Analyzing neuroimaging data with open source tools: supervised machine learning algorithm application based on multi-voxel pattern Abstract Functional magnetic resonance imaging (fMRI) constitutes a powerful tool for addressing some basic cognitive questions in cognitive neuroscience. However, conventional fMRI analysis methods try to average across voxels that show a statistically significant response to the experimental conditions, which renders the information like the signals carried by the voxels showing a weaker response to the particular condition unavailable though it can reduce noise. Therefore, it is necessary for researchers to apply more powerful pattern classification algorithms to decode the information represented in multi-voxel activity patterns. This method is called multi-voxel pattern analysis (MVPA). At present, MVPA is increasingly used for neuroimaging data analysis, and it has become a trend to employ pattern classification and other algorithms in the field of machine learning in neuroimaging data analysis in recent years. However, the principles and applications of these tools are complex, and the neuroscience problems may not be fully considered in their development, so researchers have encountered some difficulties in solving neural representation problems with these tools. In this paper, the gap between machine learning and neuroimaging was filled in by demonstrating how a general-purpose machine learning toolbox could provide state-of-the-art methods for neuroimaging data analysis while keeping the code simple and understandable by both worlds, and the analysis process of the supervised machine learning algorithm by using open data in combination with Nilearn library and scikit-learn library tools was introduced Firstly, the basic concept of machine learning and the process of data analysis, including the principle of supervised learning algorithm, was introduced in detail. Then, the use of machine learning toolbox and the selection of algorithms (including the corresponding code) matching with the software package were described to simplify the use of machine learning library and make the code simple and easy to understand through examples. We tried to make it easier for researchers to understand how to approach cognitive problems with decoding by showing how to use the SVM classification algorithm of machine learning to solve a neural representation problem. To provide some tips about programming and parameter selection, the efficiency of different algorithms in multivariate classification was compared, and the applicability of each estimator was briefly described. This paper concluded that no estimator could perform well in all conditions, and its noteworthy that what was done to the data before applying the estimator was often more important than the choice of estimator. Typically, standardizing the data was important, smoothing could often be useful, and confounding effects, such as session effect, must be removed. In brief, the Python code accompanying the machine learning tasks was straightforward, while proper data preprocessing, the choice of the right model for the problem, and result interpretation were difficult. Tackling these difficulties and providing the scientists with a simple and readable code required building a domain-specific library (such as Nilearn) that was dedicated to applying scikit-learn to neuroimaging data. These abundant machine-learning technologies could solve high-dimensional statistics problems and foster advance in new cognitive neuroscience.