Developers often utilize application programming interfaces (API) to simplify their development tasks. API recommendation methods can automatically recommend the APIs that developers need to improve development quality and efficiency. Recent research combines collaborative filtering with graph neural networks for API recommendation. However, these approaches often face the problem of sub-optimal graph representation due to data sparsity. To address these issues, we propose an API recommendation method that enhances the raw data by fusing usage patterns in similar projects. Typically, similar projects share similar functional and structural features, including code modules with similar usage patterns, which include rich information such as invocation and structural details. Enhancing the raw data with this information can effectively alleviate the sparsity problem of the interaction matrix induced by the construction graph of the raw data. Specifically, our approach consists of matching similar items for each entry in the original dataset to form new classes. These new classes are then merged into code modules with similar usage patterns to augment the original dataset. Subsequently, the graph represents the learning model capturing the higher-order collaborative signals of the API calls in the augmented dataset and integrating the structural information of the items into the graph. To evaluate the effectiveness of our approach, we conducted experiments using data collected from large open source repositories. The experimental results show that the method is effective.