{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## collections_email"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "np.random.seed(24)\n",
    "n = 5000\n",
    "email = np.random.binomial(1, 0.5, n)\n",
    "\n",
    "credit_limit = np.random.gamma(6, 200, n)\n",
    "risk_score = np.random.beta(credit_limit, credit_limit.mean(), n)\n",
    "\n",
    "opened = np.random.normal(5 + 0.001*credit_limit - 4*risk_score, 2)\n",
    "opened = (opened > 4).astype(float) * email\n",
    "\n",
    "\n",
    "agreement = np.random.normal(30 +(-0.003*credit_limit - 10*risk_score), 7) * 2 * opened\n",
    "agreement = (agreement > 40).astype(float)\n",
    "\n",
    "payments = (np.random.normal(500 + 0.16*credit_limit - 40*risk_score + 11*agreement + email, 75).astype(int) // 10) * 10\n",
    "\n",
    "data = pd.DataFrame(dict(payments=payments,\n",
    "                         email=email,\n",
    "                         opened=opened,\n",
    "                         agreement=agreement,\n",
    "                         credit_limit=credit_limit,\n",
    "                         risk_score=risk_score))\n",
    "\n",
    "data.to_csv(\"collections_email.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## hospital_treatment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "np.random.seed(24)\n",
    "n = 80\n",
    "\n",
    "hospital = np.random.binomial(1, 0.5, n)\n",
    "\n",
    "treatment = np.where(hospital.astype(bool),\n",
    "                     np.random.binomial(1, 0.9, n),\n",
    "                     np.random.binomial(1, 0.1, n))\n",
    "\n",
    "severity = np.where(hospital.astype(bool), \n",
    "                    np.random.normal(20, 5, n),\n",
    "                    np.random.normal(10, 5, n))\n",
    "\n",
    "days = np.random.normal(15 + -5*treatment + 2*severity, 7).astype(int)\n",
    "\n",
    "hospital = pd.DataFrame(dict(hospital=hospital,\n",
    "                             treatment=treatment,\n",
    "                             severity=severity,\n",
    "                             days=days))\n",
    "\n",
    "hospital.to_csv(\"hospital_treatment.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## app engagement push"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "np.random.seed(24)\n",
    "n = 10000\n",
    "\n",
    "push_assigned = np.random.binomial(1, 0.5, n)\n",
    "\n",
    "income = np.random.gamma(6, 200, n)\n",
    "\n",
    "push_delivered = np.random.normal(5 + 0.3+income, 500)\n",
    "push_delivered = ((push_delivered > 800) & (push_assigned == 1)).astype(int)\n",
    "\n",
    "in_app_purchase = (np.random.normal(100 + 20*push_delivered + 0.5*income, 75).astype(int) // 10)\n",
    "\n",
    "data = pd.DataFrame(dict(in_app_purchase=in_app_purchase,\n",
    "                         push_assigned=push_assigned,\n",
    "                         push_delivered=push_delivered))\n",
    "\n",
    "data.to_csv(\"app_engagement_push.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Drug Impact"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "def make_confounded_data(N):\n",
    "\n",
    "    def get_severity(df):\n",
    "        return ((np.random.beta(1, 3, size=df.shape[0]) * (df[\"age\"] < 30)) +\n",
    "                (np.random.beta(3, 1.5, size=df.shape[0]) * (df[\"age\"] >= 30)))\n",
    "\n",
    "    def get_treatment(df):\n",
    "        return ((.33 * df[\"sex\"] +\n",
    "                1.5 * df[\"severity\"] +  df[\"severity\"] ** 2 +\n",
    "                0.15 * np.random.normal(size=df.shape[0])) > 1.5).astype(int)\n",
    "\n",
    "    def get_recovery(df):\n",
    "        return ((2 +\n",
    "                0.5 * df[\"sex\"] +\n",
    "                0.03 * df[\"age\"] + 0.03 * ((df[\"age\"] * 0.1) ** 2) +\n",
    "                df[\"severity\"] + np.log(df[\"severity\"]) +\n",
    "                df[\"sex\"] * df[\"severity\"] -\n",
    "                df[\"medication\"]) * 10).astype(int)\n",
    "\n",
    "    np.random.seed(1111)\n",
    "    sexes = np.random.randint(0, 2, size=N)\n",
    "    ages = np.random.gamma(8, scale=4, size=N)\n",
    "    meds = np.random.beta(1, 1, size=N)\n",
    "\n",
    "    # dados com designação aleatória\n",
    "    df_rnd = pd.DataFrame(dict(sex=sexes, age=ages, medication=meds))\n",
    "    df_rnd['severity'] = get_severity(df_rnd)\n",
    "    df_rnd['recovery'] = get_recovery(df_rnd)\n",
    "\n",
    "    features = ['sex', 'age', 'severity', 'medication', 'recovery']\n",
    "    df_rnd = df_rnd[features]  # to enforce column order\n",
    "\n",
    "    # dados observacionais\n",
    "    df_obs = df_rnd.copy()\n",
    "    df_obs['medication'] = get_treatment(df_obs)\n",
    "    df_obs['recovery'] = get_recovery(df_obs)\n",
    "\n",
    "    # dados contrafactuais data\n",
    "    df_ctf = df_obs.copy()\n",
    "    df_ctf['medication'] = ((df_ctf['medication'] == 1) ^ 1).astype(float)\n",
    "    df_ctf['recovery'] = get_recovery(df_ctf)\n",
    "\n",
    "    return df_rnd, df_obs, df_ctf\n",
    "\n",
    "np.random.seed(1234)\n",
    "df_rnd, df_obs, df_ctf = make_confounded_data(20000)\n",
    "\n",
    "df_obs.to_csv(\"medicine_impact_recovery.csv\", index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Bilboard Mkt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "np.random.seed(123)\n",
    "POAMay = np.random.gamma(7,10, 500) * np.random.binomial(1, .7, 500)\n",
    "POAJul = np.random.gamma(7,15, 800) * np.random.binomial(1, .8, 800)\n",
    "FLMay = np.random.gamma(10,20, 1300) * np.random.binomial(1, .85, 1300)\n",
    "FLJul = np.random.gamma(11,21, 2000) * np.random.binomial(1, .9, 2000)\n",
    "\n",
    "data = pd.concat([\n",
    "    pd.DataFrame(dict(deposits = POAMay.astype(int), poa=1, jul=0)),\n",
    "    pd.DataFrame(dict(deposits = POAJul.astype(int), poa=1, jul=1)),\n",
    "    pd.DataFrame(dict(deposits = FLMay.astype(int), poa=0, jul=0)),\n",
    "    pd.DataFrame(dict(deposits = FLJul.astype(int), poa=0, jul=1))\n",
    "])\n",
    "data.to_csv(\"billboard_impact.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}