create-viz
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese/create-viz - Create Visualizations
/create-viz - 创建数据可视化
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Create publication-quality data visualizations using Python. Generates charts from data with best practices for clarity, accuracy, and design.
若遇到不熟悉的占位符或需要查看已连接的工具，请参考 CONNECTORS.md。
使用Python创建出版级质量的数据可视化。遵循清晰度、准确性和设计最佳实践，基于数据生成图表。
Usage
使用方法
/create-viz <data source> [chart type] [additional instructions]/create-viz <数据源> [图表类型] [额外说明]Workflow
工作流程
1. Understand the Request
1. 理解需求
Determine:
- Data source: Query results, pasted data, CSV/Excel file, or data to be queried
- Chart type: Explicitly requested or needs to be recommended
- Purpose: Exploration, presentation, report, dashboard component
- Audience: Technical team, executives, external stakeholders
确定以下信息：
- 数据源：查询结果、粘贴的数据、CSV/Excel文件，或需要查询的数据
- 图表类型：用户明确指定的类型，或需要推荐的类型
- 用途：探索性分析、演示、报告、仪表盘组件
- 受众：技术团队、管理层、外部利益相关者
2. Get the Data
2. 获取数据
If data warehouse is connected and data needs querying:
- Write and execute the query
- Load results into a pandas DataFrame
If data is pasted or uploaded:
- Parse the data into a pandas DataFrame
- Clean and prepare as needed (type conversions, null handling)
If data is from a previous analysis in the conversation:
- Reference the existing data
若已连接数据仓库且需要查询数据：
- 编写并执行查询语句
- 将结果加载至pandas DataFrame
若数据为粘贴或上传：
- 将数据解析为pandas DataFrame
- 根据需要进行清洗和预处理（类型转换、空值处理等）
若数据来自对话中之前的分析：
- 引用已有的数据
3. Select Chart Type
3. 选择图表类型
If the user didn't specify a chart type, recommend one based on the data and question:
| Data Relationship | Recommended Chart |
|---|---|
| Trend over time | Line chart |
| Comparison across categories | Bar chart (horizontal if many categories) |
| Part-to-whole composition | Stacked bar or area chart (avoid pie charts unless <6 categories) |
| Distribution of values | Histogram or box plot |
| Correlation between two variables | Scatter plot |
| Two-variable comparison over time | Dual-axis line or grouped bar |
| Geographic data | Choropleth map |
| Ranking | Horizontal bar chart |
| Flow or process | Sankey diagram |
| Matrix of relationships | Heatmap |
Explain the recommendation briefly if the user didn't specify.
若用户未指定图表类型，需根据数据和需求推荐合适的类型：
| 数据关系 | 推荐图表 |
|---|---|
| 随时间变化的趋势 | 折线图 |
| 跨类别对比 | 柱状图（类别较多时使用横向柱状图） |
| 整体与部分的构成 | 堆叠柱状图或面积图（除非类别少于6个，否则避免使用饼图） |
| 数值分布 | 直方图或箱线图 |
| 两个变量的相关性 | 散点图 |
| 双变量随时间的对比 | 双轴折线图或分组柱状图 |
| 地理数据 | 分级统计图 |
| 排名排序 | 横向柱状图 |
| 流程或流向 | 桑基图 |
| 关系矩阵 | 热力图 |
若用户未指定类型，需简要说明推荐理由。
4. Generate the Visualization
4. 生成可视化图表
Write Python code using one of these libraries based on the need:
- matplotlib + seaborn: Best for static, publication-quality charts. Default choice.
- plotly: Best for interactive charts or when the user requests interactivity.
Code requirements:
python
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd根据需求使用以下库编写Python代码：
- matplotlib + seaborn：最适合创建静态、出版级质量的图表，为默认选择。
- plotly：最适合创建交互式图表，或用户明确要求交互性时使用。
代码要求：
python
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pdSet professional style
设置专业样式
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette("husl")
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette("husl")
Create figure with appropriate size
创建合适尺寸的画布
fig, ax = plt.subplots(figsize=(10, 6))
fig, ax = plt.subplots(figsize=(10, 6))
[chart-specific code]
[图表专属代码]
Always include:
必须包含以下内容：
ax.set_title('Clear, Descriptive Title', fontsize=14, fontweight='bold')
ax.set_xlabel('X-Axis Label', fontsize=11)
ax.set_ylabel('Y-Axis Label', fontsize=11)
ax.set_title('清晰、描述性的标题', fontsize=14, fontweight='bold')
ax.set_xlabel('X轴标签', fontsize=11)
ax.set_ylabel('Y轴标签', fontsize=11)
Format numbers appropriately
合理格式化数值
- Percentages: '45.2%' not '0.452'
- 百分比：显示为'45.2%'而非'0.452'
- Currency: '$1.2M' not '1200000'
- 货币：显示为'$1.2M'而非'1200000'
- Large numbers: '2.3K' or '1.5M' not '2300' or '1500000'
- 大数值：显示为'2.3K'或'1.5M'而非'2300'或'1500000'
Remove chart junk
移除冗余图表元素
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.savefig('chart_name.png', dpi=150, bbox_inches='tight')
plt.show()
undefinedax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.savefig('chart_name.png', dpi=150, bbox_inches='tight')
plt.show()
undefined5. Apply Design Best Practices
5. 应用设计最佳实践
Color:
- Use a consistent, colorblind-friendly palette
- Use color meaningfully (not decoratively)
- Highlight the key data point or trend with a contrasting color
- Grey out less important reference data
Typography:
- Descriptive title that states the insight, not just the metric (e.g., "Revenue grew 23% YoY" not "Revenue by Month")
- Readable axis labels (not rotated 90 degrees if avoidable)
- Data labels on key points when they add clarity
Layout:
- Appropriate whitespace and margins
- Legend placement that doesn't obscure data
- Sorted categories by value (not alphabetically) unless there's a natural order
Accuracy:
- Y-axis starts at zero for bar charts
- No misleading axis breaks without clear notation
- Consistent scales when comparing panels
- Appropriate precision (don't show 10 decimal places)
色彩：
- 使用一致、适合色盲人群的配色方案
- 有意义地使用色彩（而非装饰性）
- 用对比色突出关键数据点或趋势
- 将次要参考数据设为灰色
排版：
- 标题需描述洞察，而非仅说明指标（例如："营收同比增长23%"而非"月度营收"）
- 轴标签易读（尽可能避免90度旋转）
- 在关键数据点添加数据标签以提升清晰度
布局：
- 合理的留白和边距
- 图例放置在不遮挡数据的位置
- 类别按数值排序（而非字母顺序），除非存在自然顺序
准确性：
- 柱状图的Y轴从0开始
- 除非有明确标注，否则不使用误导性的轴中断
- 对比面板时使用一致的刻度
- 合理的精度（避免显示10位小数）
6. Save and Present
6. 保存与展示
- Save the chart as a PNG file with descriptive name
- Display the chart to the user
- Provide the code used so they can modify it
- Suggest variations (different chart type, different grouping, zoomed time range)
- 将图表保存为PNG文件，文件名需具有描述性
- 向用户展示图表
- 提供所用代码，方便用户修改
- 建议变体（不同图表类型、不同分组方式、缩放时间范围等）
Examples
示例
/create-viz Show monthly revenue for the last 12 months as a line chart with the trend highlighted/create-viz Here's our NPS data by product: [pastes data]. Create a horizontal bar chart ranking products by score./create-viz Query the orders table and create a heatmap of order volume by day-of-week and hour/create-viz 展示过去12个月的月度营收，用折线图呈现并突出趋势/create-viz 这是我们按产品划分的NPS数据：[粘贴数据]。创建横向柱状图，按得分对产品进行排名。/create-viz 查询订单表，创建按星期几和小时分布的订单量热力图Tips
提示
- If you want interactive charts (hover, zoom, filter), mention "interactive" and Claude will use plotly
- Specify "presentation" if you need larger fonts and higher contrast
- You can request multiple charts at once (e.g., "create a 2x2 grid of charts showing...")
- Charts are saved to your current directory as PNG files
- 若需要交互式图表（悬停、缩放、筛选），请提及"interactive"，Claude将使用plotly
- 若用于演示，可指定"presentation"，将生成更大字体和更高对比度的图表
- 可同时请求多个图表（例如："创建2x2网格图表，展示..."）
- 图表将保存为PNG文件至当前目录