{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Demo for the DoWhy causal API\n",
    "We show a simple example of adding a causal extension to any dataframe. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dowhy.datasets\n",
    "import dowhy.api\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from statsmodels.api import OLS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = dowhy.datasets.linear_dataset(beta=5,\n",
    "        num_common_causes=1,\n",
    "        num_instruments = 0,\n",
    "        num_samples=1000,\n",
    "        treatment_is_binary=True)\n",
    "df = data['df']\n",
    "df['y'] = df['y'] + np.random.normal(size=len(df)) # Adding noise to data. Without noise, the variance in Y|X, Z is zero, and mcmc fails.\n",
    "#data['dot_graph'] = 'digraph { v ->y;X0-> v;X0-> y;}'\n",
    "\n",
    "treatment= data[\"treatment_name\"][0]\n",
    "outcome = data[\"outcome_name\"][0]\n",
    "common_cause = data[\"common_causes_names\"][0]\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# data['df'] is just a regular pandas.DataFrame\n",
    "df.causal.do(x=treatment,\n",
    "                     variable_types={treatment: 'b', outcome: 'c', common_cause: 'c'},\n",
    "                     outcome=outcome,\n",
    "                     common_causes=[common_cause],\n",
    "                     proceed_when_unidentifiable=True).groupby(treatment).mean().plot(y=outcome, kind='bar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.causal.do(x={treatment: 1}, \n",
    "              variable_types={treatment:'b', outcome: 'c', common_cause: 'c'}, \n",
    "              outcome=outcome,\n",
    "              method='weighting', \n",
    "              common_causes=[common_cause],\n",
    "              proceed_when_unidentifiable=True).groupby(treatment).mean().plot(y=outcome, kind='bar')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cdf_1 = df.causal.do(x={treatment: 1}, \n",
    "              variable_types={treatment: 'b', outcome: 'c', common_cause: 'c'}, \n",
    "              outcome=outcome, \n",
    "              dot_graph=data['dot_graph'],\n",
    "              proceed_when_unidentifiable=True)\n",
    "\n",
    "cdf_0 = df.causal.do(x={treatment: 0}, \n",
    "              variable_types={treatment: 'b', outcome: 'c', common_cause: 'c'}, \n",
    "              outcome=outcome, \n",
    "              dot_graph=data['dot_graph'],\n",
    "              proceed_when_unidentifiable=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "cdf_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cdf_1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Comparing the estimate to Linear Regression\n",
    "First, estimating the effect using the causal data frame, and the 95% confidence interval."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "(cdf_1['y'] - cdf_0['y']).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "1.96*(cdf_1['y'] - cdf_0['y']).std() / np.sqrt(len(df))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Comparing to the estimate from OLS."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = OLS(np.asarray(df[outcome]), np.asarray(df[[common_cause, treatment]], dtype=np.float64))\n",
    "result = model.fit()\n",
    "result.summary()"
   ]
  }
 ],
 "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": "3.8.5"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}