Python可视化库Matplotlib与Seaborn的使用方法

pip install matplotlib seaborn pandas numpy -i https://pypi.tuna.tsinghua.edu.cn/simple

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np

# 设置显示选项
plt.rcparams['axes.unicode_minus'] = false

# seaborn风格设置
sns.set_style("whitegrid")  # 可选: darkgrid, whitegrid, dark, white, ticks
sns.set_palette("husl")     # 设置配色方案

import matplotlib.pyplot as plt
import numpy as np

# 生成数据
months = np.arange(1, 13)
temperature = np.array([15, 18, 25, 32, 38, 42, 45, 43, 38, 30, 22, 17])

# 创建图表
plt.figure(figsize=(10, 6))
plt.plot(months, temperature, marker='o', linewidth=2, markersize=8, color='#ff6b6b')

# 添加标题和标签
plt.title('monthly average temperature trend 2024', fontsize=16, fontweight='bold', pad=20)
plt.xlabel('month', fontsize=12)
plt.ylabel('temperature (°c)', fontsize=12)

# 设置x轴刻度
month_labels = ['jan', 'feb', 'mar', 'apr', 'may', 'jun',
                'jul', 'aug', 'sep', 'oct', 'nov', 'dec']
plt.xticks(months, month_labels)

# 添加网格线
plt.grid(true, alpha=0.3, linestyle='--')

# 标注最高温和最低温
max_idx = np.argmax(temperature)
min_idx = np.argmin(temperature)
plt.annotate(f'max: {temperature[max_idx]}°c', xy=(months[max_idx], temperature[max_idx]),
             xytext=(months[max_idx]-1, temperature[max_idx]+3),
             arrowprops=dict(arrowstyle='->', color='red'))
plt.annotate(f'min: {temperature[min_idx]}°c', xy=(months[min_idx], temperature[min_idx]),
             xytext=(months[min_idx]+1, temperature[min_idx]-5),
             arrowprops=dict(arrowstyle='->', color='blue'))

plt.tight_layout()
plt.savefig('temperature_trend.png', dpi=150, bbox_inches='tight')
plt.show()

fig, ax = plt.subplots(figsize=(10, 6))

# 绘制多条线
x = np.linspace(0, 10, 100)
ax.plot(x, np.sin(x), label='sin(x)', color='#4ecdc4', linewidth=2)
ax.plot(x, np.cos(x), label='cos(x)', color='#ff6b6b', linewidth=2, linestyle='--')

# 设置标题和标签
ax.set_title('trigonometric functions', fontsize=14, pad=15)
ax.set_xlabel('x axis (radians)', fontsize=12)
ax.set_ylabel('y axis (function value)', fontsize=12)

# 设置坐标轴范围
ax.set_xlim(0, 10)
ax.set_ylim(-1.5, 1.5)

# 添加图例
ax.legend(loc='upper right', frameon=true, shadow=true)

# 添加水平参考线
ax.axhline(y=0, color='black', linewidth=0.5)
ax.axvline(x=np.pi, color='gray', linestyle=':', alpha=0.7)

# 设置刻度样式
ax.tick_params(axis='both', which='major', labelsize=10)

# 添加文字注释
ax.text(5, 1.2, 'sine and cosine functions', fontsize=12, ha='center',
        bbox=dict(boxstyle='round', facecolor='wheat', alpha=0.5))

plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(12, 10))

# 子图1：折线图
x = np.arange(5)
sales = [120, 150, 180, 165, 200]
axes[0, 0].plot(x, sales, marker='s', color='steelblue')
axes[0, 0].set_title('sales trend')
axes[0, 0].set_xticks(x)
axes[0, 0].set_xticklabels(['q1', 'q2', 'q3', 'q4', 'q5'])

# 子图2：柱状图
categories = ['a', 'b', 'c', 'd', 'e']
values = [23, 45, 56, 78, 32]
axes[0, 1].bar(categories, values, color='coral')
axes[0, 1].set_title('product sales comparison')

# 子图3：散点图
np.random.seed(42)
x_scatter = np.random.randn(50)
y_scatter = np.random.randn(50)
axes[1, 0].scatter(x_scatter, y_scatter, alpha=0.6, c=y_scatter, cmap='viridis')
axes[1, 0].set_title('scatter distribution')

# 子图4：饼图
sizes = [30, 25, 20, 15, 10]
labels = ['phone', 'pc', 'tablet', 'accessory', 'other']
axes[1, 1].pie(sizes, labels=labels, autopct='%1.1f%%', startangle=90)
axes[1, 1].set_title('category proportion')

plt.suptitle('data visualization dashboard', fontsize=16, fontweight='bold', y=1.02)
plt.tight_layout()
plt.show()

# 分组柱状图：各部门季度业绩
departments = ['tech', 'product', 'ops', 'marketing', 'support']
q1 = [85, 72, 90, 68, 75]
q2 = [88, 78, 85, 75, 80]
q3 = [92, 85, 88, 82, 78]
q4 = [95, 90, 92, 88, 85]

x = np.arange(len(departments))
width = 0.2

fig, ax = plt.subplots(figsize=(12, 6))
ax.bar(x - 1.5*width, q1, width, label='q1', color='#ff6b6b')
ax.bar(x - 0.5*width, q2, width, label='q2', color='#4ecdc4')
ax.bar(x + 0.5*width, q3, width, label='q3', color='#45b7d1')
ax.bar(x + 1.5*width, q4, width, label='q4', color='#96ceb4')

ax.set_xlabel('department', fontsize=12)
ax.set_ylabel('performance score', fontsize=12)
ax.set_title('quarterly performance by department', fontsize=14, fontweight='bold')
ax.set_xticks(x)
ax.set_xticklabels(departments)
ax.legend()
ax.set_ylim(0, 110)

# 添加数值标签
for i, v in enumerate(q4):
    ax.text(i + 1.5*width, v + 1, str(v), ha='center', fontsize=9)

plt.tight_layout()
plt.show()

# 气泡图：展示销售额、利润率和市场份额的关系
np.random.seed(42)
n = 30
sales = np.random.randint(50, 500, n)
profit_margin = np.random.uniform(5, 35, n)
market_share = np.random.uniform(1, 20, n)  # 气泡大小
categories = np.random.choice(['type a', 'type b', 'type c'], n)

colors = {'type a': '#ff6b6b', 'type b': '#4ecdc4', 'type c': '#45b7d1'}

fig, ax = plt.subplots(figsize=(10, 7))
for cat in ['type a', 'type b', 'type c']:
    mask = categories == cat
    ax.scatter(sales[mask], profit_margin[mask], 
               s=market_share[mask]*30, 
               c=colors[cat], alpha=0.6, label=cat, edgecolors='black', linewidth=0.5)

ax.set_xlabel('sales (10k cny)', fontsize=12)
ax.set_ylabel('profit margin (%)', fontsize=12)
ax.set_title('sales vs profit margin analysis (bubble size = market share)', fontsize=14)
ax.legend(title='product category')
ax.grid(true, alpha=0.3)

plt.tight_layout()
plt.show()

# 环形图
labels = ['mobile', 'pc', 'miniapp', 'h5', 'other']
sizes = [45, 25, 15, 10, 5]
colors = ['#ff6b6b', '#4ecdc4', '#45b7d1', '#96ceb4', '#ffeaa7']
explode = (0.05, 0, 0, 0, 0)

fig, ax = plt.subplots(figsize=(8, 8))
wedges, texts, autotexts = ax.pie(sizes, labels=labels, colors=colors,
                                   autopct='%1.1f%%', startangle=90,
                                   explode=explode, pctdistance=0.85,
                                   wedgeprops=dict(width=0.5, edgecolor='white'))

# 中心文字
ax.text(0, 0, 'traffic source\ndistribution', ha='center', va='center', fontsize=14, fontweight='bold')

ax.set_title('q3 2024 traffic source distribution', fontsize=14, pad=20)
plt.setp(autotexts, size=10, weight='bold')
plt.tight_layout()
plt.show()

np.random.seed(42)
data_a = np.random.normal(100, 15, 1000)
data_b = np.random.normal(130, 20, 1000)

fig, axes = plt.subplots(1, 2, figsize=(12, 5))

# 直方图
axes[0].hist(data_a, bins=30, alpha=0.7, label='group a', color='#ff6b6b', edgecolor='black')
axes[0].hist(data_b, bins=30, alpha=0.7, label='group b', color='#4ecdc4', edgecolor='black')
axes[0].set_xlabel('value')
axes[0].set_ylabel('frequency')
axes[0].set_title('histogram of data distribution')
axes[0].legend()

# 密度图
axes[1].hist(data_a, bins=30, density=true, alpha=0.5, color='#ff6b6b', label='group a')
axes[1].hist(data_b, bins=30, density=true, alpha=0.5, color='#4ecdc4', label='group b')
axes[1].set_xlabel('value')
axes[1].set_ylabel('density')
axes[1].set_title('density plot of data distribution')
axes[1].legend()

plt.tight_layout()
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

# 加载示例数据集
tips = sns.load_dataset('tips')
print(tips.head())

# 设置全局风格
sns.set_theme(style="whitegrid", palette="pastel", font_scale=1.1)

# 箱线图：展示不同日期的小费分布
fig, axes = plt.subplots(1, 2, figsize=(14, 6))

sns.boxplot(data=tips, x='day', y='total_bill', hue='sex', ax=axes[0])
axes[0].set_title('daily total bill distribution (box plot)')
axes[0].set_xlabel('day')
axes[0].set_ylabel('total bill ($)')

# 小提琴图
sns.violinplot(data=tips, x='day', y='total_bill', hue='sex', split=true, ax=axes[1])
axes[1].set_title('daily total bill distribution (violin plot)')
axes[1].set_xlabel('day')
axes[1].set_ylabel('total bill ($)')

plt.tight_layout()
plt.show()

# 联合分布图
sns.jointplot(data=tips, x='total_bill', y='tip', kind='reg', 
              height=8, color='#4ecdc4')
plt.suptitle('relationship between total bill and tip', y=1.02, fontsize=14)
plt.show()

# 配对图
iris = sns.load_dataset('iris')
sns.pairplot(iris, hue='species', height=2.5, palette='husl')
plt.suptitle('iris dataset pairwise analysis', y=1.02, fontsize=14)
plt.show()

# 构造相关性数据
np.random.seed(42)
df_corr = pd.dataframe({
    'sales': np.random.randint(100, 1000, 100),
    'ad_spend': np.random.randint(20, 200, 100),
    'customers': np.random.randint(50, 500, 100),
    'return_rate': np.random.uniform(0.01, 0.15, 100),
    'satisfaction': np.random.uniform(3.5, 5.0, 100)
})

# 添加相关性
df_corr['profit'] = df_corr['sales'] * 0.3 + np.random.normal(0, 20, 100)
df_corr['repurchase'] = df_corr['satisfaction'] * 0.1 + np.random.normal(0, 0.05, 100)

# 计算相关系数矩阵
corr_matrix = df_corr.corr()

fig, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(corr_matrix, annot=true, fmt='.2f', cmap='rdylbu_r',
            center=0, square=true, linewidths=0.5, cbar_kws={"shrink": 0.8}, ax=ax)
ax.set_title('business metrics correlation heatmap', fontsize=14, fontweight='bold', pad=20)
plt.tight_layout()
plt.show()

# 自定义颜色映射
from matplotlib.colors import linearsegmentedcolormap

colors = ['#ff6b6b', '#ffe66d', '#4ecdc4', '#45b7d1', '#96ceb4']
cmap = linearsegmentedcolormap.from_list('custom', colors)

# 使用自定义配色
fig, ax = plt.subplots(figsize=(8, 6))
data = np.random.rand(10, 10)
im = ax.imshow(data, cmap=cmap)
ax.set_title('custom color heatmap')
plt.colorbar(im, ax=ax)
plt.show()

import matplotlib.pyplot as plt
import numpy as np

# 1. 先创建图表
fig, ax = plt.subplots(figsize=(8, 6))
x = np.linspace(0, 10, 100)
ax.plot(x, np.sin(x), label='sin(x)', color='#4ecdc4', linewidth=2)
ax.plot(x, np.cos(x), label='cos(x)', color='#ff6b6b', linewidth=2, linestyle='--')
ax.set_title('export demo chart')
ax.legend()
ax.grid(true, alpha=0.3)

# 2. 再导出（在 show() 之前！）
plt.savefig('high_quality_chart.png', dpi=300, bbox_inches='tight',
            facecolor='white', edgecolor='none')

plt.savefig('vector_chart.pdf', format='pdf', bbox_inches='tight')

plt.savefig('web_chart.svg', format='svg', bbox_inches='tight')

# 3. 最后显示
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np

# 生成模拟销售数据
np.random.seed(2024)
dates = pd.date_range('2024-01-01', '2024-12-31', freq='d')
n = len(dates)

sales_data = pd.dataframe({
    'date': dates,
    'sales': np.random.normal(50000, 15000, n).clip(10000, 100000),
    'orders': np.random.poisson(200, n),
    'avg_price': np.random.normal(250, 50, n).clip(100, 500),
    'return_rate': np.random.uniform(0.02, 0.12, n),
    'category': np.random.choice(['electronics', 'clothing', 'food', 'home', 'beauty'], n),
    'region': np.random.choice(['east', 'north', 'south', 'southwest', 'northwest'], n)
})

# 添加月份列
sales_data['month'] = sales_data['date'].dt.month
sales_data['weekday'] = sales_data['date'].dt.day_name()

# 创建大屏布局
fig = plt.figure(figsize=(16, 12))
fig.suptitle('2024 annual sales data visualization dashboard', fontsize=20, fontweight='bold', y=0.98)

# 1. 月度销售额趋势（大图）
ax1 = plt.subplot2grid((3, 3), (0, 0), colspan=2)
monthly_sales = sales_data.groupby('month')['sales'].sum() / 10000
ax1.plot(monthly_sales.index, monthly_sales.values, marker='o', linewidth=3,
         markersize=8, color='#ff6b6b')
ax1.fill_between(monthly_sales.index, monthly_sales.values, alpha=0.3, color='#ff6b6b')
ax1.set_title('monthly sales trend (10k cny)', fontsize=13, fontweight='bold')
ax1.set_xlabel('month')
ax1.set_ylabel('sales')
ax1.grid(true, alpha=0.3)
for i, v in enumerate(monthly_sales.values):
    ax1.text(i+1, v+5, f'{v:.0f}', ha='center', fontsize=9)

# 2. 品类占比饼图
ax2 = plt.subplot2grid((3, 3), (0, 2))
category_sales = sales_data.groupby('category')['sales'].sum()
colors_pie = ['#ff6b6b', '#4ecdc4', '#45b7d1', '#96ceb4', '#ffeaa7']
ax2.pie(category_sales.values, labels=category_sales.index, autopct='%1.1f%%',
        colors=colors_pie, startangle=90)
ax2.set_title('sales share by category', fontsize=13, fontweight='bold')

# 3. 地区销售额柱状图
ax3 = plt.subplot2grid((3, 3), (1, 0))
region_sales = sales_data.groupby('region')['sales'].sum() / 10000
bars = ax3.bar(region_sales.index, region_sales.values, color=colors_pie[:5])
ax3.set_title('regional sales (10k cny)', fontsize=13, fontweight='bold')
ax3.set_ylabel('sales')
for bar in bars:
    height = bar.get_height()
    ax3.text(bar.get_x() + bar.get_width()/2., height,
             f'{height:.0f}', ha='center', va='bottom', fontsize=9)

# 4. 订单量与客单价散点图
ax4 = plt.subplot2grid((3, 3), (1, 1))
sample = sales_data.sample(min(500, len(sales_data)))
scatter = ax4.scatter(sample['orders'], sample['avg_price'], 
                      c=sample['sales'], cmap='ylorrd', alpha=0.6, s=30)
ax4.set_title('orders vs average price', fontsize=13, fontweight='bold')
ax4.set_xlabel('orders')
ax4.set_ylabel('avg price')
plt.colorbar(scatter, ax=ax4, label='sales')

# 5. 退货率箱线图
ax5 = plt.subplot2grid((3, 3), (1, 2))
sns.boxplot(data=sales_data, x='category', y='return_rate', hue='category', ax=ax5, palette='set2', legend=false)
ax5.set_title('return rate by category', fontsize=13, fontweight='bold')
ax5.tick_params(axis='x', rotation=45)

# 6. 星期销售热力图
ax6 = plt.subplot2grid((3, 3), (2, 0), colspan=2)
pivot_week = sales_data.pivot_table(values='sales', index='category', 
                                     columns='weekday', aggfunc='mean')
# 重新排序星期
week_order = ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday']
pivot_week = pivot_week.reindex(columns=week_order)
sns.heatmap(pivot_week/1000, annot=true, fmt='.0f', cmap='ylorrd', ax=ax6)
ax6.set_title('weekly sales heatmap by category (1k cny)', fontsize=13, fontweight='bold')
ax6.set_xlabel('')

# 7. kpi指标卡
ax7 = plt.subplot2grid((3, 3), (2, 2))
ax7.axis('off')

total_sales = sales_data['sales'].sum() / 10000
total_orders = sales_data['orders'].sum()
avg_price = sales_data['avg_price'].mean()
avg_return = sales_data['return_rate'].mean() * 100

kpi_lines = [
    "="*22,
    "   kpi dashboard",
    "="*22,
    "",
    f"  total sales: {total_sales:,.0f} (10k)",
    f"  total orders: {total_orders:,}",
    f"  avg price: {avg_price:.0f} cny",
    f"  avg return: {avg_return:.2f}%",
    "",
    "="*22
]
kpi_text = "\n".join(kpi_lines)

ax7.text(0.5, 0.5, kpi_text, transform=ax7.transaxes, fontsize=12,
         verticalalignment='center', horizontalalignment='center',
         bbox=dict(boxstyle='round', facecolor='lightblue', alpha=0.3),
         family='monospace')

plt.tight_layout(rect=[0, 0, 1, 0.96])
plt.savefig('sales_dashboard.png', dpi=150, bbox_inches='tight', facecolor='white')
plt.show()

print("\n=== data summary ===")
print(f"annual total sales: {total_sales:,.0f} (10k cny)")
print(f"annual total orders: {total_orders:,}")
print(f"average price: {avg_price:.0f} cny")
print(f"average return rate: {avg_return:.2f}%")