{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read, clean, and validate\n",
    "> A Summary of lecture \"Exploratory Data Analysis in Python\", via datacamp\n",
    "\n",
    "- toc: true \n",
    "- badges: true\n",
    "- comments: true\n",
    "- author: Chanseok Kang\n",
    "- categories: [Python, Datacamp]\n",
    "- image: images/conception.png"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## DataFrames and Series\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exploring the NSFG data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "nsfg = pd.read_hdf('./dataset/nsfg.hdf5', 'nsfg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(9358, 10)\n",
      "Index(['caseid', 'outcome', 'birthwgt_lb1', 'birthwgt_oz1', 'prglngth',\n",
      "       'nbrnaliv', 'agecon', 'agepreg', 'hpagelb', 'wgt2013_2015'],\n",
      "      dtype='object')\n",
      "0     4.0\n",
      "1    12.0\n",
      "2     4.0\n",
      "3     NaN\n",
      "4    13.0\n",
      "Name: birthwgt_oz1, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Display the number of rows and columns\n",
    "print(nsfg.shape)\n",
    "\n",
    "# Display the names of the columns\n",
    "print(nsfg.columns)\n",
    "\n",
    "# Select columns birthwgt_oz1: ounces\n",
    "ounces = nsfg['birthwgt_oz1']\n",
    "\n",
    "# Print the first 5 elements of ounces\n",
    "print(ounces.head(5))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clean and Validate"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Clean a variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0    6379\n",
       "2.0     100\n",
       "3.0       5\n",
       "8.0       1\n",
       "Name: nbrnaliv, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nsfg['nbrnaliv'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0    6379\n",
      "2.0     100\n",
      "3.0       5\n",
      "Name: nbrnaliv, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# replace the value 8 with NaN\n",
    "nsfg['nbrnaliv'].replace([8], np.nan, inplace=True)\n",
    "\n",
    "# Print the values and their frequencies\n",
    "print(nsfg['nbrnaliv'].value_counts())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Compute a variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    9358.000000\n",
       "mean     2446.330199\n",
       "std       579.392363\n",
       "min       750.000000\n",
       "25%      1983.000000\n",
       "50%      2366.000000\n",
       "75%      2850.000000\n",
       "max      4350.000000\n",
       "Name: agecon, dtype: float64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nsfg['agecon'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    9109.000000\n",
       "mean     2494.934570\n",
       "std       578.099231\n",
       "min       825.000000\n",
       "25%      2041.000000\n",
       "50%      2416.000000\n",
       "75%      2900.000000\n",
       "max      4350.000000\n",
       "Name: agepreg, dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nsfg['agepreg'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count    9109.000000\n",
      "mean        0.552069\n",
      "std         0.271479\n",
      "min         0.000000\n",
      "25%         0.250000\n",
      "50%         0.670000\n",
      "75%         0.750000\n",
      "max         0.920000\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Select the columns and divide by 100\n",
    "agecon = nsfg['agecon'] / 100\n",
    "agepreg = nsfg['agepreg'] / 100\n",
    "\n",
    "# Compute the difference\n",
    "preg_length = agepreg - agecon\n",
    "\n",
    "# Compute summary statistics\n",
    "print(preg_length.describe())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Filter and visualize"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Make a histogram"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the histogram\n",
    "plt.hist(agecon, bins=20)\n",
    "\n",
    "# Label the axes\n",
    "plt.xlabel(\"Age at conception\")\n",
    "plt.ylabel('Number of pregnancies')\n",
    "plt.savefig('../images/conception.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of pregnancies')"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAEGCAYAAACdJRn3AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAb2klEQVR4nO3de7RV1Xn38e9PvIR4O6JHBjmgkJQ3jdFWkXgpqRJNUm8RNfhGXqPEYomtaU2bNkKahrTqGxx9o4kZiYaqEVsrXpIoURuleEscrxfwjsRIDdWDRjAK3ogGefrHmlu2h30Oa+1z1r6c8/uMscdea+659npYA/bDmnOuORURmJmZFbFVswMwM7P24+RhZmaFOXmYmVlhTh5mZlaYk4eZmRW2dbMDKMNuu+0WY8eObXYYZmZtZenSpS9GRGeeuoMyeYwdO5YlS5Y0Owwzs7Yi6b/z1nWzlZmZFebkYWZmhTl5mJlZYU4eZmZWmJOHmZkV5uRhZmaFOXmYmVlhpSUPSZdLWi3p8aqyf5b0C0mPSvqxpI6qz2ZLWiHpSUl/UlV+RCpbIWlWWfGamVl+Zd55XAEc0aNsEbB3RPwB8EtgNoCkvYCTgA+nY74naZikYcB3gSOBvYBpqa6ZmTVRaU+YR8Tdksb2KLutavdeYGrangIsiIg3gV9JWgEckD5bERFPA0hakOo+UVbc1liT5t7OqrXr6zq2q2M498w6bIAjMrM8mjk9yZ8C16TtLrJkUtGdygCe7VF+YK0vkzQTmAmwxx57DGigVp5Va9ezcu7RdR07dtbNAxyNmeXVlA5zSX8PbACuqhTVqBZ9lG9eGDEvIiZGxMTOzlzzepmZWZ0afuchaTpwDHB4bFpAvRsYU1VtNPBc2u6t3MzMmqShdx6SjgDOBo6NiDeqPloInCRpO0njgPHA/cADwHhJ4yRtS9apvrCRMZuZ2eZKu/OQdDUwGdhNUjcwh2x01XbAIkkA90bEGRGxTNK1ZB3hG4AzI+Lt9D1fAG4FhgGXR8SysmI2M7N8yhxtNa1G8WV91D8POK9G+S3ALQMYmpmZ9ZOfMDczs8KcPMzMrDAnDzMzK8zJw8zMCnPyMDOzwpw8zMysMCcPMzMrzMnDzMwKc/IwM7PCnDzMzKywZq7nYdYvXR3D617TwwtJmfWPk4e1rf78+HshKbP+cbOVmZkV5uRhZmaFOXmYmVlhTh5mZlaYk4eZmRXm5GFmZoU5eZiZWWFOHmZmVpgfErQhqT9Pp1eO9xPqNpQ5ediQ1N8ffj+hbkOdm63MzKwwJw8zMyvMycPMzAorLXlIulzSakmPV5WNkLRI0lPpfZdULkkXSVoh6VFJE6qOmZ7qPyVpelnxmplZfmXeeVwBHNGjbBawOCLGA4vTPsCRwPj0mglcDFmyAeYABwIHAHMqCcfMzJqntOQREXcDL/UongLMT9vzgeOqyq+MzL1Ah6RRwJ8AiyLipYh4GVjE5gnJzMwarNF9HiMj4nmA9L57Ku8Cnq2q153KeivfjKSZkpZIWrJmzZoBD9zMzDZplQ5z1SiLPso3L4yYFxETI2JiZ2fngAZnZmbv1ujk8UJqjiK9r07l3cCYqnqjgef6KDczsyZqdPJYCFRGTE0HbqwqPzWNujoIWJeatW4FPilpl9RR/slUZmZmTVTa9CSSrgYmA7tJ6iYbNTUXuFbSDOAZ4MRU/RbgKGAF8AZwGkBEvCTpHOCBVO+fIqJnJ7yZmTVYackjIqb18tHhNeoGcGYv33M5cPkAhmZmZv3UKh3mZmbWRraYPCSdJWmn1B9xmaQHJX2yEcGZmVlrynPn8acR8QpZZ3UnWX/E3FKjMjOzlpYneVSetTgK+EFEPELt5y/MzGyIyNNhvlTSbcA4YLakHYGN5YZl1tr6sxKhVyG0wSBP8pgB7As8HRFvSNqVNJTWbKjqz4+/VyG0wSBPs1UAewF/lfa3B95TWkRmZtby8iSP7wEHA5XnNl4FvltaRGZm1vLyNFsdGBETJD0EEBEvS9q25LjMzKyF5bnz+J2kYaTZbCV14g5zM7MhLU/yuAj4MbC7pPOAnwP/t9SozMyspW2x2SoirpK0lGxOKgHHRcTy0iMzM7OW1WvykLRTRLyS1hFfDVxd9dkIz25rVh8/I2KDQV93Hv8OHAMs5d2r9yntv7/EuMwGLT8jYoNBr8kjIo5J7+MaF46ZmbWDPLPqHi9p56r9DknHlRuWmZm1sjyjreZExLrKTkSsJVsV0MzMhqg8yaNWndJWIDQzs9aXJ3kskXSBpA9Ier+kC8k60c3MbIjKkzz+EngLuAa4Dvgtvaw3bmZmQ0OehwRfB2Y1IBYzM2sTW0wekv4X8LfA2Or6EeEnlczMhqg8Hd/XAZcAlwJvlxuOmZm1gzzJY0NEXFx6JGZm1jbyJI+fSPoLspl136wUem4rq5g093ZWrV1f17FdHcMHOBoza4Q8yWN6ev+7qrJ+zW0l6a+B09P3PEa2JvooYAEwAngQOCUi3pK0HXAlsD/wG+AzEbGy3nPbwFu1dj0r5x7d7DDMrIG2OFQ3IsbVePUncXSRrYc+MSL2BoYBJwHnAxdGxHjgZWBGOmQG8HJE/B5wYapnZmZNlOc5DyTtLel/Szq18urnebcGhkvaGngv8DxwGHB9+nw+UJk/a0raJ31+uCT18/xmZtYPeYbqzgEmA3sBtwBHkq0meGU9J4yIVZL+H/AMsB64jeyJ9bURsSFV6wa60nYX8Gw6doOkdcCuwIv1nN/MzPovz53HVLJVBH8dEacBfwhsV+8JJe1CdjcxDngfsD1ZQuqpsoZIrbuM6FkgaaakJZKWrFmzpt7wzMwshzzJY31EbAQ2SNqJbFXB/iwE9XHgVxGxJiJ+B/wI+COgIzVjAYwGnkvb3cAYgPT5zsBmI70iYl5ETIyIiZ2dnf0Iz8zMtiTvxIgdwL+QNS89CNzfj3M+Axwk6b2p7+Jw4AngDrK7HMhGeN2YtheyacTXVOD2iNjszsPMzBonz9xWf5E2L5H0U2CniHi03hNGxH2SridLQhuAh4B5wM3AAknnprLL0iGXAf8qaQXZHcdJ9Z7bzMwGRq51OdLw2j0r9SUdEhF313vSiJjD5gtKPQ0cUKPub4ET6z2XmZkNvDyjrc4HPkPWtFSZ2yqAupOHmZm1tzx3HscBH4yIN7dY08zMhoQ8HeZPA9uUHYiZmbWPPHcebwAPS1rMuydG/KvSojIzs5aWJ3ksTC8zMzMg31Dd+VuqY2ZmQ0ue0VaPsfl0IOuAJcC5EfGbMgIzM7PWlafZ6j/Ihuj+e9o/iWy+qXXAFcCnSonMzDbT1TGcsbNurvvYe2YdNsAR2VCVJ3lMiohJVfuPSbonIiZJ+mxZgZnZ5vrz419v0jGrJc9Q3R0kHVjZkXQAsEPa3VD7EDMzG8zy3HmcDlwuqZIwXgVOl7Q98I3SIjMzs5aVZ7TVA8A+knYGFBFrqz6+trTIzMysZW2x2UrSSEmXAQsiYq2kvSTN2NJxZmY2eOXp87gCuJVs1T+AXwJfLCsgMzNrfXmSx24RcS2wEbJ1xNk0u66ZmQ1BeZLH65J2JT0oKOkgsmc8zMxsiMoz2upvyOa2+oCke4BONi0Xa2ZmQ1CfyUPSVsB7gEOBD5I9Wf5kRPyuAbGZmVmL6jN5RMRGSd+MiIOBZQ2KyczMWlyePo/bJH1akkqPxszM2kLePo/tgbclrSdruoqI2KnUyMzMrGXlecJ8x0YEYmbl6s+MvJXjPSuvVeS580DSCcBHyYbr/iwibig1KjMbcP394fesvFYtz/Qk3wPOAB4DHgfOkPTdsgMzM7PWlefO41Bg74ioPCQ4nyyRmJnZEJVntNWTwB5V+2OAR8sJx8zM2kGe5LErsFzSnZLuBJ4AOiUtlLSwnpNK6pB0vaRfSFou6WBJIyQtkvRUet8l1ZWkiyStkPSopAn1nNPMzAZOnmarr5Vw3m8DP42IqZK2Bd4LfAVYHBFzJc0CZgFnA0cC49PrQODi9G5mZk2SZ6juXQN5Qkk7AYcAn0vf/xbwlqQpwORUbT5wJ1nymAJcmfpc7k13LaMi4vmBjMvMzPLL02w10N4PrAF+IOkhSZemJW1HVhJCet891e8Cnq06vjuVvYukmZKWSFqyZs2acv8EZmZDXDOSx9bABODiiNgPeJ2siao3taZFic0KIuZFxMSImNjZ2TkwkZqZWU29Jg9Ji9P7+QN8zm6gOyLuS/vXkyWTFySNSuccBayuqj+m6vjRwHMDHJOZmRXQ153HKEmHAsdK2k/ShOpXvSeMiF8Dz0r6YCo6nGwE10JgeiqbDtyYthcCp6ZRVwcB69zfYWbWXH11mH+NrDlpNHBBj88C6M9cB38JXJVGWj0NnEaWyK6VNAN4Bjgx1b0FOApYAbyR6pqZWRP1mjwi4nrgekn/EBHnDORJI+JhYGKNjw6vUTeAMwfy/GZm1j95huqeI+lYsuG1AHdGxE3lhmVmZq0sz8SI3wDOIuuXeAI4K5WZmdkQlecJ86OBfSNiI7wzMeJDwOwyAzMzs9aVaz0PoAN4KW3vXFIsZtbC+rOYlBeSGnzyJI9vAA9JuoPsgb1D8F2H2ZDTnx9/LyQ1+OTpML86zab7EbLkcXZ6VsPMzIaoXM1W6aG8uqZfNzOzwacZc1uZmVmbc/IwM7PC+kwekraS9HijgjEzs/bQZ/JIz3Y8ImmPvuqZmdnQkqfDfBSwTNL9ZGtvABARx5YWlZmZtbQ8yeMfS4/CzMzaSq41zCXtCYyPiP+U9F5gWPmhmZlZq8ozMeKfka329/1U1AXcUGZQZmbW2vIM1T0TmAS8AhARTwG7lxmUmZm1tjzJ482IeKuyI2lrspUEzcxsiMqTPO6S9BVguKRPANcBPyk3LDMza2V5kscsYA3wGPB5sjXFv1pmUGZm1tryjLbamBaAuo+suerJtK64mZkNUVtMHpKOBi4B/otsSvZxkj4fEf9RdnBmZtaa8jwk+E3gYxGxAkDSB4CbAScPM7MhKk+fx+pK4kieBlaXFI+ZmbWBXu88JJ2QNpdJugW4lqzP40TggQbEZmZmLaqvZqtPVW2/AByattcAu5QWkZmZtbxek0dEnFbmiSUNA5YAqyLiGEnjgAXACOBB4JSIeEvSdsCVwP7Ab4DPRMTKMmMzM7O+5ZnbapykCyT9SNLCymsAzn0WsLxq/3zgwogYD7wMzEjlM4CXI+L3gAtTPTMza6I8HeY3ACuB75CNvKq86iZpNHA0cGnaF3AY2QSMAPOB49L2lLRP+vzwVN/MzJokz1Dd30bERQN83m8BXwZ2TPu7AmsjYkPa7yabvZf0/ixARGyQtC7Vf7H6CyXNBGYC7LGHFz40MytTnjuPb0uaI+lgSRMqr3pPKOkYsuG/S6uLa1SNHJ9tKoiYFxETI2JiZ2dnveGZmVkOee489gFOIWtW2pjKIu3XYxJwrKSjgPcAO5HdiXRI2jrdfYwGnkv1u4ExQHea0Xdn4KU6z21mZgMgT/I4Hnh/9bTs/RERs4HZAJImA38bESdLug6YSjbiajpwYzpkYdr//+nz2z23lplZc+VJHo8AHZT/VPnZwAJJ5wIPAZel8suAf5W0guyO46SS4xiSJs29nVVr19d1bFfH8AGOxsxaXZ7kMRL4haQHgDcrhRFxbH9PHhF3Anem7aeBA2rU+S3ZU+1WolVr17Ny7tHNDsPM2kSe5DGn9CjMbFDr6hjO2Fk3133sPbPq7WK1suRZz+OuRgRiZoNXf3786006Vq4863m8yqahsdsC2wCvR8ROZQZmZmatK8+dx47V+5KOo0bfhJmZDR15HhJ8l4i4gfqf8TAzs0EgT7PVCVW7WwETqfGEt5mZDR15RltVr+uxgWySxCmlRGNmZm0hT59Hqet6mJlZ++lrGdqv9XFcRMQ5JcRjZmZtoK87j9drlG1PtjjTroCTh5nZENXXMrTvLPgkaUeylf9OI5u4sF+LQZmZWXvrs89D0gjgb4CTyVbzmxARLzciMDMza1199Xn8M3ACMA/YJyJea1hUZmbW0vp6SPBLwPuArwLPSXolvV6V9EpjwjMzs1bUV59H4afPzcxsaHCCMDOzwpw8zMysMCcPMzMrzMnDzMwKyzMxoplZ03gJ29bk5GFmLc1L2LYmN1uZmVlhTh5mZlaYk4eZmRXm5GFmZoU1PHlIGiPpDknLJS2TdFYqHyFpkaSn0vsuqVySLpK0QtKjkiY0OmYzM3u3Ztx5bAC+FBEfAg4CzpS0FzALWBwR44HFaR/gSGB8es0ELm58yGZmVq3hySMino+IB9P2q8ByoAuYQrZmCOn9uLQ9BbgyMvcCHZJGNThsMzOr0tQ+D0ljgf2A+4CREfE8ZAkG2D1V6wKerTqsO5X1/K6ZkpZIWrJmzZoywzYzG/Kaljwk7QD8EPhiRPS1PohqlMVmBRHzImJiREzs7OwcqDDNzKyGpiQPSduQJY6rIuJHqfiFSnNUel+dyruBMVWHjwaea1SsZma2uWaMthJwGbA8Ii6o+mghMD1tTwdurCo/NY26OghYV2neMjOz5mjG3FaTgFOAxyQ9nMq+AswFrpU0A3gGODF9dgtwFLACeAM4rbHhmplZTw1PHhHxc2r3YwAcXqN+AGeWGpSZmRXiJ8zNzKwwJw8zMyvM63mY2aDlhaTK4+RhZoOWF5Iqj5utzMysMCcPMzMrzMnDzMwKc/IwM7PCnDzMzKwwJw8zMyvMycPMzApz8jAzs8KcPMzMrDA/YT5ITJp7O6vWrq/7+K6O4QMYjZkNdk4eg8SqtetZOffoZodhZkOEk4eZWQ39mVSxcvxgnljRycPMrIb+/vAP9okV3WFuZmaFOXmYmVlhTh5mZlaYk4eZmRXm5GFmZoV5tJWZWQkG+/rpTh5mZiUY7Ounu9nKzMwKc/IwM7PC2qbZStIRwLeBYcClETG3ySGZmZWiHfpL2iJ5SBoGfBf4BNANPCBpYUQ80dzIBlZ/Zsb1rLhmg0c79Je0RfIADgBWRMTTAJIWAFOAUpJHf6c3r1dXx3DPjGtmbaFdkkcX8GzVfjdwYHUFSTOBmWn3NUlPNii2vHYDXuyrwn8Dmt2YYPqwxThbRLvECe0Tq+McWE2LU+cXPqQS6555D2iX5KEaZfGunYh5wLzGhFOcpCURMbHZcWyJ4xx47RKr4xxY7RIn1Bdru4y26gbGVO2PBp5rUixmZkNeuySPB4DxksZJ2hY4CVjY5JjMzIastmi2iogNkr4A3Eo2VPfyiFjW5LCKatkmtR4c58Brl1gd58BqlzihjlgVEVuuZWZmVqVdmq3MzKyFOHmYmVlhTh4lkHS5pNWSHq8qGyFpkaSn0vsuzYwxxVQrzq9LWiXp4fQ6qpkxppjGSLpD0nJJyySdlcpb6pr2EWdLXVNJ75F0v6RHUpz/mMrHSbovXc9r0uCUpuoj1isk/arqmu7b7Fghmw1D0kOSbkr7LXdNoWacha+nk0c5rgCO6FE2C1gcEeOBxWm/2a5g8zgBLoyIfdPrlgbHVMsG4EsR8SHgIOBMSXvRete0tzihta7pm8BhEfGHwL7AEZIOAs4ni3M88DIwo4kxVvQWK8DfVV3Th5sX4rucBSyv2m/FawqbxwkFr6eTRwki4m7gpR7FU4D5aXs+cFxDg6qhlzhbTkQ8HxEPpu1Xyf7Sd9Fi17SPOFtKZF5Lu9ukVwCHAden8qZfT+gz1pYjaTRwNHBp2hcteE17xlkvJ4/GGRkRz0P2IwPs3uR4+vIFSY+mZq2mN69VkzQW2A+4jxa+pj3ihBa7pqnZ4mFgNbAI+C9gbURsSFW6aZHE1zPWiKhc0/PSNb1Q0nZNDLHiW8CXgY1pf1da85r2jLOi0PV08rCeLgY+QNZE8DzwzeaGs4mkHYAfAl+MiFeaHU9vasTZctc0It6OiH3JZms4APhQrWqNjaq2nrFK2huYDfw+8BFgBHB2E0NE0jHA6ohYWl1co2pTr2kvcUId19PJo3FekDQKIL2vbnI8NUXEC+kf60bgX8h+WJpO0jZkP8hXRcSPUnHLXdNacbbqNQWIiLXAnWR9NB2SKg8Ot9wUQFWxHpGaCCMi3gR+QPOv6STgWEkrgQVkzVXfovWu6WZxSvq3eq6nk0fjLASmp+3pwI1NjKVXlR/j5Hjg8d7qNkpqO74MWB4RF1R91FLXtLc4W+2aSuqU1JG2hwMfJ+ufuQOYmqo1/XpCr7H+ouo/DSLrR2jqNY2I2RExOiLGkk2fdHtEnEyLXdNe4vxsPdezLaYnaTeSrgYmA7tJ6gbmAHOBayXNAJ4BTmxehJle4pychukFsBL4fNMC3GQScArwWGr7BvgKrXdNe4tzWotd01HAfGWLrG0FXBsRN0l6Algg6VzgIbJE2Gy9xXq7pE6ypqGHgTOaGWQfzqb1rmktVxW9np6exMzMCnOzlZmZFebkYWZmhTl5mJlZYU4eZmZWmJOHmZkV5uRhg4Kk4yWFpN9vwLkmS/qjss8zECR9TtL7qvYvrZqs0axuTh42WEwDfk724FPZJgNtkTyAzwHvJI+IOD0inmheODZYOHlY20tzSU0im+76pKryrSR9L60DcZOkWyRNTZ/tL+kuSUsl3drjKfDK8Z9KazE8JOk/JY1MEx6eAfx1Wvfgj3vGIukHkh5Lk8x9OpVPS2WPSzq/qv5rks5Ttl7FvZJGpvKRkn6cyh+p3OlI+qyy9S0elvT99PBc5Xu+KelBSYvTk9lTgYlkD4A9LGm4pDslTawnJrNqTh42GBwH/DQifgm8JGlCKj8BGAvsA5wOHAzvzD/1HWBqROwPXA6cV+N7fw4cFBH7kc0D9OWIWAlcwqb1OX7W45h/ANZFxD4R8QfA7anZ6Hyy+Y72BT4iqTI19/bAvWm9iruBP0vlFwF3pfIJwDJJHwI+A0xKEwW+DZxc9T0PRsQE4C5gTkRcDywBTk6xrq8EWWdMZu/w9CQ2GEwjm4QOsh/5acCDwEeB69KEhL+WdEeq80Fgb2BRNpUPw8hmu+1pNHBNuivZFvhVjlg+TtXdT0S8LOkQ4M6IWAMg6SrgEOAG4C3gplR9KfCJtH0YcGr6jreBdZJOAfYHHkhxD2fTZJAbgWvS9r8Blckje/OROmIye4eTh7U1SbuS/dDuLSnIEkFI+jK1p8QmlS+LiIO38PXfAS6IiIWSJgNfzxMSm0+73VscAL+LTXMEvU3f/yYFzI+I2Tni2NK8QwMVkw1RbraydjcVuDIi9oyIsRExhuwO4aNkzU6fTn0fI8k6ugGeBDolvdOMJenDNb57Z2BV2p5eVf4qsGMv8dwGfKGyo2zhp/uAQyXtlvooppE1LfVlMfDn6TuGSdoplU2VtHsqHyFpz1R/KzbN3vp/0p+9r1jricnsHU4e1u6mAT/uUfZDsh/QH5Kt3vY48H2yH8x1EfEW2Q/t+ZIeIZtFtNboqa8D10n6GfBiVflPgONrdZgD5wK7pE7oR4CPpVUOZ5NNz/0IWd/ElqbmPgv4mKTHyJqOPpxGSX0VuE3So2QrAFY6+l8HPixpKdmd2D+l8iuASyod5pUvrzMms3d4Vl0b1CTtEBGvpeat+8k6m3/d7LgGmqTXImKHZsdhQ4fbMm2wu0nZYkLbAucMxsRh1gy+8zAzs8Lc52FmZoU5eZiZWWFOHmZmVpiTh5mZFebkYWZmhf0Pmga/Fj739S4AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the histogram\n",
    "plt.hist(agecon, bins=20, histtype='step')\n",
    "\n",
    "# Label the axes\n",
    "plt.xlabel(\"Age at conception\")\n",
    "plt.ylabel('Number of pregnancies')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Compute birth weight"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def resample_rows_weighted(df, column='wgt2013_2015'):\n",
    "    \"\"\"Resamples a DataFrame using probabilities proportional to given column.\n",
    "    Args:\n",
    "        df: DataFrame\n",
    "        column: string column name to use as weights\n",
    "    returns: \n",
    "        DataFrame\n",
    "    \"\"\"\n",
    "    weights = df[column].copy()\n",
    "    weights /= sum(weights)\n",
    "    indices = np.random.choice(df.index, len(df), replace=True, p=weights)\n",
    "    sample = df.loc[indices]\n",
    "    return sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Resample the data\n",
    "nsfg = resample_rows_weighted(nsfg, 'wgt2013_2015')\n",
    "\n",
    "# Clean the weight variables\n",
    "pounds = nsfg['birthwgt_lb1'].replace([98, 99], np.nan)\n",
    "ounces = nsfg['birthwgt_oz1'].replace([98, 99], np.nan)\n",
    "\n",
    "# Compute total birth weight\n",
    "birth_weight = pounds + ounces/16"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7.409452970741339\n"
     ]
    }
   ],
   "source": [
    "# Create a Boolean Series for full-term babies\n",
    "full_term = nsfg['prglngth'] >= 37\n",
    "\n",
    "# Select the weights of full-term babies\n",
    "full_term_weight = birth_weight[full_term]\n",
    "\n",
    "# Compute the mean weight of full-term babies\n",
    "print(full_term_weight.mean())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Single full-term mean: 7.421643309222423\n",
      "Multiple full-term mean: 5.765243902439025\n"
     ]
    }
   ],
   "source": [
    "# Filter full-term babies\n",
    "full_term = nsfg['prglngth'] >= 37\n",
    "\n",
    "# Filter single birth\n",
    "single = nsfg['nbrnaliv'] == 1\n",
    "\n",
    "# Compute birth weight for single full-term babies\n",
    "single_full_term_weight = birth_weight[single & full_term]\n",
    "print('Single full-term mean:', single_full_term_weight.mean())\n",
    "\n",
    "# Compute birth weight for multiple full-term babies\n",
    "mult_full_term_weight = birth_weight[~single & full_term]\n",
    "print('Multiple full-term mean:', mult_full_term_weight.mean())"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}