causal_inference_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from causality.inference.search import IC\n",
    "from causality.inference.independence_tests import RobustRegressionTest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "SIZE = 2000\n",
    "x1 = np.random.normal(size=SIZE)\n",
    "x2 = x1 + np.random.normal(size=SIZE)\n",
    "x3 = x1 + np.random.normal(size=SIZE)\n",
    "x4 = x2 + x3 + np.random.normal(size=SIZE)\n",
    "x5 = x4 + np.random.normal(size=SIZE)\n",
    "\n",
    "# load the data into a dataframe:\n",
    "X = pd.DataFrame({'x1' : x1, 'x2' : x2, 'x3' : x3, 'x4' : x4, 'x5' : x5})\n",
    "\n",
    "# define the variable types: 'c' is 'continuous'.  The variables defined here\n",
    "# are the ones the search is performed over  -- NOT all the variables defined\n",
    "# in the data frame.\n",
    "variable_types = {'x1' : 'c', 'x2' : 'c', 'x3' : 'c', 'x4' : 'c', 'x5' : 'c'}\n",
    "\n",
    "# run the search\n",
    "ic_algorithm = IC(RobustRegressionTest, X, variable_types)\n",
    "graph = ic_algorithm.search()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('x2', 'x1', {'arrows': [], 'marked': False}),\n",
       " ('x2', 'x4', {'arrows': ['x4'], 'marked': False}),\n",
       " ('x3', 'x1', {'arrows': [], 'marked': False}),\n",
       " ('x3', 'x4', {'arrows': ['x4'], 'marked': False}),\n",
       " ('x4', 'x5', {'arrows': ['x5'], 'marked': True})]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "graph.edges(data=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "SIZE = 2000\n",
    "x1 = np.random.normal(size=SIZE)\n",
    "x2 = x1 + np.random.normal(size=SIZE)\n",
    "x3 = x1 + np.random.normal(size=SIZE)\n",
    "x6 = np.random.normal(size=SIZE)\n",
    "x4 = x2 + x3 + x6 + np.random.normal(size=SIZE)\n",
    "x5 = x6 + np.random.normal(size=SIZE)\n",
    "\n",
    "# load the data into a dataframe:\n",
    "X = pd.DataFrame({'x1' : x1, 'x2' : x2, 'x3' : x3, 'x4' : x4, 'x5' : x5})\n",
    "\n",
    "# define the variable types: 'c' is 'continuous'.  The variables defined here\n",
    "# are the ones the search is performed over  -- NOT all the variables defined\n",
    "# in the data frame.\n",
    "variable_types = {'x1' : 'c', 'x2' : 'c', 'x3' : 'c', 'x4' : 'c', 'x5' : 'c'}\n",
    "\n",
    "# run the search\n",
    "ic_algorithm = IC(RobustRegressionTest, X, variable_types)\n",
    "graph = ic_algorithm.search()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('x2', 'x1', {'arrows': [], 'marked': False}),\n",
       " ('x2', 'x4', {'arrows': ['x4', 'x4'], 'marked': False}),\n",
       " ('x3', 'x1', {'arrows': [], 'marked': False}),\n",
       " ('x3', 'x4', {'arrows': ['x4', 'x4'], 'marked': False}),\n",
       " ('x4', 'x5', {'arrows': ['x4', 'x4'], 'marked': False})]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "graph.edges(data=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}