Getting Started with Plotivy: From Raw Data to Publication Figure in 5 Minutes

Remember the last time you needed a quick figure for a paper? Installing Python, managing environments, debugging matplotlib errors, searching Stack Overflow for that one syntax you forgot... again. Plotivy removes all of that friction. Go from raw data to a publication-ready figure in under 5 minutes—no coding required.

This guide walks you through your first analysis session. By the end, you'll have a professional visualization without writing a single line of code.

The 5-Minute Walkthrough

Prerequisites: None. Seriously—you don't need to install Python, manage dependencies, or configure anything. Just bring your data.

Step 1: Upload Your Data (30 seconds)

Navigate to the Analyze page and upload your dataset. Plotivy supports common formats like CSV, Excel (`.xlsx`), and JSON.

The system will automatically detect the structure of your file, identifying column names and data types. You don't need to manually format your spreadsheet beforehand; the AI can handle typical inconsistencies like missing headers or mixed data types.

Step 2: Describe Your Goal (1 minute)

Here's where the magic happens. Instead of Googling "matplotlib scatter plot error bars" for the 100th time, just describe what you want in plain English. Be specific about the variables and style you need.

"Plot mean ± 95% CI of Yield by Group; use a colorblind-safe palette"

"Create a scatter plot showing the relationship between temperature and reaction rate, with error bars and a trend line"

The AI interprets your request and generates the underlying Python code to render the plot.

Step 3: Inspect the Code (1 minute)

Unlike other AI tools that hide what's happening under the hood, Plotivy shows you every line of Python code. This is crucial for researchers who need to understand—and cite—their methods.

This feature is critical for two reasons:

• Verification: You can check exactly how the data was processed and plotted.
• Learning: By reading the code, you can learn how to use libraries like Matplotlib and Seaborn effectively.

Step 4: Export for Publication (30 seconds)

When your figure looks right, export it in journal-ready format. No more "please resubmit with higher resolution" rejections.

• SVG/PDF: Best for journal publications (vector graphics that scale infinitely).
• PNG: Best for presentations and web use (high resolution, 300+ DPI).

Next Steps

Now that you've created your first plot, try exploring more advanced features:

• Multi-Panel Figures: Ask for "a 2x2 grid of plots" to compare multiple variables.
• Statistical Analysis: Request "ANOVA results with p-value annotations" directly on the plot.
• Custom Styling: Prompt for specific journal styles, e.g., "Style for Nature publication."

Plotivy is designed to grow with your needs, from quick data checks to complex, publication-quality visualizations.