← All projects PUBLIC SOURCE / 2026

DATA ANALYSIS / COIT29225

Brisbane House Price Analysis

Turning a small Brisbane housing dataset into understandable statistics, categories and reproducible charts.

Exploratory data analysis and reporting across five suburbs, using Python to derive descriptive statistics and export chart-backed findings.

View GitHub source ↗ Academic project collection →
  • Python
  • pandas
  • NumPy
  • Matplotlib
  • EDA
Property records
110
Brisbane suburbs
5
Exported data visualisations
4

01 / PROJECT EVIDENCE

These figures are copied directly from the public GitHub repository and are presented with context.

01 / Original project outputBrisbane House Price Analysis
Bar chart showing the number of properties in each defined price bracket
Generated house-price category distribution from the public analysis repository.
02 / Original project outputBrisbane House Price Analysis
Scatter plot showing house prices and general versus high demand categories across suburbs
Original suburb-versus-demand exploration figure, not current real-estate market data.

02 / PROBLEM

The engineering question.

A supplied table of house prices is difficult to interpret without validation, distribution summaries and consistent visual comparisons between suburbs and demand categories.

03 / METHOD

What I built and evaluated.

  1. Validated the CSV's price, suburb, demand and identifier columns; checked missing entries and duplicate records.
  2. Calculated the median, low/high values, quantiles, mean, standard deviation, skewness and above-median proportions in Python.
  3. Grouped prices into entry, economical, middle-class and premium ranges; compared high and general demand categories and suburb distribution.
  4. Generated and saved charts, an ascending price-sorted CSV and a technical PDF report from the same source calculations.

04 / MEASURED FINDINGS

What the evidence shows.

  • The project generates a price-category bar chart and pie chart alongside demand-price and suburb-demand comparisons.
  • All 110 rows remain in the sorted CSV, with calculated median, minimum and maximum metadata added.
  • This is statistical exploration and reporting; no forecasting or predictive neural network is claimed for this Assignment 1 part.

05 / LIMITATIONS

Where the claims stop.

The dataset contains only 110 supplied records and five suburbs; it should not be interpreted as a representative or current picture of Brisbane housing prices.

PROJECT SOURCE

Inspect the implementation.

See the original code, data-handling choices, documented experiments and repository instructions.

Explore repository ↗