Algorithm Selection

We currently support regression and classification algorithms from scikit-learn, XGBoost, and LightGBM.

Algorithms

Gradient Boosting

Algorithm	Regression	Classification
`xgboost`	XGBRegressor	XGBClassifier
`xgboost_random_forest`	XGBRFRegressor	XGBRFClassifier
`lightgbm`	LGBMRegressor	LGBMClassifier

Scikit Ensembles

Algorithm	Regression	Classification
`ada_boost`	AdaBoostRegressor	AdaBoostClassifier
`bagging`	BaggingRegressor	BaggingClassifier
`extra_trees`	ExtraTreesRegressor	ExtraTreesClassifier
`gradient_boosting_trees`	GradientBoostingRegressor	GradientBoostingClassifier
`random_forest`	RandomForestRegressor	RandomForestClassifier
`hist_gradient_boosting`	HistGradientBoostingRegressor	HistGradientBoostingClassifier

Support Vector Machines

Algorithm	Regression	Classification
`svm`	SVR	SVC
`nu_svm`	NuSVR	NuSVC
`linear_svm`	LinearSVR	LinearSVC

Linear Models

Algorithm	Regression	Classification
`linear`	LinearRegression	LogisticRegression
`ridge`	Ridge	RidgeClassifier
`lasso`	Lasso	-
`elastic_net`	ElasticNet	-
`least_angle`	LARS	-
`lasso_least_angle`	LassoLars	-
`orthoganl_matching_pursuit`	OrthogonalMatchingPursuit	-
`bayesian_ridge`	BayesianRidge	-
`automatic_relevance_determination`	ARDRegression	-
`stochastic_gradient_descent`	SGDRegressor	SGDClassifier
`perceptron`	-	Perceptron
`passive_aggressive`	PassiveAggressiveRegressor	PassiveAggressiveClassifier
`ransac`	RANSACRegressor	-
`theil_sen`	TheilSenRegressor	-
`huber`	HuberRegressor	-
`quantile`	QuantileRegressor	-

Other

Algorithm	Regression	Classification
`kernel_ridge`	KernelRidge	-
`gaussian_process`	GaussianProcessRegressor	GaussianProcessClassifier

Comparing Algorithms

Any of the above algorithms can be passed to our pgml.train() function using the algorithm parameter. If the parameter is omitted, linear regression is used by default.

code

Example


                content_copy
                link
                edit
            
SELECT * FROM pgml.train(
    'My First PostgresML Project',
    task => 'classification',
    relation_name => 'pgml.digits',
    y_column_name => 'target',
    algorithm => 'xgboost',
);

The hyperparams argument will pass the hyperparameters on to the algorithm. Take a look at the associated documentation for valid hyperparameters of each algorithm. Our interface uses the scikit-learn notation for all parameters.

code

Example


                content_copy
                link
                edit
            
SELECT * FROM pgml.train(
    'My First PostgresML Project',
    algorithm => 'xgboost',
    hyperparams => '{
        "n_estimators": 25
    }'
);

Once prepared, the training data can be efficiently reused by other PostgresML algorithms for training and predictions. Every time the pgml.train() function receives the relation_name and y_column_name arguments, it will create a new snapshot of the relation (table) and save it in the pgml schema.

To train another algorithm on the same dataset, omit the two arguments. PostgresML will reuse the latest snapshot with the new algorithm.

help

Tip

Try experimenting with multiple algorithms to explore their performance characteristics on your dataset. It's often hard to know which algorithm will be the best.

Dashboard

The PostgresML dashboard makes it easy to compare various algorithms on your dataset. You can explore individual metrics & compare algorithms to each other, all trained on the same dataset for a fair benchmark.

Model Selection

Have Questions?

Join our Discord and ask us anything! We're friendly and would love to talk about PostgresML.

Try It Out

Try PostresML using our free serverless cloud. It comes with GPUs, 5 GiB of space and plenty of datasets to get you started.

Get Started