{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Be careful when interpreting predictive models in search of causal insights\n",
    "\n",
    "*A joint article about causality and interpretable machine learning with Eleanor Dillon, Jacob LaRiviere, Scott Lundberg, Jonathan Roth, and Vasilis Syrgkanis from Microsoft.*\n",
    "\n",
    "Predictive machine learning models like XGBoost become even more powerful when paired with interpretability tools like SHAP. These tools identify the most informative relationships between the input features and the predicted outcome, which is useful for explaining what the model is doing, getting stakeholder buy-in, and diagnosing potential problems. It is tempting to take this analysis one step further and assume that interpretation tools can also identify what features decision makers should manipulate if they want to change outcomes in the future. However, **in this article, we discuss how using predictive models to guide this kind of policy choice can often be misleading.**\n",
    "\n",
    "The reason relates to the fundamental difference between *correlation* and *causation*. SHAP makes transparent the correlations picked up by predictive ML models. But making correlations transparent does not make them causal! All predictive models implicitly assume that everyone will keep behaving the same way in the future, and therefore correlation patterns will stay constant. To understand what happens if someone starts behaving differently, we need to build causal models, which requires making assumptions and using the tools of causal analysis."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## A subscriber retention example\n",
    "\n",
    "Imagine we are tasked with building a model that predicts whether a customer will renew their product subscription. Let's assume that after a bit of digging we manage to get eight features which are important for predicting churn: customer discount, ad spending, customer's monthly usage, last upgrade, bugs reported by a customer, interactions with a customer, sales calls with a customer, and macroeconomic activity. We then use those features to train a basic XGBoost model to predict if a customer will renew their subscription when it expires:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This cell defines the functions we use to generate the data in our scenario\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import scipy.stats\n",
    "import sklearn\n",
    "import xgboost\n",
    "\n",
    "\n",
    "class FixableDataFrame(pd.DataFrame):\n",
    "    \"\"\"Helper class for manipulating generative models.\"\"\"\n",
    "\n",
    "    def __init__(self, *args, fixed={}, **kwargs):\n",
    "        self.__dict__[\"__fixed_var_dictionary\"] = fixed\n",
    "        super().__init__(*args, **kwargs)\n",
    "\n",
    "    def __setitem__(self, key, value):\n",
    "        out = super().__setitem__(key, value)\n",
    "        if isinstance(key, str) and key in self.__dict__[\"__fixed_var_dictionary\"]:\n",
    "            out = super().__setitem__(key, self.__dict__[\"__fixed_var_dictionary\"][key])\n",
    "        return out\n",
    "\n",
    "\n",
    "# generate the data\n",
    "def generator(n, fixed={}, seed=0):\n",
    "    \"\"\"The generative model for our subscriber retention example.\"\"\"\n",
    "    if seed is not None:\n",
    "        np.random.seed(seed)\n",
    "    X = FixableDataFrame(fixed=fixed)\n",
    "\n",
    "    # the number of sales calls made to this customer\n",
    "    X[\"Sales calls\"] = np.random.uniform(0, 4, size=(n,)).round()\n",
    "\n",
    "    # the number of sales calls made to this customer\n",
    "    X[\"Interactions\"] = X[\"Sales calls\"] + np.random.poisson(0.2, size=(n,))\n",
    "\n",
    "    # the health of the regional economy this customer is a part of\n",
    "    X[\"Economy\"] = np.random.uniform(0, 1, size=(n,))\n",
    "\n",
    "    # the time since the last product upgrade when this customer came up for renewal\n",
    "    X[\"Last upgrade\"] = np.random.uniform(0, 20, size=(n,))\n",
    "\n",
    "    # how much the user perceives that they need the product\n",
    "    X[\"Product need\"] = X[\"Sales calls\"] * 0.1 + np.random.normal(0, 1, size=(n,))\n",
    "\n",
    "    # the fractional discount offered to this customer upon renewal\n",
    "    X[\"Discount\"] = ((1 - scipy.special.expit(X[\"Product need\"])) * 0.5 + 0.5 * np.random.uniform(0, 1, size=(n,))) / 2\n",
    "\n",
    "    # What percent of the days in the last period was the user actively using the product\n",
    "    X[\"Monthly usage\"] = scipy.special.expit(X[\"Product need\"] * 0.3 + np.random.normal(0, 1, size=(n,)))\n",
    "\n",
    "    # how much ad money we spent per user targeted at this user (or a group this user is in)\n",
    "    X[\"Ad spend\"] = (\n",
    "        X[\"Monthly usage\"] * np.random.uniform(0.99, 0.9, size=(n,)) + (X[\"Last upgrade\"] < 1) + (X[\"Last upgrade\"] < 2)\n",
    "    )\n",
    "\n",
    "    # how many bugs did this user encounter in the since their last renewal\n",
    "    X[\"Bugs faced\"] = np.array([np.random.poisson(v * 2) for v in X[\"Monthly usage\"]])\n",
    "\n",
    "    # how many bugs did the user report?\n",
    "    X[\"Bugs reported\"] = (X[\"Bugs faced\"] * scipy.special.expit(X[\"Product need\"])).round()\n",
    "\n",
    "    # did the user renew?\n",
    "    X[\"Did renew\"] = scipy.special.expit(\n",
    "        7\n",
    "        * (\n",
    "            0.18 * X[\"Product need\"]\n",
    "            + 0.08 * X[\"Monthly usage\"]\n",
    "            + 0.1 * X[\"Economy\"]\n",
    "            + 0.05 * X[\"Discount\"]\n",
    "            + 0.05 * np.random.normal(0, 1, size=(n,))\n",
    "            + 0.05 * (1 - X[\"Bugs faced\"] / 20)\n",
    "            + 0.005 * X[\"Sales calls\"]\n",
    "            + 0.015 * X[\"Interactions\"]\n",
    "            + 0.1 / (X[\"Last upgrade\"] / 4 + 0.25)\n",
    "            + X[\"Ad spend\"] * 0.0\n",
    "            - 0.45\n",
    "        )\n",
    "    )\n",
    "\n",
    "    # in real life we would make a random draw to get either 0 or 1 for if the\n",
    "    # customer did or did not renew. but here we leave the label as the probability\n",
    "    # so that we can get less noise in our plots. Uncomment this line to get\n",
    "    # noiser causal effect lines but the same basic results\n",
    "    X[\"Did renew\"] = scipy.stats.bernoulli.rvs(X[\"Did renew\"])\n",
    "\n",
    "    return X\n",
    "\n",
    "\n",
    "def user_retention_dataset():\n",
    "    \"\"\"The observed data for model training.\"\"\"\n",
    "    n = 10000\n",
    "    X_full = generator(n)\n",
    "    y = X_full[\"Did renew\"]\n",
    "    X = X_full.drop([\"Did renew\", \"Product need\", \"Bugs faced\"], axis=1)\n",
    "    return X, y\n",
    "\n",
    "\n",
    "def fit_xgboost(X, y):\n",
    "    \"\"\"Train an XGBoost model with early stopping.\"\"\"\n",
    "    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(X, y)\n",
    "    dtrain = xgboost.DMatrix(X_train, label=y_train)\n",
    "    dtest = xgboost.DMatrix(X_test, label=y_test)\n",
    "    model = xgboost.train(\n",
    "        {\"eta\": 0.001, \"subsample\": 0.5, \"max_depth\": 2, \"objective\": \"reg:logistic\"},\n",
    "        dtrain,\n",
    "        num_boost_round=200000,\n",
    "        evals=((dtest, \"test\"),),\n",
    "        early_stopping_rounds=20,\n",
    "        verbose_eval=False,\n",
    "    )\n",
    "    return model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = user_retention_dataset()\n",
    "model = fit_xgboost(X, y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Once we have our XGBoost customer retention model in hand, we can begin exploring what it has learned with an interpretability tool like SHAP. We start by plotting the global importance of each feature in the model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 347,
       "width": 622
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import shap\n",
    "\n",
    "explainer = shap.Explainer(model)\n",
    "shap_values = explainer(X)\n",
    "\n",
    "clust = shap.utils.hclust(X, y, linkage=\"single\")\n",
    "shap.plots.bar(shap_values, clustering=clust, clustering_cutoff=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This bar plot shows that the discount offered, ad spend, and number of bugs reported are the top three factors driving the model's prediction of customer retention. This is interesting and at first glance looks reasonable. The bar plot also includes a feature redundancy clustering which we will use later.\n",
    "\n",
    "However, when we dig deeper and look at how changing the value of each feature impacts the model's prediction, we find some unintuitive patterns. SHAP scatter plots show how changing the value of a feature impacts the model's prediction of renewal probabilities. If the blue dots follow an increasing pattern, this means that the larger the feature, the higher is the model's predicted renewal probability."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1080x360 with 16 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 320,
       "width": 918
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "shap.plots.scatter(shap_values, ylabel=\"SHAP value\\n(higher means more likely to renew)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction tasks versus causal tasks\n",
    "The scatter plots show some surprising findings:\n",
    "- Users who report more bugs are more likely to renew!\n",
    "- Users with larger discounts are less likely to renew!\n",
    "\n",
    "We triple-check our code and data pipelines to rule out a bug, then talk to some business partners who offer an intuitive explanation:\n",
    "- Users with high usage who value the product are more likely to report bugs and to renew their subscriptions.\n",
    "- The sales force tends to give high discounts to customers they think are less likely to be interested in the product, and these customers have higher churn.\n",
    "\n",
    "Are these at-first counter-intuitive relationships in the model a problem? *That depends on what our goal is!*\n",
    "\n",
    "Our original goal for this model was to predict customer retention, which is useful for projects like estimating future revenue for financial planning. Since users reporting more bugs are in fact more likely to renew, capturing this relationship in the model is helpful for prediction. As long as our model has good fit out-of-sample, we should be able to provide finance with a good prediction, and therefore shouldn't worry about the direction of this relationship in the model.\n",
    "\n",
    "This is an example of a class of tasks called **prediction tasks**. In a prediction task, the goal is to predict an outcome `Y` (e.g. renewals) given a set of features `X`. A key component of a prediction exercise is that we only care that the prediction `model(X)` is close to `Y` in data distributions similar to our training set. A simple correlation between `X` and `Y` can be helpful for these types of predictions.\n",
    "\n",
    "However, suppose a second team picks up our prediction model with the new goal of determining what actions our company can take to retain more customers. This team cares a lot about how each `X` feature relates to `Y`, not just in our training distribution, but the counterfactual scenario produced when the world changes. In that use case, it is no longer sufficient to identify a stable correlation between variables; this team wants to know whether manipulating feature `X` will cause a change in `Y`. Picture the face of the chief of engineering when you tell him that you want him to introduce new bugs to increase customer renewals!\n",
    "\n",
    "This is an example of a class of tasks called **causal tasks**. In a causal task, we want to know how changing an aspect of the world X (e.g bugs reported) affects an outcome `Y` (renewals). In this case, it's critical to know whether changing `X` causes an increase in `Y`, or whether the relationship in the data is merely correlational."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The challenges of estimating causal effects\n",
    "\n",
    "A useful tool to understanding causal relationships is writing down a causal graph of the data generating process we're interested in. A causal graph of our example illustrates why the robust predictive relationships picked up by our XGBoost customer retention model differ from the causal relationships of interest to the team that wants to plan interventions to increase retention. This graph is just a summary of the true data generating mechanism (which is defined above). Solid ovals represent features that we observe, while dashed ovals represent hidden features that we don't measure. Each feature is a function of all the features with an arrow to it, plus some random effects.\n",
    "\n",
    "In our example we know the causal graph because we simulate the data. In practice the true causal graph will not be known, but we may be able to use context-specific domain knowledge about how the world works  to infer which relationships can or cannot exist."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 2.40.1 (20161225.0304)\n",
       " -->\n",
       "<!-- Title: %3 Pages: 1 -->\n",
       "<svg width=\"572pt\" height=\"332pt\"\n",
       " viewBox=\"0.00 0.00 571.82 332.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 328)\">\n",
       "<title>%3</title>\n",
       "<polygon fill=\"#ffffff\" stroke=\"transparent\" points=\"-4,4 -4,-328 567.8241,-328 567.8241,4 -4,4\"/>\n",
       "<!-- Bugs reported -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>Bugs reported</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"43.5611\" cy=\"-18\" rx=\"43.6222\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"43.5611\" y=\"-15.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Bugs reported</text>\n",
       "</g>\n",
       "<!-- Monthly usage -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>Monthly usage</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"139.5611\" cy=\"-162\" rx=\"45.8316\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"139.5611\" y=\"-159.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Monthly usage</text>\n",
       "</g>\n",
       "<!-- Ad spend -->\n",
       "<g id=\"node7\" class=\"node\">\n",
       "<title>Ad spend</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"200.5611\" cy=\"-90\" rx=\"32.9303\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"200.5611\" y=\"-87.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Ad spend</text>\n",
       "</g>\n",
       "<!-- Monthly usage&#45;&gt;Ad spend -->\n",
       "<g id=\"edge8\" class=\"edge\">\n",
       "<title>Monthly usage&#45;&gt;Ad spend</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M154.3275,-144.5708C161.9304,-135.5968 171.3295,-124.5028 179.6635,-114.666\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"182.5569,-116.6652 186.3507,-106.7729 177.216,-112.1403 182.5569,-116.6652\"/>\n",
       "</g>\n",
       "<!-- Bugs faced -->\n",
       "<g id=\"node10\" class=\"node\">\n",
       "<title>Bugs faced</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" stroke-dasharray=\"5,2\" cx=\"75.5611\" cy=\"-90\" rx=\"36.4942\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"75.5611\" y=\"-87.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Bugs faced</text>\n",
       "</g>\n",
       "<!-- Monthly usage&#45;&gt;Bugs faced -->\n",
       "<g id=\"edge6\" class=\"edge\">\n",
       "<title>Monthly usage&#45;&gt;Bugs faced</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M124.394,-144.937C116.3438,-135.8806 106.3069,-124.5891 97.4298,-114.6023\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"99.8789,-112.0893 90.6193,-106.9405 94.647,-116.7399 99.8789,-112.0893\"/>\n",
       "</g>\n",
       "<!-- Did renew -->\n",
       "<g id=\"node11\" class=\"node\">\n",
       "<title>Did renew</title>\n",
       "<ellipse fill=\"#d3d3d3\" stroke=\"#000000\" cx=\"329.5611\" cy=\"-18\" rx=\"34.9638\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"329.5611\" y=\"-15.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Did renew</text>\n",
       "</g>\n",
       "<!-- Monthly usage&#45;&gt;Did renew -->\n",
       "<g id=\"edge7\" class=\"edge\">\n",
       "<title>Monthly usage&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M138.3526,-143.7322C138.0523,-123.651 140.7551,-91.6389 158.5611,-72 175.8273,-52.9564 241.9725,-36.0116 286.7518,-26.3821\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"287.7297,-29.7531 296.7939,-24.2675 286.2873,-22.9033 287.7297,-29.7531\"/>\n",
       "</g>\n",
       "<!-- Sales calls -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>Sales calls</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"459.5611\" cy=\"-306\" rx=\"34.9638\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"459.5611\" y=\"-303.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Sales calls</text>\n",
       "</g>\n",
       "<!-- Interactions -->\n",
       "<g id=\"node8\" class=\"node\">\n",
       "<title>Interactions</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"525.5611\" cy=\"-234\" rx=\"38.0276\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"525.5611\" y=\"-231.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Interactions</text>\n",
       "</g>\n",
       "<!-- Sales calls&#45;&gt;Interactions -->\n",
       "<g id=\"edge12\" class=\"edge\">\n",
       "<title>Sales calls&#45;&gt;Interactions</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M474.5375,-289.6621C483.0235,-280.4046 493.8034,-268.6447 503.2662,-258.3217\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"506.0087,-260.5095 510.1859,-250.7729 500.8486,-255.7794 506.0087,-260.5095\"/>\n",
       "</g>\n",
       "<!-- Product need -->\n",
       "<g id=\"node9\" class=\"node\">\n",
       "<title>Product need</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" stroke-dasharray=\"5,2\" cx=\"334.5611\" cy=\"-234\" rx=\"41.4139\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"334.5611\" y=\"-231.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Product need</text>\n",
       "</g>\n",
       "<!-- Sales calls&#45;&gt;Product need -->\n",
       "<g id=\"edge11\" class=\"edge\">\n",
       "<title>Sales calls&#45;&gt;Product need</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M436.0495,-292.4574C416.99,-281.4791 389.8765,-265.8617 368.4683,-253.5306\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"370.0951,-250.4286 359.6828,-248.4701 366.6012,-256.4943 370.0951,-250.4286\"/>\n",
       "</g>\n",
       "<!-- Sales calls&#45;&gt;Did renew -->\n",
       "<g id=\"edge10\" class=\"edge\">\n",
       "<title>Sales calls&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M461.2685,-288.0197C464.3037,-246.1595 466.4418,-140.5489 419.5611,-72 407.2102,-53.9406 386.6465,-40.9427 368.291,-32.2311\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"369.507,-28.9411 358.9487,-28.0621 366.6544,-35.3335 369.507,-28.9411\"/>\n",
       "</g>\n",
       "<!-- Economy -->\n",
       "<g id=\"node4\" class=\"node\">\n",
       "<title>Economy</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"360.5611\" cy=\"-90\" rx=\"32.9303\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"360.5611\" y=\"-87.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Economy</text>\n",
       "</g>\n",
       "<!-- Economy&#45;&gt;Did renew -->\n",
       "<g id=\"edge9\" class=\"edge\">\n",
       "<title>Economy&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M352.8981,-72.2022C349.3694,-64.0064 345.1051,-54.1024 341.1923,-45.0145\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"344.3052,-43.3938 337.1358,-35.593 337.8758,-46.162 344.3052,-43.3938\"/>\n",
       "</g>\n",
       "<!-- Discount -->\n",
       "<g id=\"node5\" class=\"node\">\n",
       "<title>Discount</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"334.5611\" cy=\"-162\" rx=\"31.577\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"334.5611\" y=\"-159.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Discount</text>\n",
       "</g>\n",
       "<!-- Discount&#45;&gt;Did renew -->\n",
       "<g id=\"edge5\" class=\"edge\">\n",
       "<title>Discount&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M327.9083,-144.2896C324.3574,-133.8861 320.3574,-120.3861 318.5611,-108 315.5533,-87.2614 318.6484,-63.7539 322.3124,-45.9655\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"325.7828,-46.4847 324.5555,-35.9612 318.9524,-44.9532 325.7828,-46.4847\"/>\n",
       "</g>\n",
       "<!-- Last upgrade -->\n",
       "<g id=\"node6\" class=\"node\">\n",
       "<title>Last upgrade</title>\n",
       "<ellipse fill=\"none\" stroke=\"#000000\" cx=\"244.5611\" cy=\"-162\" rx=\"40.7358\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"244.5611\" y=\"-159.5\" font-family=\"Times,serif\" font-size=\"10.00\" fill=\"#000000\">Last upgrade</text>\n",
       "</g>\n",
       "<!-- Last upgrade&#45;&gt;Ad spend -->\n",
       "<g id=\"edge17\" class=\"edge\">\n",
       "<title>Last upgrade&#45;&gt;Ad spend</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M233.9099,-144.5708C228.6674,-135.9922 222.241,-125.4762 216.4336,-115.9732\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"219.3152,-113.9764 211.1141,-107.2687 213.3422,-117.6266 219.3152,-113.9764\"/>\n",
       "</g>\n",
       "<!-- Last upgrade&#45;&gt;Did renew -->\n",
       "<g id=\"edge16\" class=\"edge\">\n",
       "<title>Last upgrade&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M254.9837,-144.3428C269.7844,-119.2687 296.9938,-73.1728 314.1354,-44.1328\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"317.2494,-45.7427 319.3186,-35.3519 311.2212,-42.1844 317.2494,-45.7427\"/>\n",
       "</g>\n",
       "<!-- Interactions&#45;&gt;Did renew -->\n",
       "<g id=\"edge13\" class=\"edge\">\n",
       "<title>Interactions&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M524.734,-215.8711C522.2719,-182.9188 512.4825,-112.843 473.5611,-72 447.2171,-44.3554 405.3633,-30.7451 373.5522,-24.1163\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"374.0908,-20.6558 363.6092,-22.2005 372.7663,-27.5293 374.0908,-20.6558\"/>\n",
       "</g>\n",
       "<!-- Product need&#45;&gt;Bugs reported -->\n",
       "<g id=\"edge3\" class=\"edge\">\n",
       "<title>Product need&#45;&gt;Bugs reported</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M295.0199,-228.889C233.678,-220.3961 119.0471,-202.1051 84.5611,-180 50.8853,-158.4143 43.2102,-145.9473 30.5611,-108 23.8107,-87.7489 27.8179,-63.7824 33.1019,-45.6749\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"36.4767,-46.6126 36.1984,-36.0214 29.8113,-44.4745 36.4767,-46.6126\"/>\n",
       "</g>\n",
       "<!-- Product need&#45;&gt;Monthly usage -->\n",
       "<g id=\"edge4\" class=\"edge\">\n",
       "<title>Product need&#45;&gt;Monthly usage</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M302.7969,-222.2717C270.2436,-210.252 219.3901,-191.4753 183.0981,-178.0752\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"183.8686,-174.6288 173.2753,-174.4483 181.444,-181.1955 183.8686,-174.6288\"/>\n",
       "</g>\n",
       "<!-- Product need&#45;&gt;Discount -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>Product need&#45;&gt;Discount</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M334.5611,-215.8314C334.5611,-208.131 334.5611,-198.9743 334.5611,-190.4166\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"338.0612,-190.4132 334.5611,-180.4133 331.0612,-190.4133 338.0612,-190.4132\"/>\n",
       "</g>\n",
       "<!-- Product need&#45;&gt;Did renew -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>Product need&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M351.4292,-217.097C379.0811,-187.2449 428.5128,-123.4776 402.5611,-72 397.9078,-62.7699 378.8655,-48.8258 361.3972,-37.4195\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"362.8009,-34.1627 352.4905,-31.7244 359.03,-40.0602 362.8009,-34.1627\"/>\n",
       "</g>\n",
       "<!-- Bugs faced&#45;&gt;Bugs reported -->\n",
       "<g id=\"edge15\" class=\"edge\">\n",
       "<title>Bugs faced&#45;&gt;Bugs reported</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M67.6509,-72.2022C64.0355,-64.0675 59.6722,-54.2501 55.658,-45.2181\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"58.7509,-43.5592 51.4911,-35.8425 52.3542,-46.4022 58.7509,-43.5592\"/>\n",
       "</g>\n",
       "<!-- Bugs faced&#45;&gt;Did renew -->\n",
       "<g id=\"edge14\" class=\"edge\">\n",
       "<title>Bugs faced&#45;&gt;Did renew</title>\n",
       "<path fill=\"none\" stroke=\"#000000\" d=\"M104.7643,-79.0064C111.5532,-76.5848 118.7789,-74.114 125.5611,-72 181.3,-54.6257 246.6954,-37.957 288.1257,-27.8482\"/>\n",
       "<polygon fill=\"#000000\" stroke=\"#000000\" points=\"288.9735,-31.2441 297.8662,-25.4847 287.3228,-24.4415 288.9735,-31.2441\"/>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.dot.Digraph at 0x7fd1b7ebaa50>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import graphviz\n",
    "\n",
    "names = [\n",
    "    \"Bugs reported\",\n",
    "    \"Monthly usage\",\n",
    "    \"Sales calls\",\n",
    "    \"Economy\",\n",
    "    \"Discount\",\n",
    "    \"Last upgrade\",\n",
    "    \"Ad spend\",\n",
    "    \"Interactions\",\n",
    "]\n",
    "g = graphviz.Digraph()\n",
    "for name in names:\n",
    "    g.node(name, fontsize=\"10\")\n",
    "g.node(\"Product need\", style=\"dashed\", fontsize=\"10\")\n",
    "g.node(\"Bugs faced\", style=\"dashed\", fontsize=\"10\")\n",
    "g.node(\"Did renew\", style=\"filled\", fontsize=\"10\")\n",
    "\n",
    "g.edge(\"Product need\", \"Did renew\")\n",
    "g.edge(\"Product need\", \"Discount\")\n",
    "g.edge(\"Product need\", \"Bugs reported\")\n",
    "g.edge(\"Product need\", \"Monthly usage\")\n",
    "g.edge(\"Discount\", \"Did renew\")\n",
    "g.edge(\"Monthly usage\", \"Bugs faced\")\n",
    "g.edge(\"Monthly usage\", \"Did renew\")\n",
    "g.edge(\"Monthly usage\", \"Ad spend\")\n",
    "g.edge(\"Economy\", \"Did renew\")\n",
    "g.edge(\"Sales calls\", \"Did renew\")\n",
    "g.edge(\"Sales calls\", \"Product need\")\n",
    "g.edge(\"Sales calls\", \"Interactions\")\n",
    "g.edge(\"Interactions\", \"Did renew\")\n",
    "g.edge(\"Bugs faced\", \"Did renew\")\n",
    "g.edge(\"Bugs faced\", \"Bugs reported\")\n",
    "g.edge(\"Last upgrade\", \"Did renew\")\n",
    "g.edge(\"Last upgrade\", \"Ad spend\")\n",
    "g"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are lots of relationships in this graph, but the first important concern is that some of the features we can measure are influenced by **unmeasured confounding features** like product need and bugs faced. For example, users who report more bugs are encountering more bugs because they use the product more, and they are also more likely to report those bugs because they need the product more. Product need has its own direct causal effect on renewal. Because we can't directly measure product need, the correlation we end up capturing in predictive models between bugs reported and renewal combines a small negative direct effect of bugs faced and a large positive confounding effect from product need. The figure below plots the SHAP values in our example against the true causal effect of each feature (known in this example since we generated the data)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1080x360 with 16 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 320,
       "width": 918
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def marginal_effects(generative_model, num_samples=100, columns=None, max_points=20, logit=True, seed=0):\n",
    "    \"\"\"Helper function to compute the true marginal causal effects.\"\"\"\n",
    "    X = generative_model(num_samples)\n",
    "    if columns is None:\n",
    "        columns = X.columns\n",
    "    ys = [[] for _ in columns]\n",
    "    xs = [X[c].values for c in columns]\n",
    "    xs = np.sort(xs, axis=1)\n",
    "    xs = [xs[i] for i in range(len(xs))]\n",
    "    for i, c in enumerate(columns):\n",
    "        xs[i] = np.unique([np.nanpercentile(xs[i], v, method=\"nearest\") for v in np.linspace(0, 100, max_points)])\n",
    "        for x in xs[i]:\n",
    "            Xnew = generative_model(num_samples, fixed={c: x}, seed=seed)\n",
    "            val = Xnew[\"Did renew\"].mean()\n",
    "            if logit:\n",
    "                val = scipy.special.logit(val)\n",
    "            ys[i].append(val)\n",
    "        ys[i] = np.array(ys[i])\n",
    "    ys = [ys[i] - ys[i].mean() for i in range(len(ys))]\n",
    "    return list(zip(xs, ys))\n",
    "\n",
    "\n",
    "shap.plots.scatter(\n",
    "    shap_values,\n",
    "    ylabel=\"SHAP value\\n(higher means more likely to renew)\",\n",
    "    overlay={\"True causal effects\": marginal_effects(generator, 10000, X.columns)},\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The predictive model captures an overall positive effect of bugs reported on retention (as shown with SHAP), even though the causal effect of reporting a bug is zero, and the effect of encoutering a bug is negative.\n",
    "\n",
    "We see a similar problem with Discounts, which are also driven by unobserved customer need for the product. Our predictive model finds a negative relationship between discounts and retention, driven by this correlation with the unobserved feature, Product Need, even though there is actually a small positive causal effect of discounts on renewal! Put another way, if two customers with have the same Product Need and are otherwise similar, then the customer with the larger discount is more likely to renew.\n",
    "\n",
    "This plot also reveals a second, sneakier problem when we start to interpret predictive models as if they were causal. Notice that Ad Spend has a similar problem - it has no causal effect on retention (the black line is flat), but the predictive model is picking up a positive effect!\n",
    "\n",
    "In this case, Ad Spend is only driven by Last Upgrade and Monthly Usage, so we don't have an *unobserved* confounding problem, instead we have an *observed* confounding problem. There is statistical redundancy between Ad Spend and features that influence Ad Spend. When we have the same information captured by several features, predictive models can use any of those features for prediction, even though they are not all causal. While Ad Spend has no causal effect on renewal itself, it is strongly correlated with several features that do drive renewal. Our regularized model identifies Ad Spend as a useful predictor because it summarizes multiple causal drivers (so leading to a sparser model), but that becomes seriously misleading if we start to interpret it as a causal effect.\n",
    "\n",
    "We will now tackle each piece of our example in turn to illustrate when predictive models can accurately measure causal effects, and when they cannot. We will also introduce some causal tools that can sometimes estimate causal effects in cases where predictive models fail."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## When predictive models can answer causal questions\n",
    "\n",
    "Let's start with the successes in our example. Notice that our predictive model does a good job of capturing the real causal effect of the Economy feature (a better economy has a positive effect on retention). So when can we expect predictive models to capture true causal effects?\n",
    "\n",
    "The important ingredient that allowed XGBoost to get a good causal effect estimate for Economy is the feature's strong independent component (in this simulation); its predictive power for retention is not strongly redundant with any other measured features, or with any unmeasured confounders. In consequence, it is not subject to bias from either unmeasured confounders or feature redundancy."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 347,
       "width": 622
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Economy is independent of other measured features.\n",
    "shap.plots.bar(shap_values, clustering=clust, clustering_cutoff=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since we have added clustering to the right side of the SHAP bar plot we can see the redundancy structure of our data as a dendrogram. When features merge together at the bottom (left) of the dendrogram it means that that the information those features contain about the outcome (renewal) is very redundant and the model could have used either feature. When features merge together at the top (right) of the dendrogram it means the information they contain about the outcome is independent from each other.\n",
    "\n",
    "We can see that Economy is independent from all the other measured features by noting that Economy does not merge with any other features until the very top of the clustering dendrogram. This tells us that Economy does not suffer from observed confounding. But to trust that the Economy effect is causal we also need to check for unobserved confounding. Checking for unmeasured confounders is harder and requires using domain knowledge (provided by the business partners in our example above).\n",
    "\n",
    "For classic predictive ML models to deliver causal results the features need to be independent not only of other features in the model, but also of unobserved confounders. It's not common to find examples of drivers of interest that exhibit this level of independence naturally, but we can often find examples of independent features when our data contains some experiments."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## When predictive models cannot answer causal questions but causal inference methods can help\n",
    "\n",
    "In most real-world datasets features are not independent and unconfounded, so standard predictive models will not learn the true causal effects. As a result, explaining them with SHAP will not reveal causal effects. But all is not lost, sometimes we can fix or at least minimize this problem using the tools of observational causal inference.\n",
    "\n",
    "### Observed confounding\n",
    "The first scenario where causal inference can help is observed confounding. A feature is \"confounded\" when there is another feature that causally affects both the original feature and the outcome we are predicting. If we can measure that other feature it is called an *observed confounder*."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 347,
       "width": 622
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Ad spend is very redundant with Monthly usage and Last upgrade.\n",
    "shap.plots.bar(shap_values, clustering=clust, clustering_cutoff=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An example of this in our scenario is the Ad Spend feature. Even though Ad Spend has no direct causal effect on retention, it is correlated with the Last Upgrade and Monthly Usage features, which do drive retention. Our predictive model identifies Ad Spend as the one of the best single predictors of retention because it captures so many of the true causal drivers through correlations. XGBoost imposes regularization, which is a fancy way of saying that it tries to choose the simplest possible model that still predicts well. If it could predict equally well using one feature rather than three, it will tend to do that to avoid overfitting. But this means that if Ad Spend is highly correlated with both Last Upgrade and Monthly Usage, XGBoost may use Ad Spend instead of the causal features! This property of XGBoost (or any other machine learning model with regularization) is very useful for generating robust predictions of future retention, but not good for understanding which features we should manipulate if we want to increase retention.\n",
    "\n",
    "This highlights the importance of matching the right modeling tools to each question. Unlike the bug reporting example, there is nothing intuitively wrong with the conclusion that increasing ad spend increases retention. Without proper attention to what our predictive model is, and is not, measuring, we could easily have proceeded with this finding and only learned our mistake after increasing spending on advertising and not getting the renewal results we expected.\n",
    "\n",
    "### Observational Causal Inference\n",
    "The good news for Ad Spend is that we can measure all the features that could confound it (those features with arrows into Ad Spend in our causal graph above). Therefore, this is an example of observed confounding, and we should be able to disentangle the correlation patterns using only the data we've already collected; we just need to use the right tools from observational causal inference. These tools allow us to specify what features could confound Ad Spend and then adjust for those features, to get an **unconfounded** estimate of the causal effect of Ad Spend on product renewal.\n",
    "\n",
    "One particularly flexible tool for observational causal inference is double/debiased machine learning. It uses any machine learning model you want to first deconfound the feature of interest (i.e. Ad Spend) and then estimate the average causal effect of changing that feature (i.e. the average slope of the causal effect).\n",
    "\n",
    "Double ML works as follows:\n",
    "1. Train a model to predict a feature of interest (i.e. Ad Spend) using a set of possible confounders (i.e. any features not caused by Ad Spend).\n",
    "2. Train a model to predict the outcome (i.e. Did Renew) using the same set of possible confounders.\n",
    "3. Train a model to predict the residual variation of the outcome (the variation left after subtracting our prediction) using the residual variation of the causal feature of interest.\n",
    "\n",
    "The intuition is that if Ad Spend causes renewal, then the part of Ad Spend that can't be predicted by other confounding features should be correlated with the part of renewal that can't be predicted by other confounding features. Stated another way, double ML assumes that there is an independent (unobserved) noise feature that impacts Ad Spend (since Ad Spend is not perfectly determined by the other features), so we can impute the value of this independent noise feature and then train a model on this independent feature to predict the output.\n",
    "\n",
    "While we could do all the double ML steps manually, it is easier to use a causal inference package like econML or CausalML. Here we use econML's LinearDML model. This returns a P-value of whether that treatment has a non-zero a causal effect, and works beautifully in our scenario, correctly identifying that there is no evidence for a causal effect of ad spending on renewal (P-value = 0.85):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 360x216 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 214,
       "width": 346
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from econml.dml import LinearDML\n",
    "from sklearn.base import BaseEstimator, clone\n",
    "\n",
    "\n",
    "class RegressionWrapper(BaseEstimator):\n",
    "    \"\"\"Turns a classifier into a 'regressor'.\n",
    "\n",
    "    We use the regression formulation of double ML, so we need to approximate the classifer\n",
    "    as a regression model. This treats the probabilities as just quantitative value targets\n",
    "    for least squares regression, but it turns out to be a reasonable approximation.\n",
    "    \"\"\"\n",
    "\n",
    "    def __init__(self, clf):\n",
    "        self.clf = clf\n",
    "\n",
    "    def fit(self, X, y, **kwargs):\n",
    "        self.clf_ = clone(self.clf)\n",
    "        self.clf_.fit(X, y, **kwargs)\n",
    "        return self\n",
    "\n",
    "    def predict(self, X):\n",
    "        return self.clf_.predict_proba(X)[:, 1]\n",
    "\n",
    "\n",
    "# Run Double ML, controlling for all the other features\n",
    "def double_ml(y, causal_feature, control_features):\n",
    "    \"\"\"Use doubleML from econML to estimate the slope of the causal effect of a feature.\"\"\"\n",
    "    xgb_model = xgboost.XGBClassifier(objective=\"binary:logistic\", random_state=42)\n",
    "    est = LinearDML(model_y=RegressionWrapper(xgb_model))\n",
    "    est.fit(y, causal_feature, W=control_features)\n",
    "    return est.effect_inference()\n",
    "\n",
    "\n",
    "def plot_effect(effect, xs, true_ys, ylim=None):\n",
    "    \"\"\"Plot a double ML effect estimate from econML as a line.\n",
    "\n",
    "    Note that the effect estimate from double ML is an average effect *slope* not a full\n",
    "    function. So we arbitrarily draw the slope of the line as passing through the origin.\n",
    "    \"\"\"\n",
    "    plt.figure(figsize=(5, 3))\n",
    "\n",
    "    pred_xs = [xs.min(), xs.max()]\n",
    "    mid = (xs.min() + xs.max()) / 2\n",
    "    [effect.pred[0] * (xs.min() - mid), effect.pred[0] * (xs.max() - mid)]\n",
    "\n",
    "    plt.plot(xs, true_ys - true_ys[0], label=\"True causal effect\", color=\"black\", linewidth=3)\n",
    "    point_pred = effect.point_estimate * pred_xs\n",
    "    pred_stderr = effect.stderr * np.abs(pred_xs)\n",
    "    plt.plot(\n",
    "        pred_xs,\n",
    "        point_pred - point_pred[0],\n",
    "        label=\"Double ML slope\",\n",
    "        color=shap.plots.colors.blue_rgb,\n",
    "        linewidth=3,\n",
    "    )\n",
    "    # 99.9% CI\n",
    "    plt.fill_between(\n",
    "        pred_xs,\n",
    "        point_pred - point_pred[0] - 3.291 * pred_stderr,\n",
    "        point_pred - point_pred[0] + 3.291 * pred_stderr,\n",
    "        alpha=0.2,\n",
    "        color=shap.plots.colors.blue_rgb,\n",
    "    )\n",
    "    plt.legend()\n",
    "    plt.xlabel(\"Ad spend\", fontsize=13)\n",
    "    plt.ylabel(\"Zero centered effect\")\n",
    "    if ylim is not None:\n",
    "        plt.ylim(*ylim)\n",
    "    plt.gca().xaxis.set_ticks_position(\"bottom\")\n",
    "    plt.gca().yaxis.set_ticks_position(\"left\")\n",
    "    plt.gca().spines[\"right\"].set_visible(False)\n",
    "    plt.gca().spines[\"top\"].set_visible(False)\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "# estimate the causal effect of Ad spend controlling for all the other features\n",
    "causal_feature = \"Ad spend\"\n",
    "control_features = [\n",
    "    \"Sales calls\",\n",
    "    \"Interactions\",\n",
    "    \"Economy\",\n",
    "    \"Last upgrade\",\n",
    "    \"Discount\",\n",
    "    \"Monthly usage\",\n",
    "    \"Bugs reported\",\n",
    "]\n",
    "effect = double_ml(y, X[causal_feature], X.loc[:, control_features])\n",
    "\n",
    "# plot the estimated slope against the true effect\n",
    "xs, true_ys = marginal_effects(generator, 10000, X[[\"Ad spend\"]], logit=False)[0]\n",
    "plot_effect(effect, xs, true_ys, ylim=(-0.2, 0.2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Remember, double ML (or any other observational causal inference method) only works when you can measure and identify all the possible confounders of the feature for which you want to estimate causal effects. Here we know the causal graph and can see that Monthly Usage and Last Upgrade are the two direct confounders we need to control for. But if we didn't know the causal graph we could still look at the redundancy in the SHAP bar plot and see that Monthly Usage and Last Upgrade are the most redundant features and so are good candidates to control for (as are Discounts and Bugs Reported).\n",
    "\n",
    "### Non-confounding redundancy\n",
    "The second scenario where causal inference can help is non-confounding redundancy. This occurs when the feature we want causal effects for causally drives, or is driven by, another feature included in the model, but that other feature is not a confounder of our feature of interest."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 347,
       "width": 622
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Interactions and sales calls are very redundant with one another.\n",
    "shap.plots.bar(shap_values, clustering=clust, clustering_cutoff=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An example of this is the Sales Calls feature. Sales Calls directly impact retention, but also have an indirect effect on retention through Interactions. When we include both the Interactions and Sales Calls features in the model the causal effect shared by both features is forced to spread out between them. We can see this in the SHAP scatter plots above, which show how XGBoost underestimates the true causal effect of Sales Calls because most of that effect got put onto the Interactions feature.\n",
    "\n",
    "Non-confounding redundancy can be fixed in principle by removing the redundant variables from the model (see below). For example, if we removed Interactions from the model then we will capture the full effect of making a sales call on renewal probability. This removal is also important for double ML, since double ML will fail to capture indirect causal effects if you control for downstream features caused by the feature of interest. In this case double ML will only measure the \"direct\" effect that does not pass through the other feature. Double ML is however robust to controlling for upstream non-confounding redundancy (where the redundant feature causes the feature of interest), though this will reduce your statistical power to detect true effects.\n",
    "\n",
    "Unfortunately, we often don't know the true causal graph so it can be hard to know when another feature is redundant with our feature of interest because of observed confounding vs. non-confounding redundancy. If it is because of confounding then we should control for that feature using a method like double ML, whereas if it is a downstream consequence then we should drop the feature from our model if we want full causal effects rather than only direct effects. Controlling for a feature we shouldn't tends to hide or split up causal effects, while failing to control for a feature we should have controlled for tends to infer causal effects that do not exist. This generally makes controlling for a feature the safer option when you are uncertain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 320,
       "width": 399
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Fit, explain, and plot a univariate model with just Sales calls\n",
    "# Note how this model does not have to split of credit between Sales calls and\n",
    "# Interactions, so we get a better agreement with the true causal effect.\n",
    "sales_calls_model = fit_xgboost(X[[\"Sales calls\"]], y)\n",
    "sales_calls_shap_values = shap.Explainer(sales_calls_model)(X[[\"Sales calls\"]])\n",
    "shap.plots.scatter(\n",
    "    sales_calls_shap_values,\n",
    "    overlay={\"True causal effects\": marginal_effects(generator, 10000, [\"Sales calls\"])},\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## When neither predictive models nor unconfounding methods can answer causal questions\n",
    "\n",
    "Double ML (or any other causal inference method that assumes unconfoundedness) only works when you can measure and identify all the possible confounders of the feature for which you want to estimate causal effects. If you can't measure all the confounders then you are in the hardest possible scenario: unobserved confounding."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 347,
       "width": 622
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Discount and Bugs reported seem are fairly independent of the other features we can\n",
    "# measure, but they are not independent of Product need, which is an unobserved confounder.\n",
    "shap.plots.bar(shap_values, clustering=clust, clustering_cutoff=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Discount and Bugs Reported features both suffer from unobserved confounding because not all important variables (e.g., Product Need and Bugs Faced) are measured in the data. Even though both features are relatively independent of all the other features in the model, there are important drivers that are unmeasured. In this case, both predictive models and causal models that require confounders to be observed, like double ML, will fail. This is why double ML estimates a large negative causal effect for the Discount feature even when controlling for all other observed features:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 360x216 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 214,
       "width": 342
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# estimate the causal effect of Ad spend controlling for all the other features\n",
    "causal_feature = \"Discount\"\n",
    "control_features = [\n",
    "    \"Sales calls\",\n",
    "    \"Interactions\",\n",
    "    \"Economy\",\n",
    "    \"Last upgrade\",\n",
    "    \"Monthly usage\",\n",
    "    \"Ad spend\",\n",
    "    \"Bugs reported\",\n",
    "]\n",
    "effect = double_ml(y, X[causal_feature], X.loc[:, control_features])\n",
    "\n",
    "# plot the estimated slope against the true effect\n",
    "xs, true_ys = marginal_effects(generator, 10000, X[[causal_feature]], logit=False)[0]\n",
    "plot_effect(effect, xs, true_ys, ylim=(-0.5, 0.2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Barring the ability to measure the previously unmeasured features (or features correlated with them), finding causal effects in the presence of unobserved confounding is difficult. In these situations, the only way to identify causal effects that can inform policy is to create or exploit some randomization that breaks the correlation between the features of interest and the unmeasured confounders. Randomized experiments remain the gold standard for finding causal effects in this context.\n",
    "\n",
    "Specialized causal tools based on the principals of instrumental variables, differences-in-differences, or regression discontinuities can sometimes exploit partial randomization even in cases where a full experiment is impossible. For example, instrumental variable techniques can be used to identify causal effects in cases where we cannot randomly assign a treatment, but we can randomly nudge some customers towards treatment, like sending an email encouraging them to explore a new product feature. Difference-in-difference approaches can be helpful when the introduction of new treatments is staggered across groups. Finally, regression discontinuity approaches are a good option when patterns of treatment exhibit sharp cut-offs (for example qualification for treatment based on a specific, measurable trait like revenue over $5,000 per month)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Summary\n",
    "\n",
    "Flexible predictive models like XGBoost or LightGBM are powerful tools for solving prediction problems. However, they are not inherently causal models, so interpreting them with SHAP will fail to accurately answer causal questions in many common situations. Unless features in a model are the result of experimental variation, applying SHAP to predictive models without considering confounding is generally not an appropriate tool to measure causal impacts used to inform policy. SHAP and other interpretability tools can be useful for causal inference, and SHAP is integrated into many causal inference packages, but those use cases are explicitly causal in nature. To that end, using the same data we would collect for prediction problems and using causal inference methods like double ML that are particularly designed to return causal effects is often a good approach for informing policy. In other situations, only an experiment or other source of randomization can really answer what if questions. Causal inference always requires us to make important assumptions. The main point of this article is that the assumptions we make by interpreting a normal predictive model as causal are often unrealistic."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n",
    "\n",
    "Have a comment or question? Checkout [Github](https://github.com/shap/shap/blob/master/notebooks/overviews/Be%20careful%20when%20interpreting%20predictive%20models%20in%20search%20of%20causal%20insights.ipynb) or the [Medium](https://towardsdatascience.com/be-careful-when-interpreting-predictive-models-in-search-of-causal-insights-e68626e664b6) version of this article!"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}