2_train_models.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "2_train_models.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "dd13440485dd4a10b699f2a7404ac6f1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_04399edc8d2540e6a57780274f5a9e08",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_21939ecd34db46b395881b2715b4b3c1",
              "IPY_MODEL_3f975ebd2fca4b88be9f50fb074d8435",
              "IPY_MODEL_dc900fce7829426a9da51ab03bf3512c"
            ]
          }
        },
        "04399edc8d2540e6a57780274f5a9e08": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "21939ecd34db46b395881b2715b4b3c1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_5bc09027470e4b8db88254fe11303d2a",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": "100%",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_62c8f1fff31e43c2a3191bf05d6c756a"
          }
        },
        "3f975ebd2fca4b88be9f50fb074d8435": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_9a5ef9597da34d55a2952f9e3aa609f8",
            "_dom_classes": [],
            "description": "",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 3,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 3,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_63f21c28d14c4381b1fe85f3236f5932"
          }
        },
        "dc900fce7829426a9da51ab03bf3512c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_b667fffe2f4f4065b18aa38ffdcbebb7",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 3/3 [01:36&lt;00:00, 31.47s/it]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_b1abe58b84254a78bf5cbb8048ba368a"
          }
        },
        "5bc09027470e4b8db88254fe11303d2a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "62c8f1fff31e43c2a3191bf05d6c756a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9a5ef9597da34d55a2952f9e3aa609f8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "63f21c28d14c4381b1fe85f3236f5932": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "b667fffe2f4f4065b18aa38ffdcbebb7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "b1abe58b84254a78bf5cbb8048ba368a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "b13b7a67818f4630925a6c0650867fed": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_13fcfbf8004549f3be1949e84ae192bf",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_042db3084ab04f158a7a610e31f5e1bb",
              "IPY_MODEL_15519476784f451d9dece872cfd97dc4",
              "IPY_MODEL_07402b3db1c0408d86644086a34fbe89"
            ]
          }
        },
        "13fcfbf8004549f3be1949e84ae192bf": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "042db3084ab04f158a7a610e31f5e1bb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_66d2b45d4e8a46b496660f6bca0a3e2d",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": "100%",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_b76bec5b3fda4e3e96b4a74d5ebedfca"
          }
        },
        "15519476784f451d9dece872cfd97dc4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_be948e43e81840e7a2ee25bbdc7b9c2e",
            "_dom_classes": [],
            "description": "",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 3,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 3,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_9399b72261e24b259df2613d3f16b0ee"
          }
        },
        "07402b3db1c0408d86644086a34fbe89": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_074d3733a8304d7fa538e3eef9c05761",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 3/3 [00:18&lt;00:00,  5.77s/it]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_dad5f91feb104583a1d232a39dbaa51b"
          }
        },
        "66d2b45d4e8a46b496660f6bca0a3e2d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "b76bec5b3fda4e3e96b4a74d5ebedfca": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "be948e43e81840e7a2ee25bbdc7b9c2e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "9399b72261e24b259df2613d3f16b0ee": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "074d3733a8304d7fa538e3eef9c05761": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "dad5f91feb104583a1d232a39dbaa51b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-k976iTikGqm",
        "outputId": "12aefa40-81c1-4bbe-fee7-f302f7c10a91"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'gpHSP'...\n",
            "remote: Enumerating objects: 118, done.\u001b[K\n",
            "remote: Counting objects: 100% (80/80), done.\u001b[K\n",
            "remote: Compressing objects: 100% (56/56), done.\u001b[K\n",
            "remote: Total 118 (delta 46), reused 58 (delta 24), pack-reused 38\u001b[K\n",
            "Receiving objects: 100% (118/118), 32.19 MiB | 31.61 MiB/s, done.\n",
            "Resolving deltas: 100% (60/60), done.\n"
          ]
        }
      ],
      "source": [
        "! rm -rf gpHSP\n",
        "!git clone https://github.com/aspuru-guzik-group/gpHSP"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Assuming in a colab enviroment"
      ],
      "metadata": {
        "id": "CFEUih0gjjsA"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import sys\n",
        "if 'google.colab' in sys.modules:\n",
        "    print('In colab!')\n",
        "    sys.path.insert(0,'gpHSP')\n",
        "    !pip install rdkit-pypi mordred ml_collections ngboost gpflow"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qQyCA64AkN6w",
        "outputId": "5e4bebab-2578-4daa-9ba3-53b20e5a656c"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "In colab!\n",
            "Requirement already satisfied: rdkit-pypi in /usr/local/lib/python3.7/dist-packages (2021.9.4)\n",
            "Requirement already satisfied: mordred in /usr/local/lib/python3.7/dist-packages (1.2.0)\n",
            "Requirement already satisfied: ml_collections in /usr/local/lib/python3.7/dist-packages (0.1.1)\n",
            "Requirement already satisfied: ngboost in /usr/local/lib/python3.7/dist-packages (0.3.12)\n",
            "Requirement already satisfied: gpflow in /usr/local/lib/python3.7/dist-packages (2.3.1)\n",
            "Requirement already satisfied: Pillow in /usr/local/lib/python3.7/dist-packages (from rdkit-pypi) (7.1.2)\n",
            "Requirement already satisfied: numpy>=1.19 in /usr/local/lib/python3.7/dist-packages (from rdkit-pypi) (1.19.5)\n",
            "Requirement already satisfied: networkx==2.* in /usr/local/lib/python3.7/dist-packages (from mordred) (2.6.3)\n",
            "Requirement already satisfied: six==1.* in /usr/local/lib/python3.7/dist-packages (from mordred) (1.15.0)\n",
            "Requirement already satisfied: PyYAML in /usr/local/lib/python3.7/dist-packages (from ml_collections) (3.13)\n",
            "Requirement already satisfied: absl-py in /usr/local/lib/python3.7/dist-packages (from ml_collections) (1.0.0)\n",
            "Requirement already satisfied: contextlib2 in /usr/local/lib/python3.7/dist-packages (from ml_collections) (0.5.5)\n",
            "Requirement already satisfied: tqdm>=4.3 in /usr/local/lib/python3.7/dist-packages (from ngboost) (4.62.3)\n",
            "Requirement already satisfied: lifelines>=0.25 in /usr/local/lib/python3.7/dist-packages (from ngboost) (0.26.4)\n",
            "Requirement already satisfied: scipy>=1.3 in /usr/local/lib/python3.7/dist-packages (from ngboost) (1.4.1)\n",
            "Requirement already satisfied: scikit-learn>=0.21 in /usr/local/lib/python3.7/dist-packages (from ngboost) (1.0.2)\n",
            "Requirement already satisfied: pandas>=0.23.0 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (1.3.5)\n",
            "Requirement already satisfied: autograd-gamma>=0.3 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (0.5.0)\n",
            "Requirement already satisfied: matplotlib>=3.0 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (3.2.2)\n",
            "Requirement already satisfied: formulaic<0.3,>=0.2.2 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (0.2.4)\n",
            "Requirement already satisfied: autograd>=1.3 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (1.3)\n",
            "Requirement already satisfied: future>=0.15.2 in /usr/local/lib/python3.7/dist-packages (from autograd>=1.3->lifelines>=0.25->ngboost) (0.16.0)\n",
            "Requirement already satisfied: interface-meta>=1.2 in /usr/local/lib/python3.7/dist-packages (from formulaic<0.3,>=0.2.2->lifelines>=0.25->ngboost) (1.2.4)\n",
            "Requirement already satisfied: astor in /usr/local/lib/python3.7/dist-packages (from formulaic<0.3,>=0.2.2->lifelines>=0.25->ngboost) (0.8.1)\n",
            "Requirement already satisfied: wrapt in /usr/local/lib/python3.7/dist-packages (from formulaic<0.3,>=0.2.2->lifelines>=0.25->ngboost) (1.13.3)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (3.0.7)\n",
            "Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (2.8.2)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (0.11.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (1.3.2)\n",
            "Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.23.0->lifelines>=0.25->ngboost) (2018.9)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.21->ngboost) (3.1.0)\n",
            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.21->ngboost) (1.1.0)\n",
            "Requirement already satisfied: multipledispatch>=0.6 in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.6.0)\n",
            "Requirement already satisfied: tabulate in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.8.9)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.7/dist-packages (from gpflow) (3.10.0.2)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (57.4.0)\n",
            "Requirement already satisfied: tensorflow-probability>0.10.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.15.0)\n",
            "Requirement already satisfied: tensorflow>=2.2.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (2.7.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.7/dist-packages (from gpflow) (21.3)\n",
            "Requirement already satisfied: deprecated in /usr/local/lib/python3.7/dist-packages (from gpflow) (1.2.13)\n",
            "Requirement already satisfied: dataclasses in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.6)\n",
            "Requirement already satisfied: tensorboard~=2.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.7.0)\n",
            "Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.1.2)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.6.3)\n",
            "Requirement already satisfied: tensorflow-estimator<2.8,~=2.7.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.7.0)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (3.1.0)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.23.1)\n",
            "Requirement already satisfied: flatbuffers<3.0,>=1.12 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.0)\n",
            "Requirement already satisfied: gast<0.5.0,>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.4.0)\n",
            "Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (3.17.3)\n",
            "Requirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (13.0.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.1.0)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.2.0)\n",
            "Requirement already satisfied: wheel<1.0,>=0.32.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.37.1)\n",
            "Requirement already satisfied: keras<2.8,>=2.7.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.7.0)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (3.3.0)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.43.0)\n",
            "Requirement already satisfied: cached-property in /usr/local/lib/python3.7/dist-packages (from h5py>=2.9.0->tensorflow>=2.2.0->gpflow) (1.5.2)\n",
            "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (1.0.1)\n",
            "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (0.4.6)\n",
            "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (0.6.1)\n",
            "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (1.8.1)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (2.23.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (3.3.6)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (1.35.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (4.8)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (0.2.8)\n",
            "Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (4.2.4)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (1.3.1)\n",
            "Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (4.10.1)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (3.7.0)\n",
            "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.7/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (0.4.8)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (3.0.4)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (2.10)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (2021.10.8)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.6->tensorflow>=2.2.0->gpflow) (3.2.0)\n",
            "Requirement already satisfied: cloudpickle>=1.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow-probability>0.10.0->gpflow) (1.3.0)\n",
            "Requirement already satisfied: decorator in /usr/local/lib/python3.7/dist-packages (from tensorflow-probability>0.10.0->gpflow) (4.4.2)\n",
            "Requirement already satisfied: dm-tree in /usr/local/lib/python3.7/dist-packages (from tensorflow-probability>0.10.0->gpflow) (0.1.6)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from tqdm.auto import tqdm\n",
        "import scipy.stats as stats\n",
        "\n",
        "import ngboost\n",
        "import tensorflow as tf\n",
        "import gpflow as gpf\n",
        "import gphsp\n",
        "\n",
        "gphsp.notebook_context()\n",
        "gphsp.print_modules([ngboost, tf , gpf])"
      ],
      "metadata": {
        "id": "IO5wJqsskd1t",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ca2566ca-9a01-437a-92b0-4b969582f839"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "ngboost    = 0.3.12\n",
            "tensorflow = 2.7.0\n",
            "gpflow     = 2.3.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Utilities"
      ],
      "metadata": {
        "id": "HVDbXSZAliP3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "at_data_dir = lambda x: os.path.join('gpHSP/data', x)\n",
        "at_model_dir = lambda x: os.path.join('gpHSP/models', x)"
      ],
      "metadata": {
        "id": "wseewPpTCGHD"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load data and get all smiles"
      ],
      "metadata": {
        "id": "_wvvTIsMldgt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(at_data_dir('Solvents_exp.csv'))\n",
        "df['smiles'] = df['smiles'].apply(gphsp.get_isomeric_smiles)\n",
        "gphsp.peek_df(df)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 318
        },
        "id": "YYDEEwkVk9BW",
        "outputId": "8e079b78-e0cc-4069-be66-9af5c3d9c021"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Index(['key', 'Type', 'δd', 'δp', 'δh', 'smiles', 'ID_type', 'ID', 'Ref',\n",
            "       'organic', 'n_electrons', 'n_atoms', 'charge', 'MolWt', 'label',\n",
            "       'finished', 'job_name', 'homo', 'lumo', 'gap', 'd-moments', 'dipole',\n",
            "       'polar', 'run_time', 'n_cores', 'compute_time', 'Area', 'Hba', 'Hbd',\n",
            "       'Volume', 'sigma_mom_0', 'sigma_mom_1', 'sigma_mom_2', 'sigma_mom_3',\n",
            "       'sigma_mom_4', 'sigma_mom_5', 'sigma_norm', 'sigma_profile', 'drug'],\n",
            "      dtype='object')\n",
            "(193, 39)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-9567e2ed-cdb1-4dc4-b57e-180a62303928\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>key</th>\n",
              "      <th>Type</th>\n",
              "      <th>δd</th>\n",
              "      <th>δp</th>\n",
              "      <th>δh</th>\n",
              "      <th>smiles</th>\n",
              "      <th>ID_type</th>\n",
              "      <th>ID</th>\n",
              "      <th>Ref</th>\n",
              "      <th>organic</th>\n",
              "      <th>n_electrons</th>\n",
              "      <th>n_atoms</th>\n",
              "      <th>charge</th>\n",
              "      <th>MolWt</th>\n",
              "      <th>label</th>\n",
              "      <th>finished</th>\n",
              "      <th>job_name</th>\n",
              "      <th>homo</th>\n",
              "      <th>lumo</th>\n",
              "      <th>gap</th>\n",
              "      <th>d-moments</th>\n",
              "      <th>dipole</th>\n",
              "      <th>polar</th>\n",
              "      <th>run_time</th>\n",
              "      <th>n_cores</th>\n",
              "      <th>compute_time</th>\n",
              "      <th>Area</th>\n",
              "      <th>Hba</th>\n",
              "      <th>Hbd</th>\n",
              "      <th>Volume</th>\n",
              "      <th>sigma_mom_0</th>\n",
              "      <th>sigma_mom_1</th>\n",
              "      <th>sigma_mom_2</th>\n",
              "      <th>sigma_mom_3</th>\n",
              "      <th>sigma_mom_4</th>\n",
              "      <th>sigma_mom_5</th>\n",
              "      <th>sigma_norm</th>\n",
              "      <th>sigma_profile</th>\n",
              "      <th>drug</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1,1,1-Trichloroethane</td>\n",
              "      <td>Solvent</td>\n",
              "      <td>16.8</td>\n",
              "      <td>4.3</td>\n",
              "      <td>2.0</td>\n",
              "      <td>CC(Cl)(Cl)Cl</td>\n",
              "      <td>CAS</td>\n",
              "      <td>71-55-6</td>\n",
              "      <td>1</td>\n",
              "      <td>True</td>\n",
              "      <td>32</td>\n",
              "      <td>5</td>\n",
              "      <td>0</td>\n",
              "      <td>133.405</td>\n",
              "      <td>Exp-0</td>\n",
              "      <td>True</td>\n",
              "      <td>SOLSPE_Exp-0</td>\n",
              "      <td>-7.097</td>\n",
              "      <td>-1.108</td>\n",
              "      <td>5.989</td>\n",
              "      <td>[-2.37335554 -0.11768285  0.07442233]</td>\n",
              "      <td>2.377</td>\n",
              "      <td>64.374</td>\n",
              "      <td>94.214</td>\n",
              "      <td>4</td>\n",
              "      <td>376.856</td>\n",
              "      <td>1.326</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.126</td>\n",
              "      <td>0</td>\n",
              "      <td>16.6</td>\n",
              "      <td>-3.836</td>\n",
              "      <td>4.24</td>\n",
              "      <td>-2.021</td>\n",
              "      <td>1.54</td>\n",
              "      <td>41.428</td>\n",
              "      <td>[ 0.          0.          0.          0.      ...</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9567e2ed-cdb1-4dc4-b57e-180a62303928')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-9567e2ed-cdb1-4dc4-b57e-180a62303928 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-9567e2ed-cdb1-4dc4-b57e-180a62303928');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "                     key  ...   drug\n",
              "0  1,1,1-Trichloroethane  ...  False\n",
              "\n",
              "[1 rows x 39 columns]"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "poly_df = pd.read_csv(at_data_dir('Polymers_exp.csv'))\n",
        "poly_df['smiles'] = poly_df['smiles'].apply(gphsp.get_isomeric_smiles)\n",
        "gphsp.peek_df(poly_df)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 353
        },
        "id": "izpVJD2Ws1g_",
        "outputId": "e70e57da-3fff-497c-98bd-6050b9149125"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Index(['label', 'δd', 'δp', 'δh', 'smiles', 'test', 'poly_label', 'n_copies',\n",
            "       'organic', 'n_electrons', 'n_atoms', 'charge', 'MolWt', 'n_frags',\n",
            "       'largest', 'finished', 'job_name', 'poly_smiles', 'homo', 'lumo', 'gap',\n",
            "       'd-moments', 'dipole', 'polar', 'run_time', 'n_cores', 'compute_time',\n",
            "       'Area', 'Hba', 'Hbd', 'Volume', 'sigma_mom_0', 'sigma_mom_1',\n",
            "       'sigma_mom_2', 'sigma_mom_3', 'sigma_mom_4', 'sigma_mom_5',\n",
            "       'sigma_norm', 'sigma_profile'],\n",
            "      dtype='object')\n",
            "(31, 39)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-f8d79be9-9504-44e7-a4c3-9f3779e6e762\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>label</th>\n",
              "      <th>δd</th>\n",
              "      <th>δp</th>\n",
              "      <th>δh</th>\n",
              "      <th>smiles</th>\n",
              "      <th>test</th>\n",
              "      <th>poly_label</th>\n",
              "      <th>n_copies</th>\n",
              "      <th>organic</th>\n",
              "      <th>n_electrons</th>\n",
              "      <th>n_atoms</th>\n",
              "      <th>charge</th>\n",
              "      <th>MolWt</th>\n",
              "      <th>n_frags</th>\n",
              "      <th>largest</th>\n",
              "      <th>finished</th>\n",
              "      <th>job_name</th>\n",
              "      <th>poly_smiles</th>\n",
              "      <th>homo</th>\n",
              "      <th>lumo</th>\n",
              "      <th>gap</th>\n",
              "      <th>d-moments</th>\n",
              "      <th>dipole</th>\n",
              "      <th>polar</th>\n",
              "      <th>run_time</th>\n",
              "      <th>n_cores</th>\n",
              "      <th>compute_time</th>\n",
              "      <th>Area</th>\n",
              "      <th>Hba</th>\n",
              "      <th>Hbd</th>\n",
              "      <th>Volume</th>\n",
              "      <th>sigma_mom_0</th>\n",
              "      <th>sigma_mom_1</th>\n",
              "      <th>sigma_mom_2</th>\n",
              "      <th>sigma_mom_3</th>\n",
              "      <th>sigma_mom_4</th>\n",
              "      <th>sigma_mom_5</th>\n",
              "      <th>sigma_norm</th>\n",
              "      <th>sigma_profile</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Polyacrylonitrile-n5</td>\n",
              "      <td>20.0</td>\n",
              "      <td>15.1</td>\n",
              "      <td>7.9</td>\n",
              "      <td>CCC#N</td>\n",
              "      <td>True</td>\n",
              "      <td>Polyacrylonitrile</td>\n",
              "      <td>5</td>\n",
              "      <td>True</td>\n",
              "      <td>110</td>\n",
              "      <td>45</td>\n",
              "      <td>0</td>\n",
              "      <td>275.4</td>\n",
              "      <td>1</td>\n",
              "      <td>True</td>\n",
              "      <td>True</td>\n",
              "      <td>SOLSPE2_Polyacrylonitrile-n5</td>\n",
              "      <td>[C@@H](C#N)(CCC#N)C[C@@H](C#N)C[C@H](C#N)CCC#N</td>\n",
              "      <td>-7.879</td>\n",
              "      <td>-1.12</td>\n",
              "      <td>6.759</td>\n",
              "      <td>[ 0.58302575 -8.49403297 -1.86749721]</td>\n",
              "      <td>8.716</td>\n",
              "      <td>211.624</td>\n",
              "      <td>468.596</td>\n",
              "      <td>4</td>\n",
              "      <td>1874.384</td>\n",
              "      <td>3.047</td>\n",
              "      <td>1.539</td>\n",
              "      <td>0.22</td>\n",
              "      <td>0.343</td>\n",
              "      <td>0</td>\n",
              "      <td>175.0</td>\n",
              "      <td>26.1</td>\n",
              "      <td>154.0</td>\n",
              "      <td>51.4</td>\n",
              "      <td>165.0</td>\n",
              "      <td>66.77</td>\n",
              "      <td>[ 0.          0.          0.          0.      ...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f8d79be9-9504-44e7-a4c3-9f3779e6e762')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-f8d79be9-9504-44e7-a4c3-9f3779e6e762 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-f8d79be9-9504-44e7-a4c3-9f3779e6e762');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "                  label  ...                                      sigma_profile\n",
              "0  Polyacrylonitrile-n5  ...  [ 0.          0.          0.          0.      ...\n",
              "\n",
              "[1 rows x 39 columns]"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Load features"
      ],
      "metadata": {
        "id": "w1s-j6DgtpgV"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "features = gphsp.SmilesMap(at_data_dir('mordred_features.npz'))"
      ],
      "metadata": {
        "id": "jq0x70z9l-_G"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Train rfHSP model on single molecules"
      ],
      "metadata": {
        "id": "UJrOUs-hoHOE"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "save_model = True\n",
        "model_suffix = 'HSP_ngboost_mol.pkl'\n",
        "\n",
        "models = {}\n",
        "x = features(df['smiles'].to_numpy(str))\n",
        "names = gphsp.Y_COLS\n",
        "print(names)\n",
        "for name in tqdm(names, total=len(names)):\n",
        "    y = df[name].to_numpy(np.float32).reshape(-1,1)\n",
        "    model = ngboost.NGBRegressor().fit(x, y)\n",
        "    y_dists = model.pred_dist(x)\n",
        "    models[name] = model\n",
        "    if save_model:\n",
        "        fname = at_model_dir(f\"{name}_{model_suffix}\")\n",
        "        gphsp.save_model(model, fname)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 451,
          "referenced_widgets": [
            "dd13440485dd4a10b699f2a7404ac6f1",
            "04399edc8d2540e6a57780274f5a9e08",
            "21939ecd34db46b395881b2715b4b3c1",
            "3f975ebd2fca4b88be9f50fb074d8435",
            "dc900fce7829426a9da51ab03bf3512c",
            "5bc09027470e4b8db88254fe11303d2a",
            "62c8f1fff31e43c2a3191bf05d6c756a",
            "9a5ef9597da34d55a2952f9e3aa609f8",
            "63f21c28d14c4381b1fe85f3236f5932",
            "b667fffe2f4f4065b18aa38ffdcbebb7",
            "b1abe58b84254a78bf5cbb8048ba368a"
          ]
        },
        "id": "11CV8mqonS4H",
        "outputId": "bb78ebe4-38d6-479d-e7d1-4e4a35264e8d"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['δd', 'δp', 'δh']\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "dd13440485dd4a10b699f2a7404ac6f1",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "  0%|          | 0/3 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[iter 0] loss=2.0292 val_loss=0.0000 scale=1.0000 norm=1.5771\n",
            "[iter 100] loss=1.3892 val_loss=0.0000 scale=2.0000 norm=1.7636\n",
            "[iter 200] loss=0.7992 val_loss=0.0000 scale=2.0000 norm=1.2279\n",
            "[iter 300] loss=0.3868 val_loss=0.0000 scale=1.0000 norm=0.4991\n",
            "[iter 400] loss=0.0804 val_loss=0.0000 scale=1.0000 norm=0.4297\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[iter 0] loss=3.0726 val_loss=0.0000 scale=1.0000 norm=4.1787\n",
            "[iter 100] loss=2.5094 val_loss=0.0000 scale=2.0000 norm=4.7659\n",
            "[iter 200] loss=1.9639 val_loss=0.0000 scale=1.0000 norm=1.4583\n",
            "[iter 300] loss=1.4908 val_loss=0.0000 scale=1.0000 norm=1.0831\n",
            "[iter 400] loss=1.2050 val_loss=0.0000 scale=1.0000 norm=0.9079\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[iter 0] loss=3.1769 val_loss=0.0000 scale=1.0000 norm=4.6890\n",
            "[iter 100] loss=2.3695 val_loss=0.0000 scale=2.0000 norm=3.6644\n",
            "[iter 200] loss=1.6093 val_loss=0.0000 scale=2.0000 norm=2.0204\n",
            "[iter 300] loss=0.9949 val_loss=0.0000 scale=2.0000 norm=1.5120\n",
            "[iter 400] loss=0.6177 val_loss=0.0000 scale=1.0000 norm=0.6421\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Train gpHSP model on polymers"
      ],
      "metadata": {
        "id": "vgARDFB55pUB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model_suffix = 'HSP_ngboost_mol.pkl'\n",
        "names = gphsp.Y_COLS\n",
        "models = {name: gphsp.load_model(at_model_dir(f\"{name}_{model_suffix}\")) for name in names}\n",
        "mol_x = features(poly_df['smiles'].to_numpy(str))\n",
        "x = gphsp.predictions_as_features(mol_x, models)"
      ],
      "metadata": {
        "id": "uT3_wZsF-nSL"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_suffix = 'ngboost_polymer.pkl'\n",
        "\n",
        "save_models = True\n",
        "poly_models = {}\n",
        "parts = {'mean':[0,1, 2], 'std':[3, 4, 5]}\n",
        "for name in tqdm(names, total=len(names)):\n",
        "    y = poly_df[name].to_numpy(np.float32).reshape(-1,1)\n",
        "    model = ngboost.NGBRegressor().fit(x, y)\n",
        "    y_dists = model.pred_dist(x)\n",
        "    poly_models[name] = model\n",
        "    gpf.utilities.print_summary(model)\n",
        "    if save_models:\n",
        "        adir = at_model_dir(f'{name}_{model_suffix}.pkl')\n",
        "        gphsp.save_model(model, adir)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 434,
          "referenced_widgets": [
            "b13b7a67818f4630925a6c0650867fed",
            "13fcfbf8004549f3be1949e84ae192bf",
            "042db3084ab04f158a7a610e31f5e1bb",
            "15519476784f451d9dece872cfd97dc4",
            "07402b3db1c0408d86644086a34fbe89",
            "66d2b45d4e8a46b496660f6bca0a3e2d",
            "b76bec5b3fda4e3e96b4a74d5ebedfca",
            "be948e43e81840e7a2ee25bbdc7b9c2e",
            "9399b72261e24b259df2613d3f16b0ee",
            "074d3733a8304d7fa538e3eef9c05761",
            "dad5f91feb104583a1d232a39dbaa51b"
          ]
        },
        "id": "3uyX9DJkIBK8",
        "outputId": "5cbfd1c6-3d73-4939-b5c3-8c3fd688e0c7"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "b13b7a67818f4630925a6c0650867fed",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "  0%|          | 0/3 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[iter 0] loss=1.2875 val_loss=0.0000 scale=1.0000 norm=0.9061\n",
            "[iter 100] loss=0.6368 val_loss=0.0000 scale=2.0000 norm=1.0987\n",
            "[iter 200] loss=-0.1046 val_loss=0.0000 scale=2.0000 norm=0.8926\n",
            "[iter 300] loss=-0.8155 val_loss=0.0000 scale=2.0000 norm=0.7903\n",
            "[iter 400] loss=-1.4411 val_loss=0.0000 scale=2.0000 norm=0.7138\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<table>\n",
              "<thead>\n",
              "<tr></tr>\n",
              "</thead>\n",
              "<tbody>\n",
              "</tbody>\n",
              "</table>"
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[iter 0] loss=2.8508 val_loss=0.0000 scale=1.0000 norm=3.5836\n",
            "[iter 100] loss=1.9063 val_loss=0.0000 scale=2.0000 norm=2.2872\n",
            "[iter 200] loss=1.1005 val_loss=0.0000 scale=2.0000 norm=1.3370\n",
            "[iter 300] loss=0.3887 val_loss=0.0000 scale=2.0000 norm=1.0724\n",
            "[iter 400] loss=-0.2423 val_loss=0.0000 scale=2.0000 norm=0.9426\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<table>\n",
              "<thead>\n",
              "<tr></tr>\n",
              "</thead>\n",
              "<tbody>\n",
              "</tbody>\n",
              "</table>"
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[iter 0] loss=2.8877 val_loss=0.0000 scale=1.0000 norm=3.3176\n",
            "[iter 100] loss=1.9035 val_loss=0.0000 scale=2.0000 norm=2.4536\n",
            "[iter 200] loss=1.1380 val_loss=0.0000 scale=2.0000 norm=1.5236\n",
            "[iter 300] loss=0.4168 val_loss=0.0000 scale=2.0000 norm=1.2032\n",
            "[iter 400] loss=-0.2456 val_loss=0.0000 scale=2.0000 norm=1.0536\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<table>\n",
              "<thead>\n",
              "<tr></tr>\n",
              "</thead>\n",
              "<tbody>\n",
              "</tbody>\n",
              "</table>"
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {}
        }
      ]
    }
  ]
}