Excel Chart Generator

Data Visualization Pain Points in Analysis

Manually creating charts from Excel data typically involves opening the software, selecting data ranges, inserting chart types, and adjusting styles—steps that are time-consuming and require familiarity with Excel operations. This approach becomes inefficient for batch analysis or rapid iterations.

Core Capabilities and Workflow

This skill automates chart generation via the generate_chart.py script, with core capabilities including:

• Automatic Data Parsing: Reads .xlsx or .xls files, identifies all sheets, and outputs the first few rows of data, column names, data types, and statistical summaries.
• Smart Chart Recommendation: Suggests chart types based on data structure, such as:
• 1 categorical column + 1 numerical column → Bar Chart or Pie Chart
• 1 temporal column + 1 numerical column → Line Chart
• 2 numerical columns → Scatter Plot
• Multi-Format Output: Supports interactive HTML (using Plotly) and static PNG (using Matplotlib) outputs for different use cases.

The key workflow steps are:
1. Data Preview: Run the script in preview mode to get an overview of the Excel content, including sheet lists, data structure, and statistics.
2. Parameter Confirmation: Confirm with the user the worksheet, X/Y axis columns, chart type (e.g., bar, line, pie), and output format. If unspecified, the script auto-recommends based on data.
3. Chart Generation: Execute the script to generate charts; it automatically handles date parsing, missing value marking, and other preprocessing.
4. Result Presentation: HTML files are interactively previewed via the preview_url tool, while PNG files are directly sent or opened.

Applicable Boundaries and Considerations

• Data Volume Limits: For datasets exceeding 1000 rows, the script prompts for batch processing or sampling to avoid performance issues.
• Chart Type Constraints: Heatmaps (heatmap) require at least two numerical columns; box plots (box) are suitable for comparing distributions across multiple numerical columns.
• Output Format Choice: HTML is ideal for exploratory analysis, supporting zoom and hover tooltips to view data points; PNG fits static reports or sharing.
• Preprocessing Limitations: The script auto-identifies numerical and categorical columns but only marks missing values without filling them—handling depends on the chart type.

Overall, this skill focuses on simplifying Excel data visualization by automating manual steps, making it suitable for common data analysis scenarios.