{ "cells": [ { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "view-in-github" }, "source": [ "\"Open" ] }, { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "qR-vG2CF4jaz" }, "source": [ "# Causal Bayesian Networks\n", "\n", "Causal Inference is a new feature for pgmpy, so I wanted to develop a few examples which show off the features that we're developing! \n", "\n", "This particular notebook walks through the 5 games that used as examples for building intuition about backdoor paths in *The Book of Why* by Judea Peal. I have consistently been using them to test different implementations of backdoor adjustment from different libraries and include them as unit tests in pgmpy, so I wanted to walk through them and a few other related games as a potential resource to both understand the implementation of CausalInference in pgmpy, as well as develope some useful intuitions about backdoor paths. \n", "\n", "## Objective of the Games\n", "\n", "For each game we get a causal graph, and our goal is to identify the set of deconfounders (often denoted $Z$) which will close all backdoor paths from nodes $X$ to $Y$. For the time being, I'll assume that you're familiar with the concept of backdoor paths, though I may expand this portion to explain it. " ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "cellView": "both", "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "colab_type": "code", "id": "p1uBjhCQgaaG", "outputId": "25270025-2cd2-4ce6-a8e6-7d16e2855492" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/lib/python3.6/dist-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n", " from pandas.core import datetools\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Your branch is up to date with 'origin/feature/causalmodel'.\n", "Updating c459420..95af23b\n", "Fast-forward\n", " pgmpy/inference/causal_inference.py | 14 +++++++-------\n", " pgmpy/tests/test_inference/test_causal_inference.py | 2 +-\n", " 2 files changed, 8 insertions(+), 8 deletions(-)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "fatal: destination path 'pgmpy' already exists and is not an empty directory.\n", "mv: cannot move '/content/pgmpy' to '/content/pgmpydev/pgmpy': Directory not empty\n", "Already on 'feature/causalmodel'\n", "From https://github.com/mrklees/pgmpy\n", " c459420..95af23b feature/causalmodel -> origin/feature/causalmodel\n" ] } ], "source": [ "#@title Clone the Development Repo & Install Requirements\n", "#@markdown Because the Causal Inference class is currently in dev, we will actually need to pull the code from GitHub. This cell will give us a pretty good development environment for interactively developing and testing the CausalModel class and its methods.\n", "#@markdown You only need to run this the first time you've started the kernel.\n", "%%sh\n", "git clone https://github.com/mrklees/pgmpy.git\n", "mv /content/pgmpy /content/pgmpydev\n", "cd pgmpydev/\n", "git checkout feature/causalmodel\n", "git pull\n", "#@markdown In testing the CausalModel and Bayesian Network portion of pgmpy we've actually been able to use up to date version of Networkx and other packages, but we may be forced to downgrade to networkx 1.11 if errors arise.\n", "#pip install -U -r requirements-dev.txt" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "cellView": "both", "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "colab_type": "code", "id": "EkFVGD3Tv7ma", "outputId": "a3fd160d-dcdf-4495-e8ea-e5b3aedadaf5" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "The autoreload extension is already loaded. To reload it, use:\n", " %reload_ext autoreload\n" ] } ], "source": [ "#@title Imports\n", "%load_ext autoreload\n", "%autoreload 2\n", "import sys\n", "sys.path.append('/content/pgmpydev')\n", "\n", "!pip3 install -q daft\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", "import daft\n", "from daft import PGM\n", "\n", "# We can now import the development version of pgmpy\n", "from pgmpy.models.BayesianModel import BayesianModel\n", "from pgmpy.inference.causal_inference import CausalInference\n", "\n", "def convert_pgm_to_pgmpy(pgm):\n", " \"\"\"Takes a Daft PGM object and converts it to a pgmpy BayesianModel\"\"\"\n", " edges = [(edge.node1.name, edge.node2.name) for edge in pgm._edges]\n", " model = BayesianModel(edges)\n", " return model" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 201 }, "colab_type": "code", "id": "P90trQAQ7Clc", "outputId": "2e62d5b8-de0e-4e28-b14d-5c03bcd1ab61" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAAC4CAYAAAAynAqtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nKcQimft/k4wcZaGmP/YAAAAASUVORK5CYII=\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 1\n", "#@markdown While this is a \"trivial\" example, many statisticians would consider including either or both A and B in their models \"just for good measure\". Notice though how controlling for A would close off the path of causal information from X to Y, actually *impeding* your effort to measure that effect.\n", "pgm = PGM(shape=[4, 3])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 2))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 2))\n", "pgm.add_node(daft.Node('A', r\"A\", 2, 2))\n", "pgm.add_node(daft.Node('B', r\"B\", 2, 1))\n", "\n", "\n", "pgm.add_edge('X', 'A')\n", "pgm.add_edge('A', 'Y')\n", "pgm.add_edge('A', 'B')\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "cellView": "both", "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "colab_type": "code", "id": "yQyYJEC83ODX", "outputId": "07597081-bbec-4209-db8f-b731de34ae3a" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? False\n", "If so, what's the possible backdoor adjustment sets? frozenset()\n" ] } ], "source": [ "#@markdown Notice how there are no nodes with arrows pointing into X. Said another way, X has no parents. Therefore, there can't be any backdoor paths confounding X and Y. pgmpy will confirm this in the following way:\n", "game1 = convert_pgm_to_pgmpy(pgm)\n", "inference1 = CausalInference(game1)\n", "print(f\"Are there are active backdoor paths? {inference1._has_active_backdoors('X', 'Y')}\")\n", "adj_sets = inference1.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "colab_type": "code", "id": "b5RJ0UsH_kQ4", "outputId": "3e4f9430-fca7-40d4-f8b3-ffd241c6a8f8" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAADxCAYAAAAay1EJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njpM4LmLHSRwXseMkjovYcRLHRew4ifN/jHxgrkKc1LAAAAAASUVORK5CYII=\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 2\n", "#@markdown This graph looks harder, but actualy is also trivial to solve. The key is noticing the one backdoor path, which goes from X <- A -> B <- D -> E -> Y, has a collider at B (or a 'V structure'), and therefore the backdoor path is closed. \n", "pgm = PGM(shape=[4, 4])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 1))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 1))\n", "pgm.add_node(daft.Node('A', r\"A\", 1, 3))\n", "pgm.add_node(daft.Node('B', r\"B\", 2, 3))\n", "pgm.add_node(daft.Node('C', r\"C\", 3, 3))\n", "pgm.add_node(daft.Node('D', r\"D\", 2, 2))\n", "pgm.add_node(daft.Node('E', r\"E\", 2, 1))\n", "\n", "\n", "pgm.add_edge('X', 'E')\n", "pgm.add_edge('A', 'X')\n", "pgm.add_edge('A', 'B')\n", "pgm.add_edge('B', 'C')\n", "pgm.add_edge('D', 'B')\n", "pgm.add_edge('D', 'E')\n", "pgm.add_edge('E', 'Y')\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "colab_type": "code", "id": "2d6Ezs6PDDON", "outputId": "c597c0df-3271-4e8e-9a68-3200c7f105a5" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? False\n", "If so, what's the possible backdoor adjustment sets? frozenset()\n" ] } ], "source": [ "graph = convert_pgm_to_pgmpy(pgm)\n", "inference = CausalInference(graph)\n", "print(f\"Are there are active backdoor paths? {inference._has_active_backdoors('X', 'Y')}\")\n", "adj_sets = inference.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "colab_type": "code", "id": "Pg6T2WA3DZ8n", "outputId": "5d79efd3-b8f7-46a8-dcf0-da2b7997be3c" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAADxCAYAAAAay1EJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nORWxSOZUxCKZUxGLZE5FLJK5/weF62ecIGohUQAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 3\n", "#@markdown This game actually requires some action. Notice the backdoor path X <- B -> Y. This is a confounding pattern, is one of the clearest signs that we'll need to control for something, in this case B. \n", "pgm = PGM(shape=[4, 4])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 1))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 1))\n", "pgm.add_node(daft.Node('A', r\"A\", 2, 1.75))\n", "pgm.add_node(daft.Node('B', r\"B\", 2, 3))\n", "\n", "\n", "pgm.add_edge('X', 'Y')\n", "pgm.add_edge('X', 'A')\n", "pgm.add_edge('B', 'A')\n", "pgm.add_edge('B', 'X')\n", "pgm.add_edge('B', 'Y')\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "colab_type": "code", "id": "l0GI2mM3WQeI", "outputId": "7ca879e8-e678-42d9-9d03-404ffb67c51c" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? True\n", "If so, what's the possible backdoor adjustment sets? frozenset({frozenset({'B'})})\n" ] } ], "source": [ "graph = convert_pgm_to_pgmpy(pgm)\n", "inference = CausalInference(graph)\n", "print(f\"Are there are active backdoor paths? {inference._has_active_backdoors('X', 'Y')}\")\n", "adj_sets = inference.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 29, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "colab_type": "code", "id": "XP2ORZw8EtyZ", "outputId": "9f267191-b408-483b-87d9-754c949a7d72" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAADxCAYAAAAay1EJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 4\n", "#@markdown Pearl named this particular configuration \"M Bias\", not only because of it's shape, but also because of the common practice of statisticians to want to control for B in many situations. However, notice how in this configuration X and Y start out as *not confounded* and how by controlling for B we would actually introduce confounding by opening the path at the collider, B. \n", "pgm = PGM(shape=[4, 4])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 1))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 1))\n", "pgm.add_node(daft.Node('A', r\"A\", 1, 3))\n", "pgm.add_node(daft.Node('B', r\"B\", 2, 2))\n", "pgm.add_node(daft.Node('C', r\"C\", 3, 3))\n", "\n", "\n", "pgm.add_edge('A', 'X')\n", "pgm.add_edge('A', 'B')\n", "pgm.add_edge('C', 'B')\n", "pgm.add_edge('C', 'Y')\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "colab_type": "code", "id": "CBaGzLKSFmnQ", "outputId": "95c1c6a5-dbe3-4768-8f37-94d9547e9db6" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? False\n", "If so, what's the possible backdoor adjustment sets? frozenset()\n" ] } ], "source": [ "graph = convert_pgm_to_pgmpy(pgm)\n", "inference = CausalInference(graph)\n", "print(f\"Are there are active backdoor paths? {inference._has_active_backdoors('X', 'Y')}\")\n", "adj_sets = inference.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "colab_type": "code", "id": "ZAbSVPvZFxZH", "outputId": "88a7fff6-0744-4dda-b5e9-8d93dcea84d7" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAADxCAYAAAAay1EJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 5\n", "#@markdown This is the last game in The Book of Why is the most complex. In this case we have two backdoor paths, one going through A and the other through B, and it's important to notice that if we only control for B that the path: X <- A -> B <- C -> Y (which starts out as closed because B is a collider) actually is opened. Therefore we have to either close both A and B or, as astute observers will notice, we can also just close C and completely close both backdoor paths. pgmpy will nicely confirm these results for us. \n", "pgm = PGM(shape=[4, 4])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 1))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 1))\n", "pgm.add_node(daft.Node('A', r\"A\", 1, 3))\n", "pgm.add_node(daft.Node('B', r\"B\", 2, 2))\n", "pgm.add_node(daft.Node('C', r\"C\", 3, 3))\n", "\n", "\n", "pgm.add_edge('A', 'X')\n", "pgm.add_edge('A', 'B')\n", "pgm.add_edge('C', 'B')\n", "pgm.add_edge('C', 'Y')\n", "pgm.add_edge(\"X\", \"Y\")\n", "pgm.add_edge(\"B\", \"X\")\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "colab_type": "code", "id": "IF1jYMq_eNHd", "outputId": "68bcc15d-c1aa-40c4-fb61-b400e7c31abe" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? True\n", "If so, what's the possible backdoor adjustment sets? frozenset({frozenset({'B', 'A'}), frozenset({'C'})})\n" ] } ], "source": [ "graph = convert_pgm_to_pgmpy(pgm)\n", "inference = CausalInference(graph)\n", "print(f\"Are there are active backdoor paths? {inference._has_active_backdoors('X', 'Y')}\")\n", "adj_sets = inference.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 258 }, "colab_type": "code", "id": "dSjZqd5fHF06", "outputId": "05857131-230d-4dd9-88d0-25d4b800eb68" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAADxCAYAAAAay1EJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAHr9JREFUeJztnXmcHVWVx78n+0LYV4EQwlIQlgAJ\niwRIWCNoFIHIJgyokZ1RBgRlkTDiMsqHAYcgiOwIGFkURSAIRCIgJGHHlBoY2VSCGYFAEAhn/ji3\nSdt0uqveq+VVvfP9fN4n3emqc+59dX91b9269xxRVRzHqS59yi6A4zjN4SJ2nIrjInaciuMidpyK\n4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMi\ndpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInac\niuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrj\nInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInacitOv7AIUhYj0\nBfYEdgHGAJsDywEKLAQeA+YAd6rq7LLK6fSMiGwETMKu4TbAGlg7XgzMw67hg8Btqvp2WeUsElHV\nssuQKyKyPHAscDSwALgdu9CPA68BAqyONYixwH7Aq8BFwDWquqSEYjudEBEB9gFOBLYGbgIexq7j\nS8B7wFBgM0zcu4XjrgAuUNWXSih2YdRaxCKyJ3AZMAv4b1V9JME5fYGPAacC/YEjVXVergV1lomI\nrAFMA0YB3wSmJ+lhRWRD4Djgs8BXgCu1po29liIWkT7A94D9gSmqeleDNo4GpgKnqOqVmRbS6RUR\nmQDcgPWoUxsZHovIaOBK4M/AIar6VpZlbAVqJ+IgvsuADYFPquo/mrS3CXAn8G1VvTiDIjoJCKOo\n64CDVPWeJm31B34ErAfsXTch11HE5wITgL1U9c2MbK4P3A8cr6q3ZmHTWTYisiXwa+DTqjorI5t9\nsB55+WC3Ng2/ViIWkY8CNwNbquqCjG3viE2oZG7bWUroNX8H/I+qXp6D7YeBC1X1iixtl0ltRCwi\ng7DXRGeo6k9z8vE9YB1VPSgP+w6IyBnAjsDH8+gtwzPy3cBWdZm1rpOIDwcOU9U9c/QxGHgOmOAz\n1tkjIkOB54Gxqvpcjn7OB95R1VPz8lEkdVqxdSzw/TwdqOpibILk6Dz9tDGHAPfnKeDANODIMHqr\nPLXoiUVkFDaDPCLN4owoig4GrgbWiuP41YS+hmPD9tV8IUi2iMgDwDmqekeS46MoGgE8iS36UGAQ\ncEocx71OhonIDOBSVZ3eeIlbg7r0xDsAMxsQ1SHAfOCApCeo6vPA34EopS+nB0RkILAV8JuUp8Zx\nHE+I43hXbIHOmQnPuwdrN5WnLiIeg92NExNF0crAdsB/AAen9DcHW6LpZMfmwPwm3+GugS3DTMIc\nrN1UnrpsgNgE+FnKcyYDvwDuAH4YRdHacRwnbQDP4D1x1kTY95r6vCiK7sOG0msDExOe9zTWbipP\nXXriwUDahR2HANfHcbwE+ClwYIpzFwFDUvpzeqaRawhLh9M7YLvUboyiKEnnVJtrWBcRv0eKUUUU\nResA2wPnRVH0GLbhIc273/7Au6lK6PRGqmvYHXEcz8O2JK6b4PDaXMO6iPhv2FAqKQcDF8VxPDqO\n462wodzKURRtkPD8tYFXUpbR6ZlXSHcNP0SY51iLZM/FtbmGdRHxXNJNUhyM7YwBII5jBa4ieW+c\neiLN6ZW5wDZh73AaoiiK7gvPxbcDx8dx/E6C82pzDevynngv4ExV3bkAXwOwSCDrNLtDyvlXROQF\nYDdV/WMBvn4AxKp6ft6+8qYuPfH9wKYiMrIAX/sCs13AufAzbBN/roTls/sDt+XtqwhqIeKwHPIq\n4KgC3B2Hhe5xsudiYEoY7eTJZGCOqv4pZz+FUAsRBy4GPiciH8nLgYjsBqwP+J7iHFDVp7F3xbnd\njMN66a8CF+blo2hq8UzcgYhMxSYsJmW9jU1ElsPW6R6nqrdnadtZSoikMgvYTlWfzcH+t7GoL5Pr\nEhigbiIeADwCXKKq0zK0K1hUCFXVI7Ky63SPiJwMfBrYIzwqZWV3dyzkz2hV/VtWdsumViKGD6Ic\nzgROU9VrMrDXEbNrErC+qi5q1qbTMyHi6KPAW8CuWQhZRHbGIrNMVtWZzdprJer0TAxAmKzYE/im\niExtZpJERFbBoi1uD6wKpI6a6TTEmcAW2LLIu5t56yDG57GwTYfWTcBQQxEDqOoz2DazscDDIpJq\nx5GI9BGR/bFn4JeBbYGPAx8Ne16dnBCRs4GvY6GCtwZuwa7hCWlvyCHA4a+wNwq7qeqMjIvbGqhq\nbT9YdocjgBexd8kHAyv1cOzawJeAGMsQsXOXY/bBNp8/UHbd6vgBzg7f79ld/j8CZgB/Ac4BNiY8\nCnZjYwiwN/bO+e/AGUD/suuW56d2z8TdEaIcTsJeXeyIrZl9HFgCvA8Mw9K49MWGzNMwoX7oyxGR\nfYBfAg+q6o6FVKAN6NwDq+rZyzhmM+AY4JPYNXsUWzc/ENtAMQoYiUVeuRy4XjMKW9zKtIWIOxMm\nTTbGnrluxALffRlrEC90J9xubLiQMySJgLs5pyN/1uHYCOsQbAT1lKomWTtdG9pOxJ0REQUeUdXt\nGjjXhZwBjQi4y/knAeepatqNE7WhlhNbRaC24MMnu5qgWQE7hou4CVzIjeMCzg4XcZO4kNPjAs4W\nF3EGuJCT4wLOHhdxRriQe8cFnA8u4gxxIS8bF3B+uIgzxoX8YVzA+eIizgEX8lJcwPnjIs4JF7IL\nuChcxDnSzkJ2AReHizhn2lHILuBicREXQDsJ2QVcPC7igmgHIbuAy8FFXCB1FrILuDxcxAVTRyG7\ngMvFRVwCdRKyC7h8XMQlUQchu4BbAxdxiVRZyC7g1qFtRSwi48KP24bUIaVQRSG3ioBFZC0sxnhH\nuKS2pC1jbIW0LIuAwVi0y9+p6riez8q9TJWI2dUqAg5luRCLftkPC3W7rqq+VGaZyqAte+IQ0fI5\nLNZ0H1ogY3wVeuRWEnDgMeCf4ee3sUD/bUdbijgwK/y7CHiozIJ00MpCbkEBg9183w8/P5Mk3HAd\naWcRP4gJuCV64g5aUcgtKmCwXMaDsKH0b0ouS2m0s4hnA/2xrA9/LLks/0IrCbmFBYyqvgvMxzJ5\ntMRoqgzaWcTzsPrPU9X3ezu4aLoIebGIvC4i44vwLSLrichCEZlHiwq4E7/FJrZaZjRVNG0pYhEZ\nAmyFJVqbLyKbh3xNLUUQ8gXYkHEYcIOIDE1yroisISIfFZFdRWSciIwIs/K9nSdYOtflsURmcSsK\nOGSu3BhYgE1qrSoiK5VcrFJom1dMIrIV8EVgFyzp1h/Cn97FBLIu8BSWUO1SVX2hjHJ2JQynx2JD\n/8XANap6VDfH9QM+ARwGbAcMxer4NjAAGBH+nQ1Mx5KNvdWNnWOA74bzlwCvq+rKmVesAYJIjwA+\nhaU9XYglxxuMzVJvgiVYexC4Ari3LSa7yk7LmPcHmAA8ADyPpbncBhjQzXHDMIFfiKXEvBnYsAXK\nvyLWM76JTeC8BYzv9Pe+wL8DL2Az7v+G3aQ+lPoTWAvYD/g58CrwLWBIp7+PwCb7NPz7ALBeC3wH\nqwKXAP8HXAt8DFilm+P6Apti+YifBH6PJVrrNg1qXT6lFyDHC78c8H1syPwZoF/Kc08ODf1EoE8L\n1GefcHNZguXpHYoNd38L3AdsldLeCOA6bFJvJ+yd+YPYK5tFwNGt0PjDTecvwPnA6inOk3ADfxK4\nFViz7Lrk9h2VXYCcLvyaWP7ha1hGUvGEdjYKvdFPgYEtUK+OXlmBX2DPg8c3c5MB9g0iuS7YbZXe\nV4BvAn8CxjVhZyDwDeAlYIuy65XLd1V2AXK4+KuFYdRZWfQkoRHcHO7miXvznOt4Gjas3jkjexti\nz5fXtkLvG8r0bWzGedWM7B0I/BUYVXbdsv7UamJLRPoAM7Ccw6dlaHcAcBvwaJZ2GyzLuljjnqyq\nMzO0uyFwf7A7q7fj80REDgNOx3rgv2dsdyqwpaouyspu2dRNxMdis7M7qeqSjG2vgQ3RP6mqD2dp\nO0UZBPgVcL+qnpuD/X2xmenR2s3MdRGEnUmPAx9T1bk52L8CeEtVj8vadlnURsTh4j+JCXheTj4O\nBM7E7uSFLxARkUOBLwM7qOp7Ofm4Dvizqn4tD/sJ/N8I/EFVz8zJ/opYO/mMqj6Yh4+iqZOIzwLW\nUtVjcvQhwFzgVFW9Ky8/PfieDZyuqnfk6GdE8DO86N5YRNbDHhXWU9U3c/RzPDafcGBePoqkFiu2\nwmqro4CL8/Sjdse7CHsPWTTbYbPTud48VPV/sVdNB+XpZxkchS1myU3AgWuAvcLorfLUoicWkV2A\n81V1TNJzoijaCPhvbDa7L/Zq5eQ4jv/Z03lh2eMr2DvLvBtbZ7/nAa+p6jlJjo+iaAQ2bJyDva55\nD/hmHMe/TuBrP+CLqvqxxkucHhH5I3CAqj6e5PgudezMfnEcL+zF11VYMIhpjZS1lehXdgEyYizW\neyQiiqK+wE3ACXEcz4yiSLCVWmdhs6LLRFXfFJHfA6Mx4RfFWOx9ZxriOI4nAERRtAFwWxRFB8Vx\n/EQv5z0EXCIiogXd5cOSyjWxpa9p+KCOKXkI+04rTy2G08AY0u1i2ROYF8fxTIA4jhX4CpColwu+\nCmsA4dXZ1tjzeEPEcTwfOJcEjwKq+jLWcw9v1F8DbAM8nvVbhR6Yg7WbylOXnngdLNxOUjbBQrt8\nQBzHi1Oc/xywdorjm2UYQAbvTGdjyymT0FHHPzfpMylrk+4aNstzWLupPHUR8QBsN1JSFHsObpR3\ngs+iGBB8NsswbO11Et6l+DqmuYYdRFEU3dfp9ziO4w/t8uqGoq9hbtRFxG9je26TMg9bc/wBURQN\nBDaK4zjJM1nH1reieBsYlMEz6ljg0YTHDqKEOjZwXqPPxEVfw9yoyzPxfGxHT1JmAOtFUTQJIIqi\nPsB3sPW1Sdg4+CyKRdhe4o80aiBMbJ2E7QbqkfBOuug6Pht8FkWEba6oPHXpiVNNNMVx/H4URROB\nS6Mo+jo2tJqBratNwhjs9VQhqKqKSMdETJq4yh1DzYHY48NxcRw/n+C8kcAbqvpK6sI2zmPAKBEZ\noKppHh26DqcBvhLHcW9LY9NOhrYsdXlPPAa4HojyfiUiIqtikyKrpGxszfo9BxisqqcU4OsIYJKq\n7p+3ry5+HwOOL2IDhojcAtyqqlfl7Stv6jKcnou9EtmlAF+fB6YXKeDAtcDhIjKwAF9TgKsL8NOV\na7AQSrkiIh/BAgbckrevIqiFiEPvO42cl0OKSF/sFU3hq3xU9Q/Y7p4D8vQTYpGti6WUKZorgUki\nslrOfqYAN6jq6zn7KYRaDKcBRGR5QkylLPfZdvFxCjBRVffIw34C/7sDP8J2UWXeAMOiknuBm1T1\nwqztJyzDBcAKqnpETvZHAI9gu93iPHwUTW1EDCAik7AJpy2zXtcsIptim+a3VdUiFyV0LcdlwBLt\nJuJlBrZPxOKRjS9w5VTXMiwHPAGcoKqZjgbCrPsM4G5V/XaWtsukViKGDzZ9DwMOymrPrYisAswE\nLlLVXHdKJSjLCthM7jmqekWGdnfB1pOPC0P30hCRXYEfA7tmuTdcRL4B7I5tQ8xlP3YZ1OKZuAtH\nY4HPr80iILyIrI7dvW8HftCsvWZR1dewIHmXi8iRWdgUkQnAPcArZQsYQFXvBb4KzBCRUc3aE2Mq\nsD8WmaU2AgbqFygvjCwGYTOPD9NEYDRgbyxe9VRaJ4Dc2diy0e9jr7ouAZZv0FZ/LBb3K1jwPQUe\nKLuOncr3WSyi55RGv38s1vbPsHfCiUPeVulTegFybACCbTJfgO1OShx3GBgFXAX8L7B72XXpVK4O\nAZ8dfl8B+GEo52dJGFYXG4HtHRr2HVhybrDY1q0m5M2xjRt3AeOSihkbjR2PZYT4RtLvpoqf0gtQ\nQCMYAVyKZQ+4AcuQsBnQt9Mxg7DIGcdis7N/CcIfVnb5O5XxXwTc5W+7A3eGBvs9LM3JOp0bPLAK\nsBe2Z3p+EMaHsiO0qJD7AydgaWkeB04BxncegYSb9gbYxNwPsBC804Ftyi5/3p/aTWwtizAhdCi2\nIGQM9i5UsYwHfYAY65nuxFbyFL2YY5kkTS8qIhthPfJ2WB2HYhsL+mN1fRSr443aQ8ROEdkHe0/8\noKrumE0tmie8Atsdu0mNAbbErt+A8O+rWP0eAq5W2xdde9pGxF0RkUHYpoK5WPTIRrbB5U6j+YHD\n65TlsHXT7wCLNEWEzlYVcmfC4ptTsWAHy2mB4ZJaiTrOTidCVd8OPy6pm4DBVrGp6huq+qqqvp5G\nwOH8lkl0vizU3mW/HX5uSwFDG4u41WlGwFlRBSE7LuKWpBUE3IELufVxEbcYrSTgDlzIrY2LuIVo\nRQF34EJuXVzELUIrC7gDF3Jr4iJuAaog4A5cyK2Hi7hkqiTgDlzIrYWLuESqKOAOXMitg4u4JKos\n4A5cyK2Bi7gE6iDgDlzI5eMiLpg6CbgDF3K5uIgLpI4C7sCFXB4u4oKos4A7cCGXg4u4ANpBwB24\nkIvHRZwz7STgDlzIxeIizpF2FHAHLuTicBHnRDsLuAMXcjG4iHPABbwUF3L+tKWIQzDx88Kv24pI\nZilRXMAfJi8hi8hEQk5pEblGRAZnZbtKtKWIA1/o9POBWRh0AS+bnIS8KxbREyz87tAejq0tbSli\ntRCfT4Rf38PyLDWFC7h3chDyw8Ab4eeFqvpqBjYrR1uKODATWAK8iaW6bBgXcHIyFvIcLKY2WEzt\ntqSdRfwIJuBBWGNoCBdwejIU8vNY0PhMRlNVpZ1FPAcLrv6Wqv4tzYkiMlJEhruAG6erkEVkZRHZ\nIqUNBZ4E+mJpadqSfmUXoEReAhZhuX4TIyIrYw1mpfBfLuAGUdXbReTjWKaJvwPviMjWqvpMCjMz\ngR1oYjRVddpKxCG1yUgsj8/mwOvAIBE5HRPzHFX9ay9mLgGGdPr98jzK2igiMgDYAqvjSOxx4R3s\npjUbeKzFsiXci2VxGIA9304XkdHaQw5hEVkR2Aar4ybYY9FJIhJjdZwXskO0BW2Ri0lEPoLluJ2C\nJRabg81Ov4Fl01sV2BprFC8C04DrVPWNLnYmYZkVhwD/BN4Cxqjqc8XUZNmIyLZYVscDsFSnc7As\ngh0J1dbH6jcK+DVwETAjbXqXrAk5sZ4B1sC+1zeBb6nquV2OGwDsi9VxDJYdcQ7wMvZcPAir2xjs\nel4DXKyq84qpSYmUnZYxzw8wGEv1uRAT5ha9HC9Y1r2bsOHd0Sy90a0U7CjW0H4CrNQCdRyJifJZ\n4CvAqr0cPxR7R/4o8BSwfQvUYSDwHeymqOHfUZ3+/nFsEuteYDLQvxd7w7GcxH/FbrqrlV3HXL+/\nsguQY8PYDktX2tBFxO7qDwN3Y7l+p4cGthD4RAvUT4BjsHSeJ9Mp33KK8w/Echp/B+jXAnUaG25G\n7wNPAytiyd6fBXZtwN5g4LtYvul9y65fbt9b2QXIqTFMBBYAk5u00w9Lyv3XIOBW6X0F+K/Qk27S\npK01gLuAW4GBLVC3jl55CfDnIOLlmrS5I/aYdEzZ9cvjU7tnYhHZCbgFu/P+NiObJwCnA2NV9cUs\nbDZZnnOATwB7qOrCDOwNAG7E3rceqOU/Jw/BEoU/AnxBM2ikIjISG45/XVWvbNZeK1ErEYdZyyeB\nKap6R8a2zwJ2AfbMolE1UY49sBnxMaq6IEO7A7FGfoOqXpiV3QbLcgGwJnBQlt+1iGwCzAJ20hpN\neNVNxFcAi1X12Bxs9wMeAH6kqpdkbT9hGZbHZtWPUtU7c7C/MVbHHVT1T1nbT1iGXYDrsUnIpkcZ\n3dg/DvgsJuRavIaqjYjDK5abgU1VdVFOPjYDfgOsl5ePXvyfAwxX1SNy9HEK8FFV3S8vHz34Fux9\n/VRVvTknH32A+4DL6zKsrtOyy2OB/8lTXKr6NLZC6NC8fCyL8Nw6BZv0yZOLgQkisk7OfrpjHDax\ndUteDsLz/n9h7aUW1KInDkshnwU2SvKcGEXRHsAZcRxPCL+vDdwDbBvH8eu9+NoDOE9VRzdd8BSI\nyIHYMHq3JMdHUTQCmx/ovBzxsTiOv5TA1/eB/1PVsxopa6OIyI+B36nqBb0dG0XRGcCQOI6/Fn7v\nA8wFDo/j+ImezhWRvsB84ABVrfya67r0xDtjFz/RRE8cx3cDz0dRdHj4r/OA03sTcOAeYF0RWaOx\nojbMROCnKc+J4zie0OnTq4AD04G9UvpqijCU3ovkdTwP2D/cgAGOBH7Xm4ABwrPwTRRcx7yoi4jH\nkH4Xy0nAaVEU7QsMi+M4UeMJw7G5wWeRNFLHRnkU2CJM5hXFcOBdVX0pycFxHC8G/hP4RhRFQ7AF\nL2em8Deb4q9hLtRFxFthwkpMHMevYnfzG4HjU/qbi621zoywFe8eEblCRL4gIluJSP/wt/5AxNJo\nJLmitmb8BWxzQWaIyPiw7fC7InKAiKwfemCwa5h2Y/91wKbAD4Er4zh+JcW5c4PPylOXXUwrA2ku\nYAejsc0CY4E0mxgWAMeLyKca8Lks1gHWCj9PJizqF5HnsF7jHVV9O6XNKIqi+zr9PiOO43OXdXAX\nFgM/EZEsJwq3xVa+bY9tA+0HqIg8jS1nfS2NsTiONYqirwHXAp9LWZYFWLupPHURsWCNIzFRFG0H\nbIYFW7s7iqJfxXGctMG+jw3/hqcqZXKGYpsA3gU2wK5TI6OmuGPyrgH6Y71cHvQBhmFCHoRtnfwb\njT0uPAu8HMfxP1Oe9z41GYnWohJYY1gh6cFRFPXDdjWdGMfxy9gKqKkp/K0A/KeqSlYfrCd+DfgT\n1rN8GVshNhS72fQLs6pF8R62zDTLOh6C9fBzgAuwV2abhjqeikXoKIoVWBpkr9LUpSd+Chsa/zLh\n8f8BzIzj+Onw+wXAnCiKtojj+MkE54/GhJYZqvqSiKy0rGWGIvIi9oz6dHd/z5KwBHNj4PdZ2lXV\n60Xkhu7qKCJPAVtm6a8XRmPtpvLU5T3xIcD+qrp/Qf5eBHZR1WeL8Bd83gj8UlWvLsDXGOBKVU0V\n86pJn32BfwDrquo/CvB3DrZ98/S8feVNXYbTs4DxRWQAEJGO3qLoaB4zgX0K8rU3cH9BvoAP3t0+\nEHwXQeF1zItaiFhVn8c28GeSyaEXjgUuLWEn04+BiSKyZp5Owrvho4BL8/SzDC6lgOWQYZ39qsCM\nvH0VQS1EHJgG/Huekz8ishp2o7gsLx/LIgwxp5N/I98PeEFVU0UBzYifAyNFZGzOfr4EXOK7mFqM\nsDvlXuBWVT0/Jx83Yg385DzsJ/C/HvYaZrymC+ua1P5K2HrrQ1W1lGDsInIEJrJtVfXdHOxPxCKW\nbqmqSZbZtjy1ETGAiGyARYTYOetN3yIyGVvmt7WqLs7SdspyHAV8HhiXZSMPK6euxjY+nJiV3QbL\n8Qtgtqp+PWPbK2Kr3j6nqndnabtM6jScRlXnY+8bb89yK52IjMOG64eVKeDApVgM6aszXtt8FvaK\n56sZ2kxNmGv4IvA5ETm8t+OTIiJDgduA6XUSMNRMxACqejkmuN+EcCxNISJ7Y0HkDlXVphKvZUFo\n5AcDqwA3iMhyzdgTkb4i8h3gIGAvbYHA8mETxETgWyJyXKf11Q0hIqtjwQD/AJySQRFbitqJGEBV\nv4fFHb5fRE5qZLJLRIaJyMXY89OnVfWurMvZKGEN9SRsxdHjIjK+ETsisinwW2zt+M6aMidVnoRn\n/vFYr3xbSACQmvAY9AQ2XzJFSw4CmAvaAiE38/pg645nYrtjjgQGJzhnNeA0bBfPj4AVyq5HL+Wd\nhIVjnQ5MIMxz9HLOaOAH2CaAY4A+Zdejh7IOwJbELsAicoxMcE4/4FPYK6TfYzHDSq9LXp9aTWx1\nR5i13gdrrNtjMbJmY2lAXsNGI6thuX3GhmNuBqZpRaI+hAB6hwHHYQ14FrY+OcbWKg9gaRqXHbBY\n05cAl6nqX8ooc1pEZEMsI8cRwDxsXcAcbH7gXSzD5WZYHcdjN+FpwE9UNe3miEpRexF3RkSGY3Gc\nOhKqDcN2sywkJFQDZmkOURaLIDw7boNt+RsDbIjFrHoH663nhM8D2kPCslYmrMrbCavfGGB1bMfV\nW5i45wAPqWqm675bmbYSsePUkVpObDlOO+EidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMi\ndpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInac\niuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrj\nInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2\nnIrjInaciuMidpyK4yJ2nIrjInaciuMidpyK4yJ2nIrz//fZsGHg3Z2QAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 6\n", "#@markdown So these are no longer drawn from The Book of Why, but were either drawn from another source (which I will reference) or a developed to try to induce a specific bug. \n", "#@markdown This example is drawn from Causality by Pearl on p. 80. This example is kind of interesting because there are many possible combinations of nodes which will close the two backdoor paths which exist in this graph. In turns out that D plus any other node in {A, B, C, E} will deconfound X and Y. \n", "\n", "pgm = PGM(shape=[4, 4])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 1))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 1))\n", "pgm.add_node(daft.Node('A', r\"A\", 1, 3))\n", "pgm.add_node(daft.Node('B', r\"B\", 3, 3))\n", "pgm.add_node(daft.Node('C', r\"C\", 1, 2))\n", "pgm.add_node(daft.Node('D', r\"D\", 2, 2))\n", "pgm.add_node(daft.Node('E', r\"E\", 3, 2))\n", "pgm.add_node(daft.Node('F', r\"F\", 2, 1))\n", "\n", "\n", "pgm.add_edge('X', 'F')\n", "pgm.add_edge('F', 'Y')\n", "pgm.add_edge('C', 'X')\n", "pgm.add_edge('A', 'C')\n", "pgm.add_edge('A', 'D')\n", "pgm.add_edge('D', 'X')\n", "pgm.add_edge('D', 'Y')\n", "pgm.add_edge('B', 'D')\n", "pgm.add_edge('B', 'E')\n", "pgm.add_edge('E', 'Y')\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 38, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 68 }, "colab_type": "code", "id": "30OIiRt7raN2", "outputId": "4c285443-724c-4988-b9a6-2ad2fcf2654e" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? True\n", "If so, what's the possible backdoor adjustment sets? frozenset({frozenset({'B', 'D'}), frozenset({'A', 'D'}), frozenset({'C', 'D'}), frozenset({'E', 'D'})})\n", "Ehat's the possible front adjustment sets? frozenset({frozenset({'F'})})\n" ] } ], "source": [ "graph = convert_pgm_to_pgmpy(pgm)\n", "inference = CausalInference(graph)\n", "print(f\"Are there are active backdoor paths? {inference._has_active_backdoors('X', 'Y')}\")\n", "bd_adj_sets = inference.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {bd_adj_sets}\")\n", "fd_adj_sets = inference.get_all_frontdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"Ehat's the possible front adjustment sets? {fd_adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 40, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 201 }, "colab_type": "code", "id": "Z4pkuyOwM9xq", "outputId": "82e581df-b378-423c-95bd-d16b901c5296" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPEAAAC4CAYAAAAynAqtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nXIh7AAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "tags": [] }, "output_type": "display_data" } ], "source": [ "#@title # Game 7\n", "#@markdown This game tests the front door adjustment. B is taken to be unobserved, and therfore we cannot close the backdoor path X <- B -> Y. \n", "pgm = PGM(shape=[4, 3])\n", "\n", "pgm.add_node(daft.Node('X', r\"X\", 1, 1))\n", "pgm.add_node(daft.Node('Y', r\"Y\", 3, 1))\n", "pgm.add_node(daft.Node('A', r\"A\", 2, 1))\n", "pgm.add_node(daft.Node('B', r\"B\", 2, 2))\n", "\n", "\n", "pgm.add_edge('X', 'A')\n", "pgm.add_edge('A', 'Y')\n", "pgm.add_edge('B', 'X')\n", "pgm.add_edge('B', 'Y')\n", "\n", "pgm.render()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 41, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 68 }, "colab_type": "code", "id": "m8DZd_FQ4uLV", "outputId": "b73751d4-8aa9-4ec1-ba10-d509fe13c1a1" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Are there are active backdoor paths? True\n", "If so, what's the possible backdoor adjustment sets? frozenset({frozenset({'B'})})\n", "Ehat's the possible front adjustment sets? frozenset({frozenset({'A'})})\n" ] } ], "source": [ "graph = convert_pgm_to_pgmpy(pgm)\n", "inference = CausalInference(graph)\n", "print(f\"Are there are active backdoor paths? {inference._has_active_backdoors('X', 'Y')}\")\n", "bd_adj_sets = inference.get_all_backdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"If so, what's the possible backdoor adjustment sets? {bd_adj_sets}\")\n", "fd_adj_sets = inference.get_all_frontdoor_adjustment_sets(\"X\", \"Y\")\n", "print(f\"Ehat's the possible front adjustment sets? {fd_adj_sets}\")" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "colab": {}, "colab_type": "code", "id": "8zeU4DX0Bbxl" }, "outputs": [], "source": [] } ], "metadata": { "colab": { "collapsed_sections": [], "include_colab_link": true, "name": "Causal Games.ipynb", "provenance": [], "toc_visible": true, "version": "0.3.2" }, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 1 }