{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Age at first marriage\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 2;\n",
       "            var nbb_formatted_code = \"%load_ext nb_black\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%load_ext nb_black"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 3;\n",
       "            var nbb_formatted_code = \"import pandas as pd\\nimport numpy as np\\nimport matplotlib.pyplot as plt\\nimport seaborn as sns\\n\\nfrom lifelines import KaplanMeierFitter\\n\\nfrom utils import decorate\\nfrom utils import value_counts\\nfrom utils import resample_by_cycle\\nfrom utils import round_into_bins\\nfrom utils import remove_spines\\n\\nfrom empiricaldist import Pmf, Cdf\\n\\nrandom_seed = 1\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from lifelines import KaplanMeierFitter\n",
    "\n",
    "from utils import decorate\n",
    "from utils import value_counts\n",
    "from utils import resample_by_cycle\n",
    "from utils import round_into_bins\n",
    "from utils import remove_spines\n",
    "\n",
    "from empiricaldist import Pmf, Cdf\n",
    "\n",
    "random_seed = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 4;\n",
       "            var nbb_formatted_code = \"# Make the figures smaller to save some screen real estate.\\nplt.rcParams[\\\"figure.dpi\\\"] = 75\\nplt.rcParams[\\\"figure.figsize\\\"] = [5, 3.7]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make the figures smaller to save some screen real estate.\n",
    "plt.rcParams[\"figure.dpi\"] = 75\n",
    "plt.rcParams[\"figure.figsize\"] = [5, 3.7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 5;\n",
       "            var nbb_formatted_code = \"from utils import set_palette, resample_by_cycle\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from utils import set_palette, resample_by_cycle"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Age at first marriage, female respondents\n",
    "\n",
    "Load the data cleaned in `clean_nsfg.ipynb` and run the analysis with `lifelines`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 57.1 ms, sys: 19 ms, total: 76.2 ms\n",
      "Wall time: 80.9 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(75769, 46)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 6;\n",
       "            var nbb_formatted_code = \"%time resp = pd.read_hdf('FemMarriageData.hdf', 'FemMarriageData')\\nresp.shape\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%time resp = pd.read_hdf('FemMarriageData.hdf', 'FemMarriageData')\n",
    "resp.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "evrmarry\n",
       "False    36608\n",
       "True     39161\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 7;\n",
       "            var nbb_formatted_code = \"evrmarry = resp[\\\"evrmarry\\\"]\\nvalue_counts(evrmarry)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evrmarry = resp[\"evrmarry\"]\n",
    "value_counts(evrmarry)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "30 0\n",
      "40 9\n",
      "50 18\n",
      "60 33\n",
      "70 40\n",
      "80 21\n",
      "90 2\n",
      "100 1\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 8;\n",
       "            var nbb_formatted_code = \"for name, group in resp.groupby(\\\"birth_index\\\"):\\n    missing = group[\\\"evrmarry\\\"] & group[\\\"agemarry\\\"].isna()\\n    print(name, missing.sum())\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for name, group in resp.groupby(\"birth_index\"):\n",
    "    missing = group[\"evrmarry\"] & group[\"agemarry\"].isna()\n",
    "    print(name, missing.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 9;\n",
       "            var nbb_formatted_code = \"sample = resample_by_cycle(resp)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = resample_by_cycle(resp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "birth_index\n",
       "30       352\n",
       "40      3866\n",
       "50     10471\n",
       "60     15382\n",
       "70     18116\n",
       "80     15471\n",
       "90      9473\n",
       "100     2638\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 10;\n",
       "            var nbb_formatted_code = \"value_counts(sample[\\\"birth_index\\\"])\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "value_counts(sample[\"birth_index\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 11;\n",
       "            var nbb_formatted_code = \"def drop_missing(df):\\n    # find people who are married but have no agemarry\\n    missing = df[\\\"evrmarry\\\"] & df[\\\"agemarry\\\"].isna()\\n    return df[~missing]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def drop_missing(df):\n",
    "    # find people who are married but have no agemarry\n",
    "    missing = df[\"evrmarry\"] & df[\"agemarry\"].isna()\n",
    "    return df[~missing]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 12;\n",
       "            var nbb_formatted_code = \"def fill_missing(df):\\n    for cohort in range(30, 110, 10):\\n        # find people in this cohort who are married but have no agemarry\\n        missing = (df[\\\"birth_index\\\"] == cohort) & df[\\\"evrmarry\\\"] & df[\\\"agemarry\\\"].isna()\\n        n = missing.sum()\\n        if n == 0:\\n            continue\\n\\n        # find people in this cohort who have been married once\\n        donors = (df[\\\"birth_index\\\"] == cohort) & df[\\\"evrmarry\\\"] & df[\\\"agemarry\\\"].notna()\\n\\n        # select their ages when married\\n        agemarry = df.loc[donors, \\\"agemarry\\\"]\\n        low, high = np.percentile(agemarry, [1, 99])\\n        index = agemarry.between(low, high)\\n\\n        # fill missing data with a random sample\\n        sample = np.random.choice(agemarry[index], size=n, replace=True)\\n        df.loc[missing, \\\"agemarry\\\"] = sample\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def fill_missing(df):\n",
    "    for cohort in range(30, 110, 10):\n",
    "        # find people in this cohort who are married but have no agemarry\n",
    "        missing = (df[\"birth_index\"] == cohort) & df[\"evrmarry\"] & df[\"agemarry\"].isna()\n",
    "        n = missing.sum()\n",
    "        if n == 0:\n",
    "            continue\n",
    "\n",
    "        # find people in this cohort who have been married once\n",
    "        donors = (df[\"birth_index\"] == cohort) & df[\"evrmarry\"] & df[\"agemarry\"].notna()\n",
    "\n",
    "        # select their ages when married\n",
    "        agemarry = df.loc[donors, \"agemarry\"]\n",
    "        low, high = np.percentile(agemarry, [1, 99])\n",
    "        index = agemarry.between(low, high)\n",
    "\n",
    "        # fill missing data with a random sample\n",
    "        sample = np.random.choice(agemarry[index], size=n, replace=True)\n",
    "        df.loc[missing, \"agemarry\"] = sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 13;\n",
       "            var nbb_formatted_code = \"# fill_missing(sample)\\nsample = drop_missing(sample)\\n\\nmissing = sample[\\\"evrmarry\\\"] & sample[\\\"agemarry\\\"].isna()\\nmissing.sum()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# fill_missing(sample)\n",
    "sample = drop_missing(sample)\n",
    "\n",
    "missing = sample[\"evrmarry\"] & sample[\"agemarry\"].isna()\n",
    "missing.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 14;\n",
       "            var nbb_formatted_code = \"cdf = Cdf.from_seq(sample[\\\"ager\\\"], name=\\\"age\\\")\\ncdf.plot()\\ndecorate()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cdf = Cdf.from_seq(sample[\"ager\"], name=\"age\")\n",
    "cdf.plot()\n",
    "decorate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 15;\n",
       "            var nbb_formatted_code = \"cdf = Cdf.from_seq(sample[\\\"agemarry\\\"], name=\\\"agemarry\\\")\\ncdf.plot()\\ndecorate()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cdf = Cdf.from_seq(sample[\"agemarry\"], name=\"agemarry\")\n",
    "cdf.plot()\n",
    "decorate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 16;\n",
       "            var nbb_formatted_code = \"from utils import make_kmf_map\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from utils import make_kmf_map"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 17;\n",
       "            var nbb_formatted_code = \"evrmarry = sample[\\\"evrmarry\\\"]\\nsample[\\\"observed\\\"] = evrmarry\\nsample.loc[evrmarry, \\\"duration\\\"] = sample[\\\"agemarry\\\"]\\nsample.loc[~evrmarry, \\\"duration\\\"] = sample[\\\"ager\\\"]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evrmarry = sample[\"evrmarry\"]\n",
    "sample[\"observed\"] = evrmarry\n",
    "sample.loc[evrmarry, \"duration\"] = sample[\"agemarry\"]\n",
    "sample.loc[~evrmarry, \"duration\"] = sample[\"ager\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 18;\n",
       "            var nbb_formatted_code = \"grouped = sample.groupby(\\\"birth_index\\\")\\nnsfg_map = make_kmf_map(grouped)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "grouped = sample.groupby(\"birth_index\")\n",
    "nsfg_map = make_kmf_map(grouped)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 19;\n",
       "            var nbb_formatted_code = \"from utils import add_text\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from utils import add_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 20;\n",
       "            var nbb_formatted_code = \"def make_title(title, subtitle, pad=30):\\n    plt.title(title, loc=\\\"left\\\", pad=pad)\\n    add_text(0, 1.085, subtitle)\\n    add_text(0, 1.015, \\\"Analysis: allendowney.com/blog\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def make_title(title, subtitle, pad=30):\n",
    "    plt.title(title, loc=\"left\", pad=pad)\n",
    "    add_text(0, 1.085, subtitle)\n",
    "    add_text(0, 1.015, \"Analysis: allendowney.com/blog\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 21;\n",
       "            var nbb_formatted_code = \"def decorate_plot(subtitle=\\\"\\\", **options):\\n    decorate(\\n        xlabel=\\\"Age\\\",\\n        ylabel=\\\"Percent\\\",\\n        xlim=[13, 55],\\n        **options,\\n    )\\n    title = \\\"Percent ever married\\\"\\n    make_title(title, subtitle)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def decorate_plot(subtitle=\"\", **options):\n",
    "    decorate(\n",
    "        xlabel=\"Age\",\n",
    "        ylabel=\"Percent\",\n",
    "        xlim=[13, 55],\n",
    "        **options,\n",
    "    )\n",
    "    title = \"Percent ever married\"\n",
    "    make_title(title, subtitle)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 22;\n",
       "            var nbb_formatted_code = \"def plot_kmf_map(ax, kmf_map, cohorts, **options):\\n    \\\"\\\"\\\" \\\"\\\"\\\"\\n    palette = set_palette(\\\"nipy_spectral\\\", len(cohorts), reverse=True)\\n    for cohort in cohorts:\\n        series = kmf_map[cohort]\\n        label = f\\\"{cohort+1900}s\\\"\\n        series.plot(ax=ax, label=label, **options)\\n        label = \\\"\\\"\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_kmf_map(ax, kmf_map, cohorts, **options):\n",
    "    \"\"\" \"\"\"\n",
    "    palette = set_palette(\"nipy_spectral\", len(cohorts), reverse=True)\n",
    "    for cohort in cohorts:\n",
    "        series = kmf_map[cohort]\n",
    "        label = f\"{cohort+1900}s\"\n",
    "        series.plot(ax=ax, label=label, **options)\n",
    "        label = \"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 23;\n",
       "            var nbb_formatted_code = \"cohorts = range(40, 110, 10)\\n\\nfig, ax = plt.subplots()\\nplot_kmf_map(ax, nsfg_map, cohorts)\\ndecorate_plot(subtitle=\\\"Females by decade of birth, NSFG 1982-2023\\\")\\nremove_spines()\\nplt.tight_layout()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cohorts = range(40, 110, 10)\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "plot_kmf_map(ax, nsfg_map, cohorts)\n",
    "decorate_plot(subtitle=\"Females by decade of birth, NSFG 1982-2023\")\n",
    "remove_spines()\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 24;\n",
       "            var nbb_formatted_code = \"def make_kmf_series(resp, iters=21):\\n    kmf_series = {}\\n\\n    for i in range(iters):\\n        sample = resample_by_cycle(resp)\\n        sample = drop_missing(sample)\\n        evrmarry = sample[\\\"evrmarry\\\"]\\n        sample[\\\"observed\\\"] = evrmarry\\n        sample.loc[evrmarry, \\\"duration\\\"] = sample[\\\"agemarry\\\"]\\n        sample.loc[~evrmarry, \\\"duration\\\"] = sample[\\\"ager\\\"]\\n        grouped = sample.groupby(\\\"birth_index\\\")\\n        kmf_map = make_kmf_map(grouped)\\n        for cohort in kmf_map:\\n            kmf_series.setdefault(cohort, []).append(kmf_map[cohort])\\n\\n    return kmf_series\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def make_kmf_series(resp, iters=21):\n",
    "    kmf_series = {}\n",
    "\n",
    "    for i in range(iters):\n",
    "        sample = resample_by_cycle(resp)\n",
    "        sample = drop_missing(sample)\n",
    "        evrmarry = sample[\"evrmarry\"]\n",
    "        sample[\"observed\"] = evrmarry\n",
    "        sample.loc[evrmarry, \"duration\"] = sample[\"agemarry\"]\n",
    "        sample.loc[~evrmarry, \"duration\"] = sample[\"ager\"]\n",
    "        grouped = sample.groupby(\"birth_index\")\n",
    "        kmf_map = make_kmf_map(grouped)\n",
    "        for cohort in kmf_map:\n",
    "            kmf_series.setdefault(cohort, []).append(kmf_map[cohort])\n",
    "\n",
    "    return kmf_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 25;\n",
       "            var nbb_formatted_code = \"from utils import adjust_legend\\n\\n\\ndef plot_kmf_series(kmf_series, cohorts, subtitle):\\n    # always make 7 colors, but only use the last n of them\\n    palette = sns.color_palette(\\\"nipy_spectral\\\", 7)\\n    palette.reverse()\\n    n = len(cohorts)\\n    palette = palette[-n:]\\n\\n    options = dict(alpha=0.1)\\n\\n    for i, cohort in enumerate(cohorts):\\n        label = f\\\"{cohort+1900}s\\\"\\n        series_list = kmf_series[cohort]\\n        coords = []\\n        for series in series_list:\\n            coords.append((series.index[-1], series.iloc[-1]))\\n            series.plot(label=label, color=palette[i], **options)\\n            # only label the first line\\n            label = \\\"\\\"\\n\\n    decorate_plot(subtitle, loc=\\\"lower right\\\")\\n    adjust_legend(alpha=1, lw=2)\\n    remove_spines()\\n    plt.tight_layout()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from utils import adjust_legend\n",
    "\n",
    "\n",
    "def plot_kmf_series(kmf_series, cohorts, subtitle):\n",
    "    # always make 7 colors, but only use the last n of them\n",
    "    palette = sns.color_palette(\"nipy_spectral\", 7)\n",
    "    palette.reverse()\n",
    "    n = len(cohorts)\n",
    "    palette = palette[-n:]\n",
    "\n",
    "    options = dict(alpha=0.1)\n",
    "\n",
    "    for i, cohort in enumerate(cohorts):\n",
    "        label = f\"{cohort+1900}s\"\n",
    "        series_list = kmf_series[cohort]\n",
    "        coords = []\n",
    "        for series in series_list:\n",
    "            coords.append((series.index[-1], series.iloc[-1]))\n",
    "            series.plot(label=label, color=palette[i], **options)\n",
    "            # only label the first line\n",
    "            label = \"\"\n",
    "\n",
    "    decorate_plot(subtitle, loc=\"lower right\")\n",
    "    adjust_legend(alpha=1, lw=2)\n",
    "    remove_spines()\n",
    "    plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 26;\n",
       "            var nbb_formatted_code = \"kmf_series = make_kmf_series(resp)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kmf_series = make_kmf_series(resp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 27;\n",
       "            var nbb_formatted_code = \"plot_kmf_series(\\n    kmf_series, cohorts, subtitle=\\\"Females by decade of birth, NSFG 1982-2023\\\"\\n)\\nplt.savefig(\\\"marriage_female23.png\\\", dpi=300)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_kmf_series(\n",
    "    kmf_series, cohorts, subtitle=\"Females by decade of birth, NSFG 1982-2023\"\n",
    ")\n",
    "plt.savefig(\"marriage_female23.png\", dpi=300)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Percent married by education level"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 28;\n",
       "            var nbb_formatted_code = \"sample = resample_by_cycle(resp)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = resample_by_cycle(resp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 29;\n",
       "            var nbb_formatted_code = \"subset = sample.query(\\\"ager >=22 and ager < 25\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "subset = sample.query(\"ager >=22 and ager < 25\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "50 663\n",
      "60 1142\n",
      "70 1508\n",
      "80 1960\n",
      "90 1815\n",
      "100 341\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 30;\n",
       "            var nbb_formatted_code = \"for name, group in subset.groupby(\\\"birth_index\\\"):\\n    print(name, len(group))\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for name, group in subset.groupby(\"birth_index\"):\n",
    "    print(name, len(group))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "birth_index\n",
       "50     0.422323\n",
       "60     0.436077\n",
       "70     0.561008\n",
       "80     0.633673\n",
       "90     0.665565\n",
       "100    0.648094\n",
       "Name: anycoll, dtype: float64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 31;\n",
       "            var nbb_formatted_code = \"subset.groupby(\\\"birth_index\\\")[\\\"anycoll\\\"].mean()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "subset.groupby(\"birth_index\")[\"anycoll\"].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "birth_index\n",
       "50     0.601810\n",
       "60     0.464098\n",
       "70     0.442308\n",
       "80     0.250510\n",
       "90     0.170799\n",
       "100    0.120235\n",
       "Name: evrmarry, dtype: float64"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 32;\n",
       "            var nbb_formatted_code = \"subset.groupby(\\\"birth_index\\\")[\\\"evrmarry\\\"].mean()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "subset.groupby(\"birth_index\")[\"evrmarry\"].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 33;\n",
       "            var nbb_formatted_code = \"def make_marriage_table(df, query):\\n    subset = df.query(query)\\n    table = subset.groupby([\\\"birth_index\\\", \\\"anycoll\\\"])[\\\"evrmarry\\\"].mean().unstack()\\n    table.columns = [\\\"No college\\\", \\\"Any college\\\"]\\n    table.index = [f\\\"{1900+cohort}s\\\" for cohort in table.index]\\n    return table * 100\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def make_marriage_table(df, query):\n",
    "    subset = df.query(query)\n",
    "    table = subset.groupby([\"birth_index\", \"anycoll\"])[\"evrmarry\"].mean().unstack()\n",
    "    table.columns = [\"No college\", \"Any college\"]\n",
    "    table.index = [f\"{1900+cohort}s\" for cohort in table.index]\n",
    "    return table * 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 34;\n",
       "            var nbb_formatted_code = \"sample = resample_by_cycle(resp)\\ntable = make_marriage_table(sample, \\\"ager >=22 and ager < 25\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = resample_by_cycle(resp)\n",
    "table = make_marriage_table(sample, \"ager >=22 and ager < 25\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 35;\n",
       "            var nbb_formatted_code = \"table.plot()\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "table.plot()\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 36;\n",
       "            var nbb_formatted_code = \"sample = resample_by_cycle(resp)\\ntable = make_marriage_table(sample, \\\"ager >=32 and ager < 35\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = resample_by_cycle(resp)\n",
    "table = make_marriage_table(sample, \"ager >=32 and ager < 35\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 37;\n",
       "            var nbb_formatted_code = \"table.plot()\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "table.plot()\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 38;\n",
       "            var nbb_formatted_code = \"from utils import percentile_rows\\n\\n\\ndef plot_marriage_tables(tables):\\n    table = tables[0]\\n    categories = table.columns\\n    cohorts = table.index\\n    set_palette(\\\"Accent\\\", len(categories), reverse=True)\\n\\n    for col in table.columns:\\n        frame = pd.DataFrame(columns=cohorts)\\n        for i, table in enumerate(tables):\\n            frame.loc[i] = table[col]\\n\\n        # using the 84% CI, so non-overlapping corresponds to\\n        # a difference that's significant at 5% level\\n        low, median, high = percentile_rows(frame, [8, 50, 92])\\n        plt.fill_between(cohorts, low, high, alpha=0.2)\\n        plt.plot(cohorts, median, label=col)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from utils import percentile_rows\n",
    "\n",
    "\n",
    "def plot_marriage_tables(tables):\n",
    "    table = tables[0]\n",
    "    categories = table.columns\n",
    "    cohorts = table.index\n",
    "    set_palette(\"Accent\", len(categories), reverse=True)\n",
    "\n",
    "    for col in table.columns:\n",
    "        frame = pd.DataFrame(columns=cohorts)\n",
    "        for i, table in enumerate(tables):\n",
    "            frame.loc[i] = table[col]\n",
    "\n",
    "        # using the 84% CI, so non-overlapping corresponds to\n",
    "        # a difference that's significant at 5% level\n",
    "        low, median, high = percentile_rows(frame, [8, 50, 92])\n",
    "        plt.fill_between(cohorts, low, high, alpha=0.2)\n",
    "        plt.plot(cohorts, median, label=col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 39;\n",
       "            var nbb_formatted_code = \"tables23 = [\\n    make_marriage_table(resample_by_cycle(resp), \\\"ager >=22 and ager < 25\\\")\\n    for i in range(101)\\n]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tables23 = [\n",
    "    make_marriage_table(resample_by_cycle(resp), \"ager >=22 and ager < 25\")\n",
    "    for i in range(101)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 40;\n",
       "            var nbb_formatted_code = \"plot_marriage_tables(tables23)\\nmake_title(title=\\\"Percent ever married age 22-24\\\", subtitle=\\\"Females, NSFG 1982-2023 \\\")\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_marriage_tables(tables23)\n",
    "make_title(title=\"Percent ever married age 22-24\", subtitle=\"Females, NSFG 1982-2023 \")\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 41;\n",
       "            var nbb_formatted_code = \"tables34 = [\\n    make_marriage_table(resample_by_cycle(resp), \\\"ager >=32 and ager < 35\\\")\\n    for i in range(101)\\n]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tables34 = [\n",
    "    make_marriage_table(resample_by_cycle(resp), \"ager >=32 and ager < 35\")\n",
    "    for i in range(101)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 42;\n",
       "            var nbb_formatted_code = \"plot_marriage_tables(tables34)\\nmake_title(title=\\\"Percent ever married age 32-34\\\", subtitle=\\\"Females, NSFG 1982-2023 \\\")\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_marriage_tables(tables34)\n",
    "make_title(title=\"Percent ever married age 32-34\", subtitle=\"Females, NSFG 1982-2023 \")\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Age at first marriage, male respondents\n",
    "\n",
    "Load the data cleaned in `clean_nsfg.ipynb` and run the analysis with `lifelines`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 15.7 ms, sys: 3.97 ms, total: 19.6 ms\n",
      "Wall time: 19.2 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(75769, 46)"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 43;\n",
       "            var nbb_formatted_code = \"%time resp2 = pd.read_hdf('MaleMarriageData.hdf', 'MaleMarriageData')\\nresp.shape\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%time resp2 = pd.read_hdf('MaleMarriageData.hdf', 'MaleMarriageData')\n",
    "resp.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "evrmarry\n",
       "False    24634\n",
       "True     14135\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 44;\n",
       "            var nbb_formatted_code = \"evrmarry = resp2[\\\"evrmarry\\\"]\\nvalue_counts(evrmarry)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evrmarry = resp2[\"evrmarry\"]\n",
    "value_counts(evrmarry)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "50 0\n",
      "60 0\n",
      "70 1\n",
      "80 1\n",
      "90 1\n",
      "100 0\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 45;\n",
       "            var nbb_formatted_code = \"for name, group in resp2.groupby(\\\"birth_index\\\"):\\n    missing = group[\\\"evrmarry\\\"] & group[\\\"agemarry\\\"].isna()\\n    print(name, missing.sum())\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for name, group in resp2.groupby(\"birth_index\"):\n",
    "    missing = group[\"evrmarry\"] & group[\"agemarry\"].isna()\n",
    "    print(name, missing.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 46;\n",
       "            var nbb_formatted_code = \"sample = resample_by_cycle(resp2)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = resample_by_cycle(resp2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "birth_index\n",
       "50       373\n",
       "60      4862\n",
       "70     11219\n",
       "80     12059\n",
       "90      8268\n",
       "100     1988\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 47;\n",
       "            var nbb_formatted_code = \"value_counts(sample[\\\"birth_index\\\"])\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "value_counts(sample[\"birth_index\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 48;\n",
       "            var nbb_formatted_code = \"sample = drop_missing(sample)\\n\\nmissing = sample[\\\"evrmarry\\\"] & sample[\\\"agemarry\\\"].isna()\\nmissing.sum()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = drop_missing(sample)\n",
    "\n",
    "missing = sample[\"evrmarry\"] & sample[\"agemarry\"].isna()\n",
    "missing.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 49;\n",
       "            var nbb_formatted_code = \"cdf = Cdf.from_seq(sample[\\\"ager\\\"], name=\\\"age\\\")\\ncdf.plot()\\ndecorate()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cdf = Cdf.from_seq(sample[\"ager\"], name=\"age\")\n",
    "cdf.plot()\n",
    "decorate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 50;\n",
       "            var nbb_formatted_code = \"cdf = Cdf.from_seq(sample[\\\"agemarry\\\"], name=\\\"agemarry\\\")\\ncdf.plot()\\ndecorate()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cdf = Cdf.from_seq(sample[\"agemarry\"], name=\"agemarry\")\n",
    "cdf.plot()\n",
    "decorate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 51;\n",
       "            var nbb_formatted_code = \"evrmarry = sample[\\\"evrmarry\\\"]\\nsample[\\\"observed\\\"] = evrmarry\\nsample.loc[evrmarry, \\\"duration\\\"] = sample[\\\"agemarry\\\"]\\nsample.loc[~evrmarry, \\\"duration\\\"] = sample[\\\"ager\\\"]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evrmarry = sample[\"evrmarry\"]\n",
    "sample[\"observed\"] = evrmarry\n",
    "sample.loc[evrmarry, \"duration\"] = sample[\"agemarry\"]\n",
    "sample.loc[~evrmarry, \"duration\"] = sample[\"ager\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 52;\n",
       "            var nbb_formatted_code = \"grouped = sample.groupby(\\\"birth_index\\\")\\nnsfg_map = make_kmf_map(grouped)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "grouped = sample.groupby(\"birth_index\")\n",
    "nsfg_map = make_kmf_map(grouped)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 53;\n",
       "            var nbb_formatted_code = \"cohorts = range(50, 110, 10)\\n\\nfig, ax = plt.subplots()\\nplot_kmf_map(ax, nsfg_map, cohorts)\\n\\ndecorate_plot(subtitle=\\\"Males by decade of birth, NSFG 1982-2023\\\")\\nremove_spines()\\nplt.tight_layout()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cohorts = range(50, 110, 10)\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "plot_kmf_map(ax, nsfg_map, cohorts)\n",
    "\n",
    "decorate_plot(subtitle=\"Males by decade of birth, NSFG 1982-2023\")\n",
    "remove_spines()\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 54;\n",
       "            var nbb_formatted_code = \"kmf_series = make_kmf_series(resp2)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kmf_series = make_kmf_series(resp2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 55;\n",
       "            var nbb_formatted_code = \"plot_kmf_series(\\n    kmf_series, cohorts, subtitle=\\\"Males by decade of birth, NSFG 1982-2023\\\"\\n)\\nplt.savefig(\\\"marriage_male23.png\\\", dpi=300)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_kmf_series(\n",
    "    kmf_series, cohorts, subtitle=\"Males by decade of birth, NSFG 1982-2023\"\n",
    ")\n",
    "plt.savefig(\"marriage_male23.png\", dpi=300)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Percent married by education level, males"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 56;\n",
       "            var nbb_formatted_code = \"sample = resample_by_cycle(resp2)\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample = resample_by_cycle(resp2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 57;\n",
       "            var nbb_formatted_code = \"subset = sample.query(\\\"ager >=22 and ager < 25\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "subset = sample.query(\"ager >=22 and ager < 25\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "70 350\n",
      "80 1599\n",
      "90 1475\n",
      "100 268\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 58;\n",
       "            var nbb_formatted_code = \"for name, group in subset.groupby(\\\"birth_index\\\"):\\n    print(name, len(group))\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for name, group in subset.groupby(\"birth_index\"):\n",
    "    print(name, len(group))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "birth_index\n",
       "70     0.480000\n",
       "80     0.577861\n",
       "90     0.581695\n",
       "100    0.529851\n",
       "Name: anycoll, dtype: float64"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 59;\n",
       "            var nbb_formatted_code = \"subset.groupby(\\\"birth_index\\\")[\\\"anycoll\\\"].mean()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "subset.groupby(\"birth_index\")[\"anycoll\"].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "birth_index\n",
       "70     0.245714\n",
       "80     0.168230\n",
       "90     0.118644\n",
       "100    0.041045\n",
       "Name: evrmarry, dtype: float64"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 60;\n",
       "            var nbb_formatted_code = \"subset.groupby(\\\"birth_index\\\")[\\\"evrmarry\\\"].mean()\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "subset.groupby(\"birth_index\")[\"evrmarry\"].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 61;\n",
       "            var nbb_formatted_code = \"table = make_marriage_table(sample, \\\"ager >=22 and ager < 25\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "table = make_marriage_table(sample, \"ager >=22 and ager < 25\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 62;\n",
       "            var nbb_formatted_code = \"table.plot()\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "table.plot()\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 63;\n",
       "            var nbb_formatted_code = \"table = make_marriage_table(sample, \\\"ager >=32 and ager < 35\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "table = make_marriage_table(sample, \"ager >=32 and ager < 35\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAW0AAAEOCAYAAABCYUbWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAAuJAAALiQE3ycutAAA4CElEQVR4nO3de1zUVf7H8dfMcBPEC4I3LiIicpeLCN7ZSk1LLfKyYuXdUtN+1VZutdVqrbtb62blamZmpmKudLG7ljeQxCtqooh4AVRUBARRhoH5/v4YHWVVQAW+DHyej8c8kPnOd+YzHn1zOHO+52gURVEQQghhEbRqFyCEEKL6JLSFEMKCSGgLIYQFkdAWQggLIqEthBAWREJbCCEsSJ2Hdq9ever6JYUQwmJUlZGaup6nbW9vj6enZ12+pBBCWIwTJ05w+fLl2x63qsNaAPD09CQ1NbWuX1YIISyCv79/pcdlTFsIISyIhLYQQliQOh8eEULUH7L0kHo0Gs1dnSehLUQjZDAYyMrKQq/Xq11Ko2Vra4u7uzvW1tZ3dJ6EthCNUFZWFo6Ojnh6et51j0/cPUVRuHDhAllZWXh5ed3RuRLaQjQyiqKg1+vx9PREq5WPtdSg0Who1aoVubm5KIpyRz84LabFMs5fQl9WrnYZQjQY0sNW193+/VtEaCuKwpOf7CDkrxsY9+kOPkk8zpGzRfIhihAWTqPRMG7cOPP3mzdv5oEHHqjV13zzzTd56623bvqzpbCI4RGjAi8M8CEhPZeE9Fw2p50HoE0zW3p7u9DXx5le3s44N7VVuVIhxJ3QarVs3ryZ9PR0OnfurHY5FsEieto6rYaYMDf+PSqEna/ez4/P9uGVwb74tHHku/2neXZ1Ct3e+oXB8xOY++Mhth3NpcQgQylC1HcajYYXX3yROXPm3PL466+/TmBgIIGBgcyePfuWj8nNzWXUqFEEBwcTHBxMXFwcAImJiXTr1o3g4GAeeughcnJyKq3lypUrPP3003Tv3p2goCA+/PBD87F//vOfdO7cmcjISKZMmcKkSZOqPKe2VNnTPnfuHAMGDDB/n5OTQ48ePfjqq6+YNWsWa9euRavVMnfuXB577LFaLRZMjezXrhl+7ZoxpW8nSgzl7DyRZ+6Ff7TlGB9tOYadtZbuHVvRt7MzvTs706WNo4zhCXELL63dx5Gzl2r8eX3aNOWfw7tW+bjJkyfz7rvvcuTIkQr3f/PNN/zyyy/s2rULgL59+xIREcGgQYMqPO7ZZ58lMDCQL774AoC8vDz0ej2jR4/mm2++ISwsjH/96188++yz5sfcyty5cwkLC2PRokXo9Xp69erFfffdh16v59NPP2Xv3r3Y2NgQHR1tvtT8dudUdSn6vagytFu3bk1KSor5+wceeIARI0bwyy+/kJSURFpamjnIBw4cSNOmTWut2Fuxs9bRp7MLfTq7AHCuqIRtR3PNIb71iGkopbWjLb07O9OnszO9vV1wcZShFCHqAxsbG15++WVmz55t7sGCaXx7zJgx2NnZARAbG8umTZtuCu2ff/6ZhQsXmr93cnJi3759tG3blrCwMAAmTpzIP/7xj0rr+OGHH7hy5Qr/+c9/ACgsLCQtLY3MzEyGDBlizrZRo0Zx4MCBSs9RNbRvdPr0aXbt2sW6det44YUXGDduHDqdDldXV3r16sX69euJiYmprVqrpbWjHY+GuvFoqBuKopB2tojE9Fy2pufy/f4zfLnnFAB+7ZrR52qIR3g6YWetU7VuIdRSnd5wbZswYQL//Oc/6d27t/m+//3NuLLflKt6bHV+y1YUhZUrVxISElLh/vnz59/2uW53Tm26ozHtuLg4HnnkEezt7cnOzsbd3d18zMPDg6ysrBov8F5oNBp82zZjUh8vlk/ozr43BrByUiRP9fNCAyzeeownPtlB17+u54lPklm8NYNDZwplVooQdczGxoZZs2Yxd+5c833R0dGsWrUKvV5PSUkJcXFx3HfffTedO3DgwArBmpeXR5cuXcjJyTGPEixduvSW595o0KBBzJ8/n/Jy0+dh6enpFBYW0qdPH7777juKi4sxGAysWbOmynNq0x31tFesWME777wDVH/NggULFrBgwQLz9/n5+XfykjXKzlpHL2/TTJM/D4LcS3q2Hc1l65FcEo+eJyE9FziMc1Nbcy+8t7czrZvZqVazEI3F+PHjK4T20KFD2bVrF+Hh4QCMHDmSBx988Kbz5s+fz7Rp0wgMDESn0/HKK68watQoVq1axaRJkygtLcXNzY2lS5dW+vqvvfYaL774Il27mn7zcHZ2Zu3atYSFhfHkk08SEhKCk5MTvr6+NG/evNJzalO1N0FITU1lwIABZGZmotVqmTp1KhEREUyYMAGA0aNHM3z48Co/jPT396+X62krikL6uUtsPXKexKO5bD92gRKDEQDfto709namj48L3T2daGLTCIdSFAXKS6GsBMr0pj87tge5os7iKIrC4cOH8fX1lQ/nq+nSpUs0bdoUg8HAI488wpNPPsmoUaPu6Tlv1w5VZWS1e9qff/45sbGx5steY2JimDNnDmPHjiUnJ4fExEQWL158D29BXRqNBp82jvi0cWRSHy/0ZeXsPpFPwtFcEtLPsyTxOEsSj2NjpSXCs+XVDz+d8WvbDK22Dv7hK4opLK+FZqVfq/OYKr6W62++7381bQO+D4P/UOjQG3QWMe1fiDs2Y8YMUlJSuHLlCv3792fEiBGq1VKt/2WKorBq1Sq+/fZb8339+/dnw4YN+Pj4oNVqmTdvHo6OjrVWaF2ztdLR09uZnt7OvPygLxeKrrD9yGmSj5xm7/EsVmaksvYnA62bQIS7A2HtmxDc1o6WNsaaDU9ziJbW3JvT2YKVHVjd4qtdc7Bqffvj176iwLEtsHsZ7PoEmrSELg+ZAtwr+upjhGgYPv30U7VLMKvzPSLvenjEWF7N3qS+dkLTaKi5v4RKA7GKsKzWVzvQ2dz6mM6mZoc0ii/AkR8hdR0c22T64WLjCD4DTQHu/QDYONTc64l7JsMj9UOtD4+o7l++UHyuBp5IU3ng2TvcQYiagtGgsSYjv5wDZ0vYc/oKh8+XUqJYY9Ta0sXNmdBObYns3B5fVxe01rbQkP6jOLSC0MdNt5JCSF8Pqd9A2g/w+1qwagLe94PfUOjyoKknL4S4a5YT2t0ng+FK9Xuatzums67x0LQGfK/eRgD5xaVsy8gl4YhpPHzdxlzYmIuTgw29vJ3NM1PaNW9So3Wozq4ZBA033UovQ8avph74kZ/g8HegtTYNnfgPhS6DwcFZ7YqFsDiWMzxioRRF4VhuMQlXZ6X8lnGB4lLTnE7v1k3NAR7ZsRUOtpbzM/SOlOnh+FZTD/zw93AlDzRa6NAL/IeB70PQrL3aVTYaMjxSP9zt8IiEdh0rLTOyNzOfxKOmqzT3ZxegKGCt0xDe4fqslID2zdHVxayUulZeBplJph74oW/h0tVFfNy6m3rgfkOgpaeqJTZ09S20d+zYQWRkJN988w1Dhw5VrY7o6GjeeustevfuXeHPtaXhj2k3EDZWWiK9WhHp1YoXBnSh4HIpSRkXSEg/z9Yjubzzcxrv/JxGS3treno7X13wygXXFg1kKEVnBR37mm6D/gmndpl64IfWwfrXTLe2wVcDfCi4dFG7YlHLPv/8c/r27cuKFStUDW1LIVdGqKyFvQ2Dg9oxNyaYxJf/wKY/RTN7WADhHZzYknael+MP0OvvG7nvX5t5c91Bfj10lkv6MrXLrhlaLbh3h4Fvw7P74amt0OdPptk6G9+CBd3hw+6mP5/ZZ5qrLhqUsrIy4uPjWb58OVu2bOHixYvmY56enrz++ut069YNHx8fkpKSANOidVu3bjU/bsqUKbeckpeSkkLfvn3p2rUroaGhHD58GICFCxcSGBhIUFAQM2bMoKys8v9PJ0+e5OGHH6Zbt25069aNLVu2AFBSUsLjjz+On58f/fv3Z/DgwaxYsaLSc2qC9LTrEY1GQ0dnBzo6O/BkD08M5UZSsgpIOHKehKO5LP/tBMuSTmCl1RDWoaW5Fx7k2gCGUjQaaNfVdLv/L3A+7eoQyjrY+o7p1tLTNHziNxRcu8nVmDXlm+lw7nDNP29rXxi2oNKH/PTTT4SEhNChQwcGDx7M2rVrmThxovm4vb09u3btYu3atbzxxhts2LCBp556iiVLltC3b1+Ki4v54Ycf+Pe//13heQ0GA4899hhLly6lX79+6PV6DAYDKSkp/Otf/2Lnzp00b96cmJgYPv74Y6ZOnXrbGidMmMD7779PQEAAmZmZREdHk5GRYV5Z8NChQ5w6dQp/f39iY2MrPacmhqMktOsxa52WCE8nIjydeH5AFy5eNpCUkUvCUdOSs++uP8K764/QvIk1vb2dzUvPurW0V7v0e+fSBfq9aLrlHTeNfx9aB0kfmG6O7cHvYVOIe/SUqzEt1IoVKxgzZgwAY8aM4a233qoQ2teuPIyIiGDWrFkAPPLII7z00ksUFBQQHx/Pww8/jINDxWsB0tLSaNGiBf369QPA1tYWW1tbtmzZwqOPPkrLli0BGDduHKtWrbptaF+6dInExERzjQClpaWcO3eOrVu3MnnyZABcXV3NC1JVdk6bNm3u/i/rKvmXbkGa21szKKgdg4LaoSgKJy9cNl1mf+Q8W4+c5/sDZwDo6OxwdVaKC1FeTjjaWatc+T1y6gi9Zppuhafh0HemAN+5BHYsBvtWphkofkOhYz/T/HlRfVX0hmtLYWEh3333HUlJSbz66qsoikJOTg6ZmZl4eHgAprAF0Ol05mEMa2trRo8ezYoVK1i5cuUtd4u53fyKO12y1Wg0Ym9vX2FPgdu59lx3cs7dkN8vLZRGo8HT2YEnojqw+Mlu7H29P/FTe/Ds/Z1xcrBhZXImk5fvInT2BkYsSuL9X9PZk5lPWblR7dLvTbP2EDkFxn0Hf0qHIe9D+1BIiYOVw+Edb/hyiqlnXnpZ7WpFJeLj4xkyZAiZmZmcOHGCkydPMmPGDFauXFnluZMnT+Yf//gHer3evArgjXx9fSkoKDCPJev1ei5dukTfvn35+uuvKSgowGg08tlnn1W6ZGuzZs0ICAiosELgnj17ANNOOqtXrwZMew1s3LixynNqgvS0GwgrnZbwDk6Ed3Diuf4+XLxi4LeMC+YlZ+dtOMK8DUdoZmdFr6tDKX07u+DuZMFDKQ7OED7WdLtSAEd+NvXAU7+B/V+AtT107m/qgXceYLr4R9Qbn3/+Oc8880yF+0aMGMGECRP485//XOm5HTt2xMvL67Yr7VlbWxMfH88zzzxDYWEh1tbWrFq1ipCQEJ5//nnzVL7o6OgKu+XcysqVK3nmmWeYP38+BoOBqKgoli5dytSpU5kwYQJ+fn64u7sTHh5uXrL1dufUBJmn3UhkXrhMwtHzJBzJZVtGLkUlpl81PVvZXx0Ld6FHp1Y0s/ShFIDSYkjfYArwIz9D6SXTmiud7jONgXcZDPZOalepmvo2T/tuXLx4keDgYPbv328OyrpmNBopKSnB3t6e8+fPExERQUJCQoXNYSoj87RFpTxa2TOmVQfGRHagrNzI/lMXzZfZx+3IYsX2THRaDSHuLcxXaXZ1a4GVzgJH0GwcIOAR081QAsc2mwL88PemS+o1OujYxxTgvkPA8d4/HBJ154svvuDFF19k1qxZqgU2mD5c7Nu3LwaDAYPBwOuvv17twL4X0tMWFJYY2J5xgcSrGyIfzy0GwNHOip6dWtG7swt9OzvToZWFr9ZXboATiaYAP/Td1QXINOARdXUq4RBo4aF2lbWuIfS0GwK5jF3UmKy8y1cD/DyJ6bkUXh1K8XCyvzoW7kyPTs40b2LBQynGcsjacTXAv4WLV/c3bR96NcCHgbO3ujXWEgnt+kFCW9SKcqPCgVMXTRf4pOeaZqAYFXRaDWN7eDJrkC82VhY4hHIjRYHTe69+iLkO8jJM97f2v34xT5uABrOk7rWw6NKli3knKlH3jEYjaWlpEtqidl3Sl7E94wJrd2fz08Ecgt2a88HoUMsfOrlGUeDcoes98LO/m+538rreA3cNs/gAP3bsGI6OjrRq1Up62ypQFIULFy5QVFSEl5dXhWMS2qJWKIrCFzuzeGPdQWx0WuY+FsTDwQ1wedULGdcD/NRu033N3K6PgXtEgdbyNno2GAxkZWWh1+vVLqXRsrW1xd3dHWvrisOMEtqiVqXlFPHMqj2kn7vEmEgP/vKwP3bWlhdi1XIx++rl9N/CySRAAQeXG67G7GvaZMOC1PF/f3GD2/2GI6Etat3l0jLeXHeQNbuy8W3ryIexYXi3bqp2WbXr0jnTbjyHvjVt8GAsM22l1mWwKcA73QfWdmpXKSyQhLaoM1/tzebVr0xjwG89EkhMmJvKFdWRy3mm+d+HvoWjv0K5HmyaVrwa07aB/xATNUZCW9SpY+cvMX3VXg6dKeSxMDdmDwtouNuo3Yq+yLS58aFv4ch6MBSb9ibtdP/VqzEfhCYt1a5S1GMS2qLOlRjKefv7Q3y+/SSdXBz4MDYMv3aNcN0PwxXI2GgK8LQfoOQiaK/u3OM3FHwfhqYualcp6hkJbaGaHw6c4eW1+yktN/LGkABGd3dvvNPLykrhxNarH2R+B5dzTZsbe/QwBbjfEGjuqnaVoh6Q0BaqyrxwmRlxe9iXfZGHg9sxNybI8tf3vlfGcsj87fpMlMJTpvtdw00B7j/UNC9cNEoS2kJ1pWVG/vnTYZYkHqdDK3s+HB1GkJt6C/3UK0YjnN5z/WrM/OOm+9sEmXrf/kPBxdfiL+YR1SehLeqNXw+d5YX/7qNYX8Yrg/0Y19Oz8Q6X3IqimK7APPStKcDPHzLd36rz9QBvFyIB3sBJaIt65czFK8yM28vOE/n092/DO8ODaWEv24PdUm769R74mRTTfc09rge4W3fZ3LgBktAW9U5ZuZH3fklnweajtG/ehPdHhxLeQabBVSr/pOlintR1kJUMKNC0jWkGiv9Q6NBbNjduICS0Rb2VkH6e575IIf+ygT8N6MJTfb3QauVX/yoV5VwP8BOJoJSDXQvo0BPcu4N7pGmJWesmalcq7oKEtqjXzhWV8NwXKWw7eoG+Pi7MG9kV56a2apdlOYovwJEfIe1HUw+8+Lzpfq0VtA02Bfi1IJcphRZBQlvUe+VGhYWbjzJvwxGcm9oy/4+h9OjUSu2yLI+imGafZO0wBXjWzqtLy179L97M7XqAu3eHtkEWt8BVYyChLSxG8rELPLs6hXNFJcy8vzMz7uuMToZL7k1JoWlJ2WtBnr0T9IWmY1ZNTHPD3bubbm7dwUF+WKpNQltYlLziUl5Yk8KmtPNEeTkx/4+htGkmq+XVGKMRzh++2hO/GuTXduoBaOVdcUjFuYvMUKljEtrC4hiNCp8kHucfPx2meRNr5o0KoZ+PrNFRa4pzTQGevcP09dRuKCsxHbNtDu4R14PcNRxsHdWtt4GT0BYWa29mPjPi9pKdf4Wn+3XihQE+WOuk11frykrh7IHrPfHMZCg6bTqm0Zr2y3SPNA2nuHeHlp5ywU8NktAWFu3iFQMvr93PTwdzCPNowQexYbi2kKlsde5idsUhlTP7TVMNARxa3/ABZyS06yobQNwDCW1h8RRFYcX2k8z57hBNbHS8MzyYAQFt1S6rcSstNu1gf22WSlYyXMkzHdPZmC63v3GmiqO0V3VJaIsG4/dTF5kRt5fjucWM7+XJrEG+2Fo10P0oLY2imDZBzkq+3iO/tnYKQIsOFUO8dYBcwXkbNRLaxcXFTJs2je3bt6PRaHjuued46qmnmDVrFmvXrkWr1TJ37lwee+yxey5IiMpc0pfx6lcH+CblNEGuzfkwNpQOrRzULkvcypV8yN59PchP7YbSS6Zj1g7gFn59SMWtm+zoc1WNhPbTTz+Nl5cXL730EoqicP78efbv38/s2bPZtGkTOTk59OjRg9TUVJo2rXwvPAltca8UReG/u7J5fd3vWGm1zI0JYkjX9mqXJapSXgbnUq/PUslKhvwT14+7+FYcG2/l3Sg/4Lzn0C4qKqJLly5kZmZiZXX915mpU6cSERHBhAkTABg9ejQjRowgJibmngoSorqOnC1i+so9pJ+7xOjuHrwxxB87axkusShFZ6+G+NUhldN7obzUdKxJy+szVNwjwTUMbBr+b1VVZWSVg0rHjh2jTZs2PPPMM+zYsYMOHTrw3nvvkZ2dXSGgPTw8yMrKqpmqhagGnzaOrHumN2+uO0jcjkz2ZubzYWwo3q1lHrHFcGxjWmrWb4jp+zI9nNlXcWw8/WfTMY3OdOl9hfVU3Bpdb7zK0C4rKyMlJYV33nmHRYsWsXTpUiZMmECTJtWbdrVgwQIWLFhg/j4/P//uqxXifzSx0fGP4cH09G7FK18eYMgH25jzSCDDw93ULk3cDSvb65fVM8P0AWfByeszVLKSYefHsOMj0+Md21ccUmkbBFYNe332KodHzp49S0BAALm5uQBcvnyZ9u3bM3r06JuGR4YPH17lh5EyPCJqy/HcYqav3EPqmUJiwlyZMywQB1uZodDg6C/9z3oqO0w73QNY2ZmWpb0W5G7dLW7H+3seHmnTpg0BAQHs2bOHsLAwNmzYQEBAADExMcyZM4exY8eSk5NDYmIiixcvrtHihbgTHZ0d+HJaT+b+cIjPfjtJSlYBC2LD8GvXTO3SRE2ybQpe/Uw3MK2nknuk4sU/2+Zff7yTV8UhFRdf0FruZx/Vmj2SmprKxIkTKS4upkWLFnz00Uf4+fnx0ksvER8fj1ar5W9/+xsjRoyo8gWlpy3qwk+/n+HFtfvRlxl5Y4g/sd09ZD/KxuRynmlFw2tBnr0Lyq6Yjtk2M00xNK+n0g3s6s8Pdrm4RjRaWXmXeSZuL/uyCngouB1zY4JoZifrRzdK5QbT2uJZN8xUuXht4oQGWvtXvPjHyUu1DzgltEWjVlpm5N31aSzeegwPJ3s+jA0l2K2F2mWJ+uDiqYpzxs/sB6PBdMzeueKQSvuQOtu+TUJbCGDj4bO8sGYfl/RlzBrkx4RenjJcIioyXIHTKRXHxi+bJmCgtTYthGUO8u7QrHYu6JLQFuKqMxev8GxcCjtO5PGAXxveHRFMC/uGPT1M3ANFgbxjFYdUzqVi3r6tuXvFIZU2gTWyfZuEthA3KCs38v6v6Xyw6Sjtmtnx/uhQunk6qV2WsBQlF00fapqnG+6C0iLTMWv7G7Zvi4SOfe9qSEVCW4hb2HY0l2dXp5B/uZQXBvjwdN9OaGU/SnGnjOW32L7tmOnYC2l3tSSthLYQt3G+SM9zX6SQeDSXPp2d+feoEJyb2qpdlrB0l87DmRTo3P+uTq8qI2XvJtFouTjasnxCd14c2IVtR3MZND+BpIxctcsSlq6py10HdnVIaItGTavVMP0P3qye0gOdRsOYJcn8e8MRyo11+guoENUmoS0E0L2jEz8824c/dGnN/F/TGbNkO2cLS9QuS4ibSGgLcZWTgw2fjO3Gaw/5setEPoPmJ7A57ZzaZQlRgYS2EDfQaDRM6uPF2qk9cbDVMe7Tnfz9x8MYyo1qlyYEIKEtxC2FuLfguxl9GBzUlkVbMhj10W9k519WuywhJLSFuJ3mTaxZEBvGnEcC+f10IYPnJ/DzwRy1yxKNnIS2EJXQaDQ8EdWBr6b1xLmpLU99vps31x1EX1audmmikZLQFqIaAto3Z92M3jwS0p5lSSd4bGESJ3KL1S5LNEIS2kJUU1NbK/49KoR/Dg/m6LlLPPxBIuv2nVa7LNHISGgLcQc0Gg0ju7nz7TO9ad/Cjplxe/nzlwcoMchwiagbEtpC3IXObRz5Znpv/hjhTtyOTIZ9uI2j54rULks0AhLaQtylJjY6/v5YMPP/GEJ2/mWGfLCNtbuz1S5LNHAS2kLco2Ehrnw3sw9eLg786b/7eP6LFIr1ZWqXJRooCW0hakBHZwe+nNaTcT09+XLvKYZ8mEjq6UK1yxINkIS2EDXE1krHm0MDWPR4OLlFeh75zzZWbD9JHS9ZLxo4CW0hatiDgW35fmYf/Ns147Wvf+eZVXspLDGoXZZoICS0hagF7k72/PfpHjzV14vvD5zhofcT2JdVoHZZogGQ0BailljrtPx5sB+fjo+gWF/O8EVJLEk4JsMl4p5IaAtRy/7QpTU/zOxDqEdL3vr+EJOX7yK/uFTtsoSFktAWog60bW7HqkmRzLy/M78ePsfg9xPYdSJP7bKEBZLQFqKOWOm0PN/fh5UTIykzKoxavJ0Fm45ilP0oxR2Q0BaijvX0duaHmX3o2akV7/ycxthPd3C+SK92WcJCSGgLoQIXR1s+G9+dlx7sQlLGBQa/n0DS0Vy1yxIWQEJbCJVotRqmRXvzxZQorLQaxnySzLz1aZTJfpSiEhLaQqism6cTP8zsw/2+rXl/41FilySTc7FE7bJEPSWhLUQ90NLBho+f7MZfHvZnb2Y+g99PYNPhc2qXJeohCW0h6gmNRsPE3h1Z+3RPHGx1jF+2k7k/HMIgwyXiBhLaQtQzXd1b8P3MPjwU1I6Pth5j5Ee/kZV3We2yRD0hoS1EPdTMzpoPY0N5+9FADp4u5KH3E/jp9xy1yxL1gIS2EPWURqNhTGQHvp7WC2dHW55esZs31x1EXyb7UTZmEtpC1HP+7Zvx7TO9iQl1ZVnSCR5bmMSJ3GK1yxIqkdAWwgI42Foxb1QI747oSsa5Yh7+IJF1+06rXZZQgYS2EBZkeLgb387ohWuLJsyM28us+P1cKZXhksakWqHt6elJQEAAISEhhISEcODAAQBmzZqFt7c3Pj4+xMfH12qhQggT79aOfPNML0Z392D1ziyGLUgk/WyR2mWJOmJV3Qf+/PPPuLm5mb//5ZdfSEpKIi0tjZycHHr06MHAgQNp2rRprRQqhLjOzlrH3JggenRqxStfHmDIh4ksejyc6C6t1S5N1LK7Hh6Jj49n3Lhx6HQ6XF1d6dWrF+vXr6/J2oQQVRjatT3fzehNm2Z2TPl8N4npsuhUQ1ft0B4yZAghISG8+uqrGAwGsrOzcXd3Nx/38PAgKyurVooUQtyep7MDqyZH0drRlknLd7L92AW1SxK1qFqhnZCQwN69e9m2bRtpaWm8++671d7nbsGCBfj7+5tv+fn591SwEOJmri2aEDc5Cid7GyYs28lO2RWnwapWaF/rUTs4ODBp0iSSkpJwd3ev0LPOzMysMOZ9zfTp00lNTTXfWrZsWUOlCyFu5O5kT9yUKJrZWTP+053syZQOUkNUZWgXFxdTWFgIQHl5OfHx8QQHBxMTE8OyZcsoLy/n1KlTJCYmMmDAgFovWAhxex1aObBqciRNbHSM/WQH+7ML1C5J1LAqQ/vs2bP07duX4OBggoODURSFV199lf79+xMVFYWPjw/R0dHMmzcPR0fHuqhZCFEJL5emxE2OxMZKy+NLkvn91EW1SxI1SKNUd3C6hvj7+5OamlqXLylEo5SWU8QfF/8GQNyUKHzbNlO5IlEdVWWkXBEpRAPVpa0jKyZFYlRgzMfJcgFOAyGhLUQDFtC+OSsmRlJabmT0x8lknL+kdkniHkloC9HABbk1Z/mE7pQYyon9eLusEGjhJLSFaARCPVqybHwERSVlxH68XXbCsWAS2kI0Et08nVg6LoK8y6WM/ng7pwquqF2SuAsS2kI0IlFerfhkbATni/TEfrydnIslapck7pCEthCNTC9vZxY/2Y0zBSXEfrydc4US3JZEQluIRqifjwuLnggjK/8ysUuSOV+kV7skUU0S2kI0Uvf5tmFBbBgncot5fEkyecWlapckqkFCW4hGbEBAWz4YHcrR85d4fEkyBZcluOs7CW0hGrlBQe2YN7Irh3MKeeKTHVy8YlC7JFEJCW0hBMNCXHl3RFd+P32RsUt3UFQiwV1fSWgLIQCICXPjHzHBpGQVMP7TnRTry9QuSdyChLYQwmxkhDtvPxrIrpP5jF+2k8ulEtz1jYS2EKKCMZEd+OvQAHYcz2PSZ7soMZSrXZK4gYS2EOImY3t68tpDfiRlXGDycgnu+kRCWwhxS5P6ePHyg74kpOcybeUeSsuMapckkNAWQlRianQnXujvw8bD53hm1R4M5RLcapPQFkJUasb9nZl5nzfrU8/y7Oq9lElwq8pK7QKEEPXfc/19MBgVFm7OwEq7j3+PCkGn1ahdVqMkoS2EqJJGo+GlgV0wlBlZkngcK62Gd0Z0leBWgYS2EKJaNBoNrz7kR5lRYVnSCax1WubGBKGV4K5TEtpCiGrTaDS8McQfQ7mRlcmZWOk0vPVIIBqNBHddkdAWQtwRjUbDnGGBlJUrrEzOxFqn5Y0h/hLcdURCWwhxx7RaDXNjgjAYjSxLOoGV1jR0IsFd+yS0hRB3RavV8M7wrpSVK6YPJ3VaXn6wiwR3LZPQFkLcNZ1Ww7yRXSkzGlm0JQMbKy3P9/dRu6wGTUJbCHFPrHRa5v8xFEP5Ht7/NR1rrYYZ93dWu6wGS66IFELcM2udlg9jQ7nPtzX/2nCEhZsz1C6pwZLQFkLUCFsrHf8ZE0ZfHxf+8dNhliQcU7ukBklCWwhRY+ysdSx+Ipxe3q146/tDfJZ0Qu2SGhwJbSFEjbKz1rHkyQgiOzrxxrqDrEw+qXZJDYqEthCixjWx0bF0XATdOrTk1a9+Z83OLLVLajAktIUQtcLB1opPx0cQ4t6Cl7/cz5d7stUuqUGQ0BZC1BpHO2s+m9CdwPbN+dN/9/FNyim1S7J4EtpCiFrVvIk1n0/sjm/bZjy/Zh8/HDijdkkWTUJbCFHrWtjbsGJSJN4uTZkZt5f1B3PULsliSWgLIeqEk4MNKydH4unswPRVe9h4+KzaJVkkCW0hRJ1xbmrLqkmRuLe05+nP97DlyHm1S7I4dxTa06dPx8rq+nIls2bNwtvbGx8fH+Lj42u8OCFEw9O6mR2rJkfRroUdU5bvYtvRXLVLsijVDu2EhAQuXbpk/v6XX34hKSmJtLQ0Nm3axHPPPVfhuBBC3E7b5qbgdnG0ZeJnO9l+7ILaJVmMaoW2Xq9n1qxZvPvuu+b74uPjGTduHDqdDldXV3r16sX69etrrVAhRMPi2qIJcZOjcLK3YcKynew6kad2SRahWqE9e/ZsJk6ciIuLi/m+7Oxs3N3dzd97eHiQlSVXPQkhqs/dyZ5Vk6NwtLNi3Kc72ZuZr3ZJ9V6Vob1//36Sk5MZP358hfsVRanWCyxYsAB/f3/zLT9fGkUIcZ2nswOrJkfRxEbHk0t3cCD7otol1WtVhva2bdtITU2lY8eOeHp6Ul5ejqenJy4uLhV61pmZmbi5ud10/vTp00lNTTXfWrZsWbPvQAhh8Tq5NGXVpEhsdFoe/ySZg6cluG9Ho1S3y3yVlZUVZWVlbNiwgTlz5rBp0yZycnKIiooiNTUVR0fHSs/39/cnNTX1nooWQjRMh3MKGb14OwCrp/SgS9vK86Qhqioj73qedv/+/YmKisLHx4fo6GjmzZtXZWALIURlfNs2Y8WkSIwKjFmynaPnitQuqd654572vZKethCiKvuzCxizJBk7ax1fTInCy6Wp2iXVmVrraQshRG0JdmvB8gnduVJaTuzHyZy8UKx2SfWGhLYQol4K9WjJp+MjKCwxEPtxMll5l9UuqV6Q0BZC1FsRnk4sHRfBhWI9oz/ezumCK2qXpDoJbSFEvRbl1YpPxkZwvsgU3DkXS9QuSVUS2kKIeq+XtzOLn+zGmYISYj/ezrmixhvcEtpCCIvQz8eFhY+HkZV/mTEfJ5N7Sa92SaqQ0BZCWIz7/drwYWwYx3OLeXxJMnnFpWqXVOcktIUQFmVgQFveHx1K+rlLPL4kmYLLjSu4JbSFEBZncFA75o3syuGcQp5cuoOLVwxql1RnJLSFEBZpWIgr7wzvyoFTFxn36Q6KShpHcEtoCyEs1mPhbvw9Joi9mQVMWLaTYn2Z2iXVOgltIYRFGxXhwVuPBLLzRD4TP9vJldJytUuqVRLaQgiL93hUB94c4s/2Y3lMXr6LEkPDDW4JbSFEgzCuV0dee8iPxKO5PPX57gYb3BLaQogGY1IfL156sAtbjpxn+so9lJYZ1S6pxkloCyEalGnR3jzf34dfD59jRtweDOUNK7gltIUQDc7M+zsz4z5vfj54lv9bnUJZAwpuK7ULEEKI2vB8fx8M5QqLtmRgpdMwb2QIOq1G7bLumYS2EKJB0mg0vPxgFwzlRj5JPI6VVss7w4PRWnhwS2gLIRosjUbDaw/5UVZu5LPfTmKt0/C3R4MsOrgltIUQDZpGo+HNoQEYjAqrkjOx0mmYMywQjcYyg1tCWwjR4Gk0Gt4aFkhZuZEV2zOx0mp5Y4i/RQa3hLYQolHQajXMjQmmrFxhWdIJrHUaXhnsZ3HBLaEthGg0dFoN74zoisGo8HHCcax1Wl4c2MWigltCWwjRqOi0Gv49sitl5Ub+szkDa52W5/r7qF1WtcnFNUKIRsdKp+X90aH092/D/F/T+XBjutolVZuEthCiUbLWafkwNpQ/dHHh3fVH+GhLhtolVYuEthCi0bK10rHw8XD6dHZm7o+H+STxuNolVUlCWwjRqNlZ6/j4yW707NSKOd+lsvy3E2qXVCkJbSFEo2dnrWPJ2G507+jE698cZFVyptol3ZaEthBCAPY2ViwdF0F4h5a88tUB1uzKUrukW5LQFkKIq5raWrFsfARd3Vvwcvx+vtqbrXZJN5HQFkKIGzjaWbN8QncC2jfjhTX7+HbfabVLqkBCWwgh/kfzJtasmBhJl7bN+L8vUvjxwBm1SzKT0BZCiFtoYW/DykmReLs0ZUbcXjaknlW7JEBCWwghbsvJwYYVkyLp0MqeaSt3s+nwObVLktAWQojKuDjaEjc5CreW9jy1Yjdbj5xXtR4JbSGEqELrZnasmhxJ22Z2TF6+i6SjuarVIqEthBDV0K55E1ZNjsS5qS0TP9tF8rELqtQhoS2EENXk1tKe1VOiaGFvzfhlO9l9Mq/Oa6hWaA8YMICQkBCCgoIYPnw4hYWFAMyaNQtvb298fHyIj4+v1UKFEKI+cHeyJ25yFI52VoxbupOUrII6ff1qhfZ///tfUlJSOHDgAG5ubsybN49ffvmFpKQk0tLS2LRpE8899xyXLl2q7XqFEEJ1ns4OrJocha21jic/Seb3Uxfr7LWrFdrNmzcHwGg0UlJSgkajIT4+nnHjxqHT6XB1daVXr16sX7++VosVQoj6opNLU+ImR2Kt0/L4J8mkni6sk9et9pj2o48+SuvWrUlLS+OFF14gOzsbd3d383EPDw+ysurnAitCCFEbOrdxZMWkSAAe/ySZtJyiWn/Naof2V199xenTp3Fzc2Pt2rUoilKt8xYsWIC/v7/5lp+ff9fFCiFEfePXrhkrJkZSVm5kzJLtHD1Xu8PEdzR7xMbGhj/+8Y989dVXuLu7V+hZZ2Zm4ubmdtM506dPJzU11Xxr2bLlvVcthBD1SKBrcz6fGIneYCT24+0czy2utdeqMrSLioo4c8a0WIrRaGTdunUEBAQQExPDsmXLKC8v59SpUyQmJjJgwIBaK1QIIeqzru4t+Gxid4r1ZYxevJ2svMu18jpWVT2gqKiIYcOGodfrMRqNREZG8tprr2Fvb8+GDRvw8fFBq9Uyb948HB0da6VIIYSwBGEeLVk2oTsfbcmgVVObWnkNjVLdweka4u/vT2pqal2+pBBCWIyqMlKuiBRCCAsioS2EEBZEQlsIISyIhLYQQlgQCW0hhLAgEtpCCGFBJLSFEMKCSGgLIYQFqfOLa5o1a3bLNUqqIz8/v0GsXSLvo35pCO+jIbwHkPcBkJ2dbd5o5lbqPLTvRUO5mlLeR/3SEN5HQ3gPIO+jOmR4RAghLIiEthBCWBCLCu3p06erXUKNkPdRvzSE99EQ3gPI+6gOixrTFkKIxs6ietpCCNHY1XloP/vss7i5uWFldX3/hcLCQkaNGkVQUBDBwcGsW7euwjl///vf6dKlCwEBAUyYMMF8/5o1a/Dx8aFTp068+uqrdfYeGpI7bY+hQ4cSEhJCSEgI3t7eFaY1SXvcuzttj927dxMVFUVISAhdu3atcEza497daXskJCQQERFBUFAQAwcO5OzZs+ZjNdYeSh1LSEhQzpw5o+h0OvN9L730kvL8888riqIo+fn5SlBQkFJUVKQoiqLExcUpw4YNU0pLSxVFUZQzZ84oiqIoBQUFiru7u3L69GnFYDAoPXr0UDZv3lzH78by3Wl73GjOnDnK5MmTFUWR9qgpd9oePXv2VH7++WdFURTl0KFDirOzs6Io0h415U7aw2g0Kq6ursqePXsURVGUL7/8Uhk/fryiKDXbHnXe0+7duzdt27atcN/vv//Ogw8+CECLFi3w9fXlxx9/BGD+/Pn89a9/xdraGsB87k8//UR0dDTt2rXDysqKsWPHEh8fD8CiRYsIDAyka9euhIWFUVJSUldvz+LcaXvcaOXKlTzxxBOAtEdNuZv2KCgoMH9t164dIO1RU+6kPXJzc1EUhdDQUAAGDhzImjVrgJptj3oxph0aGsqaNWswGo3mTYKv7fR++PBhfvzxRyIjI+nTpw9btmwBTFcNubu7m5/Dw8PDfM7bb7/Nzp072bdvH5s2bcLGpnb2amuoKmuPa3bv3k1JSQm9e/cGpD1qU2Xt8Z///Ifnn38eDw8PBg0axNKlSwFpj9p0u/ZwdnbGysqKzZs3A7B69WqKi4vJy8ur0faoF6H95z//Ga1WS1hYGFOmTKFfv37odDoAysrKKC4uJjk5mYULFzJ69GiKiopQKpn0EhoaSmxsLEuWLEGv16PV1ou3aTEqa49rVqxYwZgxY9BoNADSHrWosvb46KOP+Nvf/kZmZiZr167lySefRFEUaY9adLv20Gg0xMfHM3v2bMLDw0lPT8fZ2RmdTlej7VHlbux1wcHBgY8++sj8/bBhw/D19QXA3d2dkSNHAhAYGIibmxsZGRm4u7uzf/9+8zmZmZnmNU2+/vprtm/fzoYNG+jWrRubN2/Gy8urDt+RZausPQDKy8tZvXq1uUcBSHvUosra47PPPuO9994D4P777yc3N5f8/Hxpj1pUWXt069aNjRs3AnDhwgWWL19O8+bNa7Y97nqE/h7dOLBfUFCglJSUKIqiKImJiUpQUJBSXl6uKIqi/OUvf1HmzZunKIqiZGZmKm3btlXy8/OVgoICxc3NrcLA/saNGxWDwaBkZGSYn3vAgAHKd999V4fvzDJVtz0URVF++uknJSIiosL50h41q7rt4efnZ/773LNnj9K+fXvzOdIeNae67ZGTk6MoiqIYjUZl2rRpyttvv20+p6bao85De8qUKYqrq6sCKK6ursq0adOU5ORkxdvbW/H19VWio6OVw4cPmx9fWFioPProo0pAQIDStWtX5euvvzYfi4uLU7y9vRUvLy9l1qxZiqIoSklJidK7d28lMDBQCQwMVMaPH2+eeSJudqftoSiK8sQTTyjz58+/6bmkPe7dnbbHtm3blPDwcCU4OFgJDQ1VNm7caD4m7XHv7rQ9Zs2apfj4+CidO3dW/u///k8xGAzmYzXVHnJFpBBCWBD5BEIIISyIhLYQQlgQCW0hhLAgEtpCCGFBJLSFEMKCSGgLIYQFkdAWtU6j0RASEkJAQAB+fn786U9/oqioqNZfNzo6msTExBp5ri+//BI/Pz9CQkIoLy+vcMzT05Ps7Oybztm1axdPP/30bZ/zvffeq7Drdk3WKxouCW1R63Q6HSkpKRw8eJDt27eTlZVFTEyM2mXdkcWLF/PBBx+QkpJy0zost9OtWzcWLVp00/2KomA0Gm8KbSGqQ0Jb1KnmzZuzePFifvvtNw4cOADA5s2b6d27N+Hh4QwYMMC8+llubi6jRo0iODiY4OBg4uLiAJgxY4Z5ofnHH38cvV4PQF5eHg899BD+/v4MHz68whKX+/fv57777iM8PJzevXubX/t/vf766wQGBhIYGMjs2bMBePXVV0lMTGTq1KmMHz/+lud98MEHhISE4O/vz6ZNm8zv64EHHjD/uUePHgwfPpzAwEDefvttTp8+zcCBAwkJCaG0tBSAdevWERUVhZeXF1999dU9/V2LBqoWrvwUooIb1224pmvXrsrq1auVCxcuKD169FAKCgoURVGUNWvWKCNHjlQURVFiY2OV2bNnm8+5cOGCoiiKkpuba75vxowZyqJFixRFUZSZM2eaLw/es2ePotVqlYSEBKW0tFSJjIxUsrOzFUVRlB07dijdu3e/qaavv/5a6dGjh3LlyhXlypUrSkREhPLDDz8oiqIo/fr1UxISEm75/jp06KC8+OKL5td1c3NT9Hq9smnTJuX+++9XFEVRNm3apNjY2CipqakVzsvKyjJ/369fP+Wpp55SFEVRdu7cqXh7e9/mb1Q0ZvVilT/R+CiKgkajISkpibS0NPr16weA0WjE0dERgJ9//pmFCxeaz3FycgLgm2++YeHChZSUlHDx4kWMRiMAW7duZeXKlYBpucvg4GAA0tLSOHjwIA899JD5ufLy8m6qafPmzYwZMwY7OzsAYmNj2bRpE4MGDary/YwdO9b8us7OzqSnp9/0mLCwMPz8/Cp9nhEjRgAQHh7OyZMnq3xd0fhIaIs6V1hYSEZGBv7+/hw/fpw+ffrw9ddf3/Kx19brvubEiRO8+eab7N69GxcXFz744AP27dtX6espikKnTp1ISUmp9HH/+1r/+/2dnHsrDg4OVT7G1tbW/HzXfhgJcSMZ0xZ1qrCwkKeffpqePXsSGBhIjx492LFjB7///jsABoPBPN48cOBA5s+fbz43Ly+PwsJCmjRpQsuWLbl8+TKff/65+Xi/fv3MPe2UlBTz8/j6+lJUVMSvv/4KmEJ87969N9UWHR3NqlWr0Ov1lJSUEBcXx3333Vet97V8+XIA9u3bx4ULF+jcuXOV5zg6OsoHkeKOSU9b1Lry8nJCQkIwGAwYjUYefvhhFi9eDICzszNxcXFMmjSJK1euUFZWxrRp0wgKCmL+/PlMmzaNwMBAdDodr7zyCqNGjSI6OhpfX19cXFzo3r27+QPH119/nSeeeAJ/f38CAgLo1q0bANbW1nz99dfMnDmT559/HoPBQExMjHkvv2uGDh3Krl27CA8PB2DkyJHmvQCr49oHisuWLavWFl5Tp07l0UcfpUmTJuzYsaParyMaN1maVQghLIgMjwghhAWR0BZCCAsioS2EEBZEQlsIISyIhLYQQlgQCW0hhLAgEtpCCGFBJLSFEMKC/D/ACvgdGcKolwAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 64;\n",
       "            var nbb_formatted_code = \"table.plot()\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "table.plot()\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 65;\n",
       "            var nbb_formatted_code = \"tables23 = [\\n    make_marriage_table(resample_by_cycle(resp2), \\\"ager >=22 and ager < 25\\\")\\n    for i in range(101)\\n]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tables23 = [\n",
    "    make_marriage_table(resample_by_cycle(resp2), \"ager >=22 and ager < 25\")\n",
    "    for i in range(101)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 66;\n",
       "            var nbb_formatted_code = \"plot_marriage_tables(tables23)\\nmake_title(title=\\\"Percent ever married age 22-24\\\", subtitle=\\\"Males, NSFG 2002-2023 \\\")\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_marriage_tables(tables23)\n",
    "make_title(title=\"Percent ever married age 22-24\", subtitle=\"Males, NSFG 2002-2023 \")\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 67;\n",
       "            var nbb_formatted_code = \"tables34 = [\\n    make_marriage_table(resample_by_cycle(resp2), \\\"ager >=32 and ager < 35\\\")\\n    for i in range(101)\\n]\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tables34 = [\n",
    "    make_marriage_table(resample_by_cycle(resp2), \"ager >=32 and ager < 35\")\n",
    "    for i in range(101)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 375x277.5 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        setTimeout(function() {\n",
       "            var nbb_cell_id = 68;\n",
       "            var nbb_formatted_code = \"plot_marriage_tables(tables34)\\nmake_title(title=\\\"Percent ever married age 32-34\\\", subtitle=\\\"Males, NSFG 2002-2023 \\\")\\ndecorate(xlabel=\\\"Decade of birth\\\")\";\n",
       "            var nbb_cells = Jupyter.notebook.get_cells();\n",
       "            for (var i = 0; i < nbb_cells.length; ++i) {\n",
       "                if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
       "                    nbb_cells[i].set_text(nbb_formatted_code);\n",
       "                    break;\n",
       "                }\n",
       "            }\n",
       "        }, 500);\n",
       "        "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_marriage_tables(tables34)\n",
    "make_title(title=\"Percent ever married age 32-34\", subtitle=\"Males, NSFG 2002-2023 \")\n",
    "decorate(xlabel=\"Decade of birth\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}