{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "d2a08ef6",
   "metadata": {},
   "source": [
    "# SHAP explanations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "767b003e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import trustyai\n",
    "\n",
    "trustyai.init()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e194eb56",
   "metadata": {},
   "source": [
    "## Simple example\n",
    "\n",
    "We start by defining our black-box model, typically represented by\n",
    "\n",
    "$$\n",
    "f(\\mathbf{x}) = \\mathbf{y}\n",
    "$$\n",
    "\n",
    "Where $\\mathbf{x}=\\{x_1, x_2, \\dots,x_m\\}$ and $\\mathbf{y}=\\{y_1, y_2, \\dots,y_n\\}$.\n",
    "\n",
    "Our example toy model, in this case, takes an all-numerical input $\\mathbf{x}$ and return a $\\mathbf{y}$ of either `true` or `false` if the sum of the $\\mathbf{x}$ components is within a threshold $\\epsilon$ of a point $\\mathbf{C}$, that is:\n",
    "\n",
    "$$\n",
    "f(\\mathbf{x}, \\epsilon, \\mathbf{C})=\\begin{cases}\n",
    "\\text{true},\\qquad \\text{if}\\ \\mathbf{C}-\\epsilon<\\sum_{i=1}^m x_i <\\mathbf{C}+\\epsilon \\\\\n",
    "\\text{false},\\qquad \\text{otherwise}\n",
    "\\end{cases}\n",
    "$$\n",
    "\n",
    "This model is provided in the `TestUtils` module. We instantiate with a $\\mathbf{C}=500$ and $\\epsilon=1.0$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "fd02e320",
   "metadata": {},
   "outputs": [],
   "source": [
    "from trustyai.utils import TestUtils\n",
    "\n",
    "center = 10.0\n",
    "epsilon = 2.0\n",
    "\n",
    "model = TestUtils.getSumThresholdModel(center, epsilon)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e4a15f8b",
   "metadata": {},
   "source": [
    "Next we need to define a **goal**.\n",
    "If our model is $f(\\mathbf{x'})=\\mathbf{y'}$ we are then defining our $\\mathbf{y'}$ and the counterfactual result will be the $\\mathbf{x'}$ which satisfies $f(\\mathbf{x'})=\\mathbf{y'}$.\n",
    "\n",
    "We will define our goal as `true`, that is, the sum is withing the vicinity of a (to be defined) point $\\mathbf{C}$. The goal is a list of `Output` which take the following parameters\n",
    "\n",
    "- The feature name\n",
    "- The feature type\n",
    "- The feature value (wrapped in `Value`)\n",
    "- A confidence threshold, which we will leave at zero (no threshold)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "bf3f4232",
   "metadata": {},
   "outputs": [],
   "source": [
    "from trustyai.model import output\n",
    "\n",
    "decision = \"inside\"\n",
    "goal = [output(name=decision, dtype=\"bool\", value=True, score=0.0)]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "64349c3e",
   "metadata": {},
   "source": [
    "We will now define our initial features, $\\mathbf{x}$. Each feature can be instantiated by using `FeatureFactory` and in this case we want to use numerical features, so we'll use `FeatureFactory.newNumericalFeature`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d688a7c8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "from trustyai.model import feature\n",
    "\n",
    "features = [feature(name=f\"x{i+1}\", dtype=\"number\", value=random.random()*10.0) for i in range(3)]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a562ef68",
   "metadata": {},
   "source": [
    "As we can see, the sum of of the features will not be within $\\epsilon$ (1.0) of $\\mathbf{C}$ (500.0). As such the model prediction will be `false`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "45695e15",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Feature x1 has value 6.164708056938084\n",
      "Feature x2 has value 3.8453023806417197\n",
      "Feature x3 has value 3.6459410618461527\n",
      "\n",
      "Features sum is 13.655951499425957\n"
     ]
    }
   ],
   "source": [
    "feature_sum = 0.0\n",
    "for f in features:\n",
    "    value = f.value.as_number()\n",
    "    print(f\"Feature {f.name} has value {value}\")\n",
    "    feature_sum += value\n",
    "print(f\"\\nFeatures sum is {feature_sum}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13001554",
   "metadata": {},
   "source": [
    "We execute the model on the generated input and collect the output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0a45c0e0",
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from org.kie.kogito.explainability.model import PredictionInput, PredictionOutput\n",
    "\n",
    "goals = model.predictAsync([PredictionInput(features)]).get()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4483bf24",
   "metadata": {},
   "outputs": [],
   "source": [
    "background = []\n",
    "for i in range(10):\n",
    "    _features = [feature(name=f\"x{i+1}\", dtype=\"number\", value=random.random()*10.0) for i in range(3)]\n",
    "    background.append(PredictionInput(_features))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "324cefdf",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We wrap these quantities in a `SimplePrediction`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8bb2aac1",
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from trustyai.model import simple_prediction\n",
    "\n",
    "prediction = simple_prediction(input_features=features, outputs=goals[0].outputs)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9bb631f9",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We can now instantiate the **explainer** itself.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "115fa89c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "SLF4J: Failed to load class \"org.slf4j.impl.StaticLoggerBinder\".\n",
      "SLF4J: Defaulting to no-operation (NOP) logger implementation\n",
      "SLF4J: See http://www.slf4j.org/codes.html#StaticLoggerBinder for further details.\n"
     ]
    }
   ],
   "source": [
    "from trustyai.explainers import SHAPExplainer\n",
    "\n",
    "explainer = SHAPExplainer(background=background)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7cd8b2b4",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We generate the **explanation** as a _dict : decision --> saliency_.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "b34e26d7",
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "explanation = explainer.explain(prediction, model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d32e4272",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We inspect the saliency scores assigned by LIME to each feature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2f0721fe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saliency{output=Output{value=false, type=boolean, score=-2.6559514994259565, name='inside'}, perFeatureImportance=[FeatureImportance{feature=Feature{name='x1', type=number, value=6.164708056938084}, score=-0.2833333333333333, confidence= +/-0.37307360101101117}, FeatureImportance{feature=Feature{name='x2', type=number, value=3.8453023806417197}, score=-0.033333333333333354, confidence= +/-0.37307360101101117}, FeatureImportance{feature=Feature{name='x3', type=number, value=3.6459410618461527}, score=0.016666666666666663, confidence= +/-0.5276057463131408}]}\n"
     ]
    }
   ],
   "source": [
    "for saliency in explanation.getSaliencies():\n",
    "    print(saliency)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9be2bd8d",
   "metadata": {},
   "source": [
    "# Python Models\n",
    "Now let's go over how to use a Python model with TrustyAI. First, let's grab a dataset, we'll use the California Housing dataset from `sklearn`, which tries\n",
    "to predict the median house value of various California housing districts given a number of different attributes of the district.\n",
    "\n",
    "After downloading the dataset, we then split it into train and test splits."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8bc071e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X Train: (16512, 8), X Test: (4128, 8), Y Train: (16512,), Y Test: (4128,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn import datasets\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X, y = datasets.fetch_california_housing(data_home=\"data\", return_X_y=True, as_frame=True)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=.8)\n",
    "print(f\"X Train: {X_train.shape}, X Test: {X_test.shape}, Y Train: {y_train.shape}, Y Test: {y_test.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ca8d106b",
   "metadata": {},
   "source": [
    "Now let's grab our model, just a simple xgboost regressor. We'll then plot its test predictions against the the true test labels, to see how well it does."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "f1b8a88b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test MSE 0.9195932918653825\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x900 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import xgboost\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "plt.style.use('https://raw.githubusercontent.com/RobGeada/stylelibs/main/material_rh.mplstyle')\n",
    "\n",
    "# uncomment to train from scratch\n",
    "# xgb_model = xgboost.XGBRegressor(objective='reg:squarederror', tree_method='gpu_hist')\n",
    "# xgb_model.fit(X_train, y_train)\n",
    "# print('Test MSE', xgb_model.score(X_test, y_test))\n",
    "# xgb_model.save_model(\"models/california_xgboost\")\n",
    " \n",
    "# load and score model\n",
    "xgb_model = xgboost.XGBRegressor(objective='reg:squarederror')\n",
    "xgb_model.load_model(\"models/california_xgboost\")\n",
    "print('Test MSE', xgb_model.score(X_test, y_test))\n",
    "\n",
    "# grab predictions and find largest error\n",
    "predictions = xgb_model.predict(X_test)\n",
    "worst = np.argmax(np.abs(predictions - y_test))\n",
    "\n",
    "# plot predictions\n",
    "plt.scatter(y_test, predictions)\n",
    "plt.scatter(y_test.iloc[worst], predictions[worst], color='r')\n",
    "plt.plot([0,5], [0,5], color='k')\n",
    "plt.xlabel(\"True Value\")\n",
    "plt.ylabel(\"Predicted Value\")\n",
    "plt.title(\"XGBoost Predictions, California Housing\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "131c76c3",
   "metadata": {},
   "source": [
    "That's pretty decent! Let's grab a point to explain; let's choose that really erroneous point marked in red in the above plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a13ef389",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MedInc          2.384600\n",
       "HouseAge       22.000000\n",
       "AveRooms        5.152866\n",
       "AveBedrms       1.146497\n",
       "Population    334.000000\n",
       "AveOccup        2.127389\n",
       "Latitude       33.480000\n",
       "Longitude    -117.660000\n",
       "Name: 10454, dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "point_to_explain = X_test.iloc[worst]\n",
    "point_to_explain"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dc78cfef",
   "metadata": {},
   "source": [
    "We'll need to convert it into a Prediction object in order to pass it to the SHAP Explainer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "ed472303",
   "metadata": {},
   "outputs": [],
   "source": [
    "from trustyai.model import feature, output\n",
    "features_to_explain = [feature(name=key, dtype='number', value=value) for key, value in point_to_explain.items()]\n",
    "output_to_explain = output(name='Median House Price', dtype='number', value=predictions[worst])\n",
    "prediction_to_explain = simple_prediction(input_features=features_to_explain, outputs=[output_to_explain])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4efca66c",
   "metadata": {},
   "source": [
    "We also need to convert our training data into TrustyAI PredictionInputs. This is pretty simple for Pandas DataFrames:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "90a7c919",
   "metadata": {},
   "outputs": [],
   "source": [
    "from org.kie.kogito.explainability.model import PredictionInput\n",
    "\n",
    "X_train_PIs = [PredictionInput([feature(name=key, dtype='number', value=value) for key, value in x.items()]) for _, x in X_train.iterrows()]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7cd4d861",
   "metadata": {},
   "source": [
    "Now we can wrap our model into a TrustyAI PredictionProvider. We do this via an `ArrowModel`, which rapidly speeds up the data transfer between Python and the TrustyAI Java library. \n",
    "To create an ArrowModel, we need to pass it a function that accepts a Pandas DataFrame as input and outputs a Pandas DataFrame or Numpy Array. All sklearn models satisfy this with their\n",
    "`predict` or `predict_proba` functions, so this is really easy to do.\n",
    "\n",
    "We then call the `get_as_prediction_provider`\n",
    "function on the ArrowModel, to which we pass an example datapoint to use as a template for our data conversions. Make sure this template point has the same schema (i.e., feature names and types) as all the other points you plan on passing to the model!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5520b4ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "from trustyai.model import ArrowModel\n",
    "trustyai_model = ArrowModel(xgb_model.predict).get_as_prediction_provider(X_train_PIs[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6754d314",
   "metadata": {},
   "source": [
    "With our model successfully wrapped, we can create our SHAP explainer. To do this we need to specify a *background dataset*, a small $(\\le100)$ set of representative examples of the model's input. We'll use the first 100 training points as our background dataset. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "544d5779",
   "metadata": {},
   "outputs": [],
   "source": [
    "from trustyai.explainers import SHAPExplainer\n",
    "explainer = SHAPExplainer(background=X_train_PIs[:100])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0df5806c",
   "metadata": {},
   "source": [
    "We can now produce our explanation:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "f87e71b3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: An illegal reflective access operation has occurred\n",
      "WARNING: Illegal reflective access by org.apache.arrow.memory.util.MemoryUtil (file:/Users/rui/.virtualenvs/trustyai-python-examples/lib/python3.7/site-packages/trustyai/dep/org/apache/arrow/arrow-memory-core/7.0.0/arrow-memory-core-7.0.0.jar) to field java.nio.Buffer.address\n",
      "WARNING: Please consider reporting this to the maintainers of org.apache.arrow.memory.util.MemoryUtil\n",
      "WARNING: Use --illegal-access=warn to enable warnings of further illegal reflective access operations\n",
      "WARNING: All illegal access operations will be denied in a future release\n"
     ]
    }
   ],
   "source": [
    "explanations = explainer.explain(prediction_to_explain, trustyai_model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "06c8630d",
   "metadata": {},
   "source": [
    "## Visualizing SHAP Values"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "021d715d",
   "metadata": {},
   "source": [
    "Now let's visualize the explanation, first as a dataframe:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "ed311402",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "#T_e14ae_row1_col1,#T_e14ae_row2_col1,#T_e14ae_row3_col1,#T_e14ae_row5_col1,#T_e14ae_row6_col1,#T_e14ae_row7_col1{\n",
       "            background-color: #ee0000;\n",
       "        }#T_e14ae_row1_col2{\n",
       "            background-color:  #f9a2a2;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row2_col2{\n",
       "            background-color:  #fffefe;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row3_col2{\n",
       "            background-color:  #fef4f4;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row4_col1,#T_e14ae_row8_col1{\n",
       "            background-color: #13ba3c;\n",
       "        }#T_e14ae_row4_col2{\n",
       "            background-color:  #f7fdf8;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row5_col2{\n",
       "            background-color:  #fef0f0;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row6_col2{\n",
       "            background-color:  #d2f2da;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row7_col2{\n",
       "            background-color:  #13ba3c;\n",
       "            color:  #000000;\n",
       "        }#T_e14ae_row8_col2{\n",
       "            background-color:  #ef1414;\n",
       "            color:  #f1f1f1;\n",
       "        }</style><table id=\"T_e14ae_\" ><caption>Explanation of Median House Price</caption><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >Mean Background Value</th>        <th class=\"col_heading level0 col1\" >Feature Value</th>        <th class=\"col_heading level0 col2\" >SHAP Value</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_e14ae_level0_row0\" class=\"row_heading level0 row0\" >Background</th>\n",
       "                        <td id=\"T_e14ae_row0_col0\" class=\"data row0 col0\" >-</td>\n",
       "                        <td id=\"T_e14ae_row0_col1\" class=\"data row0 col1\" >-</td>\n",
       "                        <td id=\"T_e14ae_row0_col2\" class=\"data row0 col2\" >2.373661</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row1\" class=\"row_heading level0 row1\" >MedInc</th>\n",
       "                        <td id=\"T_e14ae_row1_col0\" class=\"data row1 col0\" >4.070206</td>\n",
       "                        <td id=\"T_e14ae_row1_col1\" class=\"data row1 col1\" >2.384600</td>\n",
       "                        <td id=\"T_e14ae_row1_col2\" class=\"data row1 col2\" >-0.482674</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row2\" class=\"row_heading level0 row2\" >HouseAge</th>\n",
       "                        <td id=\"T_e14ae_row2_col0\" class=\"data row2 col0\" >28.060000</td>\n",
       "                        <td id=\"T_e14ae_row2_col1\" class=\"data row2 col1\" >22.000000</td>\n",
       "                        <td id=\"T_e14ae_row2_col2\" class=\"data row2 col2\" >-0.006309</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row3\" class=\"row_heading level0 row3\" >AveRooms</th>\n",
       "                        <td id=\"T_e14ae_row3_col0\" class=\"data row3 col0\" >5.325720</td>\n",
       "                        <td id=\"T_e14ae_row3_col1\" class=\"data row3 col1\" >5.152866</td>\n",
       "                        <td id=\"T_e14ae_row3_col2\" class=\"data row3 col2\" >-0.057444</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row4\" class=\"row_heading level0 row4\" >AveBedrms</th>\n",
       "                        <td id=\"T_e14ae_row4_col0\" class=\"data row4 col0\" >1.067250</td>\n",
       "                        <td id=\"T_e14ae_row4_col1\" class=\"data row4 col1\" >1.146497</td>\n",
       "                        <td id=\"T_e14ae_row4_col2\" class=\"data row4 col2\" >0.046290</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row5\" class=\"row_heading level0 row5\" >Population</th>\n",
       "                        <td id=\"T_e14ae_row5_col0\" class=\"data row5 col0\" >1528.370000</td>\n",
       "                        <td id=\"T_e14ae_row5_col1\" class=\"data row5 col1\" >334.000000</td>\n",
       "                        <td id=\"T_e14ae_row5_col2\" class=\"data row5 col2\" >-0.073580</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row6\" class=\"row_heading level0 row6\" >AveOccup</th>\n",
       "                        <td id=\"T_e14ae_row6_col0\" class=\"data row6 col0\" >2.785109</td>\n",
       "                        <td id=\"T_e14ae_row6_col1\" class=\"data row6 col1\" >2.127389</td>\n",
       "                        <td id=\"T_e14ae_row6_col2\" class=\"data row6 col2\" >0.251778</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row7\" class=\"row_heading level0 row7\" >Latitude</th>\n",
       "                        <td id=\"T_e14ae_row7_col0\" class=\"data row7 col0\" >35.876600</td>\n",
       "                        <td id=\"T_e14ae_row7_col1\" class=\"data row7 col1\" >33.480000</td>\n",
       "                        <td id=\"T_e14ae_row7_col2\" class=\"data row7 col2\" >1.330079</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row8\" class=\"row_heading level0 row8\" >Longitude</th>\n",
       "                        <td id=\"T_e14ae_row8_col0\" class=\"data row8 col0\" >-119.893900</td>\n",
       "                        <td id=\"T_e14ae_row8_col1\" class=\"data row8 col1\" >-117.660000</td>\n",
       "                        <td id=\"T_e14ae_row8_col2\" class=\"data row8 col2\" >-1.225742</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_e14ae_level0_row9\" class=\"row_heading level0 row9\" >Prediction</th>\n",
       "                        <td id=\"T_e14ae_row9_col0\" class=\"data row9 col0\" >2.373661</td>\n",
       "                        <td id=\"T_e14ae_row9_col1\" class=\"data row9 col1\" >2.156060</td>\n",
       "                        <td id=\"T_e14ae_row9_col2\" class=\"data row9 col2\" >2.156060</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x15fb6bf10>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "explanations.as_html()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33ee51a2",
   "metadata": {},
   "source": [
    "Feature values in red/green indicate a lower/higher value than the average background value of that feature. SHAP values in red/green indicate a negative/positive contribution to the prediction."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1073b9e3",
   "metadata": {},
   "source": [
    "Now let's visualize the explanation as a candlestick plot:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "f379aca0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x900 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "explanations.candlestick_plot() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dae2f1fe",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "a0b19a0e0769482a3dd54d9b1f74632fb70b79784820162adf8976b9cad4acbb"
  },
  "kernelspec": {
   "display_name": "trustyai-python-examples",
   "language": "python",
   "name": "trustyai-python-examples"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}