mkyl / carl-lib Goto Github PK
View Code? Open in Web Editor NEWCausal Inference on Relational Data
Causal Inference on Relational Data
Be able to handle a query of the form Y[x] <- T[x]?
for a ground causal model including only Y, T, and Q nodes, where Q is a confounder.
Status:
This will allow for far more interesting grounded causal models.
Create stubs for the following libraries.
Status:
Need to replace cond
in grounding process with a macro, so that predicates with more than 3 logical variables can be handled.
Be able to handle a query of the form Y[x] <- T[x]?
for a ground causal model including only Y and T nodes.
Status:
every causal model makes testable implications w.r.t. the conditional independences in the data. We should check if these independences hold and warn the user otherwise.
currently CaRL only computes the estimate for the first query, ignoring the others -- should be a straightforward fix.
no adjustment set corresponds to getting #f
from detect
.
Add a few embeddings, including:
Allow for queries that look like this:
Acceptance[P] <- Prestige[A] WHERE Author(P, A), Published(C, P)
GROUP BY Conference_Blinding[C]?
Where the output is something like this:
'Single': 0.25
'Double': 0.02
The structs in expander.rkt
are declared #:transparent
for ease of debugging. Once carl-lib is usable by end-users, this should be removed.
With the merging of #11, grounding will not work on DB's outside SQLite. This is an easy fix--just have to get around to doing it.
Need to omit the WHERE
clause if no conditions need to be checked. Occurs during creation of SQL query in ground/load.rkt
.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.