Algumas ou todas as informações nesta página podem não se aplicar à nuvem confiável da S3NS.
Visão geral da classificação
Um caso de uso comum para o aprendizado de máquina é classificar novos dados usando um modelo
treinado com dados rotulados semelhantes. Por exemplo, você pode querer prever se
um e-mail é spam ou se uma avaliação de produto do cliente é positiva, negativa ou
neutra.
É possível usar qualquer um dos modelos a seguir em combinação com a
função ML.PREDICT
para realizar a classificação:
Conhecimento recomendado
Usando as configurações padrão nas instruções CREATE MODEL
e na
função ML.PREDICT
, é possível criar e usar um modelo de classificação mesmo
sem muito conhecimento de ML. No entanto, ter conhecimentos básicos sobre
o desenvolvimento de ML ajuda a otimizar os dados e o modelo para
obter melhores resultados. Recomendamos o uso dos seguintes recursos para se familiarizar
com as técnicas e os processos de ML:
Exceto em caso de indicação contrária, o conteúdo desta página é licenciado de acordo com a Licença de atribuição 4.0 do Creative Commons, e as amostras de código são licenciadas de acordo com a Licença Apache 2.0. Para mais detalhes, consulte as políticas do site do Google Developers. Java é uma marca registrada da Oracle e/ou afiliadas.
Última atualização 2025-08-17 UTC.
[[["Fácil de entender","easyToUnderstand","thumb-up"],["Meu problema foi resolvido","solvedMyProblem","thumb-up"],["Outro","otherUp","thumb-up"]],[["Não contém as informações de que eu preciso","missingTheInformationINeed","thumb-down"],["Muito complicado / etapas demais","tooComplicatedTooManySteps","thumb-down"],["Desatualizado","outOfDate","thumb-down"],["Problema na tradução","translationIssue","thumb-down"],["Problema com as amostras / o código","samplesCodeIssue","thumb-down"],["Outro","otherDown","thumb-down"]],["Última atualização 2025-08-17 UTC."],[[["\u003cp\u003eMachine learning classification involves using a model trained on labeled data to classify new data, such as identifying spam emails or categorizing customer reviews.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eML.PREDICT\u003c/code\u003e function can be used with various classification models, including logistic regression, boosted tree, random forest, deep neural network (DNN), wide & deep, and AutoML models.\u003c/p\u003e\n"],["\u003cp\u003eDifferent models can be specified using the \u003ccode\u003eMODEL_TYPE\u003c/code\u003e option, such as \u003ccode\u003eLOGISTIC_REG\u003c/code\u003e, \u003ccode\u003eBOOSTED_TREE_CLASSIFIER\u003c/code\u003e, \u003ccode\u003eRANDOM_FOREST_CLASSIFIER\u003c/code\u003e, \u003ccode\u003eDNN_CLASSIFIER\u003c/code\u003e, \u003ccode\u003eDNN_LINEAR_COMBINED_CLASSIFIER\u003c/code\u003e, and \u003ccode\u003eAUTOML_CLASSIFIER\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eWhile classification models can be created and used without extensive ML knowledge, understanding the basics can help optimize both data and the model for better results.\u003c/p\u003e\n"],["\u003cp\u003eResources like the Machine Learning Crash Course, Intro to Machine Learning, and Intermediate Machine Learning are recommended for gaining familiarity with machine learning techniques.\u003c/p\u003e\n"]]],[],null,["# Classification overview\n=======================\n\nA common use case for machine learning is classifying new data by using a model\ntrained on similar labeled data. For example, you might want to predict whether\nan email is spam, or whether a customer product review is positive, negative, or\nneutral.\n\nYou can use any of the following models in combination with the\n[`ML.PREDICT` function](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-predict)\nto perform classification:\n\n- [Logistic regression models](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-glm): use [logistic regression](https://developers.google.com/machine-learning/crash-course/logistic-regression) by setting the `MODEL_TYPE` option to `LOGISTIC_REG`.\n- [Boosted tree models](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-boosted-tree): use a [gradient boosted decision tree](https://developers.google.com/machine-learning/decision-forests/intro-to-gbdt) by setting the `MODEL_TYPE` option to `BOOSTED_TREE_CLASSIFIER`.\n- [Random forest models](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-random-forest): use a [random forest](https://developers.google.com/machine-learning/decision-forests/intro-to-decision-forests) by setting the `MODEL_TYPE` option to `RANDOM_FOREST_CLASSIFIER`.\n- [Deep neural network (DNN) models](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-dnn-models): use a [neural network](https://developers.google.com/machine-learning/crash-course/neural-networks) by setting the `MODEL_TYPE` option to `DNN_CLASSIFIER`.\n- [Wide \\& Deep models](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-wnd-models): use [wide \\& deep learning](https://dl.acm.org/doi/10.1145/2988450.2988454) by setting the `MODEL_TYPE` option to `DNN_LINEAR_COMBINED_CLASSIFIER`.\n- [AutoML models](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-automl): use an [AutoML classification model](/vertex-ai/docs/tabular-data/classification-regression/overview) by setting the `MODEL_TYPE` option to `AUTOML_CLASSIFIER`.\n\nRecommended knowledge\n---------------------\n\nBy using the default settings in the `CREATE MODEL` statements and the\n`ML.PREDICT` function, you can create and use a classification model even\nwithout much ML knowledge. However, having basic knowledge about\nML development helps you optimize both your data and your model to\ndeliver better results. We recommend using the following resources to develop\nfamiliarity with ML techniques and processes:\n\n- [Machine Learning Crash Course](https://developers.google.com/machine-learning/crash-course)\n- [Intro to Machine Learning](https://www.kaggle.com/learn/intro-to-machine-learning)\n- [Intermediate Machine Learning](https://www.kaggle.com/learn/intermediate-machine-learning)"]]