
    alt.Color('series:N',
        scale=alt.Scale(scheme='category20b')
    )
).interactive()