[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-06-19。"],[[["BigQuery ML accommodates various input feature types, tailored to different model categories such as supervised, unsupervised, and time series models."],["Numeric, categorical, timestamp, struct, geography, and array types are supported across many BigQuery ML models, with specific models having certain specificities."],["Dense vector input is supported using `ARRAY\u003cnumerical\u003e` for model training, which includes a special embedding feature as seen in the `ML.GENERATE_EMBEDDING` function."],["Sparse input during model training is supported through the use of `ARRAY\u003cSTRUCT\u003e`, where each struct contains an `INT64` index and a numeric value."],["Matrix Factorization and ARIMA_PLUS models have unique input requirements, with the provided input types for ARIMA_PLUS_XREG only applying to external regressors."]]],[]]