Model Category | Model Types | Numeric types (INT64, NUMERIC, BIGNUMERIC, FLOAT64) | Categorical types (BOOL, STRING, BYTES, DATE, DATETIME) | TIMESTAMP | STRUCT | GEOGRAPHY | ARRAY<Numeric types> | ARRAY<Categorical types> | ARRAY<STRUCT<INT64, Numeric types>> |
---|---|---|---|---|---|---|---|---|---|
Supervised Learning | Linear & Logistic Regression | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ||
Deep Neural Networks | ✔ | ✔ | ✔ | ✔ | ✔ | ||||
Wide-and-Deep | ✔ | ✔ | ✔ | ✔ | ✔ | ||||
Boosted Trees | ✔ | ✔ | ✔ | ✔ | ✔ | ||||
AutoML Tables | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | |||
Unsupervised Learning | K-means | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ||
PCA | ✔ | ✔ | ✔ | ✔ | ✔ | ||||
Autoencoder | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | |||
Time Series Models | ARIMA_PLUS_XREG | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
Support sparse input for feature columns
BigQuery ML supports ARRAY<STRUCT>
as sparse input during model training.
Each STRUCT
contains an INT64
value that represents its zero-based index, and
a Numeric types
that represents the corresponding value.
Below is an example of sparse tensor input for an integer array [0,1,0,0,0,0,1]:
ARRAY<STRUCT<k INT64, v INT64>>[(1, 1), (6, 1)] AS f1