{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/gregory-ch/shap_flex_porting/blob/main/shap_joint.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Causal Discovery and Shapley Values Example"
      ],
      "metadata": {
        "id": "AnGCGPBF2pKA"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YkXHIq4uKq8t"
      },
      "source": [
        "###1. Libraries installation"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6f5ExEYEGRSJ",
        "outputId": "2133fd9a-e0c0-4035-cb04-e1e06ceb3cbb"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: catboost in /usr/local/lib/python3.11/dist-packages (1.2.8)\n",
            "Requirement already satisfied: graphviz in /usr/local/lib/python3.11/dist-packages (from catboost) (0.20.3)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (from catboost) (3.10.0)\n",
            "Requirement already satisfied: numpy<3.0,>=1.16.0 in /usr/local/lib/python3.11/dist-packages (from catboost) (1.24.4)\n",
            "Requirement already satisfied: pandas>=0.24 in /usr/local/lib/python3.11/dist-packages (from catboost) (1.5.3)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.11/dist-packages (from catboost) (1.15.3)\n",
            "Requirement already satisfied: plotly in /usr/local/lib/python3.11/dist-packages (from catboost) (5.24.1)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.11/dist-packages (from catboost) (1.17.0)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=0.24->catboost) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=0.24->catboost) (2025.2)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (1.3.2)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (4.58.0)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (1.4.8)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (24.2)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (11.2.1)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->catboost) (3.2.3)\n",
            "Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.11/dist-packages (from plotly->catboost) (9.1.2)\n",
            "Requirement already satisfied: shap in /usr/local/lib/python3.11/dist-packages (0.47.2)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from shap) (1.24.4)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.11/dist-packages (from shap) (1.15.3)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (from shap) (1.6.1)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from shap) (1.5.3)\n",
            "Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.11/dist-packages (from shap) (4.67.1)\n",
            "Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.11/dist-packages (from shap) (24.2)\n",
            "Requirement already satisfied: slicer==0.0.8 in /usr/local/lib/python3.11/dist-packages (from shap) (0.0.8)\n",
            "Requirement already satisfied: numba>=0.54 in /usr/local/lib/python3.11/dist-packages (from shap) (0.60.0)\n",
            "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.11/dist-packages (from shap) (3.1.1)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.11/dist-packages (from shap) (4.13.2)\n",
            "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.11/dist-packages (from numba>=0.54->shap) (0.43.0)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.11/dist-packages (from pandas->shap) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->shap) (2025.2)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn->shap) (1.5.0)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn->shap) (3.6.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.1->pandas->shap) (1.17.0)\n",
            "Requirement already satisfied: igraph in /usr/local/lib/python3.11/dist-packages (0.11.8)\n",
            "Requirement already satisfied: texttable>=1.6.2 in /usr/local/lib/python3.11/dist-packages (from igraph) (1.7.0)\n",
            "Requirement already satisfied: shapflex in /usr/local/lib/python3.11/dist-packages (0.0.2)\n",
            "Requirement already satisfied: causal-learn in /usr/local/lib/python3.11/dist-packages (0.1.4.1)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from causal-learn) (1.24.4)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.11/dist-packages (from causal-learn) (1.15.3)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (from causal-learn) (1.6.1)\n",
            "Requirement already satisfied: graphviz in /usr/local/lib/python3.11/dist-packages (from causal-learn) (0.20.3)\n",
            "Requirement already satisfied: statsmodels in /usr/local/lib/python3.11/dist-packages (from causal-learn) (0.14.4)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from causal-learn) (1.5.3)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (from causal-learn) (3.10.0)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from causal-learn) (3.4.2)\n",
            "Requirement already satisfied: pydot in /usr/local/lib/python3.11/dist-packages (from causal-learn) (3.0.4)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from causal-learn) (4.67.1)\n",
            "Requirement already satisfied: momentchi2 in /usr/local/lib/python3.11/dist-packages (from causal-learn) (0.1.8)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (1.3.2)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (4.58.0)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (1.4.8)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (24.2)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (11.2.1)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (3.2.3)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib->causal-learn) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->causal-learn) (2025.2)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn->causal-learn) (1.5.0)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn->causal-learn) (3.6.0)\n",
            "Requirement already satisfied: patsy>=0.5.6 in /usr/local/lib/python3.11/dist-packages (from statsmodels->causal-learn) (1.0.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib->causal-learn) (1.17.0)\n",
            "Requirement already satisfied: pandas==1.5.3 in /usr/local/lib/python3.11/dist-packages (1.5.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.11/dist-packages (from pandas==1.5.3) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas==1.5.3) (2025.2)\n",
            "Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.11/dist-packages (from pandas==1.5.3) (1.24.4)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.1->pandas==1.5.3) (1.17.0)\n",
            "Requirement already satisfied: numpy==1.24.4 in /usr/local/lib/python3.11/dist-packages (1.24.4)\n"
          ]
        }
      ],
      "source": [
        "!pip install catboost==1.2.8\n",
        "!pip install shap==0.47.2\n",
        "!pip install igraph==0.11.8\n",
        "!pip install shapflex==0.0.2\n",
        "!pip install causal-learn==0.1.4.1\n",
        "!pip install pandas==1.5.3\n",
        "!pip install numpy==1.24.4"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ws_xAE1eK04f"
      },
      "source": [
        "###2. Data downloading\n",
        "\n",
        " source: [Data](https://github.com/ShawhinT/YouTube-Blog/blob/main/causality/causal_discovery/df_causal_discovery.p), [Tutorial](https://towardsdatascience.com/causal-discovery-6858f9af6dcb)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "rOQv0qcIFtIP"
      },
      "outputs": [],
      "source": [
        "import pickle\n",
        "import matplotlib.pyplot as plt\n",
        "df = pickle.load( open( \"df_causal_discovery.p\", \"rb\") )"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J0DhX0KyLTfD"
      },
      "source": [
        "### 3. Setting a model to explain"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 70,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "avVoJKv7GqK7",
        "outputId": "bd1b0ac3-bd64-4de4-8e43-662b8ce778f0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Learning rate set to 0.005266\n",
            "0:\tlearn: 0.6892780\ttotal: 9ms\tremaining: 1m 30s\n",
            "100:\tlearn: 0.4915075\ttotal: 739ms\tremaining: 1m 12s\n",
            "200:\tlearn: 0.4419287\ttotal: 1.47s\tremaining: 1m 11s\n",
            "300:\tlearn: 0.4269281\ttotal: 2.18s\tremaining: 1m 10s\n",
            "400:\tlearn: 0.4211700\ttotal: 2.97s\tremaining: 1m 11s\n",
            "500:\tlearn: 0.4183080\ttotal: 3.71s\tremaining: 1m 10s\n",
            "600:\tlearn: 0.4165378\ttotal: 4.44s\tremaining: 1m 9s\n",
            "700:\tlearn: 0.4153002\ttotal: 5.15s\tremaining: 1m 8s\n",
            "800:\tlearn: 0.4144293\ttotal: 5.87s\tremaining: 1m 7s\n",
            "900:\tlearn: 0.4137281\ttotal: 6.6s\tremaining: 1m 6s\n",
            "1000:\tlearn: 0.4131087\ttotal: 7.3s\tremaining: 1m 5s\n",
            "1100:\tlearn: 0.4125886\ttotal: 9.61s\tremaining: 1m 17s\n",
            "1200:\tlearn: 0.4121477\ttotal: 12.5s\tremaining: 1m 31s\n",
            "1300:\tlearn: 0.4117578\ttotal: 14.5s\tremaining: 1m 37s\n",
            "1400:\tlearn: 0.4114092\ttotal: 15.3s\tremaining: 1m 33s\n",
            "1500:\tlearn: 0.4110725\ttotal: 16s\tremaining: 1m 30s\n",
            "1600:\tlearn: 0.4107218\ttotal: 16.7s\tremaining: 1m 27s\n",
            "1700:\tlearn: 0.4103984\ttotal: 17.4s\tremaining: 1m 24s\n",
            "1800:\tlearn: 0.4100679\ttotal: 18.1s\tremaining: 1m 22s\n",
            "1900:\tlearn: 0.4097523\ttotal: 18.8s\tremaining: 1m 20s\n",
            "2000:\tlearn: 0.4094076\ttotal: 19.6s\tremaining: 1m 18s\n",
            "2100:\tlearn: 0.4090354\ttotal: 20.3s\tremaining: 1m 16s\n",
            "2200:\tlearn: 0.4086606\ttotal: 21.8s\tremaining: 1m 17s\n",
            "2300:\tlearn: 0.4083136\ttotal: 23.6s\tremaining: 1m 18s\n",
            "2400:\tlearn: 0.4079803\ttotal: 24.3s\tremaining: 1m 16s\n",
            "2500:\tlearn: 0.4076614\ttotal: 25s\tremaining: 1m 15s\n",
            "2600:\tlearn: 0.4073819\ttotal: 26.3s\tremaining: 1m 14s\n",
            "2700:\tlearn: 0.4070933\ttotal: 27s\tremaining: 1m 12s\n",
            "2800:\tlearn: 0.4068058\ttotal: 27.7s\tremaining: 1m 11s\n",
            "2900:\tlearn: 0.4065017\ttotal: 28.4s\tremaining: 1m 9s\n",
            "3000:\tlearn: 0.4062223\ttotal: 29.1s\tremaining: 1m 7s\n",
            "3100:\tlearn: 0.4059145\ttotal: 29.9s\tremaining: 1m 6s\n",
            "3200:\tlearn: 0.4056258\ttotal: 30.6s\tremaining: 1m 4s\n",
            "3300:\tlearn: 0.4053371\ttotal: 31.3s\tremaining: 1m 3s\n",
            "3400:\tlearn: 0.4050275\ttotal: 32s\tremaining: 1m 2s\n",
            "3500:\tlearn: 0.4047438\ttotal: 32.7s\tremaining: 1m\n",
            "3600:\tlearn: 0.4044669\ttotal: 33.5s\tremaining: 59.6s\n",
            "3700:\tlearn: 0.4042065\ttotal: 35.3s\tremaining: 1m\n",
            "3800:\tlearn: 0.4039553\ttotal: 36.6s\tremaining: 59.8s\n",
            "3900:\tlearn: 0.4037135\ttotal: 37.4s\tremaining: 58.5s\n",
            "4000:\tlearn: 0.4034771\ttotal: 38.8s\tremaining: 58.2s\n",
            "4100:\tlearn: 0.4032248\ttotal: 40.9s\tremaining: 58.9s\n",
            "4200:\tlearn: 0.4029768\ttotal: 41.6s\tremaining: 57.5s\n",
            "4300:\tlearn: 0.4027417\ttotal: 42.4s\tremaining: 56.1s\n",
            "4400:\tlearn: 0.4024949\ttotal: 43.1s\tremaining: 54.8s\n",
            "4500:\tlearn: 0.4022685\ttotal: 43.8s\tremaining: 53.5s\n",
            "4600:\tlearn: 0.4020343\ttotal: 44.5s\tremaining: 52.3s\n",
            "4700:\tlearn: 0.4018102\ttotal: 45.3s\tremaining: 51s\n",
            "4800:\tlearn: 0.4015990\ttotal: 46s\tremaining: 49.8s\n",
            "4900:\tlearn: 0.4013678\ttotal: 47.7s\tremaining: 49.6s\n",
            "5000:\tlearn: 0.4011609\ttotal: 49.3s\tremaining: 49.3s\n",
            "5100:\tlearn: 0.4009639\ttotal: 50s\tremaining: 48s\n",
            "5200:\tlearn: 0.4007454\ttotal: 50.7s\tremaining: 46.8s\n",
            "5300:\tlearn: 0.4005560\ttotal: 51.5s\tremaining: 45.6s\n",
            "5400:\tlearn: 0.4003578\ttotal: 52.2s\tremaining: 44.5s\n",
            "5500:\tlearn: 0.4001564\ttotal: 53s\tremaining: 43.3s\n",
            "5600:\tlearn: 0.3999603\ttotal: 53.7s\tremaining: 42.2s\n",
            "5700:\tlearn: 0.3997656\ttotal: 54.5s\tremaining: 41.1s\n",
            "5800:\tlearn: 0.3995780\ttotal: 55.2s\tremaining: 39.9s\n",
            "5900:\tlearn: 0.3994030\ttotal: 55.9s\tremaining: 38.8s\n",
            "6000:\tlearn: 0.3992027\ttotal: 56.7s\tremaining: 37.8s\n",
            "6100:\tlearn: 0.3990184\ttotal: 57.5s\tremaining: 36.7s\n",
            "6200:\tlearn: 0.3988182\ttotal: 58.2s\tremaining: 35.6s\n",
            "6300:\tlearn: 0.3986289\ttotal: 59s\tremaining: 34.6s\n",
            "6400:\tlearn: 0.3984530\ttotal: 1m 1s\tremaining: 34.7s\n",
            "6500:\tlearn: 0.3982771\ttotal: 1m 2s\tremaining: 33.6s\n",
            "6600:\tlearn: 0.3981018\ttotal: 1m 3s\tremaining: 32.6s\n",
            "6700:\tlearn: 0.3979345\ttotal: 1m 3s\tremaining: 31.5s\n",
            "6800:\tlearn: 0.3977810\ttotal: 1m 4s\tremaining: 30.4s\n",
            "6900:\tlearn: 0.3976136\ttotal: 1m 5s\tremaining: 29.4s\n",
            "7000:\tlearn: 0.3974574\ttotal: 1m 6s\tremaining: 28.3s\n",
            "7100:\tlearn: 0.3972888\ttotal: 1m 6s\tremaining: 27.3s\n",
            "7200:\tlearn: 0.3971263\ttotal: 1m 7s\tremaining: 26.3s\n",
            "7300:\tlearn: 0.3969797\ttotal: 1m 8s\tremaining: 25.3s\n",
            "7400:\tlearn: 0.3968290\ttotal: 1m 9s\tremaining: 24.3s\n",
            "7500:\tlearn: 0.3966850\ttotal: 1m 9s\tremaining: 23.3s\n",
            "7600:\tlearn: 0.3965330\ttotal: 1m 10s\tremaining: 22.3s\n",
            "7700:\tlearn: 0.3963747\ttotal: 1m 11s\tremaining: 21.3s\n",
            "7800:\tlearn: 0.3962246\ttotal: 1m 12s\tremaining: 20.6s\n",
            "7900:\tlearn: 0.3960729\ttotal: 1m 14s\tremaining: 19.8s\n",
            "8000:\tlearn: 0.3959197\ttotal: 1m 15s\tremaining: 18.8s\n",
            "8100:\tlearn: 0.3957832\ttotal: 1m 16s\tremaining: 17.8s\n",
            "8200:\tlearn: 0.3956439\ttotal: 1m 16s\tremaining: 16.8s\n",
            "8300:\tlearn: 0.3955016\ttotal: 1m 17s\tremaining: 15.9s\n",
            "8400:\tlearn: 0.3953539\ttotal: 1m 18s\tremaining: 14.9s\n",
            "8500:\tlearn: 0.3952175\ttotal: 1m 18s\tremaining: 13.9s\n",
            "8600:\tlearn: 0.3950890\ttotal: 1m 19s\tremaining: 13s\n",
            "8700:\tlearn: 0.3949550\ttotal: 1m 20s\tremaining: 12s\n",
            "8800:\tlearn: 0.3948148\ttotal: 1m 21s\tremaining: 11.1s\n",
            "8900:\tlearn: 0.3946763\ttotal: 1m 21s\tremaining: 10.1s\n",
            "9000:\tlearn: 0.3945449\ttotal: 1m 22s\tremaining: 9.18s\n",
            "9100:\tlearn: 0.3944083\ttotal: 1m 23s\tremaining: 8.24s\n",
            "9200:\tlearn: 0.3942704\ttotal: 1m 24s\tremaining: 7.31s\n",
            "9300:\tlearn: 0.3941349\ttotal: 1m 25s\tremaining: 6.44s\n",
            "9400:\tlearn: 0.3939961\ttotal: 1m 27s\tremaining: 5.57s\n",
            "9500:\tlearn: 0.3938612\ttotal: 1m 28s\tremaining: 4.63s\n",
            "9600:\tlearn: 0.3937271\ttotal: 1m 28s\tremaining: 3.69s\n",
            "9700:\tlearn: 0.3936023\ttotal: 1m 29s\tremaining: 2.76s\n",
            "9800:\tlearn: 0.3934668\ttotal: 1m 30s\tremaining: 1.83s\n",
            "9900:\tlearn: 0.3933373\ttotal: 1m 31s\tremaining: 910ms\n",
            "9999:\tlearn: 0.3932004\ttotal: 1m 31s\tremaining: 0us\n"
          ]
        }
      ],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "from catboost import CatBoostClassifier\n",
        "data_to_explain = df.copy()\n",
        "outcome_name = 'greaterThan50k'\n",
        "outcome_col = pd.Series(data_to_explain.columns)[data_to_explain.columns==outcome_name].index[0]\n",
        "X, y = data_to_explain.drop(outcome_name, axis=1), data_to_explain[outcome_name].values\n",
        "model = CatBoostClassifier(iterations=10000)\n",
        "model.fit(X, y, verbose=100)\n",
        "def predict_function(model, data_to_explain):\n",
        "  return pd.DataFrame(model.predict_proba(data_to_explain)[:, [0]])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rkjPW4fiLbD1"
      },
      "source": [
        "###4. Non-causal case: symmetric shapley values, no prior knowledge"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 71,
      "metadata": {
        "id": "fK3URhheGuAk"
      },
      "outputs": [],
      "source": [
        "from shapflex.shapflex import shapFlex_plus\n",
        "\n",
        "explain, reference = data_to_explain.iloc[:300, :data_to_explain.shape[1]-1], data_to_explain.iloc[:, :data_to_explain.shape[1]-1]\n",
        "exmpl_of_test = shapFlex_plus(explain, model, predict_function, target_features=pd.Series([\n",
        "                                                                                         \"age\", \"inRelationship\",\n",
        "                                                                                         \"hours-per-week\", \"hasGraduateDegree\",\n",
        "                                                                                         \"isFemale\", \"isWhite\"])\n",
        ")\n",
        "result = exmpl_of_test.forward()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ua4MPBJ9NcEG"
      },
      "source": [
        "Assembling a causal data to a format with which shap's beeswarm is able to deal"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 72,
      "metadata": {
        "id": "Lo9WdEr6G5tr"
      },
      "outputs": [],
      "source": [
        "from shap._explanation import Explanation\n",
        "values = pd.DataFrame(result['shap_effect'].values.reshape(-1, 6), columns = result['feature_name'].unique()).values\n",
        "base_values = np.array([result['shap_effect intercept'][0] for i in range(explain.shape[0])])\n",
        "data = explain.values\n",
        "shap_values_shapflex = Explanation(values, base_values=base_values, data=data, feature_names=result.loc[:5, 'feature_name'].values)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 73,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 382
        },
        "id": "BWhhICMYHArF",
        "outputId": "2ef43651-1478-4ba3-a095-f16e0d7ba6fd"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x390 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "import shap\n",
        "shap.plots.beeswarm(shap_values=shap_values_shapflex )"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8vkD3iAULkZs"
      },
      "source": [
        "###5. Building a causal graph, FCI algorithm.\n",
        "\n",
        "  step 1: Use FCI without prior knowledge"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 74,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 137,
          "referenced_widgets": [
            "8ea1cff2f84a46728c28ac5d83e7f323",
            "8adb03e62782496cbe894a51411bfaae",
            "f7dc792bd0c64a809f0395dc908fd2c5",
            "0225afe78236424fb83f3989d6291175",
            "ad24b72f9bd5461bb6c02e7f65b7c58d",
            "f623cb9924774809896082be339d89f5",
            "e5da6253edcb4e0cb179828e0b4f0e49",
            "0ebd081d2d5047529ad4959a2c6c17ee",
            "6172b4918b7c4b598c277f0888496592",
            "606d9556285046a398dad9cb21ef22ad",
            "6a50b207ee3f4544a5feb33f47ec1283"
          ]
        },
        "id": "oLsPncr0HEfm",
        "outputId": "6bde083a-eb29-4525-ee06-201b5e5e03e2"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "  0%|          | 0/7 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "8ea1cff2f84a46728c28ac5d83e7f323"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "X1 --> X4\n",
            "X1 --> X7\n",
            "X2 --> X4\n",
            "X7 --> X4\n",
            "X7 --> X5\n"
          ]
        }
      ],
      "source": [
        "from causallearn.search.ConstraintBased.FCI import fci\n",
        "G = fci(df.values)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_XRmNBu4L7jc"
      },
      "source": [
        " step 2: turn off some nodes"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 76,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 491,
          "referenced_widgets": [
            "77117c86b7c34643bc6dba467bd2de45",
            "7e1367cf462c445491f12983af6d4730",
            "b02981cde8ed46cd9f4dbaf11bd19cb4",
            "7275da74d2da48d9adb4c0b1b3f3c767",
            "5efcc913d6024722bd82da75a957ee30",
            "9dbf0723b34347b0b77c8672a80b5c46",
            "4268edae355042deb96654e1a53a8350",
            "9e092b9ea22346f5b7bcdd0f6d09e035",
            "0096e2b1fea64921989b47d3d77f7563",
            "ba34acdf9aaa4c1c8f849ca1e643da05",
            "93ba7e659a9641b7942ab63b8f40605b"
          ]
        },
        "id": "vbjMZLrzHMU9",
        "outputId": "107cd631-2e5c-4f94-938d-76969fd97c03"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "  0%|          | 0/7 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "77117c86b7c34643bc6dba467bd2de45"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Starting BK Orientation.\n",
            "Orienting edge (Knowledge): X1 --> X3\n",
            "Orienting edge (Knowledge): X3 --> X2\n",
            "Orienting edge (Knowledge): X2 --> X6\n",
            "Orienting edge (Knowledge): X5 --> X3\n",
            "Orienting edge (Knowledge): X5 --> X4\n",
            "Orienting edge (Knowledge): X6 --> X4\n",
            "Orienting edge (Knowledge): X5 --> X7\n",
            "Finishing BK Orientation.\n",
            "Starting BK Orientation.\n",
            "Orienting edge (Knowledge): X1 --> X3\n",
            "Orienting edge (Knowledge): X3 --> X2\n",
            "Orienting edge (Knowledge): X2 --> X6\n",
            "Orienting edge (Knowledge): X5 --> X3\n",
            "Orienting edge (Knowledge): X5 --> X4\n",
            "Orienting edge (Knowledge): X6 --> X4\n",
            "Orienting edge (Knowledge): X5 --> X7\n",
            "Finishing BK Orientation.\n",
            "X3 --> X2\n",
            "X2 --> X4\n",
            "X2 --> X6\n",
            "X2 --> X7\n",
            "X3 --> X7\n",
            "X6 --> X4\n",
            "X4 --> X7\n"
          ]
        }
      ],
      "source": [
        "from causallearn.utils.PCUtils.BackgroundKnowledge import BackgroundKnowledge\n",
        "nodes = G[0].get_nodes()\n",
        "bc = BackgroundKnowledge() \\\n",
        "            .add_forbidden_by_node(nodes[2], nodes[0]) \\\n",
        "            .add_forbidden_by_node(nodes[1], nodes[2]) \\\n",
        "            .add_forbidden_by_node(nodes[4], nodes[5]) \\\n",
        "            .add_forbidden_by_node(nodes[5], nodes[4]) \\\n",
        "            .add_forbidden_by_node(nodes[5], nodes[0]) \\\n",
        "            .add_forbidden_by_node(nodes[0], nodes[5]) \\\n",
        "            .add_forbidden_by_node(nodes[3], nodes[4]) \\\n",
        "            .add_forbidden_by_node(nodes[6], nodes[4]) \\\n",
        "            .add_forbidden_by_node(nodes[3], nodes[5]) \\\n",
        "            .add_forbidden_by_node(nodes[2], nodes[4]) \\\n",
        "            .add_forbidden_by_node(nodes[1], nodes[4]) \\\n",
        "            .add_required_by_node(nodes[1], nodes[5])\n",
        "\n",
        "G2 = fci(df.values, background_knowledge=bc)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EBN0sbfzMDXW"
      },
      "source": [
        "###6. Assembling a causal dataframe from a causal graph"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 77,
      "metadata": {
        "id": "fdSzImPxHS2x"
      },
      "outputs": [],
      "source": [
        "nodes = []\n",
        "for edge in G2[1]:\n",
        "  nodes.append([edge.get_node1().get_name(), edge.get_node2().get_name()])\n",
        "\n",
        "names = {x:y for x, y in zip([\n",
        "                              'X' + str(i) for i in range(1, 8)\n",
        "], df.columns.values\n",
        ")}\n",
        "\n",
        "causal = pd.DataFrame()\n",
        "causal['cause'] = pd.DataFrame(nodes)[0].apply(lambda x: names[x])\n",
        "causal['effect'] = pd.DataFrame(nodes)[1].apply(lambda x: names[x])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "A0zsPjsXMcro"
      },
      "source": [
        "We don't want to have an objective node in our graph. Also, though we turned off an edge 'hours-per-week' $\\rightarrow$ 'isFemale' it somehow appeared in a graph. So, we have to delete it."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 78,
      "metadata": {
        "id": "7nlFd3wLHafP"
      },
      "outputs": [],
      "source": [
        "causal_without_objective = causal.where(causal!='greaterThan50k').dropna(axis=0)\n",
        "causal_without_objective = causal_without_objective.drop(causal_without_objective.index[6]).reset_index(drop=True)\n",
        "# drop(6)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 79,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 711
        },
        "id": "N7q_6K2cJ8Sz",
        "outputId": "4daf85ca-704b-4494-f9d7-8e3ebadcfb4e"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1500x1300 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "import networkx as nx\n",
        "fig = plt.figure(figsize=(15, 13))\n",
        "nx.draw_networkx(nx.from_pandas_edgelist(causal_without_objective, source='cause', target='effect', create_using=nx.classes.digraph.DiGraph), font_size=18, font_color='r', arrowsize=30)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zNc6bLSBNUUx"
      },
      "source": [
        "###7. Running a causal case"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(causal_without_objective.head())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BGxdUhpnySud",
        "outputId": "70348d72-d9f3-4a6d-f8f7-015fd9af9dd0"
      },
      "execution_count": 57,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "               cause             effect\n",
            "0                age  hasGraduateDegree\n",
            "1                age     inRelationship\n",
            "2  hasGraduateDegree     hours-per-week\n",
            "3     hours-per-week     inRelationship\n",
            "4     hours-per-week           isFemale\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 80,
      "metadata": {
        "id": "Ziq3ClE7Hflo"
      },
      "outputs": [],
      "source": [
        "exmpl_of_test = shapFlex_plus(explain, model, predict_function, target_features=pd.Series(\n",
        "    ['age', 'hours-per-week', 'hasGraduateDegree', 'inRelationship',\n",
        "       'isWhite', 'isFemale']), causal=causal_without_objective.columns, causal_weights=[1. for i in range(causal_without_objective.shape[0])])\n",
        "result = exmpl_of_test.forward()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 81,
      "metadata": {
        "id": "nSM3AXg1J78E"
      },
      "outputs": [],
      "source": [
        "values = pd.DataFrame(result['shap_effect'].values.reshape(-1, 6), columns = result['feature_name'].unique()).values\n",
        "base_values = np.array([result['shap_effect intercept'][0] for i in range(explain.shape[0])])\n",
        "data = explain.values\n",
        "shap_values_shapflex_2 = Explanation(values, base_values=base_values, data=data, feature_names=result.loc[:5, 'feature_name'].values)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 82,
      "metadata": {
        "id": "Ge7F5cqwJ_wt",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 382
        },
        "outputId": "cccd5b64-1ea3-4a35-cc93-c3a265a7b008"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x390 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "shap.plots.beeswarm(shap_values=shap_values_shapflex_2 )"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "8ea1cff2f84a46728c28ac5d83e7f323": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_8adb03e62782496cbe894a51411bfaae",
              "IPY_MODEL_f7dc792bd0c64a809f0395dc908fd2c5",
              "IPY_MODEL_0225afe78236424fb83f3989d6291175"
            ],
            "layout": "IPY_MODEL_ad24b72f9bd5461bb6c02e7f65b7c58d"
          }
        },
        "8adb03e62782496cbe894a51411bfaae": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f623cb9924774809896082be339d89f5",
            "placeholder": "​",
            "style": "IPY_MODEL_e5da6253edcb4e0cb179828e0b4f0e49",
            "value": "Depth=0, working on node 6: 100%"
          }
        },
        "f7dc792bd0c64a809f0395dc908fd2c5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_0ebd081d2d5047529ad4959a2c6c17ee",
            "max": 7,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_6172b4918b7c4b598c277f0888496592",
            "value": 7
          }
        },
        "0225afe78236424fb83f3989d6291175": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_606d9556285046a398dad9cb21ef22ad",
            "placeholder": "​",
            "style": "IPY_MODEL_6a50b207ee3f4544a5feb33f47ec1283",
            "value": " 7/7 [00:00&lt;00:00, 105.89it/s]"
          }
        },
        "ad24b72f9bd5461bb6c02e7f65b7c58d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f623cb9924774809896082be339d89f5": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e5da6253edcb4e0cb179828e0b4f0e49": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "0ebd081d2d5047529ad4959a2c6c17ee": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6172b4918b7c4b598c277f0888496592": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "606d9556285046a398dad9cb21ef22ad": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6a50b207ee3f4544a5feb33f47ec1283": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "77117c86b7c34643bc6dba467bd2de45": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_7e1367cf462c445491f12983af6d4730",
              "IPY_MODEL_b02981cde8ed46cd9f4dbaf11bd19cb4",
              "IPY_MODEL_7275da74d2da48d9adb4c0b1b3f3c767"
            ],
            "layout": "IPY_MODEL_5efcc913d6024722bd82da75a957ee30"
          }
        },
        "7e1367cf462c445491f12983af6d4730": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_9dbf0723b34347b0b77c8672a80b5c46",
            "placeholder": "​",
            "style": "IPY_MODEL_4268edae355042deb96654e1a53a8350",
            "value": "Depth=0, working on node 6: 100%"
          }
        },
        "b02981cde8ed46cd9f4dbaf11bd19cb4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_9e092b9ea22346f5b7bcdd0f6d09e035",
            "max": 7,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_0096e2b1fea64921989b47d3d77f7563",
            "value": 7
          }
        },
        "7275da74d2da48d9adb4c0b1b3f3c767": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ba34acdf9aaa4c1c8f849ca1e643da05",
            "placeholder": "​",
            "style": "IPY_MODEL_93ba7e659a9641b7942ab63b8f40605b",
            "value": " 7/7 [00:00&lt;00:00, 156.31it/s]"
          }
        },
        "5efcc913d6024722bd82da75a957ee30": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "9dbf0723b34347b0b77c8672a80b5c46": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4268edae355042deb96654e1a53a8350": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "9e092b9ea22346f5b7bcdd0f6d09e035": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "0096e2b1fea64921989b47d3d77f7563": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "ba34acdf9aaa4c1c8f849ca1e643da05": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "93ba7e659a9641b7942ab63b8f40605b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}