On Urban Development Index of a Country: A Fuzzy Logic and Python Approach

The development index (DI) of a region is defined by various elements such as geography, population density, gross domestic product (GDP), GDP per capita, natural resources, markets, economic development, and other relevant factors. The traditional approach to classification usually depends on the country’s total land area measured in square kilometers. Nevertheless, the transition points between different levels of development size (small, medium, and giant) are highly subjective, resulting in frequent inconsistencies and conflicts. Fuzzy logic, a superset of conventional (Boolean) logic, extends the framework to include partial truth values, ranging from “fully true” to “totally false”. This development is especially essential since human reasoning, particularly commonsense reasoning, is approximate rather than precise. This study offers a model that uses fuzzy logic and the Mamdani fuzzy inference system (MFIS) to evaluate nine main cities in Pakistan based on their populations (POPs), gross domestic products (GDPs), and literacy rates (LR). The model includes variables for the antecedents (inputs) and the consequences (outputs). The input variables are the population (POP), GDP, and LR, while the output variable is the DI. The MFIS is used with Python programming tools, including the scikit-fuzzy library for inference and aggregation and matplotlib for graphics.