从入门到精通详解Python数据可视化的深度指南

import matplotlib.pyplot as plt

# 1. 创建画布和坐标轴
fig, ax = plt.subplots(figsize=(10, 6))

# 2. 手动循环绘制每一类数据 (matplotlib不自动处理分类映射)
for category, color in zip(['a', 'b', 'c'], ['red', 'green', 'blue']):
    subset = df[df['category'] == category]
    ax.scatter(
        subset['x'], 
        subset['y'], 
        c=color, 
        label=category, 
        alpha=0.6
    )

# 3. 手动添加装饰元素
ax.set_title('matplotlib scatter')
ax.set_xlabel('x axis')
ax.set_ylabel('y axis')
ax.legend(title='category')
ax.grid(true)
plt.show()

import seaborn as sns

plt.figure(figsize=(10, 6))
# 直接传入 dataframe，指定列名映射
sns.scatterplot(
    data=df, 
    x='x', 
    y='y', 
    hue='category',  # 自动处理颜色映射和图例
    style='category', # 自动处理形状映射
    s=100,
    alpha=0.7
)
plt.title('seaborn scatter')
plt.show()

import plotly.express as px

# 一行代码生成交互式图表
fig = px.scatter(
    df, 
    x='x', 
    y='y', 
    color='category', 
    size='size',      # 气泡大小映射
    hover_data=['category'], # 悬停显示额外信息
    title='plotly interactive scatter',
    template='plotly_white'
)

# 在 jupyter notebook 中直接显示，或保存为 html
fig.show()
# fig.write_html("scatter.html")

import plotly.graph_objects as go
import pandas as pd

# 假设 df 为包含 open, high, low, close 的 dataframe
fig = go.figure(data=[go.candlestick(
    x=df.index,
    open=df['open'],
    high=df['high'],
    low=df['low'],
    close=df['close'],
    increasing_line_color='red', # 国内习惯：涨红跌绿
    decreasing_line_color='green'
)])

fig.update_layout(
    title='aapl stock price',
    xaxis_title='date',
    yaxis_title='price (usd)',
    xaxis_rangeslider_visible=false # 隐藏底部滑块
)
fig.show()

import geopandas as gpd
import matplotlib.pyplot as plt

# 1. 读取内置的世界地图数据 (包含几何形状 geometry)
world = gpd.read_file(gpd.datasets.get_path('naturalearth_lowres'))

# 2. 绘制分级统计图
fig, ax = plt.subplots(1, 1, figsize=(15, 10))
world.plot(
    column='pop_est',      # 映射颜色的数据列 (如人口)
    ax=ax,
    legend=true,           # 显示图例
    legend_kwds={'label': "population by country", 'orientation': "horizontal"},
    cmap='orrd',           # 颜色映射
    edgecolor='black',     # 边界线颜色
    linewidth=0.5
)
plt.title('world population density')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

# 1. 准备网格数据
x = np.arange(-5, 5, 0.25)
y = np.arange(-5, 5, 0.25)
x, y = np.meshgrid(x, y)
r = np.sqrt(x**2 + y**2)
z = np.sin(r)

# 2. 创建 3d 坐标轴
fig = plt.figure(figsize=(10, 8))
ax = fig.add_subplot(111, projection='3d')

# 3. 绘制曲面
surf = ax.plot_surface(
    x, y, z, 
    cmap='viridis',
    linewidth=0, 
    antialiased=false
)

fig.colorbar(surf, shrink=0.5, aspect=5)
plt.title('3d surface plot')
plt.show()

import streamlit as st
import plotly.express as px
import pandas as pd

# 1. 页面配置
st.set_page_config(layout="wide")
st.title("my first streamlit app")

# 2. 侧边栏控件
year = st.sidebar.slider("select year", 2010, 2020, 2015)

# 3. 数据处理与绘图
data = pd.dataframe({'year': [2010, 2015, 2020], 'value': [10, 20, 30]})
filtered_data = data[data['year'] == year]

st.subheader(f"data for {year}")
fig = px.bar(filtered_data, x='year', y='value')
st.plotly_chart(fig)

# 4. 显示数据表格
if st.checkbox("show data"):
    st.dataframe(filtered_data)

from dash import dash, html, dcc, callback, output, input
import plotly.express as px

app = dash(__name__)

# 1. 定义布局 (html + 组件)
app.layout = html.div([
    html.h1("dash dashboard"),
    dcc.dropdown(id='my-dropdown', options=['a', 'b'], value='a'),
    dcc.graph(id='my-graph')
])

# 2. 定义回调逻辑 (交互核心)
@callback(
    output('my-graph', 'figure'),
    input('my-dropdown', 'value')
)
def update_graph(selected_value):
    # 根据输入生成图表
    df = get_data(selected_value)
    return px.line(df, x='time', y='value')

if __name__ == '__main__':
    app.run(debug=true)

import plotly.graph_objects as go
import numpy as np

# 生成 100万个点
n = 1000000
x = np.random.randn(n)
y = np.random.randn(n)

# 使用 scattergl 替代普通的 scatter
fig = go.figure(data=go.scattergl(
    x=x,
    y=y,
    mode='markers',
    marker=dict(
        color=np.random.randn(n),
        colorscale='viridis',
        line_width=0, # 去掉描边可以显著提升性能
        opacity=0.5
    )
))

fig.update_layout(title='1 million points with webgl')
fig.show()

def optimize_memory(df):
    for col in df.columns:
        col_type = df[col].dtype
        if col_type != object:
            c_min = df[col].min()
            c_max = df[col].max()
            # 尝试转换为 int8, int16, int32
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                # ... (同理处理其他类型)
    return df

# 将秒级数据降采样为小时级均值
df_hourly = df_second.resample('h').mean()
plt.plot(df_hourly)

import matplotlib.pyplot as plt
import seaborn as sns

# 1. 全局样式配置 (global configuration)
plt.rcparams.update({
    'font.family': 'sans-serif',
    'font.sans-serif': ['arial'],   # 优先使用 arial
    'font.size': 10,                # 基础字号
    'axes.labelsize': 12,           # 轴标签字号
    'xtick.labelsize': 10,          # 刻度字号
    'ytick.labelsize': 10,
    'legend.fontsize': 10,
    'figure.figsize': (3.5, 2.5),   # 设定为单栏宽度 (英寸)
    'figure.dpi': 300,              # 设置 dpi
    'savefig.dpi': 600,             # 保存时的 dpi
    'lines.linewidth': 1.5,
    'lines.markersize': 6
})

# 2. 绘图
fig, ax = plt.subplots()
x = [1, 2, 3, 4]
y = [10, 20, 25, 30]
y_err = [1, 2, 1.5, 2]

# 使用误差棒 (error bar) 展示不确定性
ax.errorbar(x, y, yerr=y_err, fmt='-o', capsize=3, label='experiment', color='black')

# 3. 极简主义美化 (tufte's principle)
ax.set_xlabel('time (s)')
ax.set_ylabel('velocity (m/s)')
ax.spines['top'].set_visible(false)   # 去掉上边框
ax.spines['right'].set_visible(false) # 去掉右边框
ax.legend(frameon=false)              # 去掉图例边框

# 4. 保存为矢量图
plt.savefig('figure_1.pdf', bbox_inches='tight')

import seaborn as sns
import matplotlib.pyplot as plt

# 您的代码...
data = ...
sns.heatmap(data)
plt.show()