Abstract: The Python programming language has become a significant component in experimental teaching of bioinformatics due to its extensive applications in biological data analysis. In this paper, based on the data set of coral survival environment and distribution, we constructed a set of experimental framework integrating Python data analysis and machine learning techniques, aiming at exploring the influence of environmental factors such as salinity and temperature on coral distribution, and evaluating the efficacy of the models such as Random Forests and Support Vector Machines in predicting the coral existence state. Analysis of the survey data revealed that coral predominantly inhabits low-latitude regions, while machine learning methods demonstrated that coral presence could be predicted with considerable accuracy using salinity, January temperature, and June temperature as parameters. This experimental design provides a reusable technical path for ecological data analysis, and its methodological framework can be extended to predict the distribution of other marine organisms and support decision-making for conservation.