SQL-inf extends any SQL dialect by introducing specialized commands designed for data analysis and predictive analytics. Understanding the syntax will enable you to get the most out of SQL-inf's capabilities. This document discusses the general structure, input handling, and output generation in SQL-inf.
The PREDICT command lets you run a prediction on a given column using the rest of the column names specified in the SELECT statement as inputs to the prediction.
The EXPLAIN command takes an SQL-inf command as input and outputs an "explanation" of the output of the inner
📄️ How it works: PREDICT & EXPLAIN
PREDICT is easily the most popular command at Infer, often used in combination with EXPLAIN to gain valuable insights on the data-of-interest.
The SENTIMENT commands lets you predict the sentiment of text given a text column as input.
📄️ How it works: SENTIMENT
SENTIMENT allows users to get the sentiment (Positive, Negative, Neutral) of any kind of text data using a Sentiment Analysis model powered by large language models.
The TOPICS commands lets you predict the topics of a piece of text given a text column as input.
📄️ How it works: TOPICS
Topic analysis is a technique used to identify and extract common themes or topics from a collection of documents or text data.
The CLUSTER command clusters the rows in the input data table into groups of rows that are similar.
📄️ How it works: CLUSTER
Clustering is a type of analysis that allows us to place similar data objects (users, companies, etc) into groups or clusters.
The FORECAST commands lets you forecast a time series, given a time and a column to predict.
The UPLIFT command is very similar to the AB_TEST command, where we are calculating how effective an A/B test has been.
The AB_TEST command calculates a number of useful statistics for comparing groups,
📄️ Combining Commands
SQL-inf supports combining SQL-inf commands through chaining.
The CORRELATION command calculates the correlations in your dataset between each input column, including both numeric can categorical columns.
The DESCRIBE command summarises your dataset using different useful metrics, so you can get a quick overview without deep analysis.
The SHAP command takes an SQL-inf command as input and outputs a shap value for each row of the output and each column of the input data the inner SQL-inf command.
The SIMILAR_TO commands lets you compute a similarity score between a specific row and all other rows in the data set.
The TRANSLATE commands lets you translate text from a number of different languages to English.