bigquery-data-science 0.7.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- bigquery_data_science/__init__.py +58 -0
- bigquery_data_science/_skills/PLANS.md +76 -0
- bigquery_data_science/_skills/bigquery-ai/SKILL.md +66 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_agg.md +528 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_classify.md +450 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_count_tokens.md +180 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_detect_anomalies.md +322 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_embed.md +425 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_evaluate.md +368 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_forecast.md +437 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate.md +693 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate_bool.md +248 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate_double.md +254 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate_embedding.md +402 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate_int.md +252 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate_table.md +447 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_generate_text.md +356 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_if.md +373 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_key_drivers.md +331 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_parse_document.md +416 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_predict.md +559 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_score.md +310 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_search.md +465 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ai_similarity.md +371 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/catalog_search.md +951 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/content_analysis.md +284 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/content_moderation.md +369 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/data_enrichment.md +426 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/document_intelligence.md +470 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/document_rag.md +453 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/image_deduplication.md +770 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/log_analysis.md +668 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/metric_diagnostics.md +568 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_annotate_image.md +680 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_generate_embedding.md +217 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_generate_text.md +223 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_process_document.md +392 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_transcribe.md +815 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_translate.md +600 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/ml_understand_text.md +673 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/multimodal_analysis.md +266 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/rag_pipeline.md +593 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/semantic_search.md +510 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/tabular_prediction.md +485 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/time_series_intelligence.md +489 -0
- bigquery_data_science/_skills/bigquery-ai/narrative/vector_search.md +672 -0
- bigquery_data_science/_skills/bigquery-ai/reference/augmented-analytics.md +77 -0
- bigquery_data_science/_skills/bigquery-ai/reference/cloud-ai-service-models.md +88 -0
- bigquery_data_science/_skills/bigquery-ai/reference/document-processing.md +95 -0
- bigquery_data_science/_skills/bigquery-ai/reference/embeddings-and-search.md +166 -0
- bigquery_data_science/_skills/bigquery-ai/reference/general-purpose-generation.md +87 -0
- bigquery_data_science/_skills/bigquery-ai/reference/managed-functions.md +72 -0
- bigquery_data_science/_skills/bigquery-ai/reference/predictive-ai.md +113 -0
- bigquery_data_science/_skills/bigquery-ai/reference/workflows.md +56 -0
- bigquery_data_science/_skills/bigquery-ai/skill.manifest.json +109 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/INDEX.md +71 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiagg.md +67 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aicausal_effect-covered-in-bigquery-ml.md +17 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiclassify.md +72 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aicount_tokens.md +53 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aidetect_anomalies.md +63 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiembed.md +85 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aievaluate.md +114 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiforecast.md +123 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate.md +69 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate_bool.md +53 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate_double.md +45 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate_embedding.md +108 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate_int.md +45 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate_table.md +64 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aigenerate_text.md +167 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiif.md +56 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aikey_drivers.md +76 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiparse_document.md +91 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aipredict.md +74 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aiscore.md +52 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aisearch.md +66 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/aisimilarity.md +79 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/choosing-between-these-and-the-ai-functions.md +11 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/hybrid-search-capability.md +165 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mlannotate_image.md +24 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mlgenerate_embedding.md +34 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mlgenerate_text.md +65 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mlprocess_document.md +125 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mltranscribe.md +26 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mltranslate.md +27 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/mlunderstand_text.md +32 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/multimodal-input-patterns-by-function.md +128 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/object-tables.md +109 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/objectref-and-objectrefruntime-schema-reference.md +50 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/objfetch_metadata.md +49 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/objget_access_url.md +66 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/objget_read_url.md +40 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/objlist.md +34 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/objmake_ref.md +58 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/per-row-failures-and-the-retry-pattern.md +19 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/setup-apis-connection-roles.md +39 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/two-input-shapes.md +22 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/vector_search.md +78 -0
- bigquery_data_science/_skills/bigquery-ai/syntax/what-the-five-have-in-common.md +27 -0
- bigquery_data_science/_skills/bigquery-data-science/SKILL.md +69 -0
- bigquery_data_science/_skills/bigquery-data-science/reference/namespace-matrix.md +112 -0
- bigquery_data_science/_skills/bigquery-data-science/skill.manifest.json +13 -0
- bigquery_data_science/_skills/bigquery-ml/SKILL.md +70 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/airflow_with_kfp.md +379 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/anomaly_fraud_detection.md +195 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/arima_plus.md +635 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/arima_plus_xreg.md +453 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/autoencoder.md +470 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/automl_classifier.md +291 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/automl_regressor.md +274 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/boosted_tree_classifier.md +449 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/boosted_tree_regressor.md +400 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/bucketizing.md +201 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/causal_effect.md +773 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/churn_retention.md +271 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/cloud_workflows.md +370 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/composer_airflow.md +475 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/contribution_analysis.md +346 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/cross_validation.md +185 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/customer_segmentation.md +233 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/dataform.md +372 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/dbt.md +283 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/difference_in_differences.md +280 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/distance.md +195 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/dnn_classifier.md +326 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/dnn_regressor.md +308 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/embeddings_classification.md +426 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/encoding.md +238 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/ensembling.md +278 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/evaluation.md +445 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/exploration.md +779 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/export.md +321 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/feature_engineering.md +280 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/feature_store.md +652 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/feature_store_workflow.md +426 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/ga4_churn_prediction.md +285 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/hierarchical_forecasting.md +441 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/image.md +791 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/imported.md +426 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/kmeans.md +348 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/linear_regression.md +372 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/logistic_regression.md +390 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/matrix_factorization.md +404 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/model_monitoring.md +609 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/pca.md +357 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/price_elasticity_dml.md +286 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/propensity_score_matching.md +350 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/random_forest_classifier.md +445 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/random_forest_regressor.md +409 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/recommendation.md +281 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/regression_based_forecasting.md +491 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/remote.md +428 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/scalers.md +325 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/scheduled_queries.md +284 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/sql_scripting.md +243 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/survival_analysis.md +363 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/synthetic_control.md +221 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/text.md +215 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/time_series.md +669 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/transform_only.md +273 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/uplift_cate.md +241 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/vertex_kfp.md +360 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/wide_and_deep_classifier.md +316 -0
- bigquery_data_science/_skills/bigquery-ml/narrative/wide_and_deep_regressor.md +298 -0
- bigquery_data_science/_skills/bigquery-ml/reference/classification.md +80 -0
- bigquery_data_science/_skills/bigquery-ml/reference/model-management.md +90 -0
- bigquery_data_science/_skills/bigquery-ml/reference/preprocessing-functions.md +234 -0
- bigquery_data_science/_skills/bigquery-ml/reference/regression.md +79 -0
- bigquery_data_science/_skills/bigquery-ml/reference/unsupervised-and-specialized.md +101 -0
- bigquery_data_science/_skills/bigquery-ml/reference/workflows-and-pipelines.md +111 -0
- bigquery_data_science/_skills/bigquery-ml/skill.manifest.json +177 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/1-model_type-catalog.md +28 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/2-task-mlevaluate-metric-columns.md +26 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/3-capability-matrix-per-model-type.md +21 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/4-explainability-weights-functions.md +14 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/5-connection-matrix.md +11 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/6-which-model-free-function-no-create-model-no-connection.md +15 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/7-point-in-time-feature-retrieval-which-of-the-two.md +11 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/INDEX.md +111 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/aicausal_effect.md +85 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/arima_plus-forecasting-lifecycle-functions.md +14 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/arima_plus-univariate-time-series-forecasting.md +132 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/arima_plus_xreg-multivariate-time-series-with-external-regressors.md +103 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/autoencoder.md +102 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/automl_classifier-automl_regressor.md +88 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/boosted_tree_classifier-boosted_tree_regressor.md +117 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/contribution_analysis.md +113 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/dnn_classifier-dnn_regressor.md +107 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/dnn_linear_combined_classifier-dnn_linear_combined_regressor-wide-and-deep.md +98 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/explainability-functions-mlexplain_predict-mlglobal_explain-mlfeature_importance.md +7 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/exploratory-data-analysis-mldescribe_data-mlcorrelation.md +11 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/export-model.md +92 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/feature-engineering-standalone-preprocessing-functions.md +13 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/image-preprocessing-functions-mldecode_image-mlresize_image-mlconvert_image_type-mlconvert_color_space.md +63 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/imported-models-tensorflow-tensorflow_lite-onnx-xgboost.md +36 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/kmeans.md +87 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/linear_reg-logistic_reg-generalized-linear-models.md +101 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/matrix_factorization.md +162 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mladvanced_weights.md +76 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlarima_coefficients.md +30 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlarima_evaluate.md +49 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlbag_of_words.md +47 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlbucketize.md +47 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlcentroids.md +46 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlconfusion_matrix.md +56 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlconvert_color_space.md +53 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlconvert_image_type.md +39 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlcorrelation.md +78 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mldecode_image.md +44 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mldescribe_data.md +74 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mldetect_anomalies.md +86 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mldistance.md +48 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlentity_features_at_time.md +56 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlevaluate.md +72 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlexplain_forecast.md +50 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlexplain_predict.md +66 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlfeature_cross.md +46 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlfeature_importance.md +47 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlfeature_info.md +50 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlfeatures_at_time.md +51 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlforecast.md +76 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlgenerate_embedding-from-a-bqml-pca-autoencoder-matrix_factorization-model.md +64 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlglobal_explain.md +63 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlhash_bucketize.md +47 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlholiday_info.md +46 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlimputer.md +46 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mllp_norm.md +47 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlmetrics.md +80 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlngrams.md +37 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlone_hot_encoder-mlmulti_hot_encoder-mllabel_encoder.md +67 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlpolynomial_expand.md +47 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlpredict.md +67 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlprincipal_component_info.md +42 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlprincipal_components.md +40 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlquantile_bucketize.md +43 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlrecommend.md +60 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlreconstruction_loss.md +48 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlresize_image.md +45 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlroc_curve.md +63 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltf_idf.md +37 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltfdv_describe.md +34 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltfdv_validate.md +48 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltraining_info.md +78 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltransform-applying-a-saved-transform.md +52 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltranspose-not-a-function-pointer.md +32 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mltrial_info.md +60 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlvalidate_data_drift.md +99 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlvalidate_data_skew.md +50 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/mlweights.md +84 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/model-free-time-series-decomposition-mltrend-mlseasonality-mldetect_change_points.md +100 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/model-introspection-mlfeature_info-mltraining_info-mltrial_info.md +7 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/model-monitoring-data-validation.md +23 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/numerical-scalers-mlstandard_scaler-mlmin_max_scaler-mlmax_abs_scaler-mlrobust_scaler-mlnormalizer.md +77 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/onnx.md +55 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/pca.md +91 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/point-in-time-feature-retrieval-mlfeatures_at_time-mlentity_features_at_time.md +25 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/quick-comparison.md +14 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/random_forest_classifier-random_forest_regressor.md +123 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/remote-remote-model-over-a-vertex-ai-endpoint-the-mechanism.md +87 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/tensorflow.md +48 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/tensorflow_lite.md +29 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/text-preprocessing-functions-mlngrams-mltf_idf-mlbag_of_words.md +18 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/timesfm-built-in-foundation-forecaster-see-bigquery-ai.md +28 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/transform_only.md +91 -0
- bigquery_data_science/_skills/bigquery-ml/syntax/xgboost.md +72 -0
- bigquery_data_science/_skills/pinned-models.json +28 -0
- bigquery_data_science/catalog.py +1107 -0
- bigquery_data_science/cli.py +786 -0
- bigquery_data_science/installer.py +282 -0
- bigquery_data_science/mcp_server.py +317 -0
- bigquery_data_science/tooling/__init__.py +15 -0
- bigquery_data_science/tooling/convert_notebook.py +176 -0
- bigquery_data_science/tooling/link_policy.py +247 -0
- bigquery_data_science/tooling/manifest.py +152 -0
- bigquery_data_science/tooling/markdown_anchors.py +84 -0
- bigquery_data_science/tooling/narrative_drift.py +163 -0
- bigquery_data_science/tooling/pinned_models.py +216 -0
- bigquery_data_science/tooling/reference_structure.py +85 -0
- bigquery_data_science/tooling/sync_syntax.py +407 -0
- bigquery_data_science/tooling/validate.py +208 -0
- bigquery_data_science-0.7.0.dist-info/METADATA +306 -0
- bigquery_data_science-0.7.0.dist-info/RECORD +286 -0
- bigquery_data_science-0.7.0.dist-info/WHEEL +4 -0
- bigquery_data_science-0.7.0.dist-info/entry_points.txt +5 -0
- bigquery_data_science-0.7.0.dist-info/licenses/LICENSE +201 -0
|
@@ -0,0 +1,437 @@
|
|
|
1
|
+
> **Source (`statmike/bigquery-data-science`):** **Notebook:** [`bigquery-ai/functions/ai_forecast/ai_forecast.ipynb`](https://github.com/statmike/bigquery-data-science/blob/main/bigquery-ai/functions/ai_forecast/ai_forecast.ipynb) · **SQL:** [`bigquery-ai/functions/ai_forecast/ai_forecast.sql`](https://github.com/statmike/bigquery-data-science/blob/main/bigquery-ai/functions/ai_forecast/ai_forecast.sql)
|
|
2
|
+
|
|
3
|
+
# AI.FORECAST — BigQuery AI Functions
|
|
4
|
+
|
|
5
|
+
`AI.FORECAST` is a table-valued function that forecasts future time series values using BigQuery ML's built-in TimesFM model. No model creation or training required. Univariate forecasting is GA; multivariate forecasting and the TimesFM 3.0 model are Preview.
|
|
6
|
+
|
|
7
|
+
**When to use it:**
|
|
8
|
+
- You want to forecast future values from historical time series data
|
|
9
|
+
- You need prediction intervals (confidence bounds) for forecasts
|
|
10
|
+
- You want to forecast multiple independent time series at once
|
|
11
|
+
- You need a zero-setup forecasting solution (no CREATE MODEL)
|
|
12
|
+
- You can specify a target date with `forecast_end_timestamp` instead of a numeric `horizon`
|
|
13
|
+
- You can control how much history the model sees with `context_window` (64–15,360 on TimesFM 2.5; 64–2,048 on TimesFM 3.0)
|
|
14
|
+
- You have related series to forecast together, or covariates that should shape the forecast — TimesFM 3.0 (Preview) adds multivariate forecasting with `target_cols`, `past_covariate_cols` and `future_covariate_cols`
|
|
15
|
+
|
|
16
|
+
**Alternatives:**
|
|
17
|
+
- `functions/ai_detect_anomalies` (`AI.DETECT_ANOMALIES`) — Detect anomalies by comparing data against a forecast baseline
|
|
18
|
+
- `functions/ai_evaluate` (`AI.EVALUATE`) — Evaluate forecast accuracy against actual values
|
|
19
|
+
- `bigquery-ml/models/arima_plus` (`ARIMA_PLUS`) — the trainable, in-BigQuery classical statistical alternative: custom holiday effects, hierarchical reconciliation across a real dimension hierarchy, decomposable and explainable components (`ML.EXPLAIN_FORECAST`), and forecast bounds — none of which the TimesFM functions expose. External regressors are no longer the dividing line: `bigquery-ml/models/arima_plus_xreg` (`ARIMA_PLUS_XREG`) and TimesFM 3.0's covariates (section 9 below) both take them. Use `AI.FORECAST` for a fast, no-training baseline — with 3.0, a covariate-aware one; reach for `ARIMA_PLUS` when you need that level of control and explanation.
|
|
20
|
+
- `bigquery-ml/functions/time_series` (`ML.TREND` / `ML.SEASONALITY` / `ML.DETECT_CHANGE_POINTS`) — model-free decomposition rather than forecasting: trend, seasonal components, and sustained structural change points, with no `CREATE MODEL` and no foundation model. Reach for these when the question is *what has this series been doing* rather than *what will it do next*.
|
|
21
|
+
- `bigquery-ml/workflows/causal_effect` (`AI.CAUSAL_EFFECT`) — **the same forecasting idea aimed backwards.** It is not TimesFM: it wraps `ARIMA_PLUS`, and the sibling notebook reproduces its counterfactual bit-for-bit with a plain `CREATE MODEL ... ARIMA_PLUS`. Instead of forecasting past the end of the data, it forecasts past a point *inside* the data — the intervention date — and reports how far the observed values ran from that counterfactual. Reach for it when the question is *what would have happened without the change*, and for `AI.FORECAST` when the question is *what happens next*.
|
|
22
|
+
|
|
23
|
+
**Featured in:** `workflows/time_series_intelligence` (Time Series Intelligence)
|
|
24
|
+
|
|
25
|
+
**References:** `RESOURCES.md` (Full syntax reference) | [Official documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-forecast) | `setup` (Setup guide)
|
|
26
|
+
|
|
27
|
+
---
|
|
28
|
+
## Setup
|
|
29
|
+
|
|
30
|
+
Set your project and location, authenticate, and create a temporary dataset for this notebook.
|
|
31
|
+
|
|
32
|
+
> This function doesn't require a connection or model — it uses end-user credentials automatically. See the `setup` (Setup Reference) for details.
|
|
33
|
+
|
|
34
|
+
```python
|
|
35
|
+
PROJECT_ID = 'statmike-mlops-349915' # <-- Replace with your project ID
|
|
36
|
+
LOCATION = 'US' # BigQuery dataset location
|
|
37
|
+
DATASET_ID = 'bq_ai_functions' # Shared dataset across all notebooks
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
### Environment
|
|
41
|
+
|
|
42
|
+
> **Already set up the project environment?** The cell below is a no-op — packages are already in your kernel. See the `setup` (Setup Reference) for details.
|
|
43
|
+
>
|
|
44
|
+
> **Running standalone** (Colab, Colab Enterprise, Vertex AI Workbench)? The cell below installs required packages into your current kernel.
|
|
45
|
+
|
|
46
|
+
```python
|
|
47
|
+
from google.cloud import bigquery
|
|
48
|
+
import pandas as pd
|
|
49
|
+
|
|
50
|
+
client = bigquery.Client(project=PROJECT_ID)
|
|
51
|
+
pd.set_option('display.max_colwidth', None)
|
|
52
|
+
|
|
53
|
+
# Create the shared dataset (idempotent)
|
|
54
|
+
dataset_ref = bigquery.DatasetReference(PROJECT_ID, DATASET_ID)
|
|
55
|
+
dataset = bigquery.Dataset(dataset_ref)
|
|
56
|
+
dataset.location = LOCATION
|
|
57
|
+
client.create_dataset(dataset, exists_ok=True)
|
|
58
|
+
print(f'Dataset {PROJECT_ID}.{DATASET_ID} ready')
|
|
59
|
+
|
|
60
|
+
# Register %%bigquery cell magic (auto-loaded in Colab, needed elsewhere)
|
|
61
|
+
%load_ext bigquery_magics
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
---
|
|
65
|
+
## Examples — SQL
|
|
66
|
+
|
|
67
|
+
Progressive examples from simplest to most advanced. Each cell adds one new concept.
|
|
68
|
+
|
|
69
|
+
### Setup: Create sample time series data
|
|
70
|
+
|
|
71
|
+
Generate synthetic daily sales data with realistic patterns using SQL.
|
|
72
|
+
|
|
73
|
+
```python
|
|
74
|
+
# Create synthetic daily sales data with trend and weekly seasonality
|
|
75
|
+
query = f'''
|
|
76
|
+
CREATE OR REPLACE TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales` AS
|
|
77
|
+
WITH dates AS (
|
|
78
|
+
SELECT date
|
|
79
|
+
FROM UNNEST(GENERATE_DATE_ARRAY('2024-01-01', '2024-12-31')) AS date
|
|
80
|
+
)
|
|
81
|
+
SELECT
|
|
82
|
+
date,
|
|
83
|
+
-- Base sales + trend + weekly seasonality + noise
|
|
84
|
+
GREATEST(0,
|
|
85
|
+
1000
|
|
86
|
+
+ EXTRACT(DAYOFYEAR FROM date) * 2 -- upward trend
|
|
87
|
+
+ CASE EXTRACT(DAYOFWEEK FROM date)
|
|
88
|
+
WHEN 1 THEN -200 -- Sunday dip
|
|
89
|
+
WHEN 7 THEN 300 -- Saturday peak
|
|
90
|
+
WHEN 6 THEN 200 -- Friday boost
|
|
91
|
+
ELSE 0
|
|
92
|
+
END
|
|
93
|
+
+ CAST(200 * (RAND() - 0.5) AS INT64) -- random noise
|
|
94
|
+
) AS daily_sales
|
|
95
|
+
FROM dates
|
|
96
|
+
'''
|
|
97
|
+
client.query(query).result()
|
|
98
|
+
|
|
99
|
+
# Preview the data
|
|
100
|
+
df = client.query(f'SELECT * FROM `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales` ORDER BY date LIMIT 10').to_dataframe()
|
|
101
|
+
print(f'Rows: {client.query(f"SELECT COUNT(*) AS n FROM `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`").to_dataframe().iloc[0]["n"]}')
|
|
102
|
+
df
|
|
103
|
+
```
|
|
104
|
+
|
|
105
|
+
### 1. Basic forecast
|
|
106
|
+
|
|
107
|
+
`AI.FORECAST` requires `data_col` and `timestamp_col`. Default horizon is 10 time steps.
|
|
108
|
+
|
|
109
|
+
```python
|
|
110
|
+
query = f'''
|
|
111
|
+
SELECT *
|
|
112
|
+
FROM AI.FORECAST(
|
|
113
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`,
|
|
114
|
+
data_col => 'daily_sales',
|
|
115
|
+
timestamp_col => 'date'
|
|
116
|
+
)
|
|
117
|
+
'''
|
|
118
|
+
client.query(query).to_dataframe()
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
### 2. Custom horizon
|
|
122
|
+
|
|
123
|
+
Forecast more time steps into the future.
|
|
124
|
+
|
|
125
|
+
```python
|
|
126
|
+
query = f'''
|
|
127
|
+
SELECT *
|
|
128
|
+
FROM AI.FORECAST(
|
|
129
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`,
|
|
130
|
+
data_col => 'daily_sales',
|
|
131
|
+
timestamp_col => 'date',
|
|
132
|
+
horizon => 30
|
|
133
|
+
)
|
|
134
|
+
'''
|
|
135
|
+
client.query(query).to_dataframe()
|
|
136
|
+
```
|
|
137
|
+
|
|
138
|
+
### 3. Include historical data
|
|
139
|
+
|
|
140
|
+
Set `output_historical_time_series => TRUE` to get historical + forecasted data in one result for comparison.
|
|
141
|
+
|
|
142
|
+
```python
|
|
143
|
+
query = f'''
|
|
144
|
+
SELECT *
|
|
145
|
+
FROM AI.FORECAST(
|
|
146
|
+
(SELECT * FROM `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`
|
|
147
|
+
WHERE date >= '2024-11-01'), -- last 2 months for context
|
|
148
|
+
data_col => 'daily_sales',
|
|
149
|
+
timestamp_col => 'date',
|
|
150
|
+
horizon => 14,
|
|
151
|
+
output_historical_time_series => TRUE
|
|
152
|
+
)
|
|
153
|
+
ORDER BY time_series_timestamp
|
|
154
|
+
'''
|
|
155
|
+
df = client.query(query).to_dataframe()
|
|
156
|
+
print(f'Historical rows: {(df["time_series_type"] == "history").sum()}')
|
|
157
|
+
print(f'Forecast rows: {(df["time_series_type"] == "forecast").sum()}')
|
|
158
|
+
df.tail(20)
|
|
159
|
+
```
|
|
160
|
+
|
|
161
|
+
### 4. Multi-series forecasting with id_cols
|
|
162
|
+
|
|
163
|
+
Forecast multiple independent time series at once by specifying `id_cols`.
|
|
164
|
+
|
|
165
|
+
```python
|
|
166
|
+
# Create multi-series data
|
|
167
|
+
query = f'''
|
|
168
|
+
CREATE OR REPLACE TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_multi_series` AS
|
|
169
|
+
WITH dates AS (
|
|
170
|
+
SELECT date
|
|
171
|
+
FROM UNNEST(GENERATE_DATE_ARRAY('2024-01-01', '2024-12-31')) AS date
|
|
172
|
+
),
|
|
173
|
+
stores AS (
|
|
174
|
+
SELECT * FROM UNNEST([
|
|
175
|
+
STRUCT('downtown' AS store_id, 1500 AS base_sales),
|
|
176
|
+
STRUCT('suburban', 800),
|
|
177
|
+
STRUCT('airport', 2000)
|
|
178
|
+
])
|
|
179
|
+
)
|
|
180
|
+
SELECT
|
|
181
|
+
s.store_id,
|
|
182
|
+
d.date,
|
|
183
|
+
GREATEST(0, s.base_sales + EXTRACT(DAYOFYEAR FROM d.date) * 1 + CAST(100 * (RAND() - 0.5) AS INT64)) AS daily_sales
|
|
184
|
+
FROM dates d CROSS JOIN stores s
|
|
185
|
+
'''
|
|
186
|
+
client.query(query).result()
|
|
187
|
+
print('Multi-series data created')
|
|
188
|
+
```
|
|
189
|
+
|
|
190
|
+
```python
|
|
191
|
+
# Forecast each store independently
|
|
192
|
+
query = f'''
|
|
193
|
+
SELECT *
|
|
194
|
+
FROM AI.FORECAST(
|
|
195
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_multi_series`,
|
|
196
|
+
data_col => 'daily_sales',
|
|
197
|
+
timestamp_col => 'date',
|
|
198
|
+
id_cols => ['store_id'],
|
|
199
|
+
horizon => 14
|
|
200
|
+
)
|
|
201
|
+
ORDER BY store_id, forecast_timestamp
|
|
202
|
+
'''
|
|
203
|
+
client.query(query).to_dataframe()
|
|
204
|
+
```
|
|
205
|
+
|
|
206
|
+
### 5. Confidence level and TimesFM model version
|
|
207
|
+
|
|
208
|
+
Control prediction interval width with `confidence_level`, and pin the model version with `model`.
|
|
209
|
+
|
|
210
|
+
**The default is TimesFM 2.5.** The other accepted value is `'TimesFM 3.0'` (Preview) — section 8 covers what it adds. Pin `model` whenever the numbers have to be reproducible: an unpinned call follows the default, and the default moves when Google advances it.
|
|
211
|
+
|
|
212
|
+
```python
|
|
213
|
+
query = f'''
|
|
214
|
+
SELECT *
|
|
215
|
+
FROM AI.FORECAST(
|
|
216
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`,
|
|
217
|
+
data_col => 'daily_sales',
|
|
218
|
+
timestamp_col => 'date',
|
|
219
|
+
horizon => 14,
|
|
220
|
+
confidence_level => 0.99,
|
|
221
|
+
model => 'TimesFM 2.5'
|
|
222
|
+
)
|
|
223
|
+
'''
|
|
224
|
+
client.query(query).to_dataframe()
|
|
225
|
+
```
|
|
226
|
+
|
|
227
|
+
### 6. Forecast to a specific date
|
|
228
|
+
|
|
229
|
+
Use `forecast_end_timestamp` instead of `horizon` to forecast up to a target date. The horizon is calculated automatically from the data's frequency. Mutually exclusive with `horizon`.
|
|
230
|
+
|
|
231
|
+
```python
|
|
232
|
+
query = f'''
|
|
233
|
+
SELECT *
|
|
234
|
+
FROM AI.FORECAST(
|
|
235
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`,
|
|
236
|
+
data_col => 'daily_sales',
|
|
237
|
+
timestamp_col => 'date',
|
|
238
|
+
forecast_end_timestamp => '2025-01-15'
|
|
239
|
+
)
|
|
240
|
+
'''
|
|
241
|
+
df = client.query(query).to_dataframe()
|
|
242
|
+
print(f'Forecasted {len(df)} days (through {df["forecast_timestamp"].max().strftime("%Y-%m-%d")})')
|
|
243
|
+
df
|
|
244
|
+
```
|
|
245
|
+
|
|
246
|
+
### 7. Setting the context window
|
|
247
|
+
|
|
248
|
+
The `context_window` controls how many of the most recent historical points the model sees. The two model versions handle it differently:
|
|
249
|
+
|
|
250
|
+
- **TimesFM 2.5** (default): 64, 128, 256, 512, 1024, 2048, 4096, 8192 or 15360. When unspecified, the smallest window covering your data is auto-selected. Any other value is rejected.
|
|
251
|
+
- **TimesFM 3.0**: a multiple of 32 from 64 to 2048. When unspecified, the **maximum** (2048) is used, and points older than that are ignored. A value above 2048 is rejected; a value that is not a multiple of 32 is accepted rather than rejected, so stay on the documented grid if you want to know what the model saw.
|
|
252
|
+
|
|
253
|
+
```python
|
|
254
|
+
query = f'''
|
|
255
|
+
SELECT
|
|
256
|
+
forecast_timestamp,
|
|
257
|
+
ROUND(forecast_value, 0) AS forecast,
|
|
258
|
+
ROUND(prediction_interval_lower_bound, 0) AS lower,
|
|
259
|
+
ROUND(prediction_interval_upper_bound, 0) AS upper
|
|
260
|
+
FROM AI.FORECAST(
|
|
261
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales`,
|
|
262
|
+
data_col => 'daily_sales',
|
|
263
|
+
timestamp_col => 'date',
|
|
264
|
+
horizon => 7,
|
|
265
|
+
context_window => 128
|
|
266
|
+
)
|
|
267
|
+
'''
|
|
268
|
+
client.query(query).to_dataframe()
|
|
269
|
+
```
|
|
270
|
+
|
|
271
|
+
### 8. TimesFM 3.0 (Preview): multivariate forecasting with `target_cols`
|
|
272
|
+
|
|
273
|
+
TimesFM 3.0 is selected with `model => 'TimesFM 3.0'`. On a single series it is a drop-in alternative to 2.5 with the same output columns, and a shorter reach: `horizon` is capped at 1,024 and the context window at 2,048 points.
|
|
274
|
+
|
|
275
|
+
What it adds is **multivariate forecasting**: pass `target_cols` (an array of column names) instead of `data_col`, and the model forecasts the series jointly. This syntax requires `model => 'TimesFM 3.0'` — with any other model, or with no `model` at all, the call fails with the generic `Invalid table-valued function AI.FORECAST`.
|
|
276
|
+
|
|
277
|
+
The output is restructured for multiple targets:
|
|
278
|
+
- the timestamp column **keeps its input name** (`date` here, not `forecast_timestamp`) and comes back as a `TIMESTAMP`
|
|
279
|
+
- each target becomes a `STRUCT<value, prediction_interval_lower_bound, prediction_interval_upper_bound>` under its own name
|
|
280
|
+
- `time_series_type` (`forecast`, or `history` when `output_historical_time_series => TRUE`), `confidence_level` and `ai_forecast_status` complete the row
|
|
281
|
+
|
|
282
|
+
`forecast_end_timestamp` is accepted in this form too, although the documented multivariate syntax lists only `horizon`.
|
|
283
|
+
|
|
284
|
+
First, a second table with two related daily series — sales and web visits — plus two columns that will serve as covariates in section 9. It covers 2024 as history and includes **14 future dates with the targets left NULL**; section 9 explains why.
|
|
285
|
+
|
|
286
|
+
```python
|
|
287
|
+
# Two related daily series (sales, web visits) plus two covariates (promo flag, weekend flag).
|
|
288
|
+
# History: 2024. Future: 14 days with the targets NULL and the future covariates populated.
|
|
289
|
+
query = f'''
|
|
290
|
+
CREATE OR REPLACE TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales_mv` AS
|
|
291
|
+
WITH days AS (
|
|
292
|
+
SELECT date,
|
|
293
|
+
EXTRACT(DAYOFWEEK FROM date) AS dow,
|
|
294
|
+
DATE_DIFF(date, DATE '2024-01-01', DAY) AS t
|
|
295
|
+
FROM UNNEST(GENERATE_DATE_ARRAY('2024-01-01', '2025-01-14')) AS date
|
|
296
|
+
)
|
|
297
|
+
SELECT
|
|
298
|
+
date,
|
|
299
|
+
IF(date <= '2024-12-31', GREATEST(0,
|
|
300
|
+
1000 + t * 2
|
|
301
|
+
+ CASE dow WHEN 1 THEN -200 WHEN 7 THEN 300 WHEN 6 THEN 200 ELSE 0 END
|
|
302
|
+
+ IF(MOD(t + 20, 30) < 3, 400, 0) -- promotion lift
|
|
303
|
+
+ CAST(200 * (RAND() - 0.5) AS INT64)), NULL) AS daily_sales,
|
|
304
|
+
IF(date <= '2024-12-31', GREATEST(0,
|
|
305
|
+
5000 + t * 5
|
|
306
|
+
+ CASE dow WHEN 1 THEN -800 WHEN 7 THEN 1200 WHEN 6 THEN 800 ELSE 0 END
|
|
307
|
+
+ CAST(600 * (RAND() - 0.5) AS INT64)), NULL) AS web_visits,
|
|
308
|
+
IF(MOD(t + 20, 30) < 3, 1, 0) AS promo_flag, -- known in advance: the promotion calendar
|
|
309
|
+
IF(dow IN (1, 7), 1, 0) AS is_weekend -- known in advance: the calendar
|
|
310
|
+
FROM days
|
|
311
|
+
'''
|
|
312
|
+
client.query(query).result()
|
|
313
|
+
|
|
314
|
+
# The seam between history and future: targets stop, future covariates continue
|
|
315
|
+
df = client.query(f'''
|
|
316
|
+
SELECT * FROM `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales_mv`
|
|
317
|
+
WHERE date BETWEEN '2024-12-29' AND '2025-01-03' ORDER BY date''').to_dataframe()
|
|
318
|
+
df
|
|
319
|
+
```
|
|
320
|
+
|
|
321
|
+
Forecast both series jointly from the history rows. Each target comes back as its own `STRUCT`; the query below flattens the fields it wants.
|
|
322
|
+
|
|
323
|
+
```python
|
|
324
|
+
query = f'''
|
|
325
|
+
SELECT
|
|
326
|
+
date,
|
|
327
|
+
ROUND(daily_sales.value) AS sales_forecast,
|
|
328
|
+
ROUND(daily_sales.prediction_interval_lower_bound) AS sales_lower,
|
|
329
|
+
ROUND(daily_sales.prediction_interval_upper_bound) AS sales_upper,
|
|
330
|
+
ROUND(web_visits.value) AS visits_forecast,
|
|
331
|
+
time_series_type,
|
|
332
|
+
ai_forecast_status
|
|
333
|
+
FROM AI.FORECAST(
|
|
334
|
+
(SELECT date, daily_sales, web_visits
|
|
335
|
+
FROM `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales_mv`
|
|
336
|
+
WHERE date <= '2024-12-31'),
|
|
337
|
+
target_cols => ['daily_sales', 'web_visits'],
|
|
338
|
+
timestamp_col => 'date',
|
|
339
|
+
model => 'TimesFM 3.0',
|
|
340
|
+
horizon => 7
|
|
341
|
+
)
|
|
342
|
+
ORDER BY date
|
|
343
|
+
'''
|
|
344
|
+
client.query(query).to_dataframe()
|
|
345
|
+
```
|
|
346
|
+
|
|
347
|
+
### 9. Past and future covariates
|
|
348
|
+
|
|
349
|
+
Covariates are extra columns the model may use to shape the forecast. TimesFM 3.0 distinguishes two kinds by *when they are known*:
|
|
350
|
+
|
|
351
|
+
- **`past_covariate_cols`** — known only historically. Web visits influence sales, but tomorrow's visits are not known today: populated for history rows, NULL for the future rows.
|
|
352
|
+
- **`future_covariate_cols`** — known for the past *and* the future. The promotion calendar and the day of the week are fixed in advance: populated on every row, including the 14 future dates.
|
|
353
|
+
|
|
354
|
+
That is why the input table carries future rows with NULL targets: the future covariates have to be supplied for every timestamp you want forecast. Covariates require the `target_cols` form — `data_col` plus a covariate argument is rejected. Three things measured here that the syntax does not say:
|
|
355
|
+
|
|
356
|
+
- `horizon` is **capped by the future rows you supply** — ask for 30 with 14 future rows and you get 14, silently.
|
|
357
|
+
- Without `horizon`, the default of 10 applies even when more future rows are available.
|
|
358
|
+
- A past covariate alone, with no future rows at all, also works — it simply conditions the forecast on the history.
|
|
359
|
+
|
|
360
|
+
```python
|
|
361
|
+
query = f'''
|
|
362
|
+
WITH forecast AS (
|
|
363
|
+
SELECT
|
|
364
|
+
date,
|
|
365
|
+
ROUND(daily_sales.value) AS sales_forecast,
|
|
366
|
+
ROUND(daily_sales.prediction_interval_lower_bound) AS lower,
|
|
367
|
+
ROUND(daily_sales.prediction_interval_upper_bound) AS upper
|
|
368
|
+
FROM AI.FORECAST(
|
|
369
|
+
TABLE `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales_mv`,
|
|
370
|
+
target_cols => ['daily_sales'],
|
|
371
|
+
timestamp_col => 'date',
|
|
372
|
+
model => 'TimesFM 3.0',
|
|
373
|
+
horizon => 14,
|
|
374
|
+
past_covariate_cols => ['web_visits'],
|
|
375
|
+
future_covariate_cols => ['promo_flag', 'is_weekend']
|
|
376
|
+
)
|
|
377
|
+
)
|
|
378
|
+
SELECT f.date, f.sales_forecast, f.lower, f.upper, c.promo_flag, c.is_weekend
|
|
379
|
+
FROM forecast f
|
|
380
|
+
JOIN `{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales_mv` c ON DATE(f.date) = c.date
|
|
381
|
+
ORDER BY f.date
|
|
382
|
+
'''
|
|
383
|
+
client.query(query).to_dataframe()
|
|
384
|
+
```
|
|
385
|
+
|
|
386
|
+
---
|
|
387
|
+
## Examples — `%%bigquery` Magics
|
|
388
|
+
|
|
389
|
+
The same examples using IPython magic commands. Magics let you write SQL directly in notebook cells without Python string wrapping.
|
|
390
|
+
|
|
391
|
+
Key patterns:
|
|
392
|
+
- `%%bigquery` — run SQL, display results inline
|
|
393
|
+
- `%%bigquery df` — run SQL, capture results into a pandas DataFrame
|
|
394
|
+
|
|
395
|
+
### Basic forecast with `%%bigquery`
|
|
396
|
+
|
|
397
|
+
```sql
|
|
398
|
+
%%bigquery --project {PROJECT_ID}
|
|
399
|
+
|
|
400
|
+
SELECT *
|
|
401
|
+
FROM AI.FORECAST(
|
|
402
|
+
TABLE `statmike-mlops-349915.bq_ai_functions.ai_forecast_sales`,
|
|
403
|
+
data_col => 'daily_sales',
|
|
404
|
+
timestamp_col => 'date',
|
|
405
|
+
horizon => 7
|
|
406
|
+
)
|
|
407
|
+
```
|
|
408
|
+
|
|
409
|
+
---
|
|
410
|
+
## Examples — BigFrames
|
|
411
|
+
|
|
412
|
+
BigFrames wraps `AI.FORECAST` via `bbq.ai.forecast()`. No model object needed. Pass `model` explicitly: the wrapper's own default is `'TimesFM 2.0'`, a version the SQL reference page no longer lists, so an unpinned wrapper call and an unpinned SQL call run different models.
|
|
413
|
+
|
|
414
|
+
```python
|
|
415
|
+
import bigframes.pandas as bpd
|
|
416
|
+
import bigframes.bigquery as bbq
|
|
417
|
+
|
|
418
|
+
bpd.options.bigquery.project = PROJECT_ID
|
|
419
|
+
bpd.options.bigquery.location = LOCATION
|
|
420
|
+
```
|
|
421
|
+
|
|
422
|
+
### Basic forecast
|
|
423
|
+
|
|
424
|
+
```python
|
|
425
|
+
# Load the time series data
|
|
426
|
+
df = bpd.read_gbq(f'{PROJECT_ID}.{DATASET_ID}.ai_forecast_sales')
|
|
427
|
+
|
|
428
|
+
# Forecast
|
|
429
|
+
forecast = bbq.ai.forecast(
|
|
430
|
+
df,
|
|
431
|
+
data_col='daily_sales',
|
|
432
|
+
timestamp_col='date',
|
|
433
|
+
horizon=14,
|
|
434
|
+
model='TimesFM 2.5'
|
|
435
|
+
)
|
|
436
|
+
forecast.to_pandas()
|
|
437
|
+
```
|