{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "6c4d4faf-ab84-4a72-a80e-535b211747cd",
   "metadata": {
    "tags": []
   },
   "source": [
    "# Partial Dependence for 2 Features Explainer Demo\n",
    "\n",
    "This example demonstrates how to interpret a model using the H2O Sonar library and retrieve the data and **partial dependence plot for 2 featues**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "69f414e3-bc88-478b-bed5-890352b1041a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type='text/css'>\n",
       ".datatable table.frame { margin-bottom: 0; }\n",
       ".datatable table.frame thead { border-bottom: none; }\n",
       ".datatable table.frame tr.coltypes td {  color: #FFFFFF;  line-height: 6px;  padding: 0 0.5em;}\n",
       ".datatable .bool    { background: #DDDD99; }\n",
       ".datatable .object  { background: #565656; }\n",
       ".datatable .int     { background: #5D9E5D; }\n",
       ".datatable .float   { background: #4040CC; }\n",
       ".datatable .str     { background: #CC4040; }\n",
       ".datatable .time    { background: #40CC40; }\n",
       ".datatable .row_index {  background: var(--jp-border-color3);  border-right: 1px solid var(--jp-border-color0);  color: var(--jp-ui-font-color3);  font-size: 9px;}\n",
       ".datatable .frame tbody td { text-align: left; }\n",
       ".datatable .frame tr.coltypes .row_index {  background: var(--jp-border-color0);}\n",
       ".datatable th:nth-child(2) { padding-left: 12px; }\n",
       ".datatable .hellipsis {  color: var(--jp-cell-editor-border-color);}\n",
       ".datatable .vellipsis {  background: var(--jp-layout-color0);  color: var(--jp-cell-editor-border-color);}\n",
       ".datatable .na {  color: var(--jp-cell-editor-border-color);  font-size: 80%;}\n",
       ".datatable .sp {  opacity: 0.25;}\n",
       ".datatable .footer { font-size: 9px; }\n",
       ".datatable .frame_dimensions {  background: var(--jp-border-color3);  border-top: 1px solid var(--jp-border-color0);  color: var(--jp-ui-font-color3);  display: inline-block;  opacity: 0.6;  padding: 1px 10px 1px 5px;}\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import logging\n",
    "import os\n",
    "\n",
    "import daimojo\n",
    "import datatable\n",
    "import webbrowser\n",
    "\n",
    "from h2o_sonar import interpret\n",
    "from h2o_sonar.lib.api import commons, explainers\n",
    "from h2o_sonar.lib.api.models import ModelApi\n",
    "from h2o_sonar.explainers.pd_2_features_explainer import PdFor2FeaturesExplainer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bef37207-bd90-4a60-a927-bbc2c54ab149",
   "metadata": {},
   "outputs": [],
   "source": [
    "# dataset\n",
    "dataset_path = \"../../data/creditcard.csv\"\n",
    "target_col = \"default payment next month\"\n",
    "\n",
    "# model\n",
    "mojo_path = \"../../data/models/creditcard-binomial.mojo\"\n",
    "mojo_model = daimojo.model(mojo_path)\n",
    "model = ModelApi().create_model(\n",
    "    model_src=mojo_model,\n",
    "    target_col=target_col,\n",
    "    used_features=list(mojo_model.feature_names),\n",
    ")\n",
    "\n",
    "# results\n",
    "results_location = \"./results\"\n",
    "os.makedirs(results_location, exist_ok=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "bbe0ca51",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'id': 'h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer',\n",
       " 'name': 'PdFor2FeaturesExplainer',\n",
       " 'display_name': 'Partial Dependence Plot for Two Features',\n",
       " 'description': 'Partial dependence for 2 features portrays the average\\nprediction behavior of a model across the domains of two input variables\\ni.e. interaction of feature tuples with the prediction. While PD for one feature\\nproduces 2D plot, PD for two features produces 3D plots. This explainer plots PD for\\ntwo features using heatmap, contour 3D or surface 3D.\\n',\n",
       " 'model_types': ['iid', 'time_series'],\n",
       " 'can_explain': ['regression', 'binomial'],\n",
       " 'explanation_scopes': ['global_scope'],\n",
       " 'explanations': [{'explanation_type': 'global-partial-dependence',\n",
       "   'name': 'PartialDependenceExplanation',\n",
       "   'category': None,\n",
       "   'scope': 'global',\n",
       "   'has_local': None,\n",
       "   'formats': []}],\n",
       " 'parameters': [{'name': 'sample_size',\n",
       "   'description': 'Sample size for Partial Dependence Plot of 2 features.',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 25000,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'max_features',\n",
       "   'description': 'Partial Dependence Plot number of features.',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 3,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'features',\n",
       "   'description': 'List of features from which to choose pairs to compute PD for two features.',\n",
       "   'comment': '',\n",
       "   'type': 'list',\n",
       "   'val': None,\n",
       "   'predefined': [],\n",
       "   'tags': ['SOURCE_DATASET_COLUMN_NAMES'],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'grid_resolution',\n",
       "   'description': 'Partial Dependence Plot observations per bin (number of equally spaced points used to create bins).',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 10,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'oor_grid_resolution',\n",
       "   'description': 'Partial Dependence Plot number of out of range bins.',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 0,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'quantile-bin-grid-resolution',\n",
       "   'description': 'Partial Dependence Plot quantile binning (total quantile points used to create bins).',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 0,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'plot_type',\n",
       "   'description': 'Plot type.',\n",
       "   'comment': '',\n",
       "   'type': 'str',\n",
       "   'val': 'heatmap',\n",
       "   'predefined': ['heatmap', 'contour-3d', 'surface-3d'],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''}],\n",
       " 'keywords': []}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# explainer description\n",
    "interpret.describe_explainer(PdFor2FeaturesExplainer)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "90d401d2-14cd-4686-982f-3cac9e9f5eb7",
   "metadata": {
    "tags": []
   },
   "source": [
    "## Interpretation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0ba8f0aa-2e0e-4a0a-93ab-77ce9e968fa0",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/srasaratnam/projects/h2o-sonar/venv/lib/python3.8/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 10.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 10.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 10.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 10.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 20.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 30.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 40.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 50.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 60.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 70.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 70.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 70.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 70.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 70.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 70.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 80.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 80.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 80.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 80.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 80.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 90.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 90.0%\n",
      "h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer: progress 90.0%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "FixedFormatter should only be used together with FixedLocator\n",
      "FixedFormatter should only be used together with FixedLocator\n",
      "FixedFormatter should only be used together with FixedLocator\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "interpretation = interpret.run_interpretation(\n",
    "    dataset=dataset_path,\n",
    "    model=model,\n",
    "    target_col=target_col,\n",
    "    results_location=results_location,\n",
    "    log_level=logging.INFO,\n",
    "    explainers=[\n",
    "        commons.ExplainerToRun(\n",
    "            explainer_id=PdFor2FeaturesExplainer.explainer_id(),\n",
    "            params=\"\",\n",
    "        )\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff9df4be-d4da-44db-a479-7d8d7f45c29d",
   "metadata": {},
   "source": [
    "## Explainer Result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "25556ca5-8239-4201-8a23-1ace2b3a46d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# retrieve the result\n",
    "result = interpretation.get_explainer_result(PdFor2FeaturesExplainer.explainer_id())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "38c26ac9-df8e-480f-ab6c-c14b43860c5d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# open interpretation HTML report in web browser\n",
    "webbrowser.open(interpretation.result.get_html_report_location())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "76c46623-6e24-4ac1-b6cc-66fc29b7ea0c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'id': 'h2o_sonar.explainers.pd_2_features_explainer.PdFor2FeaturesExplainer',\n",
       " 'name': 'PdFor2FeaturesExplainer',\n",
       " 'display_name': 'Partial Dependence Plot for Two Features',\n",
       " 'description': 'Partial dependence for 2 features portrays the average\\nprediction behavior of a model across the domains of two input variables\\ni.e. interaction of feature tuples with the prediction. While PD for one feature\\nproduces 2D plot, PD for two features produces 3D plots. This explainer plots PD for\\ntwo features using heatmap, contour 3D or surface 3D.\\n',\n",
       " 'model_types': ['iid', 'time_series'],\n",
       " 'can_explain': ['regression', 'binomial'],\n",
       " 'explanation_scopes': ['global_scope'],\n",
       " 'explanations': [{'explanation_type': 'global-report',\n",
       "   'name': 'Partial Dependence Plot for Two Features',\n",
       "   'category': 'DAI MODEL',\n",
       "   'scope': 'global',\n",
       "   'has_local': None,\n",
       "   'formats': ['text/markdown']},\n",
       "  {'explanation_type': 'global-3d-data',\n",
       "   'name': 'Partial Dependence Plot for Two Features',\n",
       "   'category': 'DAI MODEL',\n",
       "   'scope': 'global',\n",
       "   'has_local': None,\n",
       "   'formats': ['application/json', 'application/vnd.h2oai.json+csv']},\n",
       "  {'explanation_type': 'global-html-fragment',\n",
       "   'name': 'Partial Dependence Plot for Two Features',\n",
       "   'category': 'DAI MODEL',\n",
       "   'scope': 'global',\n",
       "   'has_local': None,\n",
       "   'formats': ['text/html']}],\n",
       " 'parameters': [{'name': 'sample_size',\n",
       "   'description': 'Sample size for Partial Dependence Plot of 2 features.',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 25000,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'max_features',\n",
       "   'description': 'Partial Dependence Plot number of features.',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 3,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'features',\n",
       "   'description': 'List of features from which to choose pairs to compute PD for two features.',\n",
       "   'comment': '',\n",
       "   'type': 'list',\n",
       "   'val': None,\n",
       "   'predefined': [],\n",
       "   'tags': ['SOURCE_DATASET_COLUMN_NAMES'],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'grid_resolution',\n",
       "   'description': 'Partial Dependence Plot observations per bin (number of equally spaced points used to create bins).',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 10,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'oor_grid_resolution',\n",
       "   'description': 'Partial Dependence Plot number of out of range bins.',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 0,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'quantile-bin-grid-resolution',\n",
       "   'description': 'Partial Dependence Plot quantile binning (total quantile points used to create bins).',\n",
       "   'comment': '',\n",
       "   'type': 'int',\n",
       "   'val': 0,\n",
       "   'predefined': [],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''},\n",
       "  {'name': 'plot_type',\n",
       "   'description': 'Plot type.',\n",
       "   'comment': '',\n",
       "   'type': 'str',\n",
       "   'val': 'heatmap',\n",
       "   'predefined': ['heatmap', 'contour-3d', 'surface-3d'],\n",
       "   'tags': [],\n",
       "   'min_': 0.0,\n",
       "   'max_': 0.0,\n",
       "   'category': ''}],\n",
       " 'keywords': []}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# summary\n",
    "result.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e30e08f6-69b9-408f-8bd6-6dad14638694",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'sample_size': 25000,\n",
       " 'max_features': 3,\n",
       " 'features': None,\n",
       " 'grid_resolution': 10,\n",
       " 'oor_grid_resolution': 0,\n",
       " 'quantile-bin-grid-resolution': 0,\n",
       " 'plot_type': 'heatmap'}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# parameters\n",
    "result.params()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "490d132b-b7e2-48a2-8ec4-dbd71886edf9",
   "metadata": {},
   "source": [
    "### Display PD Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "2aa6274e-79d5-49b1-b29a-2263db5cb8a8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'10000': {'6': 0.2552240192890167,\n",
       "  '5': 0.2552240192890167,\n",
       "  '4': 0.25266972184181213,\n",
       "  '3': 0.25266972184181213,\n",
       "  '2': 0.2251938432455063,\n",
       "  '1': 0.2251938432455063,\n",
       "  '0': 0.2251938432455063},\n",
       " '208000': {'6': 0.21158096194267273,\n",
       "  '5': 0.21158096194267273,\n",
       "  '4': 0.20898468792438507,\n",
       "  '3': 0.20898468792438507,\n",
       "  '2': 0.17519091069698334,\n",
       "  '1': 0.17519091069698334,\n",
       "  '0': 0.17519091069698334},\n",
       " '307000': {'6': 0.20750007033348083,\n",
       "  '5': 0.20750007033348083,\n",
       "  '4': 0.20484082400798798,\n",
       "  '3': 0.20484082400798798,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '406000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '505000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '604000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '703000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '802000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '901000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279},\n",
       " '1000000': {'6': 0.20645806193351746,\n",
       "  '5': 0.20645806193351746,\n",
       "  '4': 0.2037988305091858,\n",
       "  '3': 0.2037988305091858,\n",
       "  '2': 0.17081709206104279,\n",
       "  '1': 0.17081709206104279,\n",
       "  '0': 0.17081709206104279}}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result.data(feature_names=\"'LIMIT_BAL' and 'EDUCATION'\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df8a083b-3b88-4349-bb63-28551c24cc4f",
   "metadata": {},
   "source": [
    "### Plot PD Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5a9d8262-574e-4073-a282-567d4fd1209c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "FixedFormatter should only be used together with FixedLocator\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot(feature_names=\"'LIMIT_BAL' and 'EDUCATION'\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a493b092-6236-419f-906c-16d52c47674f",
   "metadata": {},
   "source": [
    "### Save Explainer Log and Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "7c638a2c-6b01-4228-aa0f-93fd8dd7feab",
   "metadata": {},
   "outputs": [],
   "source": [
    "# save the explainer log\n",
    "result.log(path=\"./pd-2-features-demo.log\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f5d91240-09ff-4893-b652-b0259a8f222a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2023-03-12 23:27:53,358 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 BEGIN calculation\n",
      "2023-03-12 23:27:53,359 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 loading dataset\n",
      "2023-03-12 23:27:53,360 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 loaded dataset has 10000 rows and 25 columns\n",
      "2023-03-12 23:27:53,360 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 getting features list, importanceand metadata\n",
      "2023-03-12 23:27:53,361 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 all most important model features: ['ID', 'LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0', 'PAY_2', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'BILL_AMT1', 'BILL_AMT2', 'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6', 'PAY_AMT1', 'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6']\n",
      "2023-03-12 23:27:53,362 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 features used by model: ['ID', 'LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0', 'PAY_2', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'BILL_AMT1', 'BILL_AMT2', 'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6', 'PAY_AMT1', 'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6']\n",
      "2023-03-12 23:27:53,362 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885: calculating PD for features ['ID', 'LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0', 'PAY_2', 'PAY_3', 'PAY_4']\n",
      "2023-03-12 23:27:53,363 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 feature metadata: {'id': [], 'categorical': [], 'numeric': [], 'catnum': [], 'date': [], 'time': [], 'datetime': [], 'text': [], 'image': [], 'date-format': [], 'quantile-bin': {}}\n",
      "2023-03-12 23:27:53,363 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 1 frame strategy: True\n",
      "2023-03-12 23:27:53,364 INFO PD/ICE a30a4f57-9c78-4c5f-9c8e-85198b523c1c/745668cc-bbc8-42be-9b39-47487112a885 residual PD/ICE should NOT be calculated, but y has been specified - setting it None\n"
     ]
    }
   ],
   "source": [
    "!head pd-ice-demo.log"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "da4e2b28-96d7-440e-bfea-41cb694a52d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# save the explainer data\n",
    "result.zip(file_path=\"./pd-ice-demo-archive.zip\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c0540819-f896-481a-b470-b9d53a243b0a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Archive:  pd-ice-demo-archive.zip\n",
      "  Length      Date    Time    Name\n",
      "---------  ---------- -----   ----\n",
      "     4474  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/result_descriptor.json\n",
      "      122  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_report/text_markdown.meta\n",
      "     2642  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_report/text_markdown/explanation.md\n",
      "    92249  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_report/text_markdown/image-1.png\n",
      "    80252  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_report/text_markdown/image-2.png\n",
      "    75679  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_report/text_markdown/image-0.png\n",
      "    92249  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/work/image-1.png\n",
      "    80252  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/work/image-2.png\n",
      "    75679  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/work/image-0.png\n",
      "     1247  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/work/explanation.html\n",
      "    40216  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/work/mli_dataset_y_hat.jay\n",
      "     2642  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/work/report.md\n",
      "      110  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_html_fragment/text_html.meta\n",
      "    92249  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_html_fragment/text_html/image-1.png\n",
      "    80252  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_html_fragment/text_html/image-2.png\n",
      "    75679  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_html_fragment/text_html/image-0.png\n",
      "     1247  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_html_fragment/text_html/explanation.html\n",
      "      141  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_json.meta\n",
      "      161  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_vnd_h2oai_json_csv.meta\n",
      "     2583  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_json/data3d_feature_1_class_0.json\n",
      "     1484  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_json/explanation.json\n",
      "      902  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_json/data3d_feature_0_class_0.json\n",
      "      498  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_json/data3d_feature_2_class_0.json\n",
      "      285  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_vnd_h2oai_json_csv/data3d_feature_2_class_0.csv\n",
      "     1466  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_vnd_h2oai_json_csv/data3d_feature_1_class_0.csv\n",
      "     1481  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_vnd_h2oai_json_csv/explanation.json\n",
      "      475  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/global_3d_data/application_vnd_h2oai_json_csv/data3d_feature_0_class_0.csv\n",
      "        2  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/model_problems/problems_and_actions.json\n",
      "     2054  2023-03-12 23:35   explainer_h2o_sonar_explainers_pd_2_features_explainer_PdFor2FeaturesExplainer_993771ed-6505-450c-b5dd-4d81f871d218/log/explainer_run_993771ed-6505-450c-b5dd-4d81f871d218.log\n",
      "---------                     -------\n",
      "   808772                     29 files\n"
     ]
    }
   ],
   "source": [
    "!unzip -l pd-ice-demo-archive.zip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "584ad6ad-9989-46e4-9c65-aae4bff14df6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "h2o-sonar",
   "language": "python",
   "name": "h2o-sonar"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}