Skip to content
MIYA·AI·LAB / generative-AI test logs LLM · Claude Code · MLX · Ollama
AI MiyaAILab_
  • // Lab
  • // all logs
JA / EN
← Miya-Gadget
Generative AI PC

Build a Budget Tracker App with Claude Code: Data Visualization Made Easy

2025年11月18日 · Shichinomiya
Build a Budget Tracker App with Claude Code: Data Visualization Made Easy

Do you keep proper track of your monthly expenses?

I often find my wallet looking thin before I realize it, and end up wondering “what did I spend money on this month?” after the fact.

So this time, I used Claude Code to build a budget tracking app. It does not just record expenses — it visualizes spending with graphs so you can spot trends at a glance.

Data visualization might sound intimidating, but with Claude Code it is surprisingly easy. Let us build one together!

 

Table of Contents

Toggle
  • Recap from Last Time
  • What We Are Building Budget App with Graph Display
      • Core Features
      • Graph Features
  • Creating the Project with Claude Code
      • Creating the Project Folder
      • Instructions for Claude Code
  • Installing Required Libraries
      • Installation Command
  • Running the App
      • How to Launch
      • Recording an Expense
  • Visualizing Data with Graphs
      • Category Pie Chart
      • Monthly Trend Graph
  • Managing Data in Excel
      • CSV Export
  • Adding Useful Features
      • Improvement Request
  • Stumbling Points and Solutions
      • Japanese Display in matplotlib
      • Date Format
  • The Power of Data Visualization
  • Summary
      • Key Takeaways
  • You might also like

Recap from Last Time

In the previous article, we built a Todo list app.

It was a simple command-line tool, but it enabled practical task management.

This time, we are stepping up by building a budget app with visual data display. Having graphs makes it much easier to understand spending trends.

 

What We Are Building: Budget App with Graph Display

Here are the specifications for the budget app:

Core Features

  • Expense Recording: Enter date, category, amount, and memo
  • Data Display: View all expenses in a list
  • Category Management: Freely set categories like food, transportation, entertainment
  • CSV Export: Save data as a CSV file for Excel

Graph Features

  • Category Pie Chart: See at a glance which categories consume the most
  • Monthly Trend Bar Graph: View spending changes by month
  • Statistics: Auto-calculate totals, averages, min/max

Data is stored in JSON files, and graphs are drawn using the matplotlib Python library.

 

Creating the Project with Claude Code

Let us get started with Claude Code.

Creating the Project Folder

  1. Create a folder called “budget_app” on your desktop
  2. Open PowerShell or Command Prompt
  3. Run the following commands
cd Desktop/budget_app
claude

Once Claude Code launches, give it the following instructions.

Budget app creation request to Claude Code

Instructions for Claude Code

Build a budget tracking app.

Features:
1. Record expenses (date, category, amount, memo)
2. Display all expenses in a list
3. Show category breakdown as a pie chart
4. Display monthly spending trend as a bar graph
5. Export data to CSV file

Store data in JSON files.
Use matplotlib for graph display.

Claude Code will process these instructions and create the necessary program.

In my environment, it generated a file called budget.py along with library installation instructions.

 

Installing Required Libraries

To display graphs in the budget app, we need the matplotlib library.

Claude Code will automatically suggest the installation command — just follow along.

Installation Command

pip install matplotlib

This installs matplotlib and its dependencies automatically. Once installation is complete, you can run the program.

 

Running the App

Let us try using the budget app.

How to Launch

python budget.py

This displays the main menu.

Budget app main menu

Select a number from the menu to perform various operations.

Recording an Expense

Select “1” from the menu to open the expense entry screen.

Expense entry screen

Enter the date, category, amount, and memo. For example:

Date: 2025-11-15
Category: Food
Amount: 3500
Memo: Lunch and dinner

The data is saved once entry is complete.

 

Visualizing Data with Graphs

After entering several expenses, let us visualize the data.

Category Pie Chart

Select “3” from the menu to display a category breakdown pie chart.

Category pie chart

This graph makes it easy to see things like “food accounts for 40% of total spending.”

In my case, I was surprised to find entertainment took up more than expected.

Monthly Trend Graph

Select “4” to display monthly spending as a bar graph.

Monthly trend bar graph

The monthly graph makes it easy to spot changes like “I am spending more than last month.”

 

Managing Data in Excel

Sometimes you want to analyze data in Excel rather than just viewing it in the app. That is where the CSV export feature comes in.

CSV Export

Select “5” to generate a budget_export.csv file.

Open this CSV in Excel to see data organized by date. You can use Excel pivot tables for even more detailed analysis.

 

Adding Useful Features

The basic features were complete, but I wanted to make it more user-friendly. So I asked Claude Code for additional improvements.

Improvement Request

Add a feature to display only this month's expenses.
Also show total amounts per category.

Claude Code responded immediately, adding a “This Month’s Spending Summary” menu item. Now I can check “how much budget is left this month” at the start of each month.

 

Stumbling Points and Solutions

I ran into a couple of issues during development.

Japanese Display in matplotlib

Initially, category names appeared garbled in graphs because matplotlib’s default font does not support Japanese characters. When I told Claude Code “the Japanese text in graphs is garbled,” it added code to configure a Japanese-compatible font.

Date Format

I once entered a date as “2025/11/15” and got an error. The correct format is “2025-11-15” (hyphen-separated). Claude Code also fixed this by adding input format examples to the prompt.

 

The Power of Data Visualization

Adding graph features really drove home the value of data visualization. Graphs are far more intuitive than plain number lists. The pie chart especially makes “which category eats the most money” instantly obvious.

The monthly trend graph also helped me realize “I have been overspending lately.”

With Claude Code, building sophisticated data visualization apps like this is surprisingly straightforward.

 

Summary

This time, we used Claude Code to build a budget tracking app with graph visualization.

Key Takeaways

  • Record expense data and visualize it with graphs
  • Category pie charts and monthly bar graphs reveal trends at a glance
  • CSV export enables Excel analysis
  • Claude Code supports everything from library installation to implementation

Next time, I plan to build an automated price monitoring tool for sites like Amazon.

Even programming beginners can build data visualization tools with Claude Code. Give it a try and customize it for your own needs!

You might also like

More generative-AI logs from the lab.

  • Auto-Generate PDF Reports with Claude Code: From Raw Data to Polished Documents
  • Building a Weather Forecast App with Claude Code and API Integration
  • Can you really cut your AI API bill? I deployed the context-compression tool “Headroom” and measured it
  • Can GTX 1080 Ti Run Modern AI? Qwen 3.5 Local LLM Benchmark Results
Previous Article Simplify Task Management with Claude Code! Building a Simple Todo List App
Next Article Easy Task Management with Claude Code — Building a Mobile Budget App from Your Smartphone

Related Posts

Automate Email Sending with Claude Code: Fully Automating Routine Tasks

Automate Email Sending with Claude Code: Fully Automating Routine Tasks

Tesla V100 32GB in 2026: Local LLM Benchmark with Qwen 3.6 — 98.8 tok/s on MoE 35B, 1.6x Faster Than M1 Max (Used, ≈$900)

Tesla V100 32GB in 2026: Local LLM Benchmark with Qwen 3.6 — 98.8 tok/s on MoE 35B, 1.6x Faster Than M1 Max (Used, ≈$900)

Smart Shopping with Claude Code: Building an Automatic Price Monitoring Tool

Smart Shopping with Claude Code: Building an Automatic Price Monitoring Tool

Darkbloom Review: Can a Mac Really Earn Money Serving AI? (I Tested It for a Day)

Darkbloom Review: Can a Mac Really Earn Money Serving AI? (I Tested It for a Day)

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Shichinomiya

Shichinomiya

A blogger who loves PC and gadgets. Sharing daily discoveries.

@shichinomiya_s

Popular Posts

  • Does the trending Claude Code skill “ADHD” actually make the agent smarter? A measured duel vs single-shot
  • Automate Email Sending with Claude Code: Fully Automating Routine Tasks
  • Auto-Generate PDF Reports with Claude Code: From Raw Data to Polished Documents
  • Build a Budget Tracker App with Claude Code: Data Visualization Made Easy
  • Can GTX 1080 Ti Run Modern AI? Qwen 3.5 Local LLM Benchmark Results

Categories

  • Announcements
  • Cars
  • Cycling
  • Gadgets
  • Generative AI
  • Home Appliances
  • Internet Service
  • Outings
  • Overseas Shopping
  • PC
  • Rental Servers & VPS
  • Travel

MiyaAILab

A hands-on lab for generative AI — new models, tools, and services tested for real, from benchmarks to everyday usefulness.

Lab

  • AI Lab トップ
  • 生成AI 全記事
  • ← Miya-Gadget 本体

Latest

  • Dual Tesla V100 SXM2 on a Single PCIe Slot: 64GB VRAM & 300 GB/s NVLink Tested — Is This $700 Setup Worth It?
  • Modded RTX 4080 32GB Benchmarked: Qwen3.8-27B at 262K Context, 125B MoE, and MiniMax H3 Video — What 32GB Actually Delivers
  • Tesla V100 32GB Runs Qwen3.8-27B: 131k Context on a Single Card — Measured Benchmark
  • Tesla V100 32GB in 2026: Local LLM Benchmark with Qwen 3.6 — 98.8 tok/s on MoE 35B, 1.6x Faster Than M1 Max (Used, ≈$900)
© 2026 Miya AI Lab — a section of Miya-Gadget. miyagadget.page