jburroni

;; gorilla-repl.fileformat = 1

;; **
;;; # Interventional Operator
;;; 
;;; This example shows how to implement an interventional operator (the 'do' operator from the causal literature, but the name was already taken in closure).
;;; 
;;; Once we define a model, the _do_ operator represents external interventions to the model. As we are writing the model, there is nothing that forbids us of writing the same model (queries) with the required intervention. The problem with that approach is that we end up duplicating the model’s logic. To solve this problem, we could implement the intervention as an operator, i.e., a function from the space of queries to the space of queries. 
;;; 
;;; In this Worksheet we are going to use the famous _sprinkler_ example. 

jburroni

jburroni

jburroni

jburroni

###Author: Javier Burroni 
###Creation: March 2016
###Please give credit when using this code

import matplotlib
matplotlib.use('Agg')
import pandas as pd
import numpy as np
import seaborn as sns
from matplotlib import pyplot as plt

jburroni

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [

jburroni

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [

jburroni

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [

jburroni

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {

jburroni

Iteration	Trade Blocks
0
	Canada, USA
1
	Malaysia, Singapore
	Brazil, Argentina
	Neth.Ant.Aru, Venezuela
	China, China HK SAR
	Germany, France,Monac