stuff

levkk · levkk · commit 45cd3a3a9689 · 2022-04-08T17:08:22.000-07:00
diff --git a/pgml/README.md b/pgml/README.md
@@ -1 +1,19 @@
-# pgml
+# PgML - Postgres Machine Learning
+
+This package implements data processing, training and scoring of ML models. It is built to be used
+inside PL/Python functions, inside a Postgres connection process.
+
+Most functions can work in any Python environment; some functions are tightly coupled to
+PL/Python by requiring a `plpy` object passed in as an argument: it provides database access methods.
+
+## Installation
+
+For now, we require that this package is installed into the system Python packages space:
+
+```bash
+sudo pip3 setup.py install
+```
+
+## Usage
+
+See `../sql/install.sql` for list of functions. This package is not meant to be used directly.
diff --git a/sql/install.sql b/sql/install.sql
@@ -2,10 +2,13 @@
 -- Create the PL/Python3 extension.
 CREATE EXTENSION IF NOT EXISTS plpython3u;
 
+DROP SCHEMA pgml CASCADE;
+CREATE SCHEMA IF NOT EXISTS pgml;
+
 ---
 --- Extension version.
 ---
-CREATE OR REPLACE FUNCTION pgml_version()
+CREATE OR REPLACE FUNCTION pgml.version()
 RETURNS TEXT
 AS $$
 	import pgml
@@ -15,7 +18,6 @@ $$ LANGUAGE plpython3u;
 ---
 --- Track table versions.
 ---
-CREATE SCHEMA IF NOT EXISTS pgml;
 CREATE TABLE pgml.model_versions(
 	id BIGSERIAL PRIMARY KEY,
 	name VARCHAR,
@@ -33,7 +35,7 @@ CREATE TABLE pgml.model_versions(
 --- Run some validations on the table/view to make sure
 --- it'll work without our package.
 ---
-CREATE OR REPLACE FUNCTION pgml_validate(table_name TEXT)
+CREATE OR REPLACE FUNCTION pgml.validate(table_name TEXT)
 RETURNS BOOL
 AS $$
 	from pgml.sql import all_rows
@@ -47,7 +49,7 @@ $$ LANGUAGE plpython3u;
 ---
 --- Train the model.
 ---
-CREATE OR REPLACE FUNCTION pgml_train(table_name TEXT, y TEXT)
+CREATE OR REPLACE FUNCTION pgml.train(table_name TEXT, y TEXT)
 RETURNS TEXT
 AS $$
 	from pgml.train import train
@@ -88,8 +90,7 @@ $$ LANGUAGE plpython3u;
 ---
 --- Predict
 ---
-DROP FUNCTION pgml_score(model_name TEXT, VARIADIC features DOUBLE PRECISION[]);
-CREATE OR REPLACE FUNCTION pgml_score(model_name TEXT, VARIADIC features DOUBLE PRECISION[])
+CREATE OR REPLACE FUNCTION pgml.score(model_name TEXT, VARIADIC features DOUBLE PRECISION[])
 RETURNS DOUBLE PRECISION
 AS $$
 	from pgml.sql import models_directory
diff --git a/sql/test.sql b/sql/test.sql
@@ -4,21 +4,21 @@
 \i sql/install.sql
 \i data/winequality-red.sql
 
-SELECT pgml_version();
+SELECT pgml.version();
 
 -- Valiate our wine data.
-SELECT pgml_validate('wine_quality_red');
+SELECT pgml.validate('wine_quality_red');
 
 -- Train twice
-SELECT pgml_train('wine_quality_red', 'quality');
+SELECT pgml.train('wine_quality_red', 'quality');
 
 SELECT * FROM pgml.model_versions;
 
 \timing
 WITH latest_model AS (
 	SELECT name || '_' || id AS model_name FROM pgml.model_versions ORDER BY id DESC LIMIT 1
 )
-SELECT pgml_score(
+SELECT pgml.score(
 	(SELECT model_name FROM latest_model), -- last model we just trained
 
 	-- features as variadic arguments
