diff --git a/notebooks/2_match_households_and_individuals.ipynb b/notebooks/2_match_households_and_individuals.ipynb
index 2d055d4..05e5b85 100644
--- a/notebooks/2_match_households_and_individuals.ipynb
+++ b/notebooks/2_match_households_and_individuals.ipynb
@@ -22,22 +22,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import pickle as pkl\n",
+    "\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "import geopandas as gpd\n",
-    "from sklearn.neighbors import NearestNeighbors\n",
-    "import pickle as pkl\n",
     "\n",
-    "from acbm.matching import match_individuals, match_psm\n",
+    "from acbm.matching import match_categorical, match_individuals\n",
     "from acbm.preprocessing import (\n",
     "    count_per_group,\n",
-    "    nts_filter_by_region,\n",
+    "    #nts_filter_by_region,\n",
     "    nts_filter_by_year,\n",
     "    num_adult_child_hh,\n",
     "    transform_by_group,\n",
     "    truncate_values,\n",
-    "    match_coverage_col\n",
     ")\n",
     "\n",
     "pd.set_option('display.max_columns', None)"
@@ -454,7 +452,8 @@
    "outputs": [],
    "source": [
     "# temporary reduction of the dataset for quick analysis\n",
-    "spc = spc.head(15000)"
+    "spc = spc.head(15000)\n",
+    "#spc = spc.head(500000)"
    ]
   },
   {
@@ -642,9 +641,9 @@
    "source": [
     "years = [2019, 2021, 2022]\n",
     "\n",
-    "nts_individuals_filtered = nts_filter_by_year(nts_individuals, psu, years)\n",
-    "nts_households_filtered = nts_filter_by_year(nts_households, psu, years)\n",
-    "nts_trips_filtered = nts_filter_by_year(nts_trips, psu, years)\n",
+    "nts_individuals = nts_filter_by_year(nts_individuals, psu, years)\n",
+    "nts_households = nts_filter_by_year(nts_households, psu, years)\n",
+    "nts_trips = nts_filter_by_year(nts_trips, psu, years)\n",
     "\n"
    ]
   },
@@ -665,9 +664,9 @@
    "source": [
     "# regions = ['Yorkshire and the Humber', 'North West']\n",
     "\n",
-    "# nts_individuals_filtered = nts_filter_by_region(nts_individuals_filtered, psu, regions)\n",
-    "# nts_households_filtered = nts_filter_by_region(nts_households_filtered, psu, regions)\n",
-    "# nts_trips_filtered = nts_filter_by_region(nts_trips_filtered, psu, regions)\n"
+    "# nts_individuals = nts_filter_by_region(nts_individuals, psu, regions)\n",
+    "# nts_households = nts_filter_by_region(nts_households, psu, regions)\n",
+    "# nts_trips = nts_filter_by_region(nts_trips, psu, regions)\n"
    ]
   },
   {
@@ -974,13 +973,13 @@
     }
    ],
    "source": [
-    "# bar plot showing spc_edited.salary_yearly_hh_cat and nts_households_filtered.HHIncome2002_B02ID side by side\n",
+    "# bar plot showing spc_edited.salary_yearly_hh_cat and nts_households.HHIncome2002_B02ID side by side\n",
     "fig, ax = plt.subplots(1, 2, figsize=(12, 6), sharey=True)\n",
     "ax[0].bar(spc_edited['salary_yearly_hh_cat'].value_counts().index, spc_edited['salary_yearly_hh_cat'].value_counts().values)\n",
     "ax[0].set_title('SPC')\n",
     "ax[0].set_xlabel('Income Bracket - Household level')\n",
     "ax[0].set_ylabel('No of Households')\n",
-    "ax[1].bar(nts_households_filtered['HHIncome2002_B02ID'].value_counts().index, nts_households_filtered['HHIncome2002_B02ID'].value_counts().values)\n",
+    "ax[1].bar(nts_households['HHIncome2002_B02ID'].value_counts().index, nts_households['HHIncome2002_B02ID'].value_counts().values)\n",
     "ax[1].set_title('NTS')\n",
     "ax[1].set_xlabel('Income Bracket - Household level')\n",
     "plt.show()\n",
@@ -991,7 +990,7 @@
     "ax[0].set_title('SPC')\n",
     "ax[0].set_xlabel('Income Bracket - Household level')\n",
     "ax[0].set_ylabel('Fraction of Households')\n",
-    "ax[1].bar(nts_households_filtered['HHIncome2002_B02ID'].value_counts(normalize=True).index, nts_households_filtered['HHIncome2002_B02ID'].value_counts(normalize=True).values)\n",
+    "ax[1].bar(nts_households['HHIncome2002_B02ID'].value_counts(normalize=True).index, nts_households['HHIncome2002_B02ID'].value_counts(normalize=True).values)\n",
     "ax[1].set_title('NTS')\n",
     "ax[1].set_xlabel('Income Bracket - Household level')\n",
     "plt.show()"
@@ -1020,7 +1019,7 @@
    ],
    "source": [
     "# get the % of households in each income bracket for the nts\n",
-    "nts_households_filtered['HHIncome2002_B02ID'].value_counts(normalize=True) * 100"
+    "nts_households['HHIncome2002_B02ID'].value_counts(normalize=True) * 100"
    ]
   },
   {
@@ -1453,13 +1452,13 @@
     }
    ],
    "source": [
-    "# bar plot of counts_df['pwkstat_NTS_match'] and nts_households_filtered['HHoldEmploy_B01ID']\n",
+    "# bar plot of counts_df['pwkstat_NTS_match'] and nts_households['HHoldEmploy_B01ID']\n",
     "fig, ax = plt.subplots(1, 2, figsize=(12, 6))\n",
     "ax[0].bar(counts_df['pwkstat_NTS_match'].value_counts().index, counts_df['pwkstat_NTS_match'].value_counts().values)\n",
     "ax[0].set_title('SPC')\n",
     "ax[0].set_xlabel('Employment status - Household level')\n",
     "ax[0].set_ylabel('Frequency')\n",
-    "ax[1].bar(nts_households_filtered['HHoldEmploy_B01ID'].value_counts().index, nts_households_filtered['HHoldEmploy_B01ID'].value_counts().values)\n",
+    "ax[1].bar(nts_households['HHoldEmploy_B01ID'].value_counts().index, nts_households['HHoldEmploy_B01ID'].value_counts().values)\n",
     "ax[1].set_title('NTS')\n",
     "ax[1].set_xlabel('Employment status - Household level')\n",
     "plt.show()\n",
@@ -1470,7 +1469,7 @@
     "ax[0].set_title('SPC')\n",
     "ax[0].set_xlabel('Employment status - Household level')\n",
     "ax[0].set_ylabel('Frequency (normalized)')\n",
-    "ax[1].bar(nts_households_filtered['HHoldEmploy_B01ID'].value_counts().index, nts_households_filtered['HHoldEmploy_B01ID'].value_counts(normalize=True).values)\n",
+    "ax[1].bar(nts_households['HHoldEmploy_B01ID'].value_counts().index, nts_households['HHoldEmploy_B01ID'].value_counts(normalize=True).values)\n",
     "ax[1].set_title('NTS')\n",
     "ax[1].set_xlabel('Employment status - Household level')\n",
     "plt.show()\n",
@@ -1849,28 +1848,28 @@
     "\n",
     "\n",
     "census_2011_to_nts_B03ID = {\n",
-    "    'Urban major conurbation': 'Urban', \n",
+    "    'Urban major conurbation': 'Urban',\n",
     "    'Urban minor conurbation': 'Urban',\n",
     "    'Urban city and town': 'Urban',\n",
     "    'Urban city and town in a sparse setting': 'Urban',\n",
-    "    'Rural town and fringe': 'Rural', \n",
+    "    'Rural town and fringe': 'Rural',\n",
     "    'Rural town and fringe in a sparse setting': 'Rural',\n",
     "    'Rural village': 'Rural',\n",
     "    'Rural village in a sparse setting': 'Rural',\n",
-    "    'Rural hamlets and isolated dwellings': 'Rural', \n",
+    "    'Rural hamlets and isolated dwellings': 'Rural',\n",
     "    'Rural hamlets and isolated dwellings in a sparse setting': 'Rural'\n",
     "}\n",
     "\n",
     "census_2011_to_nts_B04ID = {\n",
-    "    'Urban major conurbation': 'Urban Conurbation', \n",
+    "    'Urban major conurbation': 'Urban Conurbation',\n",
     "    'Urban minor conurbation': 'Urban Conurbation',\n",
     "    'Urban city and town': 'Urban City and Town',\n",
     "    'Urban city and town in a sparse setting': 'Urban City and Town',\n",
-    "    'Rural town and fringe': 'Rural Town and Fringe', \n",
+    "    'Rural town and fringe': 'Rural Town and Fringe',\n",
     "    'Rural town and fringe in a sparse setting': 'Rural Town and Fringe',\n",
     "    'Rural village': 'Rural Village, Hamlet and Isolated Dwellings',\n",
     "    'Rural village in a sparse setting': 'Rural Village, Hamlet and Isolated Dwellings',\n",
-    "    'Rural hamlets and isolated dwellings': 'Rural Village, Hamlet and Isolated Dwellings', \n",
+    "    'Rural hamlets and isolated dwellings': 'Rural Village, Hamlet and Isolated Dwellings',\n",
     "    'Rural hamlets and isolated dwellings in a sparse setting': 'Rural Village, Hamlet and Isolated Dwellings'\n",
     "}\n"
    ]
@@ -2277,7 +2276,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nts_pensioners = count_per_group(df = nts_individuals_filtered,\n",
+    "nts_pensioners = count_per_group(df = nts_individuals,\n",
     "                                 group_col='HouseholdID',\n",
     "                                 count_col='OfPenAge_B01ID',\n",
     "                                 values=[1],\n",
@@ -2286,7 +2285,7 @@
     "nts_pensioners.head()\n",
     "\n",
     "# join onto the nts household df\n",
-    "nts_households_filtered = nts_households_filtered.merge(nts_pensioners, left_on='HouseholdID', right_index=True, how='left')"
+    "nts_households = nts_households.merge(nts_pensioners, left_on='HouseholdID', right_index=True, how='left')"
    ]
   },
   {
@@ -2466,9 +2465,9 @@
    "source": [
     "\n",
     "# Create a new column in NTS\n",
-    "nts_households_filtered.loc[:, 'NumCar_SPC_match'] = nts_households_filtered['NumCar'].apply(truncate_values, upper = 2)\n",
+    "nts_households.loc[:, 'NumCar_SPC_match'] = nts_households['NumCar'].apply(truncate_values, upper = 2)\n",
     "\n",
-    "nts_households_filtered[['NumCar', 'NumCar_SPC_match']].head(20)"
+    "nts_households[['NumCar', 'NumCar_SPC_match']].head(20)"
    ]
   },
   {
@@ -2567,10 +2566,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Create a new column in nts_households_filtered\n",
-    "nts_households_filtered['tenure_nts_for_matching'] = (nts_households_filtered['Ten1_B02ID']\n",
+    "# Create a new column in nts_households\n",
+    "nts_households['tenure_nts_for_matching'] = (nts_households['Ten1_B02ID']\n",
     "                                                    .map(matching_dict_nts_tenure) # map the values to the new dictionary\n",
-    "                                                    .fillna(nts_households_filtered['Ten1_B02ID'])) # fill the NaNs with the original values\n",
+    "                                                    .fillna(nts_households['Ten1_B02ID'])) # fill the NaNs with the original values\n",
     "\n",
     "# Create a new column in spc\n",
     "spc_edited['tenure_spc_for_matching'] = (spc_edited['tenure']\n",
@@ -3080,7 +3079,7 @@
     }
    ],
    "source": [
-    "nts_matching = nts_households_filtered[[\n",
+    "nts_matching = nts_households[[\n",
     "    'HouseholdID','HHIncome2002_B02ID',\n",
     "    'HHoldNumAdults', 'HHoldNumChildren', 'num_pension_age_nts',\n",
     "    'HHoldEmploy_B01ID', 'NumCar_SPC_match',\n",
@@ -3126,7 +3125,7 @@
    ],
    "source": [
     "# column_names (keys) for the dictionary\n",
-    "matching_ids = ['household_id', 'yearly_income', 'number_adults', 'number_children', 'num_pension_age', \n",
+    "matching_ids = ['household_id', 'yearly_income', 'number_adults', 'number_children', 'num_pension_age',\n",
     "                'employment_status', 'number_cars', 'tenure_status', 'rural_urban_2_categories', 'rural_urban_4_categories']\n",
     "\n",
     "# i want the value to be a list with spc_matching and nts_matching\n",
@@ -3138,270 +3137,71 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Attempt 1: Match on all possible columns"
+    "#### Match on a subset of columns (exclude salary, tenure, and employment status)\n",
+    "\n",
+    "To decide on the subset of columns to match on, we explore the results from different combinations. This is shown in a separate notebook: `2.1_sandbox-match_households.ipynb`."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 34,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "991 households in the SPC had no match\n",
-      "14.7 % of households in the SPC had no match\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# columns for matching\n",
-    "keys = ['yearly_income', 'number_adults', 'number_children', 'num_pension_age', \n",
-    "        'employment_status', 'number_cars', 'tenure_status', 'rural_urban_2_categories']\n",
-    "\n",
-    "\n",
+    "keys = ['number_adults', 'number_children', 'num_pension_age', 'number_cars', 'rural_urban_2_categories']\n",
+    "# extract equivalent column names from dictionary\n",
     "spc_cols = [matching_dfs_dict[key][0] for key in keys]\n",
-    "nts_cols = [matching_dfs_dict[key][1] for key in keys]\n",
-    "\n",
-    "# match\n",
-    "spc_nts_1 = spc_matching.merge(nts_matching,\n",
-    "                               left_on= spc_cols,\n",
-    "                               right_on= nts_cols,\n",
-    "                               how = 'left')\n",
-    "\n",
-    "# Calculate how many rows from nts_matching are matched onto each hid in spc_matching,\n",
-    "spc_nts_1['count'] = spc_nts_1.groupby('hid')['HouseholdID'].transform('count')\n",
-    "\n",
-    "spc_nts_1_hist = spc_nts_1.drop_duplicates(subset='hid')\n",
-    "\n",
-    "\n",
-    "# plot a histogram of the counts and label the axis and title\n",
-    "plt.hist(spc_nts_1_hist['count'], bins=50)\n",
-    "plt.xlabel('Number of matches per household')\n",
-    "plt.ylabel('Number of households')\n",
-    "plt.title('Categorical Matching')\n",
-    "\n",
-    "print(spc_nts_1_hist[spc_nts_1_hist['count'] == 0].shape[0], \"households in the SPC had no match\")\n",
-    "print(round((spc_nts_1_hist[spc_nts_1_hist['count'] == 0].shape[0] / spc_matching['hid'].unique().shape[0]) * 100, 1), \"% of households in the SPC had no match\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>Total</th>\n",
-       "      <th>Matched</th>\n",
-       "      <th>Percentage Matched</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>num_children</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>4666</td>\n",
-       "      <td>4489.0</td>\n",
-       "      <td>96.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1786</td>\n",
-       "      <td>1088.0</td>\n",
-       "      <td>61.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>218</td>\n",
-       "      <td>132.0</td>\n",
-       "      <td>61.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>51</td>\n",
-       "      <td>25.0</td>\n",
-       "      <td>49.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>4</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "              Total  Matched  Percentage Matched\n",
-       "num_children                                    \n",
-       "0              4666   4489.0                96.0\n",
-       "1              1786   1088.0                61.0\n",
-       "2               218    132.0                61.0\n",
-       "3                51     25.0                49.0\n",
-       "4                 4      NaN                 NaN"
-      ]
-     },
-     "execution_count": 35,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# calculate matching coverage for all columns\n",
-    "\n",
-    "match_coverage_1 = {key: match_coverage_col(data=spc_nts_1, \n",
-    "                                            id_x='hid', \n",
-    "                                            id_y='HouseholdID',\n",
-    "                                            column=matching_dfs_dict[key][0]) \n",
-    "                    for key in matching_dfs_dict.keys()\n",
-    "            }\n",
-    "\n",
-    "# extract any df from the list\n",
-    "match_coverage_1['number_children']\n",
-    "\n"
+    "nts_cols = [matching_dfs_dict[key][1] for key in keys]\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Attempt 2: Match on a subset of columns (exclude salary)"
+    "Match"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "674 households in the SPC had no match\n",
-      "10.0 % of households in the SPC had no match\n"
+      "matching rows  0 to 50000  out of  6725\n"
      ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
-    "# columns for matching\n",
-    "keys = ['number_adults', 'number_children', 'num_pension_age', 'employment_status', \n",
-    "        'number_cars', 'tenure_status','rural_urban_2_categories']\n",
-    "# extract equivalent column names from dictionary\n",
-    "spc_cols = [matching_dfs_dict[key][0] for key in keys]\n",
-    "nts_cols = [matching_dfs_dict[key][1] for key in keys]\n",
-    "\n",
-    "# match\n",
-    "spc_nts_2 = spc_matching.merge(nts_matching,\n",
-    "                               left_on= spc_cols,\n",
-    "                               right_on= nts_cols,\n",
-    "                               how = 'left')\n",
-    "\n",
-    "# Calculate how many rows from nts_matching are matched onto each hid in spc_matching,\n",
-    "spc_nts_2['count'] = spc_nts_2.groupby('hid')['HouseholdID'].transform('count')\n",
-    "\n",
-    "spc_nts_2_hist = spc_nts_2.drop_duplicates(subset='hid')\n",
-    "\n",
-    "\n",
-    "# plot a histogram of the counts and label the axis and title\n",
-    "plt.hist(spc_nts_2_hist['count'], bins=50)\n",
-    "plt.xlabel('Number of matches per household')\n",
-    "plt.ylabel('Number of households')\n",
-    "plt.title('Categorical Matching')\n",
-    "\n",
-    "\n",
-    "print(spc_nts_2_hist[spc_nts_2_hist['count'] == 0].shape[0], \"households in the SPC had no match\")\n",
-    "print(round((spc_nts_2_hist[spc_nts_2_hist['count'] == 0].shape[0] / spc_matching['hid'].unique().shape[0]) * 100, 1), \"% of households in the SPC had no match\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# calculate matching coverage for all columns\n",
-    "\n",
-    "match_coverage_2 = {key: match_coverage_col(data=spc_nts_2, \n",
-    "                                            id_x='hid', \n",
-    "                                            id_y='HouseholdID',\n",
-    "                                            column=matching_dfs_dict[key][0]) \n",
-    "                    for key in matching_dfs_dict.keys()\n",
-    "            }\n",
-    "\n",
-    "# extract any df from the list\n",
-    "#match_coverage_2['number_cars']"
+    "matches_hh_level = match_categorical(\n",
+    "    df_pop = spc_matching,\n",
+    "    df_pop_cols = spc_cols,\n",
+    "    df_pop_id = 'hid',\n",
+    "    df_sample = nts_matching,\n",
+    "    df_sample_cols = nts_cols,\n",
+    "    df_sample_id = 'HouseholdID',\n",
+    "    chunk_size = 50000,\n",
+    "    show_progress = True)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Attempt 3: Match on a subset of columns (exclude salary and tenure)"
+    "Plot number of matches for each SPC household"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "547 households in the SPC had no match\n",
-      "8.1 % of households in the SPC had no match\n"
-     ]
-    },
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkQAAAHHCAYAAABeLEexAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAABQpklEQVR4nO3deVwVZf8//tcBWYUDskMioBiCoigmgnsSiGaa3pU7KmkprigqlYp6F6hpLrfZx76JVm7pbeYWinsq7uEOiuJSgeYCR0RZr98f/ZjbCUSOHdZ5PR+PecRc13Vm3jND8Wq2oxJCCBAREREpmF5VF0BERERU1RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIqEaJjo6GSqWqsOUPHToUrq6uFbb8ytK5c2c0a9bsheNu3LgBlUqFVatWVXxRRNUYAxFRDXPt2jV88MEHaNiwIYyNjaFWq9GuXTssXrwYT5480Xp5X375Jf8YvoTOnTtDpVKhcePGpfYnJCRApVJBpVJh06ZNWi//0qVLiI6Oxo0bN/5hpURUHgxERDXIjh074O3tjR9++AE9e/bE0qVLERMTgwYNGiAyMhLjx4/Xepk1LRB98sknLxX8KoKxsTFSU1Nx4sSJEn1r1qyBsbHxSy/70qVLmDVrVoUHIhcXFzx58gSDBw+u0PUQVXd1qroAIiqftLQ09OvXDy4uLti3bx8cHR2lvvDwcKSmpmLHjh1VWGHFevz4MerWrYs6deqgTp3q8Z+uRo0aoaCgAOvWrUObNm2k9qdPn+LHH39Ejx498N///rcKK3wxlUr1j4IbUW3BM0RENcS8efOQnZ2Nb775RhaGirm7u8vOEMXFxeH111+HnZ0djIyM4OXlheXLl8s+4+rqiosXL+LgwYPS5Z3OnTtL/ZmZmZgwYQKcnZ1hZGQEd3d3zJ07F0VFRbLl3L9/H4MHD4ZarYalpSVCQ0Nx9uzZUu9N2bdvHzp06IC6devC0tISvXr1wuXLl2Vjiu8TunTpEgYMGIB69eqhffv2sr6/+/7779GmTRuYmpqiXr166NixI3bv3i31//TTT+jRowecnJxgZGSERo0aYc6cOSgsLCx7x79A//79sWHDBtk+2bZtG3JycvDuu++WGH/z5k2MHj0aHh4eMDExgbW1Nd555x3ZmaBVq1bhnXfeAQB06dJFOjYHDhyQxvz888/o1KkTzM3NoVar8dprr2Ht2rUl1nfp0iV06dIFpqameOWVVzBv3jxZf2n3EA0dOhRmZmb4/fff0bt3b5iZmcHW1haTJ08usb+0OfZE1Vn1+N8sInqhbdu2oWHDhggICCjX+OXLl6Np06Z46623UKdOHWzbtg2jR49GUVERwsPDAQCLFi3C2LFjYWZmho8//hgAYG9vDwDIyclBp06d8Pvvv+ODDz5AgwYNcPToUURFRSE9PR2LFi0CABQVFaFnz544ceIERo0ahSZNmuCnn35CaGhoiZr27NmDkJAQNGzYENHR0Xjy5AmWLl2Kdu3a4cyZMyVuZn7nnXfQuHFjfPbZZxBCPHdbZ82ahejoaAQEBGD27NkwNDTE8ePHsW/fPgQFBQH4K2SYmZkhIiICZmZm2LdvH2bMmAGNRoP58+eXa5+WZsCAAYiOjsaBAwfw+uuvAwDWrl2Lrl27ws7OrsT4kydP4ujRo+jXrx/q16+PGzduYPny5ejcuTMuXboEU1NTdOzYEePGjcOSJUvw0UcfwdPTEwCkf65atQrDhw9H06ZNERUVBUtLS/z666+Ij4/HgAEDpHU9fPgQ3bp1Q58+ffDuu+9i06ZNmDp1Kry9vRESElLmdhUWFiI4OBh+fn74/PPPsWfPHixYsACNGjXCqFGjAGh37ImqPUFE1V5WVpYAIHr16lXuz+Tk5JRoCw4OFg0bNpS1NW3aVHTq1KnE2Dlz5oi6deuKK1euyNqnTZsm9PX1xa1bt4QQQvz3v/8VAMSiRYukMYWFheL1118XAERcXJzU7uPjI+zs7MT9+/eltrNnzwo9PT0xZMgQqW3mzJkCgOjfv3+Juor7il29elXo6emJt99+WxQWFsrGFhUVlbk/PvjgA2FqaiqePn0qtYWGhgoXF5cSY/+uU6dOomnTpkIIIVq3bi3CwsKEEEI8fPhQGBoaitWrV4v9+/cLAGLjxo1l1pGYmCgAiG+//VZq27hxowAg9u/fLxubmZkpzM3NhZ+fn3jy5Mlzt7dTp04llpmbmyscHBxE3759pba0tLQSxyk0NFQAELNnz5Ytv2XLlsLX11ea1+bYE1V3vGRGVANoNBoAgLm5ebk/Y2JiIv2clZWFe/fuoVOnTrh+/TqysrJe+PmNGzeiQ4cOqFevHu7duydNgYGBKCwsxKFDhwAA8fHxMDAwwIgRI6TP6unpSWehiqWnpyMpKQlDhw6FlZWV1N68eXO88cYb2LlzZ4kaPvzwwxfWuWXLFhQVFWHGjBnQ05P/J+3ZS2vP7o9Hjx7h3r176NChA3JycpCcnPzC9ZRlwIAB2Lx5M/Ly8rBp0ybo6+vj7bffLnXss3Xk5+fj/v37cHd3h6WlJc6cOfPCdSUkJODRo0eYNm1aiXt//n4p0czMDIMGDZLmDQ0N0aZNG1y/fr1c2/X3/d+hQwfZZ8t77IlqAgYiohpArVYD+OsPeXkdOXIEgYGB0r06tra2+OijjwCgXIHo6tWriI+Ph62trWwKDAwEANy9exfAX/fEODo6wtTUVPZ5d3d32fzNmzcBAB4eHiXW5enpiXv37uHx48eydjc3txfWee3aNejp6cHLy6vMcRcvXsTbb78NCwsLqNVq2NraSmGhPPujLP369UNWVhZ+/vlnrFmzBm+++eZzw+uTJ08wY8YM6b4sGxsb2NraIjMzs1x1XLt2DQDK9Y6h+vXrlwhJ9erVw8OHD1/4WWNjY9ja2pb52fIee6KagPcQEdUAarUaTk5OuHDhQrnGX7t2DV27dkWTJk2wcOFCODs7w9DQEDt37sQXX3xR4qbo0hQVFeGNN97AlClTSu1/9dVXtdqGl/Hs2ZR/IjMzE506dYJarcbs2bPRqFEjGBsb48yZM5g6dWq59kdZHB0d0blzZyxYsABHjhwp88mysWPHIi4uDhMmTIC/vz8sLCygUqnQr1+/f1zH3+nr65faLsq4H+tFnyWqrRiIiGqIN998EytWrEBiYiL8/f3LHLtt2zbk5uZi69ataNCggdS+f//+EmOf99bnRo0aITs7Wzoj9DwuLi7Yv38/cnJyZGcKUlNTS4wDgJSUlBLLSE5Oho2NDerWrVvmup5XZ1FRES5dugQfH59Sxxw4cAD379/H5s2b0bFjR6k9LS1N6/U9z4ABA/D+++/D0tIS3bt3f+64TZs2ITQ0FAsWLJDanj59iszMTNm4so4LAFy4cKHKz8SU99gT1QS8ZEZUQ0yZMgV169bF+++/jzt37pTov3btGhYvXgzgf/93/+yZgKysLMTFxZX4XN26dUv8MQaAd999F4mJidi1a1eJvszMTBQUFAAAgoODkZ+fj6+//lrqLyoqwrJly2SfcXR0hI+PD1avXi1b34ULF7B79+4yQ0RZevfuDT09PcyePbvEGZbi7S9tf+Tl5eHLL798qXWW5l//+hdmzpyJL7/8EoaGhs8dp6+vX+IMzdKlS0s8zl4cDv9+bIKCgmBubo6YmBg8ffpU1leeMz+6VN5jT1QT8AwRUQ3RqFEjrF27Fu+99x48PT0xZMgQNGvWDHl5eTh69Cg2btyIoUOHAvjrj6ahoSF69uyJDz74ANnZ2fj6669hZ2eH9PR02XJ9fX2xfPly/Pvf/4a7uzvs7Ozw+uuvIzIyElu3bsWbb76JoUOHwtfXF48fP8b58+exadMm3LhxAzY2NujduzfatGmDSZMmITU1FU2aNMHWrVvx4MEDAPIzHfPnz0dISAj8/f0RFhYmPXZvYWGB6Ojol9ov7u7u+PjjjzFnzhx06NABffr0gZGREU6ePAknJyfExMQgICAA9erVQ2hoKMaNGweVSoXvvvtOpwGivNvw5ptv4rvvvoOFhQW8vLyQmJiIPXv2wNraWjbOx8cH+vr6mDt3LrKysmBkZCS9V+qLL77A+++/j9dee016T9PZs2eRk5OD1atX62ybXkSbY09U7VXhE25E9BKuXLkiRowYIVxdXYWhoaEwNzcX7dq1E0uXLpU9Pr5161bRvHlzYWxsLFxdXcXcuXPFypUrBQCRlpYmjcvIyBA9evQQ5ubmAoDsEfxHjx6JqKgo4e7uLgwNDYWNjY0ICAgQn3/+ucjLy5PG/fnnn2LAgAHC3NxcWFhYiKFDh4ojR44IAGL9+vWy+vfs2SPatWsnTExMhFqtFj179hSXLl2SjSl+tP7PP/8ssf1/f+y+2MqVK0XLli2FkZGRqFevnujUqZNISEiQ+o8cOSLatm0rTExMhJOTk5gyZYrYtWtXiUfbX+ax++cp7bH7hw8fimHDhgkbGxthZmYmgoODRXJysnBxcRGhoaGyz3/99deiYcOGQl9fv0SdW7duFQEBAdJ+bNOmjVi3bt0L6/v79j3vsfu6deuW+Gxp+16bY09UnamEqORzrESkCFu2bMHbb7+Nw4cPo127dlVdDlUiHnuqiRiIiOgfe/LkieyJsMLCQgQFBeHUqVPIyMjQ2dNiVP3w2FNtwXuIiOgfGzt2LJ48eQJ/f3/k5uZi8+bNOHr0KD777DP+QazleOyptuAZIiL6x9auXYsFCxYgNTUVT58+hbu7O0aNGoUxY8ZUdWlUwXjsqbZgICIiIiLF43uIiIiISPEYiIiIiEjxeFN1ORQVFeGPP/6Aubk5XzRGRERUQwgh8OjRIzg5OUFPr+xzQAxE5fDHH3/A2dm5qssgIiKil3D79m3Ur1+/zDEMROVgbm4O4K8dqlarq7gaIiIiKg+NRgNnZ2fp73hZGIjKofgymVqtZiAiIiKqYcpzuwtvqiYiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsWrU9UFEOA6bccLx9yI7VEJlRARESkTzxARERGR4jEQERERkeJVaSA6dOgQevbsCScnJ6hUKmzZskXWr1KpSp3mz58vjXF1dS3RHxsbK1vOuXPn0KFDBxgbG8PZ2Rnz5s2rjM0jIiKiGqJKA9Hjx4/RokULLFu2rNT+9PR02bRy5UqoVCr07dtXNm727NmycWPHjpX6NBoNgoKC4OLigtOnT2P+/PmIjo7GihUrKnTbiIiIqOao0puqQ0JCEBIS8tx+BwcH2fxPP/2ELl26oGHDhrJ2c3PzEmOLrVmzBnl5eVi5ciUMDQ3RtGlTJCUlYeHChRg5cuQ/3wgiIiKq8WrMPUR37tzBjh07EBYWVqIvNjYW1tbWaNmyJebPn4+CggKpLzExER07doShoaHUFhwcjJSUFDx8+LDUdeXm5kKj0cgmIiIiqr1qzGP3q1evhrm5Ofr06SNrHzduHFq1agUrKyscPXoUUVFRSE9Px8KFCwEAGRkZcHNzk33G3t5e6qtXr16JdcXExGDWrFkVtCVERERU3dSYQLRy5UoMHDgQxsbGsvaIiAjp5+bNm8PQ0BAffPABYmJiYGRk9FLrioqKki1Xo9HA2dn55QonIiKiaq9GBKJffvkFKSkp2LBhwwvH+vn5oaCgADdu3ICHhwccHBxw584d2Zji+efdd2RkZPTSYYqIiIhqnhpxD9E333wDX19ftGjR4oVjk5KSoKenBzs7OwCAv78/Dh06hPz8fGlMQkICPDw8Sr1cRkRERMpTpYEoOzsbSUlJSEpKAgCkpaUhKSkJt27dksZoNBps3LgR77//fonPJyYmYtGiRTh79iyuX7+ONWvWYOLEiRg0aJAUdgYMGABDQ0OEhYXh4sWL2LBhAxYvXiy7JEZERETKVqWXzE6dOoUuXbpI88UhJTQ0FKtWrQIArF+/HkII9O/fv8TnjYyMsH79ekRHRyM3Nxdubm6YOHGiLOxYWFhg9+7dCA8Ph6+vL2xsbDBjxgw+ck9EREQSlRBCVHUR1Z1Go4GFhQWysrKgVqt1vnx+uSsREZHuafP3u0bcQ0RERERUkRiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxGIiIiIhI8RiIiIiISPGqNBAdOnQIPXv2hJOTE1QqFbZs2SLrHzp0KFQqlWzq1q2bbMyDBw8wcOBAqNVqWFpaIiwsDNnZ2bIx586dQ4cOHWBsbAxnZ2fMmzevojeNiIiIapAqDUSPHz9GixYtsGzZsueO6datG9LT06Vp3bp1sv6BAwfi4sWLSEhIwPbt23Ho0CGMHDlS6tdoNAgKCoKLiwtOnz6N+fPnIzo6GitWrKiw7SIiIqKapU5VrjwkJAQhISFljjEyMoKDg0OpfZcvX0Z8fDxOnjyJ1q1bAwCWLl2K7t274/PPP4eTkxPWrFmDvLw8rFy5EoaGhmjatCmSkpKwcOFCWXAiIiIi5ar29xAdOHAAdnZ28PDwwKhRo3D//n2pLzExEZaWllIYAoDAwEDo6enh+PHj0piOHTvC0NBQGhMcHIyUlBQ8fPiw1HXm5uZCo9HIJiIiIqq9qnUg6tatG7799lvs3bsXc+fOxcGDBxESEoLCwkIAQEZGBuzs7GSfqVOnDqysrJCRkSGNsbe3l40pni8e83cxMTGwsLCQJmdnZ11vGhEREVUjVXrJ7EX69esn/ezt7Y3mzZujUaNGOHDgALp27Vph642KikJERIQ0r9FoGIqIiIhqsWp9hujvGjZsCBsbG6SmpgIAHBwccPfuXdmYgoICPHjwQLrvyMHBAXfu3JGNKZ5/3r1JRkZGUKvVsomIiIhqrxoViH777Tfcv38fjo6OAAB/f39kZmbi9OnT0ph9+/ahqKgIfn5+0phDhw4hPz9fGpOQkAAPDw/Uq1evcjeAiIiIqqUqDUTZ2dlISkpCUlISACAtLQ1JSUm4desWsrOzERkZiWPHjuHGjRvYu3cvevXqBXd3dwQHBwMAPD090a1bN4wYMQInTpzAkSNHMGbMGPTr1w9OTk4AgAEDBsDQ0BBhYWG4ePEiNmzYgMWLF8suiREREZGyVWkgOnXqFFq2bImWLVsCACIiItCyZUvMmDED+vr6OHfuHN566y28+uqrCAsLg6+vL3755RcYGRlJy1izZg2aNGmCrl27onv37mjfvr3sHUMWFhbYvXs30tLS4Ovri0mTJmHGjBl85J6IiIgkKiGEqOoiqjuNRgMLCwtkZWVVyP1ErtN2vHDMjdgeOl8vERFRbabN3+8adQ8RERERUUVgICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixdNJIMrMzNTFYoiIiIiqhNaBaO7cudiwYYM0/+6778La2hqvvPIKzp49q9PiiIiIiCqD1oHoq6++grOzMwAgISEBCQkJ+PnnnxESEoLIyEidF0hERERU0epo+4GMjAwpEG3fvh3vvvsugoKC4OrqCj8/P50XSERERFTRtD5DVK9ePdy+fRsAEB8fj8DAQACAEAKFhYW6rY6IiIioEmh9hqhPnz4YMGAAGjdujPv37yMkJAQA8Ouvv8Ld3V3nBRIRERFVNK0D0RdffAFXV1fcvn0b8+bNg5mZGQAgPT0do0eP1nmBRERERBVN60BkYGCAyZMnl2ifOHGiTgoiIiIiqmzlCkRbt24t9wLfeuutly6GiIiIqCqUKxD17t1bNq9SqSCEkM0X443VREREVNOU6ymzoqIiadq9ezd8fHzw888/IzMzE5mZmdi5cydatWqF+Pj4iq6XiIiISOe0fux+woQJWLx4MYKDg6FWq6FWqxEcHIyFCxdi3LhxWi3r0KFD6NmzJ5ycnKBSqbBlyxapLz8/H1OnToW3tzfq1q0LJycnDBkyBH/88YdsGa6urlCpVLIpNjZWNubcuXPo0KEDjI2N4ezsjHnz5mm72URERFSLaR2Irl27BktLyxLtFhYWuHHjhlbLevz4MVq0aIFly5aV6MvJycGZM2cwffp0nDlzBps3b0ZKSkqp9yjNnj0b6enp0jR27FipT6PRICgoCC4uLjh9+jTmz5+P6OhorFixQqtaiYiIqPbS+imz1157DREREfjuu+9gb28PALhz5w4iIyPRpk0brZYVEhIivcfo7ywsLJCQkCBr+89//oM2bdrg1q1baNCggdRubm4OBweHUpezZs0a5OXlYeXKlTA0NETTpk2RlJSEhQsXYuTIkVrVS0RERLWT1meIVq5cifT0dDRo0ADu7u5wd3dHgwYN8Pvvv+Obb76piBolWVlZUKlUJc5QxcbGwtraGi1btsT8+fNRUFAg9SUmJqJjx44wNDSU2oKDg5GSkoKHDx+Wup7c3FxoNBrZRERERLWX1meI3N3dce7cOSQkJCA5ORkA4OnpicDAQNnTZrr29OlTTJ06Ff3794darZbax40bh1atWsHKygpHjx5FVFQU0tPTsXDhQgB/ffeam5ubbFnFZ7YyMjJQr169EuuKiYnBrFmzKmxbiIiIqHrROhABfz1mHxQUhKCgIF3XU6r8/Hy8++67EEJg+fLlsr6IiAjp5+bNm8PQ0BAffPABYmJiYGRk9FLri4qKki1Xo9FIX2hLREREtU+5AtGSJUvKvUBtnzR7keIwdPPmTezbt092dqg0fn5+KCgowI0bN+Dh4QEHBwfcuXNHNqZ4/nn3HRkZGb10mCIiIqKap1yB6IsvvijXwlQqlU4DUXEYunr1Kvbv3w9ra+sXfiYpKQl6enqws7MDAPj7++Pjjz9Gfn4+DAwMAAAJCQnw8PAo9XIZERERKU+5AlFaWlqFrDw7Oxupqamy9SQlJcHKygqOjo7417/+hTNnzmD79u0oLCxERkYGAMDKygqGhoZITEzE8ePH0aVLF5ibmyMxMRETJ07EoEGDpLAzYMAAzJo1C2FhYZg6dSouXLiAxYsXlzvkERERUe2nEs9+B4eWij/6sjdTHzhwAF26dCnRHhoaiujo6BI3Qxfbv38/OnfujDNnzmD06NFITk5Gbm4u3NzcMHjwYERERMgueZ07dw7h4eE4efIkbGxsMHbsWEydOrXcdWo0GlhYWCArK+uFl+xehuu0HS8ccyO2h87XS0REVJtp8/f7pQLRt99+i/nz5+Pq1asAgFdffRWRkZEYPHjwy1VczTEQERER1Tza/P3W+imzhQsXYvr06RgzZgzatWsHADh8+DA+/PBD3Lt3DxMnTny5qomIiIiqiNaBaOnSpVi+fDmGDBkitb311lto2rQpoqOjGYiIiIioxtH6TdXp6ekICAgo0R4QEID09HSdFEVERERUmbQORO7u7vjhhx9KtG/YsAGNGzfWSVFERERElUnrS2azZs3Ce++9h0OHDkn3EB05cgR79+4tNSgRERERVXdanyHq27cvjh8/DhsbG2zZsgVbtmyBjY0NTpw4gbfffrsiaiQiIiKqUC/1XWa+vr74/vvvdV0LERERUZV4qUBUVFSE1NRU3L17F0VFRbK+jh076qQwIiIiosqidSA6duwYBgwYgJs3b+Lv73RUqVQoLCzUWXFERERElUHrQPThhx+idevW2LFjBxwdHV/6azuIiIiIqgutA9HVq1exadMmuLu7V0Q9RERERJVO66fM/Pz8ZN9QT0RERFTTlesM0blz56Sfx44di0mTJiEjIwPe3t4wMDCQjW3evLluKyQiIiKqYOUKRD4+PlCpVLKbqIcPHy79XNzHm6qJiIioJipXIEpLS6voOoiIiIiqTLkCkYuLS0XXQURERFRltL6pGgC+++47tGvXDk5OTrh58yYAYNGiRfjpp590WhwRERFRZdA6EC1fvhwRERHo3r07MjMzpXuGLC0tsWjRIl3XR0RERFThtA5ES5cuxddff42PP/4Y+vr6Unvr1q1x/vx5nRZHREREVBm0DkRpaWlo2bJliXYjIyM8fvxYJ0URERERVSatA5GbmxuSkpJKtMfHx8PT01MXNRERERFVKq2/uiMiIgLh4eF4+vQphBA4ceIE1q1bh5iYGPy///f/KqJGIiIiogqldSB6//33YWJigk8++QQ5OTkYMGAAnJycsHjxYvTr168iaiQiIiKqUFoHIgAYOHAgBg4ciJycHGRnZ8POzk7XdRERERFVGq3vIXry5AlycnIAAKampnjy5AkWLVqE3bt367w4IiIiosqgdSDq1asXvv32WwBAZmYm2rRpgwULFqBXr15Yvny5zgskIiIiqmhaB6IzZ86gQ4cOAIBNmzbBwcEBN2/exLfffoslS5bovEAiIiKiiqZ1IMrJyYG5uTkAYPfu3ejTpw/09PTQtm1b6Ws8iIiIiGoSrQORu7s7tmzZgtu3b2PXrl0ICgoCANy9exdqtVrnBRIRERFVNK0D0YwZMzB58mS4urrCz88P/v7+AP46W1TaG6yJiIiIqjutH7v/17/+hfbt2yM9PR0tWrSQ2rt27Yq3335bp8URERERVYaXeg+Rg4MDHBwcZG1t2rTRSUFERERElU3rQNSlSxeoVKrn9u/bt+8fFURERERU2bQORD4+PrL5/Px8JCUl4cKFCwgNDdVVXURERESVRutA9MUXX5TaHh0djezs7H9cEBEREVFl0/ops+cZNGgQVq5cqavFEREREVUanQWixMREGBsb62pxRERERJVG60tmffr0kc0LIZCeno5Tp05h+vTpOiuMiIiIqLJofYbIwsJCNllZWaFz587YuXMnZs6cqdWyDh06hJ49e8LJyQkqlQpbtmyR9QshMGPGDDg6OsLExASBgYG4evWqbMyDBw8wcOBAqNVqWFpaIiwsrMS9TOfOnUOHDh1gbGwMZ2dnzJs3T9vNJiIiolpM6zNEcXFxOlv548eP0aJFCwwfPrzEmScAmDdvHpYsWYLVq1fDzc0N06dPR3BwMC5duiRdnhs4cCDS09ORkJCA/Px8DBs2DCNHjsTatWsBABqNBkFBQQgMDMRXX32F8+fPY/jw4bC0tMTIkSN1ti1ERERUc6mEEOJlPnj69GlcvnwZANC0adN//LUdKpUKP/74I3r37g3gr7NDTk5OmDRpEiZPngwAyMrKgr29PVatWoV+/frh8uXL8PLywsmTJ9G6dWsAQHx8PLp3747ffvsNTk5OWL58OT7++GNkZGTA0NAQADBt2jRs2bIFycnJ5apNo9HAwsICWVlZFfJ9ba7TdrxwzI3YHjpfLxERUW2mzd9vrS+Z3b17F6+//jpee+01jBs3DuPGjYOvry+6du2KP//886WL/ru0tDRkZGQgMDBQarOwsICfnx8SExMB/HUjt6WlpRSGACAwMBB6eno4fvy4NKZjx45SGAKA4OBgpKSk4OHDhzqrl4iIiGourQPR2LFj8ejRI1y8eBEPHjzAgwcPcOHCBWg0GowbN05nhWVkZAAA7O3tZe329vZSX0ZGBuzs7GT9derUgZWVlWxMact4dh1/l5ubC41GI5uIiIio9tI6EMXHx+PLL7+Ep6en1Obl5YVly5bh559/1mlxVSUmJkZ247izs3NVl0REREQVSOtAVFRUBAMDgxLtBgYGKCoq0klRAKQvj71z546s/c6dO1Kfg4MD7t69K+svKCjAgwcPZGNKW8az6/i7qKgoZGVlSdPt27f/+QYRERFRtaV1IHr99dcxfvx4/PHHH1Lb77//jokTJ6Jr1646K8zNzQ0ODg7Yu3ev1KbRaHD8+HH4+/sDAPz9/ZGZmYnTp09LY/bt24eioiL4+flJYw4dOoT8/HxpTEJCAjw8PFCvXr1S121kZAS1Wi2biIiIqPbSOhD95z//gUajgaurKxo1aoRGjRrBzc0NGo0GS5cu1WpZ2dnZSEpKQlJSEoC/bqROSkrCrVu3oFKpMGHCBPz73//G1q1bcf78eQwZMgROTk7Sk2ienp7o1q0bRowYgRMnTuDIkSMYM2YM+vXrBycnJwDAgAEDYGhoiLCwMFy8eBEbNmzA4sWLERERoe2mExERUS2l9XuInJ2dcebMGezZs0d6bN3T01P2NFh5nTp1Cl26dJHmi0NKaGgoVq1ahSlTpuDx48cYOXIkMjMz0b59e8THx8u+ImTNmjUYM2YMunbtCj09PfTt2xdLliyR+i0sLLB7926Eh4fD19cXNjY2mDFjBt9BRERERJKXfg+RkvA9RERERDWPNn+/tT5DBAB79+7F3r17cffu3RI3UvMb74mIiKim0ToQzZo1C7Nnz0br1q3h6OgIlUpVEXURERERVRqtA9FXX32FVatWYfDgwRVRDxEREVGl0/ops7y8PAQEBFRELURERERVQutA9P7770vfJE9ERERUG5Trktmz7+wpKirCihUrsGfPHjRv3rzEW6sXLlyo2wqJiIiIKli5AtGvv/4qm/fx8QEAXLhwQdbOG6yJiIioJipXINq/f39F10FERERUZbS+h4iIiIiotmEgIiIiIsVjICIiIiLFYyAiIiIixStXIGrVqhUePnwIAJg9ezZycnIqtCgiIiKiylSuQHT58mU8fvwYwF/fZZadnV2hRRERERFVpnI9du/j44Nhw4ahffv2EELg888/h5mZWaljZ8yYodMCiYiIiCpauQLRqlWrMHPmTGzfvh0qlQo///wz6tQp+VGVSsVARERERDVOuQKRh4cH1q9fDwDQ09PD3r17YWdnV6GFEREREVWWcgWiZxUVFVVEHURERERVRutABADXrl3DokWLcPnyZQCAl5cXxo8fj0aNGum0OCIiIqLKoPV7iHbt2gUvLy+cOHECzZs3R/PmzXH8+HE0bdoUCQkJFVEjERERUYXS+gzRtGnTMHHiRMTGxpZonzp1Kt544w2dFUdERERUGbQ+Q3T58mWEhYWVaB8+fDguXbqkk6KIiIiIKpPWgcjW1hZJSUkl2pOSkvjkGREREdVIWl8yGzFiBEaOHInr168jICAAAHDkyBHMnTsXEREROi+QiIiIqKJpHYimT58Oc3NzLFiwAFFRUQAAJycnREdHY9y4cTovkIiIiKiiaR2IVCoVJk6ciIkTJ+LRo0cAAHNzc50XRkRERFRZXuo9RMUYhIiIiKg20PqmaiIiIqLahoGIiIiIFI+BiIiIiBRPq0CUn5+Prl274urVqxVVDxEREVGl0yoQGRgY4Ny5cxVVCxEREVGV0PqS2aBBg/DNN99URC1EREREVULrx+4LCgqwcuVK7NmzB76+vqhbt66sf+HChTorjoiIiKgyaB2ILly4gFatWgEArly5IutTqVS6qYqIiIioEmkdiPbv318RdRARERFVmZd+7D41NRW7du3CkydPAABCCJ0VRURERFSZtA5E9+/fR9euXfHqq6+ie/fuSE9PBwCEhYVh0qRJOi+QiIiIqKJpHYgmTpwIAwMD3Lp1C6amplL7e++9h/j4eJ0WR0RERFQZtA5Eu3fvxty5c1G/fn1Ze+PGjXHz5k2dFVbM1dUVKpWqxBQeHg4A6Ny5c4m+Dz/8ULaMW7duoUePHjA1NYWdnR0iIyNRUFCg81qJiIioZtL6purHjx/LzgwVe/DgAYyMjHRS1LNOnjyJwsJCaf7ChQt444038M4770htI0aMwOzZs6X5Z+srLCxEjx494ODggKNHjyI9PR1DhgyBgYEBPvvsM53XS0RERDWP1meIOnTogG+//VaaV6lUKCoqwrx589ClSxedFgcAtra2cHBwkKbt27ejUaNG6NSpkzTG1NRUNkatVkt9u3fvxqVLl/D999/Dx8cHISEhmDNnDpYtW4a8vDyd10tEREQ1j9aBaN68eVixYgVCQkKQl5eHKVOmoFmzZjh06BDmzp1bETVK8vLy8P3332P48OGydx6tWbMGNjY2aNasGaKiopCTkyP1JSYmwtvbG/b29lJbcHAwNBoNLl68WOp6cnNzodFoZBMRERHVXlpfMmvWrBmuXLmC//znPzA3N0d2djb69OmD8PBwODo6VkSNki1btiAzMxNDhw6V2gYMGAAXFxc4OTnh3LlzmDp1KlJSUrB582YAQEZGhiwMAZDmMzIySl1PTEwMZs2aVTEbQURERNWO1oEIACwsLPDxxx/rupYX+uabbxASEgInJyepbeTIkdLP3t7ecHR0RNeuXXHt2jU0atTopdYTFRWFiIgIaV6j0cDZ2fnlCyciIqJq7aUC0cOHD/HNN9/g8uXLAAAvLy8MGzYMVlZWOi3uWTdv3sSePXukMz/P4+fnB+CvF0c2atQIDg4OOHHihGzMnTt3AAAODg6lLsPIyKhCbhAnIiKi6knre4gOHToEV1dXLFmyBA8fPsTDhw+xZMkSuLm54dChQxVRIwAgLi4OdnZ26NGjR5njkpKSAEC6fOfv74/z58/j7t270piEhASo1Wp4eXlVWL1ERERUc2h9hig8PBzvvfceli9fDn19fQB/Pdo+evRohIeH4/z58zovsqioCHFxcQgNDUWdOv8r+dq1a1i7di26d+8Oa2trnDt3DhMnTkTHjh3RvHlzAEBQUBC8vLwwePBgzJs3DxkZGfjkk08QHh7Os0BEREQE4CXOEKWmpmLSpElSGAIAfX19REREIDU1VafFFduzZw9u3bqF4cOHy9oNDQ2xZ88eBAUFoUmTJpg0aRL69u2Lbdu2yWrbvn079PX14e/vj0GDBmHIkCGy9xYRERGRsml9hqhVq1a4fPkyPDw8ZO2XL19GixYtdFbYs4KCgkr98lhnZ2ccPHjwhZ93cXHBzp07K6I0IiIiqgXKFYjOnTsn/Txu3DiMHz8eqampaNu2LQDg2LFjWLZsGWJjYyumSiIiIqIKpBKlnXr5Gz09PahUqlLP0sgWplLJvmajttBoNLCwsEBWVpbsLdi64jpth06WcyO27BvOiYiIlESbv9/lOkOUlpamk8KIiIiIqqNyBSIXF5eKroOIiIioyrzUixn/+OMPHD58GHfv3kVRUZGsb9y4cTopjIiIiKiyaB2IVq1ahQ8++ACGhoawtraWfcmqSqViICIiIqIaR+tANH36dMyYMQNRUVHQ09P6NUZERERE1Y7WiSYnJwf9+vVjGCIiIqJaQ+tUExYWho0bN1ZELURERERVQutLZjExMXjzzTcRHx8Pb29vGBgYyPoXLlyos+KIiIiIKsNLBaJdu3ZJX93x95uqiYiIiGoarQPRggULsHLlSgwdOrQCyiEiIiKqfFrfQ2RkZIR27dpVRC1EREREVULrQDR+/HgsXbq0ImohIiIiqhJaXzI7ceIE9u3bh+3bt6Np06YlbqrevHmzzoojIiIiqgxaByJLS0v06dOnImohIiIiqhJaB6K4uLiKqIOIiIioyvB100RERKR4Wp8hcnNzK/N9Q9evX/9HBRERERFVNq0D0YQJE2Tz+fn5+PXXXxEfH4/IyEhd1UVERERUabQOROPHjy+1fdmyZTh16tQ/LoiIiIiosunsHqKQkBD897//1dXiiIiIiCqNzgLRpk2bYGVlpavFEREREVUarS+ZtWzZUnZTtRACGRkZ+PPPP/Hll1/qtDgiIiKiyqB1IOrdu7dsXk9PD7a2tujcuTOaNGmiq7qIiIiIKo3WgWjmzJkVUQcRERFRleGLGYmIiEjxyn2GSE9Pr8wXMgKASqVCQUHBPy6KiIiIqDKVOxD9+OOPz+1LTEzEkiVLUFRUpJOiiIiIiCpTuQNRr169SrSlpKRg2rRp2LZtGwYOHIjZs2frtDgiIiKiyvBS9xD98ccfGDFiBLy9vVFQUICkpCSsXr0aLi4uuq6PiIiIqMJpFYiysrIwdepUuLu74+LFi9i7dy+2bduGZs2aVVR9RERERBWu3JfM5s2bh7lz58LBwQHr1q0r9RIaERERUU2kEkKI8gzU09ODiYkJAgMDoa+v/9xxmzdv1llx1YVGo4GFhQWysrKgVqt1vnzXaTt0spwbsT10shwiIqLaQJu/3+U+QzRkyJAXPnZPREREVBOVOxCtWrWqAssgXSjPmaaaeBaptm4XERFVH3xTNRERESkeAxEREREpXrUORNHR0VCpVLKpSZMmUv/Tp08RHh4Oa2trmJmZoW/fvrhz545sGbdu3UKPHj1gamoKOzs7REZG8utFiIiISEbrb7uvbE2bNsWePXuk+Tp1/lfyxIkTsWPHDmzcuBEWFhYYM2YM+vTpgyNHjgAACgsL0aNHDzg4OODo0aNIT0/HkCFDYGBggM8++6zSt4WIiIiqp2ofiOrUqQMHB4cS7VlZWfjmm2+wdu1avP766wCAuLg4eHp64tixY2jbti12796NS5cuYc+ePbC3t4ePjw/mzJmDqVOnIjo6GoaGhpW9OURERFQNVetLZgBw9epVODk5oWHDhhg4cCBu3boFADh9+jTy8/MRGBgojW3SpAkaNGiAxMREAH996ay3tzfs7e2lMcHBwdBoNLh48eJz15mbmwuNRiObiIiIqPaq1oHIz88Pq1atQnx8PJYvX460tDR06NABjx49QkZGBgwNDWFpaSn7jL29PTIyMgAAGRkZsjBU3F/c9zwxMTGwsLCQJmdnZ91uGBEREVUr1fqSWUhIiPRz8+bN4efnBxcXF/zwww8wMTGpsPVGRUUhIiJCmtdoNAxFREREtVi1PkP0d5aWlnj11VeRmpoKBwcH5OXlITMzUzbmzp070j1HDg4OJZ46K54v7b6kYkZGRlCr1bKJiIiIaq8aFYiys7Nx7do1ODo6wtfXFwYGBti7d6/Un5KSglu3bsHf3x8A4O/vj/Pnz+Pu3bvSmISEBKjVanh5eVV6/URERFQ9VetLZpMnT0bPnj3h4uKCP/74AzNnzoS+vj769+8PCwsLhIWFISIiAlZWVlCr1Rg7diz8/f3Rtm1bAEBQUBC8vLwwePBgzJs3DxkZGfjkk08QHh4OIyOjKt46IiIiqi6qdSD67bff0L9/f9y/fx+2trZo3749jh07BltbWwDAF198AT09PfTt2xe5ubkIDg7Gl19+KX1eX18f27dvx6hRo+Dv74+6desiNDQUs2fPrqpNIiIiomqoWgei9evXl9lvbGyMZcuWYdmyZc8d4+Ligp07d+q6NCIiIqpFatQ9REREREQVgYGIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUr05VF0BERESVz3XajheOuRHboxIqqR54hoiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI/fZUaKwe/tISKi5+EZIiIiIlI8BiIiIiJSPAYiIiIiUjwGIiIiIlI83lStMLyxmIiIqCQGIiIiokrA/yGt3qr1JbOYmBi89tprMDc3h52dHXr37o2UlBTZmM6dO0OlUsmmDz/8UDbm1q1b6NGjB0xNTWFnZ4fIyEgUFBRU5qYQERFRNVatzxAdPHgQ4eHheO2111BQUICPPvoIQUFBuHTpEurWrSuNGzFiBGbPni3Nm5qaSj8XFhaiR48ecHBwwNGjR5Geno4hQ4bAwMAAn332WaVuT23C/9MhIqLapFoHovj4eNn8qlWrYGdnh9OnT6Njx45Su6mpKRwcHEpdxu7du3Hp0iXs2bMH9vb28PHxwZw5czB16lRER0fD0NCwQrdByRiaiIiopqjWl8z+LisrCwBgZWUla1+zZg1sbGzQrFkzREVFIScnR+pLTEyEt7c37O3tpbbg4GBoNBpcvHix1PXk5uZCo9HIJiIiIqq9qvUZomcVFRVhwoQJaNeuHZo1aya1DxgwAC4uLnBycsK5c+cwdepUpKSkYPPmzQCAjIwMWRgCIM1nZGSUuq6YmBjMmjWrgraEiIiIqpsaE4jCw8Nx4cIFHD58WNY+cuRI6Wdvb284Ojqia9euuHbtGho1avRS64qKikJERIQ0r9Fo4Ozs/HKFExERUbVXIy6ZjRkzBtu3b8f+/ftRv379Msf6+fkBAFJTUwEADg4OuHPnjmxM8fzz7jsyMjKCWq2WTURERFR7VetAJITAmDFj8OOPP2Lfvn1wc3N74WeSkpIAAI6OjgAAf39/nD9/Hnfv3pXGJCQkQK1Ww8vLq0LqJiIiopqlWl8yCw8Px9q1a/HTTz/B3NxcuufHwsICJiYmuHbtGtauXYvu3bvD2toa586dw8SJE9GxY0c0b94cABAUFAQvLy8MHjwY8+bNQ0ZGBj755BOEh4fDyMioKjePiIiIqolqfYZo+fLlyMrKQufOneHo6ChNGzZsAAAYGhpiz549CAoKQpMmTTBp0iT07dsX27Ztk5ahr6+P7du3Q19fH/7+/hg0aBCGDBkie28RERERKVu1PkMkhCiz39nZGQcPHnzhclxcXLBz505dlUVERES1TLU+Q0RERERUGRiIiIiISPEYiIiIiEjxqvU9REREZeH35RGRrvAMERERESkeAxEREREpHgMRERERKR4DERERESkeAxEREREpHp8yIyLSkcp86q0869Ll+ohqO54hIiIiIsVjICIiIiLF4yUzomqMLx4kIqocPENEREREisczRERERFShasLZbp4hIiIiIsVjICIiIiLFYyAiIiIixeM9RFRCeV/4RkREVFswEBE9oybc+EdERLrHQES1As9qERHRP8F7iIiIiEjxGIiIiIhI8RiIiIiISPEYiIiIiEjxeFM1kQLw6TkiorIxEBFpieGCiKj24SUzIiIiUjwGIiIiIlI8BiIiIiJSPAYiIiIiUjwGIiIiIlI8BiIiIiJSPAYiIiIiUjwGIiIiIlI8BiIiIiJSPAYiIiIiUjwGIiIiIlI8RQWiZcuWwdXVFcbGxvDz88OJEyequiQiIiKqBhQTiDZs2ICIiAjMnDkTZ86cQYsWLRAcHIy7d+9WdWlERERUxRQTiBYuXIgRI0Zg2LBh8PLywldffQVTU1OsXLmyqksjIiKiKqaIQJSXl4fTp08jMDBQatPT00NgYCASExOrsDIiIiKqDupUdQGV4d69eygsLIS9vb2s3d7eHsnJySXG5+bmIjc3V5rPysoCAGg0mgqpryg3p0KWWxOUZ5/WxP2jq9+V8my7rvZhRf1+V6Tqtl2VWU95/72oice1tuLva+Wsq7RlCiFePFgowO+//y4AiKNHj8raIyMjRZs2bUqMnzlzpgDAiRMnTpw4caoF0+3bt1+YFRRxhsjGxgb6+vq4c+eOrP3OnTtwcHAoMT4qKgoRERHSfFFRER48eABra2uoVCqd1qbRaODs7Izbt29DrVbrdNmkGzxGNQOPU/XHY1Qz1KbjJITAo0eP4OTk9MKxighEhoaG8PX1xd69e9G7d28Af4WcvXv3YsyYMSXGGxkZwcjISNZmaWlZoTWq1eoa/4tX2/EY1Qw8TtUfj1HNUFuOk4WFRbnGKSIQAUBERARCQ0PRunVrtGnTBosWLcLjx48xbNiwqi6NiIiIqphiAtF7772HP//8EzNmzEBGRgZ8fHwQHx9f4kZrIiIiUh7FBCIAGDNmTKmXyKqSkZERZs6cWeISHVUfPEY1A49T9cdjVDMo9TiphCjPs2hEREREtZciXsxIREREVBYGIiIiIlI8BiIiIiJSPAYiIiIiUjwGoiq0bNkyuLq6wtjYGH5+fjhx4kRVl6QYMTExeO2112Bubg47Ozv07t0bKSkpsjFPnz5FeHg4rK2tYWZmhr59+5Z42/mtW7fQo0cPmJqaws7ODpGRkSgoKKjMTVGM2NhYqFQqTJgwQWrjMaoefv/9dwwaNAjW1tYwMTGBt7c3Tp06JfULITBjxgw4OjrCxMQEgYGBuHr1qmwZDx48wMCBA6FWq2FpaYmwsDBkZ2dX9qbUWoWFhZg+fTrc3NxgYmKCRo0aYc6cObLv+FL8cdLBV4XRS1i/fr0wNDQUK1euFBcvXhQjRowQlpaW4s6dO1VdmiIEBweLuLg4ceHCBZGUlCS6d+8uGjRoILKzs6UxH374oXB2dhZ79+4Vp06dEm3bthUBAQFSf0FBgWjWrJkIDAwUv/76q9i5c6ewsbERUVFRVbFJtdqJEyeEq6uraN68uRg/frzUzmNU9R48eCBcXFzE0KFDxfHjx8X169fFrl27RGpqqjQmNjZWWFhYiC1btoizZ8+Kt956S7i5uYknT55IY7p16yZatGghjh07Jn755Rfh7u4u+vfvXxWbVCt9+umnwtraWmzfvl2kpaWJjRs3CjMzM7F48WJpjNKPEwNRFWnTpo0IDw+X5gsLC4WTk5OIiYmpwqqU6+7duwKAOHjwoBBCiMzMTGFgYCA2btwojbl8+bIAIBITE4UQQuzcuVPo6emJjIwMaczy5cuFWq0Wubm5lbsBtdijR49E48aNRUJCgujUqZMUiHiMqoepU6eK9u3bP7e/qKhIODg4iPnz50ttmZmZwsjISKxbt04IIcSlS5cEAHHy5ElpzM8//yxUKpX4/fffK654BenRo4cYPny4rK1Pnz5i4MCBQggeJyGE4CWzKpCXl4fTp08jMDBQatPT00NgYCASExOrsDLlysrKAgBYWVkBAE6fPo38/HzZMWrSpAkaNGggHaPExER4e3vL3nYeHBwMjUaDixcvVmL1tVt4eDh69OghOxYAj1F1sXXrVrRu3RrvvPMO7Ozs0LJlS3z99ddSf1paGjIyMmTHycLCAn5+frLjZGlpidatW0tjAgMDoaenh+PHj1fextRiAQEB2Lt3L65cuQIAOHv2LA4fPoyQkBAAPE6Awt5UXV3cu3cPhYWFJb42xN7eHsnJyVVUlXIVFRVhwoQJaNeuHZo1awYAyMjIgKGhYYkv9bW3t0dGRoY0prRjWNxH/9z69etx5swZnDx5skQfj1H1cP36dSxfvhwRERH46KOPcPLkSYwbNw6GhoYIDQ2V9nNpx+HZ42RnZyfrr1OnDqysrHicdGTatGnQaDRo0qQJ9PX1UVhYiE8//RQDBw4EAB4nMBARITw8HBcuXMDhw4eruhR6xu3btzF+/HgkJCTA2Ni4qsuh5ygqKkLr1q3x2WefAQBatmyJCxcu4KuvvkJoaGgVV0fFfvjhB6xZswZr165F06ZNkZSUhAkTJsDJyYnH6f/HS2ZVwMbGBvr6+iWehrlz5w4cHByqqCplGjNmDLZv3479+/ejfv36UruDgwPy8vKQmZkpG//sMXJwcCj1GBb30T9z+vRp3L17F61atUKdOnVQp04dHDx4EEuWLEGdOnVgb2/PY1QNODo6wsvLS9bm6emJW7duAfjffi7rv3cODg64e/eurL+goAAPHjzgcdKRyMhITJs2Df369YO3tzcGDx6MiRMnIiYmBgCPE8BAVCUMDQ3h6+uLvXv3Sm1FRUXYu3cv/P39q7Ay5RBCYMyYMfjxxx+xb98+uLm5yfp9fX1hYGAgO0YpKSm4deuWdIz8/f1x/vx52X8gEhISoFarS/yBIO117doV58+fR1JSkjS1bt0aAwcOlH7mMap67dq1K/HKiitXrsDFxQUA4ObmBgcHB9lx0mg0OH78uOw4ZWZm4vTp09KYffv2oaioCH5+fpWwFbVfTk4O9PTkf/L19fVRVFQEgMcJAB+7ryrr168XRkZGYtWqVeLSpUti5MiRwtLSUvY0DFWcUaNGCQsLC3HgwAGRnp4uTTk5OdKYDz/8UDRo0EDs27dPnDp1Svj7+wt/f3+pv/iR7qCgIJGUlCTi4+OFra0tH+muQM8+ZSYEj1F1cOLECVGnTh3x6aefiqtXr4o1a9YIU1NT8f3330tjYmNjhaWlpfjpp5/EuXPnRK9evUp9nLtly5bi+PHj4vDhw6Jx48a15nHu6iA0NFS88sor0mP3mzdvFjY2NmLKlCnSGKUfJwaiKrR06VLRoEEDYWhoKNq0aSOOHTtW1SUpBoBSp7i4OGnMkydPxOjRo0W9evWEqampePvtt0V6erpsOTdu3BAhISHCxMRE2NjYiEmTJon8/PxK3hrl+Hsg4jGqHrZt2yaaNWsmjIyMRJMmTcSKFStk/UVFRWL69OnC3t5eGBkZia5du4qUlBTZmPv374v+/fsLMzMzoVarxbBhw8SjR48qczNqNY1GI8aPHy8aNGggjI2NRcOGDcXHH38se/2E0o+TSohnXlNJREREpEC8h4iIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIiIiIFI+BiIiIiBSPgYiIiIgUj4GIqIa4ceMGVCoVkpKSqroUSXJyMtq2bQtjY2P4+PhUdTkvFB0dXSPqfFkHDhyASqUq8f1u1c3QoUPRu3fvf7SMVatWwdLSsswxtf14k24xEBGV09ChQ6FSqRAbGytr37JlC1QqVRVVVbVmzpyJunXrIiUlRfYdSJVBF39UiYiKMRARacHY2Bhz587Fw4cPq7oUncnLy3vpz167dg3t27eHi4sLrK2tdVgVlaWwsFD6Uk4i0g0GIiItBAYGwsHBATExMc8dU9pp+kWLFsHV1VWaLz678dlnn8He3h6WlpaYPXs2CgoKEBkZCSsrK9SvXx9xcXEllp+cnIyAgAAYGxujWbNmOHjwoKz/woULCAkJgZmZGezt7TF48GDcu3dP6u/cuTPGjBmDCRMmwMbGBsHBwaVuR1FREWbPno369evDyMgIPj4+iI+Pl/pVKhVOnz6N2bNnQ6VSITo6utTldO7cGWPHjsWECRNQr1492Nvb4+uvv8bjx48xbNgwmJubw93dHT///LP0mcLCQoSFhcHNzQ0mJibw8PDA4sWLZft49erV+Omnn6BSqaBSqXDgwAEAwG+//Yb+/fvDysoKdevWRevWrXH8+HFZTd999x1cXV1hYWGBfv364dGjR7LtjomJkdbdokULbNq0Sep/+PAhBg4cCFtbW5iYmKBx48alHqe/7+8xY8bAwsICNjY2mD59Op791qTc3FxMnjwZr7zyCurWrQs/Pz9pe4D/XR7aunUrvLy8YGRkhFu3bj13nadPn0br1q1hamqKgICAEt9Gv3z5cjRq1AiGhobw8PDAd999J/WVdmk2MzNTto9ftA9u376Nd999F5aWlrCyskKvXr1w48aNEnV+/vnncHR0hLW1NcLDw5Gfny/bz0OGDEG9evVgamqKkJAQXL169bnbDACxsbGwt7eHubk5wsLC8PTp0zLHE8lU8XepEdUYoaGholevXmLz5s3C2NhY3L59WwghxI8//iie/Vdp5syZokWLFrLPfvHFF8LFxUW2LHNzcxEeHi6Sk5PFN998IwCI4OBg8emnn4orV66IOXPmCAMDA2k9aWlpAoCoX7++2LRpk7h06ZJ4//33hbm5ubh3754QQoiHDx9K3+Z++fJlcebMGfHGG2+ILl26SOvu1KmTMDMzE5GRkSI5OVkkJyeXur0LFy4UarVarFu3TiQnJ4spU6YIAwMDceXKFSGEEOnp6aJp06Zi0qRJIj09/blf8NipUydhbm4u5syZI22Xvr6+CAkJEStWrBBXrlwRo0aNEtbW1uLx48dCCCHy8vLEjBkzxMmTJ8X169fF999/L0xNTcWGDRuEEEI8evRIvPvuu6Jbt24iPT1dpKeni9zcXPHo0SPRsGFD0aFDB/HLL7+Iq1evig0bNoijR49Kx8bMzEz06dNHnD9/Xhw6dEg4ODiIjz76SKr33//+t2jSpImIj48X165dE3FxccLIyEgcOHBACCFEeHi48PHxESdPnhRpaWkiISFBbN269bm/N8X7e/z48SI5OVnalme/APX9998XAQEB4tChQyI1NVXMnz9fGBkZSfs6Li5OGBgYiICAAHHkyBGRnJws7atn7d+/XwAQfn5+4sCBA+LixYuiQ4cOIiAgQBqzefNmYWBgIJYtWyZSUlLEggULhL6+vti3b5/s9+zXX3+VPvPw4UMBQOzfv/+F+yAvL094enqK4cOHi3PnzolLly6JAQMGCA8PD+mLRENDQ4VarRYffvihuHz5sti2bVuJffLWW28JT09PcejQIZGUlCSCg4OFu7u7yMvLk/aJhYWFNH7Dhg3CyMhI/L//9/9EcnKy+Pjjj4W5uXmJfxeJnoeBiKicigOREEK0bdtWDB8+XAjx8oHIxcVFFBYWSm0eHh6iQ4cO0nxBQYGoW7euWLdunRDif3+oYmNjpTH5+fmifv36Yu7cuUIIIebMmSOCgoJk6759+7YAIH1rdadOnUTLli1fuL1OTk7i008/lbW99tprYvTo0dJ8ixYtxMyZM8tcTqdOnUT79u1LbNfgwYOltvT0dAFAJCYmPnc54eHhom/fvtL8s8ej2P/93/8Jc3Nzcf/+/VKXMXPmTGFqaio0Go3UFhkZKfz8/IQQQjx9+lSYmppKAapYWFiY6N+/vxBCiJ49e4phw4aVuc3P6tSpk/D09BRFRUVS29SpU4Wnp6cQQoibN28KfX198fvvv8s+17VrVxEVFSWE+OuPPwCRlJRU5rqKA9GePXukth07dggA4smTJ0IIIQICAsSIESNkn3vnnXdE9+7dhRDlC0Rl7YPvvvtOeHh4yLY3NzdXmJiYiF27dgkh/vf7X1BQIKvhvffeE0IIceXKFQFAHDlyROq/d++eMDExET/88IO0T54NRP7+/rLfTSGE8PPzYyCicuMlM6KXMHfuXKxevRqXL19+6WU0bdoUenr/+1fQ3t4e3t7e0ry+vj6sra1x9+5d2ef8/f2ln+vUqYPWrVtLdZw9exb79++HmZmZNDVp0gTAX/f7FPP19S2zNo1Ggz/++APt2rWTtbdr1+6ltrl58+YltuvZbbW3twcA2bYuW7YMvr6+sLW1hZmZGVasWFHmZSIASEpKQsuWLWFlZfXcMa6urjA3N5fmHR0dpfWmpqYiJycHb7zxhmwffvvtt9L+GzVqFNavXw8fHx9MmTIFR48efeH2t23bVnbjvb+/P65evYrCwkKcP38ehYWFePXVV2XrPHjwoOyYGRoayvZjWZ4d5+joCOB/+/by5cv/+LiWtQ/Onj2L1NRUmJubS9tiZWWFp0+fyranadOm0NfXl9X5bI116tSBn5+f1G9tbQ0PD4/n1nn58mXZeED+7wrRi9Sp6gKIaqKOHTsiODgYUVFRGDp0qKxPT09Pdn8IANm9EcUMDAxk8yqVqtQ2bW6ezc7ORs+ePTF37twSfcV/GAGgbt265V6mLrxoW4vDQvG2rl+/HpMnT8aCBQvg7+8Pc3NzzJ8/v8S9QH9nYmLyUrUUrzc7OxsAsGPHDrzyyiuycUZGRgCAkJAQ3Lx5Ezt37kRCQgK6du2K8PBwfP755y9cd2mys7Ohr6+P06dPywICAJiZmUk/m5iYlPtpxrL27YsUh/Rnf4f//vtb1j7Izs6Gr68v1qxZU2LZtra2pdZYXCdvFKeqxDNERC8pNjYW27ZtQ2Jioqzd1tYWGRkZsj8ounx30LFjx6SfCwoKcPr0aXh6egIAWrVqhYsXL8LV1RXu7u6ySZsQpFar4eTkhCNHjsjajxw5Ai8vL91sSBmOHDmCgIAAjB49Gi1btoS7u7vs7ALw1xmTwsJCWVvz5s2RlJSEBw8evNR6n71h+e/7z9nZWRpna2uL0NBQfP/991i0aBFWrFhR5nL/HuSOHTuGxo0bQ19fHy1btkRhYSHu3r1bYp0ODg4vtR1l8fT0LPO4FoeW9PR0qb+039/n7YNWrVrh6tWrsLOzK7E9FhYW5a6xoKBAtt/u37+PlJSU5/7+eXp6lrqficqLgYjoJXl7e2PgwIFYsmSJrL1z5874888/MW/ePFy7dg3Lli2TPUH1Ty1btgw//vgjkpOTER4ejocPH2L48OEAgPDwcDx48AD9+/fHyZMnce3aNezatQvDhg0rER5eJDIyEnPnzsWGDRuQkpKCadOmISkpCePHj9fZtjxP48aNcerUKezatQtXrlzB9OnTcfLkSdkYV1dXnDt3DikpKbh37x7y8/PRv39/ODg4oHfv3jhy5AiuX7+O//73vyVC6/OYm5tj8uTJmDhxIlavXo1r167hzJkzWLp0KVavXg0AmDFjBn766Sekpqbi4sWL2L59uxRIn+fWrVuIiIhASkoK1q1bh6VLl0r78dVXX8XAgQMxZMgQbN68GWlpaThx4gRiYmKwY8eOl9h7ZYuMjMSqVauwfPlyXL16FQsXLsTmzZsxefJkAH+diWrbti1iY2Nx+fJlHDx4EJ988olsGWXtg4EDB8LGxga9evXCL7/8grS0NBw4cADjxo3Db7/9Vq4aGzdujF69emHEiBE4fPgwzp49i0GDBuGVV15Br169Sv3M+PHjsXLlSsTFxeHKlSuYOXMmLl68+A/2FCkNAxHRPzB79uwSp/k9PT3x5ZdfYtmyZWjRogVOnDgh/bHRhdjYWMTGxqJFixY4fPgwtm7dChsbGwCQzuoUFhYiKCgI3t7emDBhAiwtLWX3K5XHuHHjEBERgUmTJsHb2xvx8fHYunUrGjdurLNteZ4PPvgAffr0wXvvvQc/Pz/cv38fo0ePlo0ZMWIEPDw80Lp1a9ja2uLIkSMwNDTE7t27YWdnh+7du8Pb2xuxsbElLkWVZc6cOZg+fTpiYmLg6emJbt26YceOHXBzcwPw15mpqKgoNG/eHB07doS+vj7Wr19f5jKHDBmCJ0+eoE2bNggPD8f48eMxcuRIqT8uLg5DhgzBpEmT4OHhgd69e+PkyZNo0KCBFnutfHr37o3Fixfj888/R9OmTfF///d/iIuLQ+fOnaUxK1euREFBAXx9fTFhwgT8+9//li2jrH1gamqKQ4cOoUGDBujTpw88PT2lR+DVanW564yLi4Ovry/efPNN+Pv7QwiBnTt3lrjUVuy9997D9OnTMWXKFPj6+uLmzZsYNWqU9juIFEsl/n6zAxER6Uznzp3h4+ODRYsWVXUpRFQGniEiIiIixWMgIiIiIsXjJTMiIiJSPJ4hIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixWMgIiIiIsVjICIiIiLFYyAiIiIixfv/AFR+/5IBgam3AAAAAElFTkSuQmCC",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -3411,66 +3211,29 @@
     }
    ],
    "source": [
+    "# Get the counts of each key\n",
+    "counts = [len(v) for v in matches_hh_level.values()]\n",
     "\n",
-    "# columns for matching\n",
-    "keys = ['number_adults', 'number_children', 'num_pension_age', 'employment_status', \n",
-    "        'number_cars', 'rural_urban_2_categories']\n",
-    "# extract equivalent column names from dictionary\n",
-    "spc_cols = [matching_dfs_dict[key][0] for key in keys]\n",
-    "nts_cols = [matching_dfs_dict[key][1] for key in keys]\n",
-    "\n",
-    "# matc\n",
-    "spc_nts_3 = spc_matching.merge(nts_matching,\n",
-    "                               left_on= spc_cols,\n",
-    "                               right_on= nts_cols,\n",
-    "                               how = 'left')\n",
-    "\n",
-    "# Calculate how many rows from nts_matching are matched onto each hid in spc_matching,\n",
-    "spc_nts_3['count'] = spc_nts_3.groupby('hid')['HouseholdID'].transform('count')\n",
-    "\n",
-    "spc_nts_3_hist = spc_nts_3.drop_duplicates(subset='hid')\n",
-    "\n",
-    "\n",
-    "# plot a histogram of the counts and label the axis and title\n",
-    "plt.hist(spc_nts_3_hist['count'], bins=50)\n",
-    "plt.xlabel('Number of matches per household')\n",
-    "plt.ylabel('Number of households')\n",
-    "plt.title('Categorical Matching')\n",
-    "\n",
-    "\n",
-    "print(spc_nts_3_hist[spc_nts_3_hist['count'] == 0].shape[0], \"households in the SPC had no match\")\n",
-    "print(round((spc_nts_3_hist[spc_nts_3_hist['count'] == 0].shape[0] / spc_matching['hid'].unique().shape[0]) * 100, 1), \"% of households in the SPC had no match\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# calculate matching coverage for all columns\n",
+    "# Create the histogram\n",
+    "plt.hist(counts, bins='auto')  # 'auto' automatically determines the number of bins\n",
     "\n",
-    "match_coverage_3 = {key: match_coverage_col(data=spc_nts_3, \n",
-    "                                            id_x='hid', \n",
-    "                                            id_y='HouseholdID',\n",
-    "                                            column=matching_dfs_dict[key][0]) \n",
-    "                    for key in matching_dfs_dict.keys()\n",
-    "            }\n",
+    "plt.title('Categorical (Exact) Matching - Household Level')\n",
+    "plt.xlabel('No. of Households in SPC')\n",
+    "plt.ylabel('No. of matching households in NTS')\n",
     "\n",
-    "# extract any df from the list\n",
-    "#match_coverage_2['number_cars']"
+    "plt.show()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Attempt 4: Match on a subset of columns (exclude salary, tenure, and employment status)"
+    "Number of unmatched households"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [
     {
@@ -3480,408 +3243,39 @@
       "266 households in the SPC had no match\n",
       "4.0 % of households in the SPC had no match\n"
      ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
+    "# no. of keys where value is na\n",
+    "na_count = sum([1 for v in matches_hh_level.values() if pd.isna(v).all()])\n",
     "\n",
-    "# columns for matching\n",
-    "keys = ['number_adults', 'number_children', 'num_pension_age', 'number_cars', 'rural_urban_2_categories']\n",
-    "# extract equivalent column names from dictionary\n",
-    "spc_cols = [matching_dfs_dict[key][0] for key in keys]\n",
-    "nts_cols = [matching_dfs_dict[key][1] for key in keys]\n",
-    "\n",
-    "# matc\n",
-    "spc_nts_4 = spc_matching.merge(nts_matching,\n",
-    "                               left_on= spc_cols,\n",
-    "                               right_on= nts_cols,\n",
-    "                               how = 'left')\n",
-    "\n",
-    "# Calculate how many rows from nts_matching are matched onto each hid in spc_matching,\n",
-    "spc_nts_4['count'] = spc_nts_4.groupby('hid')['HouseholdID'].transform('count')\n",
-    "\n",
-    "spc_nts_4_hist = spc_nts_4.drop_duplicates(subset='hid')\n",
-    "\n",
-    "\n",
-    "# plot a histogram of the counts and label the axis and title\n",
-    "plt.hist(spc_nts_4_hist['count'], bins=50)\n",
-    "plt.xlabel('Number of matches per household')\n",
-    "plt.ylabel('Number of households')\n",
-    "plt.title('Categorical Matching')\n",
-    "\n",
-    "\n",
-    "print(spc_nts_4_hist[spc_nts_4_hist['count'] == 0].shape[0], \"households in the SPC had no match\")\n",
-    "print(round((spc_nts_4_hist[spc_nts_4_hist['count'] == 0].shape[0] / spc_matching['hid'].unique().shape[0]) * 100, 1), \"% of households in the SPC had no match\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 41,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# calculate matching coverage for all columns\n",
-    "\n",
-    "match_coverage_4 = {key: match_coverage_col(data=spc_nts_4, \n",
-    "                                            id_x='hid', \n",
-    "                                            id_y='HouseholdID',\n",
-    "                                            column=matching_dfs_dict[key][0]) \n",
-    "                    for key in matching_dfs_dict.keys()\n",
-    "            }\n",
     "\n",
-    "# extract any df from the list\n",
-    "#match_coverage_2['number_cars']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Removing salary has a significant impact on matching"
+    "print(na_count, \"households in the SPC had no match\")\n",
+    "print(round((na_count / len(matches_hh_level)) * 100, 1), \"% of households in the SPC had no match\")\n",
+    "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "6725 Total households in SPC\n",
-      "991 Unmatched households - matching on all categories\n",
-      "674 Unmatched households - exclusing Salary from matching\n",
-      "547 Unmatched households - exclusing Salary and Tenure from matching\n",
-      "266 Unmatched households - exclusing Salary, Tenure and Employment status from matching\n"
+      "('E02002183_0091', [2019001902.0, 2019004101.0, 2019004092.0, 2019004108.0, 2019004125.0, 2019004121.0, 2019001719.0, 2019001714.0, 2019001119.0, 2019001130.0, 2019001148.0, 2019000880.0, 2019003240.0, 2019002767.0, 2019002775.0, 2019002769.0, 2019005597.0, 2019002770.0, 2019003252.0, 2019005438.0, 2019006462.0, 2019006475.0, 2019003208.0, 2019004196.0, 2019004191.0, 2019004200.0, 2019004197.0, 2019000839.0, 2019000350.0, 2019000855.0, 2019001091.0, 2019001721.0, 2019001716.0, 2019000813.0, 2019004159.0, 2019000823.0, 2019004177.0, 2019001167.0, 2019000633.0, 2019000536.0, 2019005323.0, 2019005356.0, 2019004637.0, 2019005612.0, 2019002547.0, 2019005638.0, 2019001816.0, 2019002329.0, 2019002894.0, 2019001865.0, 2019003329.0, 2019002919.0, 2019002929.0, 2019005553.0, 2019000307.0, 2019004714.0, 2019002980.0, 2019001202.0, 2019001205.0, 2019001210.0, 2019001782.0, 2019001788.0, 2019002721.0, 2019005579.0, 2019000863.0, 2019001896.0, 2019001909.0, 2019000589.0, 2019000701.0, 2019002368.0, 2019002369.0, 2019002374.0, 2019002378.0, 2019002376.0, 2019002366.0, 2019001012.0, 2019002405.0, 2019002392.0, 2019002712.0, 2019002711.0, 2019001044.0, 2019001066.0, 2019001084.0, 2019001268.0, 2019003070.0, 2019004770.0, 2019002288.0, 2019001949.0, 2019002312.0, 2019000961.0, 2019003385.0, 2019003394.0, 2019000244.0, 2019003381.0, 2019003384.0, 2019001373.0, 2019006564.0, 2019001450.0, 2019006569.0, 2019001371.0, 2019006568.0, 2019005410.0, 2019005415.0, 2019005417.0, 2019000491.0, 2019000187.0, 2019003333.0, 2019002952.0, 2019005752.0, 2019002951.0, 2019000199.0, 2019004994.0, 2019004997.0, 2019005174.0, 2019005909.0, 2019005185.0, 2019005177.0, 2019005914.0, 2019005558.0, 2019001437.0, 2019005574.0, 2019004547.0, 2019000074.0, 2019006080.0, 2019006090.0, 2019005020.0, 2019005024.0, 2019000088.0, 2019006273.0, 2019002705.0, 2019002203.0, 2019000762.0, 2019000759.0, 2019000655.0, 2019000661.0, 2019000662.0, 2019004035.0, 2019000660.0, 2019000767.0, 2019000529.0, 2019005311.0, 2019005342.0, 2019005501.0, 2019002739.0, 2019001245.0, 2019001286.0, 2019001255.0, 2019001246.0, 2019004776.0, 2019001261.0, 2019001259.0, 2019001295.0, 2019003022.0, 2019003023.0, 2019001269.0, 2019003725.0, 2019003726.0, 2019003737.0, 2019006300.0, 2019003738.0, 2019000518.0, 2019000523.0, 2019000525.0, 2019000212.0, 2019003411.0, 2019005772.0, 2019005779.0, 2019001284.0, 2019005849.0, 2019001596.0, 2019002044.0, 2019002039.0, 2019003127.0, 2019001490.0, 2019001493.0, 2019005972.0, 2019003150.0, 2019001959.0, 2019001964.0, 2019001966.0, 2019001543.0, 2019001983.0, 2019001524.0, 2019006505.0, 2019001350.0, 2019001349.0, 2019001352.0, 2019001355.0, 2019006549.0, 2019001367.0, 2019001400.0, 2019004598.0, 2019003484.0, 2019005143.0, 2019005152.0, 2019005172.0, 2019005810.0, 2019005039.0, 2019003494.0, 2019000052.0, 2019000056.0, 2019000081.0, 2019003540.0, 2019000134.0, 2019003554.0, 2019006630.0, 2019003560.0, 2019004432.0, 2019002492.0, 2019002518.0, 2019005498.0, 2019002519.0, 2019001670.0, 2019005821.0, 2019005869.0, 2019005116.0, 2019002058.0, 2019005864.0, 2019002061.0, 2019005069.0, 2019001826.0, 2019002872.0, 2019005708.0, 2019005693.0, 2019003294.0, 2019003297.0, 2019003273.0, 2019005654.0, 2019000907.0, 2019000913.0, 2019000904.0, 2019001823.0, 2019001839.0, 2019002861.0, 2019003365.0, 2019004669.0, 2019004660.0, 2019000293.0, 2019003910.0, 2019003911.0, 2019003921.0, 2019003801.0, 2019002075.0, 2019005823.0, 2019005218.0, 2019005226.0, 2019003630.0, 2019004305.0, 2019003648.0, 2019004314.0, 2019004315.0, 2019004291.0, 2019004303.0, 2019000247.0, 2019004579.0, 2019006669.0, 2019003730.0, 2019003713.0, 2019003618.0, 2019006291.0, 2019000021.0, 2019006077.0, 2019006110.0, 2019000030.0, 2019000041.0, 2019000025.0, 2019006127.0, 2019006764.0, 2019005947.0, 2019005959.0, 2019005812.0, 2019003831.0, 2019006755.0, 2019006754.0, 2019004601.0, 2019003077.0, 2019003104.0, 2019001320.0, 2019000452.0, 2019006436.0, 2019006446.0, 2019006425.0, 2019000459.0, 2019001318.0, 2019003125.0, 2019006375.0, 2019000329.0, 2019006406.0, 2019006409.0, 2019003164.0, 2019003220.0, 2019002599.0, 2019004341.0, 2019004327.0, 2019004349.0, 2019003683.0, 2019004334.0, 2019004343.0, 2019004354.0, 2019004854.0, 2019003777.0, 2019004802.0, 2019003968.0, 2019003944.0, 2019003962.0, 2019003754.0, 2019000038.0, 2019003699.0, 2019003694.0, 2019003704.0, 2019004385.0, 2019003706.0, 2019004367.0, 2019004379.0, 2019004387.0, 2019004819.0, 2019006822.0, 2019006239.0, 2019003571.0, 2019006642.0, 2019006229.0, 2019003586.0, 2019006248.0, 2019006663.0, 2019006677.0, 2019005784.0, 2019005793.0, 2019000224.0, 2019004485.0, 2019004981.0, 2019003821.0, 2019003852.0, 2019004508.0, 2019004515.0, 2019003858.0, 2019003864.0, 2019003889.0, 2021003917.0, 2021003873.0, 2021003878.0, 2021003879.0, 2021003008.0, 2021003874.0, 2021003880.0, 2021003633.0, 2021003020.0, 2021003914.0, 2021002626.0, 2021002635.0, 2021002656.0, 2021002664.0, 2021003779.0, 2021002082.0, 2021002092.0, 2021002220.0, 2021003126.0, 2021002234.0, 2021002531.0, 2021002249.0, 2021002546.0, 2021002959.0, 2021002954.0, 2021002968.0, 2021002844.0, 2021002595.0, 2021002598.0, 2021002858.0, 2021003704.0, 2021004011.0, 2021003082.0, 2021003707.0, 2021004022.0, 2021004025.0, 2021003745.0, 2021004057.0, 2021003800.0, 2021004098.0, 2021004102.0, 2021004100.0, 2021004110.0, 2021002538.0, 2021003180.0, 2021001152.0, 2021001179.0, 2021004549.0, 2021004176.0, 2021000529.0, 2021004303.0, 2021004567.0, 2021001893.0, 2021004313.0, 2021000557.0, 2021000523.0, 2021004209.0, 2021000563.0, 2021001900.0, 2021004572.0, 2021000556.0, 2021001203.0, 2021003945.0, 2021000172.0, 2021004792.0, 2021004791.0, 2021004794.0, 2021000165.0, 2021000159.0, 2021001661.0, 2021001907.0, 2021000199.0, 2021001724.0, 2021001954.0, 2021001736.0, 2021001721.0, 2021001967.0, 2021000464.0, 2021004234.0, 2021000514.0, 2021000987.0, 2021000997.0, 2021000976.0, 2021000775.0, 2021000804.0, 2021000797.0, 2021000801.0, 2021000789.0, 2021004514.0, 2021004260.0, 2021003028.0, 2021003746.0, 2021003027.0, 2021002703.0, 2021002706.0, 2021002394.0, 2021002159.0, 2021002379.0, 2021002147.0, 2021004317.0, 2021001450.0, 2021001242.0, 2021001435.0, 2021001429.0, 2021001456.0, 2021004591.0, 2021001224.0, 2021001499.0, 2021000582.0, 2021004371.0, 2021004375.0, 2021004373.0, 2021004379.0, 2021001036.0, 2021001305.0, 2021004397.0, 2021001083.0, 2021001100.0, 2021001335.0, 2021001081.0, 2021003792.0, 2021002083.0, 2021002210.0, 2021002525.0, 2021002353.0, 2021002511.0, 2021003061.0, 2021003694.0, 2021003685.0, 2021003978.0, 2021003692.0, 2021003500.0, 2021000307.0, 2021004668.0, 2021000072.0, 2021004703.0, 2021003511.0, 2021003529.0, 2021000372.0, 2021001979.0, 2021001983.0, 2021001978.0, 2021001552.0, 2021002003.0, 2021000634.0, 2021000638.0, 2021000629.0, 2021000491.0, 2021000632.0, 2021000649.0, 2021000296.0, 2021003478.0, 2021000064.0, 2021003362.0, 2021004673.0, 2021003360.0, 2021004676.0, 2021003371.0, 2021003377.0, 2021002406.0, 2021000222.0, 2021001692.0, 2021000422.0, 2021000414.0, 2021000418.0, 2021001707.0, 2021001955.0, 2021001911.0, 2021000206.0, 2021001680.0, 2021000020.0, 2021000225.0, 2021000226.0, 2021000025.0, 2021002482.0, 2021001802.0, 2021004223.0, 2021001803.0, 2021004641.0, 2021001809.0, 2021001800.0, 2021004642.0, 2021000736.0, 2021000745.0, 2021004233.0, 2021001820.0, 2021000945.0, 2021000972.0, 2021004666.0, 2021000969.0, 2021003546.0, 2021003554.0, 2021000371.0, 2021000388.0, 2021000826.0, 2021003855.0, 2021002073.0, 2021000814.0, 2021000816.0, 2021000850.0, 2021004137.0, 2021004533.0, 2021004144.0, 2021000835.0, 2021004526.0, 2021001400.0, 2021003417.0, 2021002259.0, 2021003242.0, 2021003269.0, 2021002286.0, 2021003281.0, 2021000599.0, 2021001274.0, 2021003603.0, 2021001590.0, 2021000501.0, 2021000881.0, 2021000889.0, 2021001562.0, 2021001595.0, 2021000879.0, 2021000887.0, 2021001612.0, 2021001594.0, 2021003270.0, 2021003282.0, 2021002294.0, 2021002293.0, 2021003307.0, 2021003308.0, 2021002297.0, 2021003467.0, 2021001356.0, 2021001347.0, 2021001326.0, 2021001114.0, 2021004441.0, 2021004445.0, 2021004430.0, 2021004460.0, 2021001132.0, 2021004436.0, 2021001128.0, 2021003096.0, 2021003097.0, 2021000130.0, 2021004781.0, 2021004776.0, 2021004785.0, 2021004772.0, 2022001047.0, 2022001062.0, 2022001110.0, 2022001120.0, 2022001123.0, 2022001176.0, 2022001215.0, 2022001217.0, 2022001223.0, 2022001228.0, 2022001255.0, 2022001300.0, 2022001301.0, 2022001310.0, 2022001375.0, 2022001376.0, 2022001381.0, 2022001402.0, 2022001410.0, 2022001415.0, 2022001419.0, 2022001429.0, 2022001434.0, 2022001449.0, 2022001549.0, 2022001552.0, 2022000006.0, 2022000010.0, 2022000014.0, 2022000064.0, 2022000107.0, 2022000110.0, 2022000116.0, 2022000123.0, 2022000126.0, 2022000181.0, 2022000218.0, 2022002651.0, 2022002676.0, 2022002688.0, 2022002698.0, 2022002707.0, 2022002722.0, 2022002757.0, 2022002777.0, 2022002778.0, 2022002787.0, 2022002848.0, 2022003170.0, 2022003226.0, 2022003247.0, 2022003274.0, 2022003279.0, 2022003295.0, 2022003300.0, 2022003315.0, 2022003324.0, 2022003340.0, 2022003388.0, 2022003394.0, 2022003414.0, 2022003423.0, 2022003427.0, 2022003430.0, 2022003476.0, 2022003515.0, 2022003525.0, 2022003536.0, 2022003539.0, 2022003579.0, 2022003600.0, 2022003627.0, 2022000552.0, 2022000556.0, 2022000579.0, 2022000596.0, 2022000624.0, 2022000633.0, 2022000653.0, 2022000659.0, 2022000662.0, 2022000668.0, 2022000695.0, 2022000718.0, 2022000719.0, 2022000720.0, 2022000735.0, 2022000758.0, 2022000815.0, 2022000816.0, 2022000823.0, 2022000844.0, 2022000867.0, 2022000874.0, 2022000887.0, 2022000918.0, 2022001652.0, 2022001663.0, 2022001669.0, 2022001678.0, 2022001681.0, 2022001682.0, 2022001684.0, 2022001685.0, 2022001708.0, 2022001734.0, 2022001745.0, 2022001759.0, 2022001765.0, 2022001767.0, 2022001828.0, 2022001856.0, 2022001934.0, 2022001937.0, 2022001944.0, 2022001953.0, 2022001988.0, 2022001998.0, 2022002009.0, 2022002098.0, 2022002136.0, 2022002140.0, 2022002166.0, 2022002174.0, 2022002197.0, 2022002211.0, 2022002256.0, 2022002336.0, 2022002346.0, 2022002356.0, 2022002358.0, 2022002363.0, 2022002364.0, 2022002380.0, 2022002429.0, 2022002435.0, 2022002460.0, 2022002509.0, 2022002522.0, 2022002525.0, 2022002531.0, 2022002571.0, 2022002582.0, 2022002590.0, 2022003660.0, 2022003669.0, 2022003720.0, 2022003727.0, 2022003759.0, 2022003808.0, 2022003813.0, 2022003817.0, 2022003841.0, 2022003844.0, 2022003872.0, 2022003881.0, 2022003890.0, 2022003892.0, 2022003904.0, 2022003912.0, 2022003913.0, 2022003916.0, 2022003921.0, 2022003932.0, 2022003935.0, 2022003937.0, 2022003940.0, 2022003945.0, 2022003961.0, 2022003976.0, 2022003978.0, 2022003984.0, 2022004015.0, 2022004048.0, 2022004075.0, 2022004078.0, 2022004096.0, 2022004130.0, 2022000262.0, 2022000268.0, 2022000269.0, 2022000284.0, 2022000357.0, 2022000439.0, 2022000444.0, 2022000461.0, 2022000484.0, 2022000485.0, 2022000517.0, 2022002869.0, 2022002872.0, 2022002878.0, 2022002897.0, 2022002907.0, 2022002908.0, 2022002931.0, 2022002937.0, 2022002967.0, 2022002974.0, 2022002987.0, 2022003004.0, 2022003042.0, 2022003049.0, 2022003056.0, 2022003058.0, 2022003065.0, 2022003067.0, 2022003104.0, 2022003106.0, 2022003114.0, 2022003116.0, 2022004222.0, 2022004240.0, 2022004255.0, 2022004305.0, 2022004329.0, 2022004359.0])\n"
      ]
     }
    ],
    "source": [
-    "print(spc_matching['hid'].nunique(), \"Total households in SPC\")\n",
-    "\n",
-    "# Attempt 1\n",
-    "print(spc_nts_1_hist[spc_nts_1_hist['count'] == 0].shape[0], \"Unmatched households - matching on all categories\")\n",
-    "# Attempt 2\n",
-    "print(spc_nts_2_hist[spc_nts_2_hist['count'] == 0].shape[0], \"Unmatched households - exclusing Salary from matching\")\n",
-    "# Attempt 3\n",
-    "print(spc_nts_3_hist[spc_nts_3_hist['count'] == 0].shape[0], \"Unmatched households - exclusing Salary and Tenure from matching\")\n",
-    "# Attempt 4\n",
-    "print(spc_nts_4_hist[spc_nts_4_hist['count'] == 0].shape[0], \"Unmatched households - exclusing Salary, Tenure and Employment status from matching\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Plot matching coverage for each attempt + variable (key) combination\n",
-    "\n",
-    "This will show us, for each matching key, the % of spc households from each unique category that were matched to the NTS"
+    "# print the 6th key, value in the matches_hh_level dictionary\n",
+    "print(list(matches_hh_level.items())[90])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+0AAAIeCAYAAADONu4QAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB8AklEQVR4nOzdeXhNV9/G8ftkDokYk4gpxibmFDWLeaiZomiNNU9FSlWRaGsqqqmpD5UYS1vlMTVKSilqKmoqLSGGmEUkISQ57x8e53WaICGRQ76f68p15ay99jq/vROnvbP2XttgNBqNAgAAAAAAFscqowsAAAAAAADJI7QDAAAAAGChCO0AAAAAAFgoQjsAAAAAABaK0A4AAAAAgIUitAMAAAAAYKEI7QAAAAAAWChCOwAAAAAAForQDgAAAACAhSK0AwAsSnBwsAwGg/bt2/fUvrVr11bt2rXTvyikq5CQEJUvX14ODg4yGAyKjIzM6JJeqK1bt8pgMOiHH37I6FIAABaI0A4AmczDUGwwGPTbb78l2W40GlWgQAEZDAY1a9bsmd5jwoQJWr169XNWiszg+vXrat++vRwdHTVr1iwtXrxYWbNmzeiyAACwGDYZXQAAIGM4ODho2bJlqlGjhln7r7/+qvPnz8ve3v6Zx54wYYLeeusttWrV6jmrfLKff/45XcdH+tu7d69u376tTz75RPXr18/ocgAAsDjMtANAJvXmm2/q+++/V3x8vFn7smXLVKFCBbm7u2dQZSlnZ2cnOzu7jC7jpRATE5PRJSTrypUrkqTs2bOn2ZiWeqwZzVLOS2Jiou7evZvRZQDAS4PQDgCZVMeOHXX9+nVt2rTJ1Hbv3j398MMP6tSpU7L7TJ06VdWqVVOuXLnk6OioChUqJLkP12AwKCYmRgsXLjRdht+tWzfT9gsXLqhnz57y8PCQvb29ChcurH79+unevXtm48TFxWnYsGHKkyePsmbNqtatW+vq1atmff59T/vDe4O/++47ffbZZ8qfP78cHBxUr149/fPPP0mOZ9asWSpSpIgcHR31xhtvaPv27am6T37JkiV64403lCVLFuXIkUO1atVKMvs/e/ZslSpVSvb29vLw8NCAAQPM7tkeOHCgnJycFBsbm2T8jh07yt3dXQkJCaa2n376STVr1lTWrFnl7Oyspk2b6ujRo2b7devWTU5OTjp16pTefPNNOTs7q3PnzpKk7du3q127dipYsKDs7e1VoEABDR06VHfu3Eny/t9//71KliwpBwcHlS5dWqtWrVK3bt3k6elp1i8xMVEzZsxQqVKl5ODgIDc3N/Xp00c3b9584vmrXbu2unbtKkmqVKlSkt+V77//XhUqVJCjo6Ny586td955RxcuXEjxsSbH399fBoNB//zzj7p166bs2bPLxcVF3bt3N/sZnDlzRgaDQcHBwUnGMBgM8vf3TzLmyZMn9c4778jFxUV58uTRmDFjZDQade7cObVs2VLZsmWTu7u7pk2blmxtCQkJ+uijj+Tu7q6sWbOqRYsWOnfuXJJ+u3fvVuPGjeXi4qIsWbLI19dXO3bsSPY4jx07pk6dOilHjhxJrqp5krt378rf318lSpSQg4OD8ubNqzZt2ujUqVOmPin5PHh4vgYOHKilS5ea/i2EhIRIkpYvX64KFSrI2dlZ2bJlU5kyZfTll1+muE4AyAwI7QCQSXl6eqpq1ar69ttvTW0//fSTbt26pbfffjvZfb788kv5+Pho/PjxmjBhgmxsbNSuXTutX7/e1Gfx4sWyt7dXzZo1tXjxYi1evFh9+vSRJF28eFFvvPGGli9frg4dOigwMFDvvvuufv311yShddCgQTp06JDGjRunfv36ae3atRo4cGCKjm3SpElatWqV/Pz8NGrUKP3+++9JgtycOXM0cOBA5c+fX1OmTFHNmjXVqlUrnT9/PkXvERAQoHfffVe2trYaP368AgICVKBAAf3yyy+mPv7+/howYIA8PDw0bdo0tW3bVl9//bUaNmyo+/fvS5I6dOigmJgYs3MoSbGxsVq7dq3eeustWVtbm85t06ZN5eTkpMmTJ2vMmDE6duyYatSooTNnzpjtHx8fr0aNGsnV1VVTp05V27ZtJT0IwrGxserXr5+++uorNWrUSF999ZW6dOlitv/69evVoUMH2draauLEiWrTpo169uyp/fv3JzkXffr00QcffKDq1avryy+/VPfu3bV06VI1atTIdJzJGT16tHr37i1JGj9+vNnvSnBwsNq3by9ra2tNnDhRvXr10o8//qgaNWokWajuccf6JO3bt9ft27c1ceJEtW/fXsHBwQoICHjqfk/SoUMHJSYmatKkSapcubI+/fRTzZgxQw0aNFC+fPk0efJkFStWTH5+ftq2bVuS/T/77DOtX79eI0eO1ODBg7Vp0ybVr1/f7A8qv/zyi2rVqqWoqCiNGzdOEyZMUGRkpOrWras9e/YkGbNdu3aKjY3VhAkT1KtXrxQdR0JCgpo1a6aAgABVqFBB06ZN05AhQ3Tr1i0dOXLE1C8lnweP1j106FB16NBBX375pTw9PbVp0yZ17NhROXLk0OTJkzVp0iTVrl07yR8gACDTMwIAMpWgoCCjJOPevXuNM2fONDo7OxtjY2ONRqPR2K5dO2OdOnWMRqPRWKhQIWPTpk3N9n3Y76F79+4ZS5cubaxbt65Ze9asWY1du3ZN8t5dunQxWllZGffu3ZtkW2Jioll99evXN7UZjUbj0KFDjdbW1sbIyEhTm6+vr9HX19f0esuWLUZJRm9vb2NcXJyp/csvvzRKMh4+fNhoNBqNcXFxxly5chkrVapkvH//vqlfcHCwUZLZmMn5+++/jVZWVsbWrVsbExISkj2OK1euGO3s7IwNGzY06zNz5kyjJOOCBQtM/fPly2ds27at2TjfffedUZJx27ZtRqPRaLx9+7Yxe/bsxl69epn1u3TpktHFxcWsvWvXrkZJxg8//DBJ7f/+GRqNRuPEiRONBoPBePbsWVNbmTJljPnz5zfevn3b1LZ161ajJGOhQoVMbdu3bzdKMi5dutRszJCQkGTb/+3R38eH7t27Z3R1dTWWLl3aeOfOHVP7unXrjJKMY8eOTdGxJmfcuHFGScYePXqYtbdu3dqYK1cu0+uwsDCjJGNQUFCSMSQZx40bl2TM3r17m9ri4+ON+fPnNxoMBuOkSZNM7Tdv3jQ6Ojqa/ft4+HubL18+Y1RUlKn94e/Al19+aTQaH/yuFC9e3NioUSOzfxuxsbHGwoULGxs0aJCkpo4dO6bovDxqwYIFRknG6dOnJ9n27/d91OM+DyQZraysjEePHjVrHzJkiDFbtmzG+Pj4VNcIAJkJM+0AkIm1b99ed+7c0bp163T79m2tW7fusZfGS5Kjo6Pp+5s3b+rWrVuqWbOm/vjjj6e+V2JiolavXq3mzZurYsWKSbYbDAaz17179zZrq1mzphISEnT27Nmnvlf37t3N7nWvWbOmJOn06dOSpH379un69evq1auXbGz+f03Wzp07K0eOHE8df/Xq1UpMTNTYsWNlZWX+n9KHNW/evFn37t3T+++/b9anV69eypYtm2k20mAwqF27dtqwYYOio6NN/VasWKF8+fKZLmnetGmTIiMj1bFjR127ds30ZW1trcqVK2vLli1J6uzXr1+Stkd/hjExMbp27ZqqVasmo9GoAwcOSHpwRcThw4fVpUsXOTk5mfr7+vqqTJkyZuN9//33cnFxUYMGDczqqlChgpycnJKt62n27dunK1euqH///nJwcDC1N23aVF5eXsnO5CZ3rE/St29fs9c1a9bU9evXFRUVlep6H3rvvfdM31tbW6tixYoyGo3q2bOnqT179ux67bXXTL+Lj+rSpYucnZ1Nr9966y3lzZtXGzZskCQdPHhQf//9tzp16qTr16+bznVMTIzq1aunbdu2KTEx8YnHmRIrV65U7ty5NWjQoCTbHv03mZrPA19fX5UsWdKsLXv27IqJiTG7RQcAkBSrxwNAJpYnTx7Vr19fy5YtU2xsrBISEvTWW289tv+6dev06aef6uDBg4qLizO1/ztwJ+fq1auKiopS6dKlU1RbwYIFzV4/DNNPu086Jfs+DP7FihUz62djY5Pkfu3knDp1SlZWVklCyKMevsdrr71m1m5nZ6ciRYqY/fGhQ4cOmjFjhtasWaNOnTopOjpaGzZsUJ8+fUzn9u+//5Yk1a1bN9n3y5YtW5JjyZ8/f5J+4eHhGjt2rNasWZPkXN66dcus9n+fn4dtj4ayv//+W7du3ZKrq2uydT1caC41HnfuJMnLyyvJowofd6xP8qTfkX+fy2cd08XFRQ4ODsqdO3eS9uvXryfZv3jx4mavDQaDihUrZrr14eHvwMN1AJJz69Ytsz88FS5cOFXHID34/X7ttdfM/qCVnNR8HiRXR//+/fXdd9+pSZMmypcvnxo2bKj27durcePGqa4ZAF5lhHYAyOQ6deqkXr166dKlS2rSpMljV/Hevn27WrRooVq1amn27NnKmzevbG1tFRQUpGXLlqV5XQ/v4/43o9GYrvtmhCpVqsjT01PfffedOnXqpLVr1+rOnTvq0KGDqc/DGdTFixcnu7L/vwOWvb19kqsAEhIS1KBBA924cUMjR46Ul5eXsmbNqgsXLqhbt25JZmlTIjExUa6urlq6dGmy2/PkyZPqMVMruWN9mqf9jjzuD1GPLgqYkjHT8nfx4c/n888/V/ny5ZPt8+iVEZL5bHhaSu3nQXJ1uLq66uDBg9q4caN++ukn/fTTTwoKClKXLl20cOHCdKkbAF5GhHYAyORat26tPn366Pfff9eKFSse22/lypVycHDQxo0bzZ7hHhQUlKRvcoEnT548ypYtm9lCVhmlUKFCkqR//vlHderUMbXHx8frzJkzKlu27BP3L1q0qBITE3Xs2LHHhqeH73HixAkVKVLE1H7v3j2FhYUleSZ5+/bt9eWXXyoqKkorVqyQp6enqlSpYvae0oOg86zPMz98+LBOnjyphQsXmi089+/Lkx89P//277aiRYtq8+bNql69epoFxEfP3b+vLDhx4oRpe3p6OFv970XvUnJ7xrN6OJP+kNFo1D///GP6fXz4O5AtW7Z0faZ90aJFtXv3bt2/f1+2trbJ9knN58GT2NnZqXnz5mrevLkSExPVv39/ff311xozZkyyV3oAQGbEPe0AkMk5OTlpzpw58vf3V/PmzR/bz9raWgaDwWym8cyZM1q9enWSvlmzZk0SdqysrNSqVSutXbtW+/btS7LPi5wFr1ixonLlyqV58+aZPad+6dKlKbr8vlWrVrKystL48eOTzE4/PI769evLzs5OgYGBZsf2zTff6NatW2ratKnZfh06dFBcXJwWLlyokJAQtW/f3mx7o0aNlC1bNk2YMCHZFdn//Ti85Dyc9X20HqPRmOQRWx4eHipdurQWLVpkdp/9r7/+qsOHD5v1bd++vRISEvTJJ58keb/4+PgkvwcpUbFiRbm6umru3Llml13/9NNPOn78eJJzlx6yZcum3LlzJ1nlffbs2en2nosWLdLt27dNr3/44QdFRESoSZMmkqQKFSqoaNGimjp1qtnP5aGU/A6kRNu2bXXt2jXNnDkzybaHvzup+Tx4nH/fImBlZWX6A8WjP3cAyOyYaQcAPPEe2YeaNm2q6dOnq3HjxurUqZOuXLmiWbNmqVixYvrzzz/N+laoUEGbN2/W9OnT5eHhocKFC6ty5cqaMGGCfv75Z/n6+qp3797y9vZWRESEvv/+e/3222+PvTQ/rdnZ2cnf31+DBg1S3bp11b59e505c0bBwcEqWrToU+/RL1asmEaPHq1PPvlENWvWVJs2bWRvb6+9e/fKw8NDEydOVJ48eTRq1CgFBASocePGatGihU6cOKHZs2erUqVKeuedd8zGfP31103jxsXFmV0aLz0IkXPmzNG7776r119/XW+//bby5Mmj8PBwrV+/XtWrV082ZD3Ky8tLRYsWlZ+fny5cuKBs2bJp5cqVyf6hYsKECWrZsqWqV6+u7t276+bNm5o5c6ZKly5tFhh9fX3Vp08fTZw4UQcPHlTDhg1la2urv//+W99//72+/PLLJ66TkBxbW1tNnjxZ3bt3l6+vrzp27KjLly+bHhU2dOjQVI33rN577z1NmjRJ7733nipWrKht27bp5MmT6fZ+OXPmVI0aNdS9e3ddvnxZM2bMULFixUyParOystL8+fPVpEkTlSpVSt27d1e+fPl04cIFbdmyRdmyZdPatWufu44uXbpo0aJFGjZsmPbs2aOaNWsqJiZGmzdvVv/+/dWyZctUfR48znvvvacbN26obt26yp8/v86ePauvvvpK5cuXl7e393MfBwC8MjJkzXoAQIZJ7hFbyUnukW/ffPONsXjx4kZ7e3ujl5eXMSgoyPRoqUf99ddfxlq1ahkdHR2Nksweb3X27Fljly5djHny5DHa29sbixQpYhwwYIDpEW2Pq+/hY7G2bNlianvcI9++//57s30f9/iuwMBAY6FChYz29vbGN954w7hjxw5jhQoVjI0bN37iuXlowYIFRh8fH6O9vb0xR44cRl9fX+OmTZvM+sycOdPo5eVltLW1Nbq5uRn79etnvHnzZrLjjR492ijJWKxYsce+55YtW4yNGjUyuri4GB0cHIxFixY1duvWzbhv3z5Tn65duxqzZs2a7P7Hjh0z1q9f3+jk5GTMnTu3sVevXsZDhw4le36WL19u9PLyMtrb2xtLly5tXLNmjbFt27ZGLy+vJOP+5z//MVaoUMHo6OhodHZ2NpYpU8Y4YsQI48WLFx97LEbjk38fV6xYYTq/OXPmNHbu3Nl4/vx5sz5POtbkPPx9vXr1arJ1hIWFmdpiY2ONPXv2NLq4uBidnZ2N7du3N165cuWxj3z795iPq83X19dYqlQp0+uHv7fffvutcdSoUUZXV1ejo6OjsWnTpmaP4XvowIEDxjZt2hhz5cpltLe3NxYqVMjYvn17Y2ho6FNrSqnY2Fjj6NGjjYULFzba2toa3d3djW+99Zbx1KlTpj4p/TyQZBwwYECS9/jhhx+MDRs2NLq6uhrt7OyMBQsWNPbp08cYERHxTDUDwKvKYDRa6Ko8AAC8YImJicqTJ4/atGmjefPmZXQ5Fql8+fLKkycPj+kCAOAF4Z52AECmdPfu3ST30S9atEg3btxQ7dq1M6YoC3L//n2z+/0laevWrTp06BDnBwCAF4iZdgBAprR161YNHTpU7dq1U65cufTHH3/om2++kbe3t/bv3y87O7uMLjFDnTlzRvXr19c777wjDw8P/fXXX5o7d65cXFx05MgR5cqVK6NLRCrdu3dPN27ceGIfFxeXdHtMHADg2bAQHQAgU/L09FSBAgUUGBioGzduKGfOnOrSpYsmTZqU6QO79OCRZxUqVND8+fN19epVZc2aVU2bNtWkSZMI7C+pnTt3mj3iMDlBQUHq1q3biykIAJAizLQDAABkAjdv3tT+/fuf2KdUqVLKmzfvC6oIAJAShHYAAAAAACwUC9EBAAAAAGChuKddDx7xc/HiRTk7O8tgMGR0OQAAAACAV5zRaNTt27fl4eEhK6vHz6cT2iVdvHhRBQoUyOgyAAAAAACZzLlz55Q/f/7Hbie0S3J2dpb04GRly5Ytg6sBAAAAALzqoqKiVKBAAVMefRxCu2S6JD5btmyEdgAAAADAC/O0W7RZiA4AAAAAAAuVoaF927Ztat68uTw8PGQwGLR69Wqz7UajUWPHjlXevHnl6Oio+vXr6++//zbrc+PGDXXu3FnZsmVT9uzZ1bNnT0VHR7/AowAAAAAAIH1kaGiPiYlRuXLlNGvWrGS3T5kyRYGBgZo7d652796trFmzqlGjRrp7966pT+fOnXX06FFt2rRJ69at07Zt29S7d+8XdQgAAAAAAKQbg9FoNGZ0EdKD6/hXrVqlVq1aSXowy+7h4aHhw4fLz89PknTr1i25ubkpODhYb7/9to4fP66SJUtq7969qlixoiQpJCREb775ps6fPy8PD48UvXdUVJRcXFx069Yt7mkHAAAAkpGQkKD79+9ndBnAS8PW1lbW1taP3Z7SHGqxC9GFhYXp0qVLql+/vqnNxcVFlStX1q5du/T2229r165dyp49uymwS1L9+vVlZWWl3bt3q3Xr1smOHRcXp7i4ONPrqKio9DsQAAAA4CVmNBp16dIlRUZGZnQpwEsne/bscnd3f+pic09isaH90qVLkiQ3Nzezdjc3N9O2S5cuydXV1Wy7jY2NcubMaeqTnIkTJyogICCNKwYAAABePQ8Du6urq7JkyfJc4QPILIxGo2JjY3XlyhVJUt68eZ95LIsN7elp1KhRGjZsmOn1w+fjAQAAAPh/CQkJpsCeK1eujC4HeKk4OjpKkq5cuSJXV9cnXir/JBb7yDd3d3dJ0uXLl83aL1++bNrm7u5u+svFQ/Hx8bpx44apT3Ls7e1Nz2Tn2ewAAABA8h7ew54lS5YMrgR4OT38t/M860FYbGgvXLiw3N3dFRoaamqLiorS7t27VbVqVUlS1apVFRkZqf3795v6/PLLL0pMTFTlypVfeM0AAADAq4hL4oFnkxb/djL08vjo6Gj9888/ptdhYWE6ePCgcubMqYIFC+r999/Xp59+quLFi6tw4cIaM2aMPDw8TCvMe3t7q3HjxurVq5fmzp2r+/fva+DAgXr77bdTvHI8AAAAAACWKkNn2vft2ycfHx/5+PhIkoYNGyYfHx+NHTtWkjRixAgNGjRIvXv3VqVKlRQdHa2QkBA5ODiYxli6dKm8vLxUr149vfnmm6pRo4b+85//ZMjxAAAAAADSXnBwsLJnz57m4545c0YGg0EHDx5M87HTSobOtNeuXVtPeky8wWDQ+PHjNX78+Mf2yZkzp5YtW5Ye5QEAAAB4DM8P17/Q9zszqWmq+nfr1k0LFy6U9OB52QULFlSXLl300UcfycbGstfjNhgMWrVqlekK44z28BLvXbt2qUqVKqb2uLg4eXh46MaNG9qyZYtq166dovH8/f21evVqiw7KjzN48GDt2LFDR44ckbe39ws5Bou9px0AAAAAnkfjxo0VERGhv//+W8OHD5e/v78+//zzZxorISFBiYmJaVzhy6NAgQIKCgoya1u1apWcnJwyqKKM06NHD3Xo0OGFvR+hHQAAAMAryd7eXu7u7ipUqJD69eun+vXra82aNZIezBL7+fkpX758ypo1qypXrqytW7ea9n14OfaaNWtUsmRJ2dvbKzw8XHFxcRo5cqQKFCgge3t7FStWTN98841pvyNHjqhJkyZycnKSm5ub3n33XV27ds20vXbt2ho8eLBGjBihnDlzyt3dXf7+/qbtnp6ekqTWrVvLYDCYXp86dUotW7aUm5ubnJycVKlSJW3evNnseCMiItS0aVM5OjqqcOHCWrZsmTw9PTVjxgxTn8jISL333nvKkyePsmXLprp16+rQoUNPPZddu3bV8uXLdefOHVPbggUL1LVr1yR9R44cqRIlSihLliwqUqSIxowZY1o9PTg4WAEBATp06JAMBoMMBoOCg4NNtfXp00dubm5ycHBQ6dKltW7dOrOxN27cKG9vbzk5OZn+KPOo+fPny9vbWw4ODvLy8tLs2bPNtu/Zs0c+Pj5ycHBQxYoVdeDAgace+6MCAwM1YMAAFSlSJFX7PQ9COwAAAIBMwdHRUffu3ZMkDRw4ULt27dLy5cv1559/ql27dmrcuLH+/vtvU//Y2FhNnjxZ8+fP19GjR+Xq6qouXbro22+/VWBgoI4fP66vv/7aNNscGRmpunXrysfHR/v27VNISIguX76s9u3bm9WxcOFCZc2aVbt379aUKVM0fvx4bdq0SZK0d+9eSVJQUJAiIiJMr6Ojo/Xmm28qNDRUBw4cUOPGjdW8eXOFh4ebxu3SpYsuXryorVu3auXKlfrPf/6T5BHZ7dq105UrV/TTTz9p//79ev3111WvXj3duHHjieeuQoUK8vT01MqVKyVJ4eHh2rZtm959990kfZ2dnRUcHKxjx47pyy+/1Lx58/TFF19Ikjp06KDhw4erVKlSioiIUEREhDp06KDExEQ1adJEO3bs0JIlS3Ts2DFNmjTJ7NnmsbGxmjp1qhYvXqxt27YpPDxcfn5+pu1Lly7V2LFj9dlnn+n48eOaMGGCxowZY7pNIjo6Ws2aNVPJkiW1f/9++fv7m+1vqSz7Zg4AAAAAeE5Go1GhoaHauHGjBg0apPDwcAUFBSk8PNz01Ck/Pz+FhIQoKChIEyZMkPTg2dqzZ89WuXLlJEknT57Ud999p02bNql+/fqSZDbjOnPmTPn4+Jj2lx7MRhcoUEAnT55UiRIlJElly5bVuHHjJEnFixfXzJkzFRoaqgYNGihPnjySpOzZs8vd3d00Trly5Ux1SNInn3yiVatWac2aNRo4cKD++usvbd68WXv37lXFihUlPZh1Ll68uGmf3377TXv27NGVK1dkb28vSZo6dapWr16tH374Qb17937ieezRo4cWLFigd955R8HBwXrzzTdN9T7q448/Nn3v6ekpPz8/LV++XCNGjJCjo6OcnJxkY2Njdnw///yz9uzZo+PHj5vO079ns+/fv6+5c+eqaNGikh784eXR9c/GjRunadOmqU2bNpIePEb82LFj+vrrr9W1a1ctW7ZMiYmJ+uabb+Tg4KBSpUrp/Pnz6tev3xOPO6MR2gEAAAC8ktatWycnJyfdv39fiYmJ6tSpk/z9/bV161YlJCSYwuFDcXFxypUrl+m1nZ2dypYta3p98OBBWVtby9fXN9n3O3TokLZs2ZLsfd6nTp0yC+2Pyps3b5IZ8X+Ljo6Wv7+/1q9fr4iICMXHx+vOnTummfYTJ07IxsZGr7/+ummfYsWKKUeOHGb1RUdHmx2jJN25c0enTp164vtL0jvvvKMPP/xQp0+fVnBwsAIDA5Ptt2LFCgUGBurUqVOKjo5WfHy8smXL9sSxDx48qPz58yf5mTwqS5YspsAumZ+3mJgYnTp1Sj179lSvXr1MfeLj4+Xi4iJJOn78uMqWLWv2NLKqVas+9bgzGqEdAAAAwCupTp06mjNnjuzs7OTh4WFaNT46OlrW1tbav3+/2eXXkswCt6Ojo2nl9IevnyQ6OlrNmzfX5MmTk2zLmzev6XtbW1uzbQaD4amL3Pn5+WnTpk2aOnWqihUrJkdHR7311lumy/1TIjo6Wnnz5jW7d/+hlDxOLVeuXGrWrJl69uypu3fvqkmTJrp9+7ZZn127dqlz584KCAhQo0aN5OLiouXLl2vatGlPHPtp51ZK/rw9fBpZdHS0JGnevHmqXLmyWb9//4xfNoR2AAAAAK+krFmzqlixYknafXx8lJCQoCtXrqhmzZopHq9MmTJKTEzUr7/+aro8/lGvv/66Vq5cKU9Pz+d6rJytra0SEhLM2nbs2KFu3bqpdevWkh6E1DNnzpi2v/baa4qPj9eBAwdUoUIFSdI///yjmzdvmtV36dIl2djYmBa4S60ePXrozTff1MiRI5MNwzt37lShQoU0evRoU9vZs2fN+tjZ2SU5vrJly+r8+fNmtxGkhpubmzw8PHT69Gl17tw52T7e3t5avHix7t69a5pt//3331P9Xi8aoR0AALySjnt5Z3QJj+X91/GMLgHI1EqUKKHOnTurS5cumjZtmnx8fHT16lWFhoaqbNmyato0+WfCe3p6qmvXrurRo4cCAwNVrlw5nT17VleuXFH79u01YMAAzZs3Tx07djStDv/PP/9o+fLlmj9/fopnfD09PRUaGqrq1avL3t5eOXLkUPHixfXjjz+qefPmMhgMGjNmjNnsvJeXl+rXr6/evXtrzpw5srW11fDhw82uFqhfv76qVq2qVq1aacqUKSpRooQuXryo9evXq3Xr1qZ74Z+kcePGunr16mMvdy9evLjCw8O1fPlyVapUSevXr9eqVauSHF9YWJjpknhnZ2f5+vqqVq1aatu2raZPn65ixYrpr7/+ksFgUOPGjVN03gICAjR48GC5uLiocePGiouL0759+3Tz5k0NGzZMnTp10ujRo9WrVy+NGjVKZ86c0dSpU1M09kP//POPoqOjdenSJd25c8f0nPaSJUvKzs4uVWOlFKEdAAAAQKqdmZR8sH1ZBAUF6dNPP9Xw4cN14cIF5c6dW1WqVFGzZs2euN+cOXP00UcfqX///rp+/boKFiyojz76SJLk4eGhHTt2aOTIkWrYsKHi4uJUqFAhNW7cWFZWKX9w17Rp0zRs2DDNmzdP+fLl05kzZzR9+nT16NFD1apVU+7cuTVy5EhFRUWZ7bdo0SL17NlTtWrVkru7uyZOnKijR4+aZpUNBoM2bNig0aNHq3v37rp69arc3d1Vq1Ytubm5pag2g8Gg3LlzP3Z7ixYtNHToUA0cOFBxcXFq2rSpxowZY/ZYu7Zt2+rHH39UnTp1FBkZqaCgIHXr1k0rV66Un5+fOnbsqJiYGBUrVkyTJk1K8Xl77733lCVLFn3++ef64IMPlDVrVpUpU0bvv/++pAe3Pqxdu1Z9+/aVj4+PSpYsqcmTJ6tt27apeo9ff/3V9NrHx0eSFBYW9sxXLzyNwfjwJoBMLCoqSi4uLrp169ZTF0gAAAAvB2baged39+5dhYWFqXDhwmaLd+HlcP78eRUoUECbN29WvXr1MrqcTOlJ/4ZSmkOZaQcAAACAV8Avv/yi6OholSlTRhERERoxYoQ8PT1Vq1atjC4Nz4HQDkASM1IAAAAvu/v37+ujjz7S6dOn5ezsrGrVqmnp0qVJVl1H8vr27aslS5Yku+2dd97R3LlzX3BFDxDaAQAAAOAV0KhRIzVq1Cijy3hpjR8/Xn5+fsluy8jbqAntAAAAAIBMz9XVVa6urhldRhIpX8IQAAAAAAC8UIR2AAAAAAAsFJfHAwAAAMBL4M6RIxldwmM5li6d0SW8sphpBwAAAADAQhHaAQAAAACwUIR2AAAAAIBFCw4OVvbs2dN83DNnzshgMOjgwYNpPnZa4Z524AUrs7BMRpeQrO8yugAAAPBy8Xd5we93K1Xdu3XrpoULF0qSbG1tVbBgQXXp0kUfffSRbGwsOwYZDAatWrVKrVq1yuhSJElZyjz4/9etS5bojXLlTO1x9+6paN26unHrlrZs2aLatWunaDx/f3+tXr3aooNycg4dOqRJkybpt99+07Vr1+Tp6am+fftqyJAh6fq+lv3bCgAAAADPqHHjxgoKClJcXJw2bNigAQMGyNbWVqNGjUr1WAkJCTIYDLKyypwXK+d3d9ei1avNQvua0FBlzZJFN26l7g8qL6v9+/fL1dVVS5YsUYECBbRz50717t1b1tbWGjhwYLq9b+b8jQMAAADwyrO3t5e7u7sKFSqkfv36qX79+lqzZo0kKS4uTn5+fsqXL5+yZs2qypUra+vWraZ9H16OvWbNGpUsWVL29vYKDw9XXFycRo4cqQIFCsje3l7FihXTN998Y9rvyJEjatKkiZycnOTm5qZ3331X165dM22vXbu2Bg8erBEjRihnzpxyd3eXv7+/abunp6ckqXXr1jIYDKbXp06dUrtBg+Tp66s8b7yhGm+/rV927TI73oirV9W6f3/lrFhR3o0ba8X69fJq1EgzFy829YmMilK/ceNUsFYtuVWpoiY9e+rPEyeeei47t2ihH0JCdOfuXVPbolWr1LlFiyR9R44cqRIlSihLliwqUqSIxowZo/v375vOa0BAgA4dOiSDwSCDwaDg4OAHtUVGqk+fPnJzc5ODg4NKly6tdevWmY29ceNGeXt7y8nJSY0bN1ZERITZ9vnz58vb21sODg7y8vLS7Nmzzbbv2bNHPj4+cnBwUMWKFXXgwIGnHvtDPXr00JdffilfX18VKVJE77zzjrp3764ff/wxxWM8C0I7AAAAgEzB0dFR9+7dkyQNHDhQu3bt0vLly/Xnn3+qXbt2aty4sf7++29T/9jYWE2ePFnz58/X0aNH5erqqi5duujbb79VYGCgjh8/rq+//lpOTk6SHoTOunXrysfHR/v27VNISIguX76s9u3bm9WxcOFCZc2aVbt379aUKVM0fvx4bdq0SZK0d+9eSVJQUJAiIiJMr6Ojo9WoZk2tnz9fu77/Xg2qV9dbgwbp3COhtddHHyni6lWFLFigZdOna8EPP+jqjRtm7/3O8OG6euOGVs2Zox0rVqi8t7eavvfeU2fLfUqWVCEPD63+X53nIiL02/796tS8eZK+zs7OCg4O1rFjx/Tll19q3rx5+uKLLyRJHTp00PDhw1WqVClFREQoIiJCHTp0UGJiopo0aaIdO3ZoyZIlOnbsmCZNmiRra2uzn8fUqVO1ePFibdu2TeHh4fLz8zNtX7p0qcaOHavPPvtMx48f14QJEzRmzBjTbRLR0dFq1qyZSpYsqf3798vf399s/2dx69Yt5cyZ87nGeBoujwcAAADwSjMajQoNDdXGjRs1aNAghYeHKygoSOHh4fLw8JAk+fn5KSQkREFBQZowYYIk6f79+5o9e7bK/e+S8JMnT+q7777Tpk2bVL9+fUlSkSJFTO8zc+ZM+fj4mPaXpAULFqhAgQI6efKkSpQoIUkqW7asxo0bJ0kqXry4Zs6cqdDQUDVo0EB58uSRJGXPnl3u7u6mccqVK6cSjwTYcYMGae0vv2jdli3q16mTTpw+rV9+/13bly9XhVKlJEmzAwJUpmlT0z47//hD+44c0dlff5W9nZ0kaaKfn9b+8otW/fyzerZr98Tz2KV1ay1avVodmzfX4tWr1ahmTeXOkSNJv48//tj0vaenp/z8/LR8+XKNGDFCjo6OcnJyko2Njdnx/fzzz9qzZ4+OHz9uOk+PntuHP4+5c+eqaNGikh784WX8+PH/f07GjdO0adPUpk0bSVLhwoV17Ngxff311+ratauWLVumxMREffPNN3JwcFCpUqV0/vx59evX74nH/Tg7d+7UihUrtH79+mfaP6UI7QAA4LmwwCYAS7Vu3To5OTnp/v37SkxMVKdOneTv76+tW7cqISHBFA4fiouLU65cuUyv7ezsVLZsWdPrgwcPytraWr6+vsm+36FDh7RlyxbTzPujTp06ZRbaH5U3b15duXLliccSHR2tj6dOVci2bbp07Zri4+N1Jy5O5y9dkiSdPHNGNjY28vH2Nu1TtGBB5ciWzfT6zxMnFB0bq/w1apiNfScuTmHnzj3x/SXp7WbNNGbGDIWdO6cl//2vpj5mbYAVK1YoMDBQp06dUnR0tOLj45XtkTqSc/DgQeXPnz/Jz+RRWbJkMQV2yfy8xcTE6NSpU+rZs6d69epl6hMfHy8XlweLJh4/flxly5aVg4ODaXvVqlWfetzJOXLkiFq2bKlx48apYcOGzzRGShHaAQAAALyS6tSpozlz5sjOzk4eHh6mVeOjo6NlbW2t/fv3m11+LckscDs6OspgMJi9fpLo6Gg1b95ckydPTrItb968pu9tbW3NthkMBiUmJj5xbD8/P/0cGqoJfn4qWqCAHB0c1GnYMN37373iKRETGyv33Lm1MSgoyTYXZ+en7p8re3Y1qVVL/caN091799SoRg3djokx67Nr1y517txZAQEBatSokVxcXLR8+XJNmzbtiWM/7dxKyZ83o9Eo6cG5l6R58+apcuXKZv3+/TN+XseOHVO9evXUu3dvs6sK0guhHQAAAMArKWvWrCpWrFiSdh8fHyUkJOjKlSuqWbNmiscrU6aMEhMT9euvv5ouj3/U66+/rpUrV8rT0/O5Hitna2urhIQEs7YdO3bonZYt1bJePUlSdGyswi9eNG0v4emp+Ph4HTx+XK//7/L4U+HhuhkVZepT3ttbl69fl421tQrly/dMtXVp3Vqt+/fX8B49kg3DO3fuVKFChTR69GhT29mzZ8362NnZJTm+smXL6vz582a3EaSGm5ubPDw8dPr0aXXu3DnZPt7e3lq8eLHu3r1rmm3//fffU/U+R48eVd26ddW1a1d99tlnqa7zWbAQHQAAAIBMpUSJEurcubO6dOmiH3/8UWFhYdqzZ48mTpz4xPuTPT091bVrV/Xo0UOrV69WWFiYtm7dqu++e3BDzoABA3Tjxg117NhRe/fu1alTp7Rx40Z17949SUh9Ek9PT4WGhurSpUu6efOmpAf3vv83NFSH/vpLf544oW4jR5rNzr9WpIjqVqmigQEB2nv4sA4eP66BAQFydHAwXS1Qt2pVVS5XTu2HDNHmnTt19sIF/X7woMYFBmr/0aMpqq1hjRoK37ZNYx7ziLPixYsrPDxcy5cv16lTpxQYGKhVq1YlOb6wsDAdPHhQ165dU1xcnHx9fVWrVi21bdtWmzZtUlhYmH766SeFhISk+LwFBARo4sSJCgwM1MmTJ3X48GEFBQVp+vTpkqROnTrJYDCoV69eOnbsmDZs2KCpU6emePwjR46oTp06atiwoYYNG6ZLly7p0qVLunr1aorHeBbMtAMAAABIPf+X+9ncQUFB+vTTTzV8+HBduHBBuXPnVpUqVdSsWbMn7jdnzhx99NFH6t+/v65fv66CBQvqo48+kiR5eHhox44dGjlypBo2bKi4uDgVKlRIjRs3TtXz3adNm6Zhw4Zp3rx5ypcvn86cOaPp06erW4cOqvvuu8qVPbuG9eih2/+7JPyheRMmqN/YsWrYrZvccufW+CFDdPyff0yLzhkMBq2aPVv+gYHqM2aMrt24IbfcuVWjQgW5PXIv/5MYDIZkF597qEWLFho6dKgGDhyouLg4NW3aVGPGjDF7rF3btm31448/qk6dOoqMjFRQUJC6deumlStXys/PTx07dlRMTIyKFSumSZMmpfi8vffee8qSJYs+//xzffDBB8qaNavKlCmj999/X9KDWx/Wrl2rvn37ysfHRyVLltTkyZPVtm3bFI3/ww8/6OrVq1qyZImWLFliai9UqJDOnDmT4jpTy2B8eBNAJhYVFSUXFxfdunXrqQskAM/LYhdsmhif0SU8lvdfxzO6BCDj+btkdAWPVaZwwYwuIVl8rgHP7+7duwoLC1PhwoXNFu9Cxrhz5Eiq+p+/dEklGjTQ+nnzVKdKlXSq6gHH0qXTdfyX1ZP+DaU0hzLTDgAAAACvgK27dys6NlalixfXpWvXNHr6dBXKl081KlTI6NLwHLinHQAAAABeAffj4+UfGKgKrVvr7SFDlDtHDm1csCDJqutIXt++feXk5JTsV9++fTOsLmbaAQAAAOAV0KB6dTWoXj2jy3hpjR8/Xn5+fsluy8jbqAnteDVZ8L2fstB7PwEAAIDMzNXVVa6urhldRhJcHg8AAAAAgIUitAMAAAAAYKEI7QAAAAAAWChCOwAAAAAAFoqF6AAA+B/PD9dndAmPdcYhoysAgMzj6LWjGV1CsopkdAHIEMy0AwAAAAAsWnBwsLJnz57m4545c0YGg0EHDx5M87HTCjPtAAAAAFKtzMIyL/T9Dnc9nKr+3bp108KFCyVJtra2KliwoLp06aKPPvpINjaWHYNK5ymtLxd+qXpv1svoUiRJWco8+FlvXbJEb5QrZ2qPu3dPRevW1Y1bt7RlyxbVrl07ReP5+/tr9erVFh2Uk3P9+nV17txZf/75p65fvy5XV1e1bNlSEyZMSNfnuDPTDgAAAOCV1LhxY0VEROjvv//W8OHD5e/vr88///yZxkpISFBiYmIaV/jyyO/urkWrV5u1rQkNVdYsWTKmoAxgZWWlli1bas2aNTp58qSCg4O1efNm9e3bN33fN11HBwAAAIAMYm9vL3d3dxUqVEj9+vVT/fr1tWbNGklSXFyc/Pz8lC9fPmXNmlWVK1fW1q1bTfuu/na1qhatqi0hW9Siegu9nu91RZyP0L24e5o+frrqlasnn3w+alKpiVYuWWna7+/jf6tvh76qVKiSapWspQ/7f6ib12+atndr2U0TRk3QtIBpqla8mnxL+mrWlFmm7Q1fbyhJGtJ1iErnKW16HR4WrnaDBsnT11d53nhDNd5+W7/s2mV2vBFXr6p1//7KWbGivBs31or16+XVqJFmLl5s6hMZFaV+48apYK1acqtSRU169tSfJ0489Vx2btFCP4SE6M7du6a2RatWqXOLFkn6jhw5UiVKlFCWLFlUpEgRjRkzRvfv35f04DL3gIAAHTp0SAaDQQaDQcHBwQ9qi4xUnz595ObmJgcHB5UuXVrr1q0zG3vjxo3y9vaWk5OT6Y8yj5o/f768vb3l4OAgLy8vzZ4922z7nj175OPjIwcHB1WsWFEHDhx46rE/lCNHDvXr108VK1ZUoUKFVK9ePfXv31/bt29P8RjPwrKvCwEAAACANOLo6Kjr169LkgYOHKhjx45p+fLl8vDw0KpVq9S4cWMdPnxYyvGg/507d/RN4DcK+CJA2XNmV87cOTVqwCgd2ndIoyaM0mulXtOF8AumUB51K0o92/RUm85tNOLTEYq7E6fpn0zX8PeGa8GqBaY61qxYoy79uujbkG91cN9BfTzoY/m84aNqtatp+c/LVcu7lj4N/FQ16taQlfWDedbYmFg1qllT/oMHy97OTkvXrNFbgwbp0Nq1KpA3rySp10cf6VpkpEIWLJCtjY0+/PxzXb1xw+wcvDN8uBwcHLRqzhy5ODnpm++/V9P33tOhdeuU08XlsefOp2RJFfLw0OpNm9SxeXOdi4jQb/v364vRozXp66/N+jo7Oys4OFgeHh46fPiwevXqJWdnZ40YMUIdOnTQkSNHFBISos2bN0uSXFxclJiYqCZNmuj27dtasmSJihYtqmPHjsna2to0bmxsrKZOnarFixfLyspK77zzjvz8/LR06VJJ0tKlSzV27FjNnDlTPj4+OnDggHr16qWsWbOqa9euio6OVrNmzdSgQQMtWbJEYWFhGjJkSKp/jx66ePGifvzxR/n6+j7zGClBaAcAAADwSjMajQoNDdXGjRs1aNAghYeHKygoSOHh4fLw8JAk+fn5KSQkREFBQeo8rLMkKf5+vD6e8rG8SntJks6cOqON/92oeT/MU1XfqpKkAp4FTO/z7fxv5VXaS+9//L6p7ZMvP1H9cvV15tQZeRb1lCSVKFlC/T/oL0kqVLSQvv3mW+3etlvValdTztw5JUnOLs7K7ZbbNI5XaS+9mfs10+txgwZp7S+/aN2WLerXqZNOnD6tX37/XduXL1eFUqUkSbMDAlSmaVPTPjv/+EP7jhzR2V9/lb2dnSRpop+f1v7yi1b9/LN6tmv3xPPYpXVrLVq9Wh2bN9fi1avVqGZN5c6RI0m/jz/+2PS9p6en/Pz8tHz5co0YMUKOjo5ycnKSjY2N3N3dTf1+/vln7dmzR8ePH1eJEiUkSUWKmK+Xf//+fc2dO1dFixaV9OAPL+PHj///czJunKZNm6Y2bdpIkgoXLqxjx47p66+/VteuXbVs2TIlJibqm2++kYODg0qVKqXz58+rX79+Tzzuf+vYsaP++9//6s6dO2revLnmz5+fqv1Ti9AOAAAA4JW0bt06OTk56f79+0pMTFSnTp3k7++vrVu3KiEhwRQOH4qLi1OuXLlMr23tbPVaqf8Pyn8d/kvW1taqWK1isu934ugJ7dmxR5UKVUqy7VzYObPQ/qg8bnl0/dr1Jx5LbHSsRk2dpZBt23Tp2jXFx8frTlyczl+6JEk6eeaMbGxs5OPtbdqnaMGCyvHIAml/njih6NhY5a9Rw2zsO3FxCjt37onvL0lvN2umMTNmKOzcOS357381ddSoZPutWLFCgYGBOnXqlKKjoxUfH//UhdoOHjyo/PnzJ/mZPCpLliymwC5JefPm1ZUrVyRJMTExOnXqlHr27KlevXqZ+sTHx8vlf1cQHD9+XGXLlpWDw/8/R7Vq1apPPe5/++KLLzRu3DidPHlSo0aN0rBhw5Jchp+WCO0AAAAAXkl16tTRnDlzZGdnJw8PD9Oq8dHR0bK2ttb+/fvNLr+WJCcnJ13XgwDt4OAgg8Fg2ubg6KAniY2JVe2GtTVs7LAk2x6dNbexNY9hBoNBxkTjE8f+3P9z7QvdpQl+fipaoIAcHRzUadgw3fvfveIpERMbK/fcubUxKCjJNhdn56funyt7djWpVUv9xo3T3Xv31KhGDd2OiTHrs2vXLnXu3FkBAQFq1KiRXFxctHz5ck2bNu2JYzs6Oj71/W1tbc1eGwwGGY0Pzlt0dLQkad68eapcubJZv3//jJ+Xu7u73N3d5eXlpZw5c6pmzZoaM2aM8v7vNoW0RmjHM/P8cH1Gl/BYZ578eQoAAIBMIGvWrCpWrFiSdh8fHyUkJOjKlSuqWbNmku2Pm/Uu7l1ciYmJ2rdzn+ny+Ed5l/XW5nWb5VHQ47keK2dja6PEBPOV6g/uOah3WrZUy3oPHgMXHRur8IsXTdtLeHoqPj5eB48f1+v/uzz+VHi4bkZFmfqU9/bW5evXZWNtrUL58j1TbV1at1br/v01vEePZMPwzp07VahQIY0ePdrUdvbsWbM+dnZ2SkhIMGsrW7aszp8/r5MnTz5xtv1x3Nzc5OHhodOnT6tz587J9vH29tbixYt19+5d02z777//nur3etTDJwrExcU91zhPwurxAAAAADKVEiVKqHPnzurSpYt+/PFHhYWFac+ePZo4caLWr3/8xFS+gvnUskNLjRkyRqEbQnX+7Hnt2bFHIatDJEkde3bUrchbGtF7hA4fOKzwsHDt+GWHPh70cZKQ+iT5CuTT79t/17XL13Qr8pYkqWCRgvpvaKgO/fWX/jxxQt1GjjR7BN1rRYqobpUqGhgQoL2HD+vg8eMaGBAgx0euFqhbtaoqlyun9kOGaPPOnTp74YJ+P3hQ4wIDtf/o0RTV1rBGDYVv26YxAwcmu7148eIKDw/X8uXLderUKQUGBmrVqlVmfTw9PRUWFqaDBw/q2rVriouLk6+vr2rVqqW2bdtq06ZNCgsL008//aSQkJAUn7eAgABNnDhRgYGBOnnypA4fPqygoCBNnz5dktSpUycZDAb16tVLx44d04YNGzR16tQUj79hwwYFBQXpyJEjOnPmjNavX6++ffuqevXq8vT0TPE4qUVoBwAAAJDpBAUFqUuXLho+fLhee+01tWrVSnv37lXBggWfuN+Yz8eoYfOG+nTEp2perbn8h/rrTuwdSZKru6sWr1ushMQE9WnXR21822jSx5Pk7OIsK6uUR68Pxn+gXVt3qX75+mpX98HicCPGj1CObNlU99139dbAgapfrZrKP3L/uiTNmzBBrrlyqWG3bnr7/ffVvW1bOWfJYlp0zmAwaNXs2apRoYL6jBmjss2aqcsHH+jcxYtye+Re/icxGAzKnSOH7P51qfpDLVq00NChQzVw4ECVL19eO3fu1JgxY8z6tG3bVo0bN1adOnWUJ08effvtt5KklStXqlKlSurYsaNKliypESNGpOqPHe+9957mz5+voKAglSlTRr6+vgoODlbhwoUlPbj1Ye3atTp8+LB8fHw0evRoTZ48OcXjOzo6at68eapRo4a8vb01dOhQtWjRIslj6dKawfjwJoBMLCoqSi4uLrp169ZTF0jA/7Psy+M7ZXQJj1Wm8JP/Q5BRvpsYn9ElPJb3X8czugRkEnyuPRs+11KPzzW8LO7evauwsDAVLlzYbPGuV93RaymbdX7RilxKXXQ7f+mSSjRooPXz5qlOlSrpVNUDjqVLp+v4L6sn/RtKaQ7lnnYAAAAAL97FAxldweP9b2b6ZbN1925Fx8aqdPHiunTtmkZPn65C+fKpRoUKGV0angOXxwMAAADAK+B+fLz8AwNVoXVrvT1kiHLnyKGNCxYkWXUdyevbt6+cnJyS/erbt2+G1cVMOwAAAAC8AhpUr64G1atndBkvrfHjx8vPzy/ZbRl5GzWhHQAAAACQ6bm6usrV1TWjy0iCy+MBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAACARQsODlb27NnTfNwzZ87IYDDo4MGDaT52WuGRbwAAAABS7biX9wt9P+9flqWqf7f3x2nh92slSba2NiqYz11d3mqmjwb1kI2NZceg0nlK68uFX6rem/UyuhRJUpYyZSRJW5cs0Rvlypna4+7dU9G6dXXj1i1t2bJFtWvXTtF4/v7+Wr16tUUH5ae5fv26ypUrpwsXLujmzZvp8geFh5hpBwAAAPBKalynmiIO/Ky/f1ut4b3flf+0r/X5nEXPNFZCQoISExPTuMKXR353dy1avdqsbU1oqLJmyZIxBWWwnj17qmzZsi/kvQjtAAAAAF5J9nZ2cnfNrUL5PdSvazvVr1lZa37+VZIUF3dPfuO/UL4KjZS1WDVVbtZFW3fuM+27+tvVqlq0qraEbFGL6i30er7XFXE+Qvfi7mn6+OmqV66efPL5qEmlJlq5ZKVpv7+P/62+HfqqUqFKqlWylj7s/6FuXr9p2t6tZTdNGDVB0wKmqVrxavIt6atZU2aZtjd8vaEkaUjXISqdp7TpdXhYuNoNGiRPX1/leeMN1Xj7bf2ya5fZ8UZcvarW/fsrZ8WK8m7cWCvWr5dXo0aauXixqU9kVJT6jRungrVqya1KFTXp2VN/njjx1HPZuUUL/RASojt375raFq1apc4tWiTpO3LkSJUoUUJZsmRRkSJFNGbMGN2/f1/Sg8vcAwICdOjQIRkMBhkMBgUHBz+oLTJSffr0kZubmxwcHFS6dGmtW7fObOyNGzfK29tbTk5Oaty4sSIiIsy2z58/X97e3nJwcJCXl5dmz55ttn3Pnj3y8fGRg4ODKlasqAMHDjz12P9tzpw5ioyMlJ+fX6r3fRaWfV0IAAAAAKQRRwd7Xb8ZKUka+PFkHTt5WstnT5SHWx6tCtmixu8M1OHN30lexSRJd+7c0TeB3yjgiwBlz5ldOXPn1KgBo3Ro3yGNmjBKr5V6TRfCL5hCedStKPVs01NtOrfRiE9HKO5OnKZ/Ml3D3xuuBasWmOpYs2KNuvTrom9DvtXBfQf18aCP5fOGj6rVrqblPy9XLe9a+jTwU9WoW0NW1g/mWWNjYtWoZk35Dx4sezs7LV2zRm8NGqRDa9eqQN68kqReH32ka5GRClmwQLY2Nvrw88919cYNs3PwzvDhcnBw0Ko5c+Ti5KRvvv9eTd97T4fWrVNOF5fHnjufkiVVyMNDqzdtUsfmzXUuIkK/7d+vL0aP1qSvvzbr6+zsrODgYHl4eOjw4cPq1auXnJ2dNWLECHXo0EFHjhxRSEiINm/eLElycXFRYmKimjRpotu3b2vJkiUqWrSojh07Jmtra9O4sbGxmjp1qhYvXiwrKyu988478vPz09KlSyVJS5cu1dixYzVz5kz5+PjowIED6tWrl7JmzaquXbsqOjpazZo1U4MGDbRkyRKFhYVpyJAhqfodOnbsmMaPH6/du3fr9OnTqdr3WRHaAQAAALzSjEajQrfv0cZfd2lQ9w4KvxChoBVrFL5ngzzc80iS/Pp2UciWnQpa8V91HjdckhR/P14fT/lYXqW9JElnTp3Rxv9u1Lwf5qmqb1VJUgHPAqb3+Xb+t/Iq7aX3P37f1PbJl5+ofrn6OnPqjDyLekqSSpQsof4f9JckFSpaSN9+8612b9utarWrKWfunJIkZxdn5XbLbRrHq7SX3sz9mun1uEGDtPaXX7Ruyxb169RJJ06f1i+//67ty5erQqlSkqTZAQEq07SpaZ+df/yhfUeO6Oyvv8rezk6SNNHPT2t/+UWrfv5ZPdu1e+J57NK6tRatXq2OzZtr8erValSzpnLnyJGk38cff2z63tPTU35+flq+fLlGjBghR0dHOTk5ycbGRu7u7qZ+P//8s/bs2aPjx4+rRIkSkqQiRYqYjXv//n3NnTtXRYsWlSQNHDhQ48eP//9zMm6cpk2bpjZt2kiSChcurGPHjunrr79W165dtWzZMiUmJuqbb76Rg4ODSpUqpfPnz6tfv35PPO6H4uLi1LFjR33++ecqWLAgoR0AAAAAnse6zdvlVLy67sfHKzHRqE6tGst/eF9t3blPCQkJKlGzlVn/uHv3lSvH/88229rZ6rVS/x+U/zr8l6ytrVWxWsVk3+/E0RPas2OPKhWqlGTbubBzZqH9UXnc8uj6tetPPJbY6FiNmjpLIdu26dK1a4qPj9eduDidv3RJknTyzBnZ2NjIx/v/FwgsWrCgcmTLZnr954kTio6NVf4aNczGvhMXp7Bz5574/pL0drNmGjNjhsLOndOS//5XU0eNSrbfihUrFBgYqFOnTik6Olrx8fHK9kgdyTl48KDy589vCuzJyZIliymwS1LevHl15coVSVJMTIxOnTqlnj17qlevXqY+8fHxcvnfFQTHjx9X2bJl5eDgYNpetWrVpx73Q6NGjZK3t7feeeedFO+TFgjtAAAAAF5JdapV1JyJo2RnZysPtzymVeOjY2JlbW2t/T8tlbW1+TJfTlmz6GF8dnBwkMFgMG1zcHTQk8TGxKp2w9oaNnZYkm2Pzprb2JrHMIPBIGOi8Yljf+7/ufaF7tIEPz8VLVBAjg4O6jRsmO79717xlIiJjZV77tzaGBSUZJuLs/NT98+VPbua1KqlfuPG6e69e2pUo4Zux8SY9dm1a5c6d+6sgIAANWrUSC4uLlq+fLmmTZv2xLEdHR2f+v62trZmrw0Gg4zGB+ctOjpakjRv3jxVrlzZrN+jl9g/j19++UWHDx/WDz/8IEmm986dO7dGjx6tgICANHmffyO0AwAAAHglZc3iqGKFCyZp9yntpYSEBF25fkM1K7+eZPvj5ryLexdXYmKi9u3cZ7o8/lHeZb21ed1meRT0eK7HytnY2igxwXyl+oN7Duqdli3Vst6Dx8BFx8Yq/OJF0/YSnp6Kj4/XwePH9fr/Lo8/FR6um1FRpj7lvb11+fp12Vhbq1C+fM9UW5fWrdW6f38N79Ej2TC8c+dOFSpUSKNHjza1nT171qyPnZ2dEhISzNrKli2r8+fP6+TJk0+cbX8cNzc3eXh46PTp0+rcuXOyfby9vbV48WLdvXvXNNv++++/p/g9Vq5cqTt37phe7927Vz169ND27dvNrgBIa6weDwAAACBTKVG0kDq3aaIuQ8bqxw2hCgu/oD0HjmjiVwu0fvP2x+6Xr2A+tezQUmOGjFHohlCdP3tee3bsUcjqEElSx54ddSvylkb0HqHDBw4rPCxcO37ZoY8HfZwkpD5JvgL59Pv233Xt8jXdirwlSSpYpKD+GxqqQ3/9pT9PnFC3kSPNHkH3WpEiqluligYGBGjv4cM6ePy4BgYEyPGRqwXqVq2qyuXKqf2QIdq8c6fOXrig3w8e1LjAQO0/ejRFtTWsUUPh27ZpzMCByW4vXry4wsPDtXz5cp06dUqBgYFatWqVWR9PT0+FhYXp4MGDunbtmuLi4uTr66tatWqpbdu22rRpk8LCwvTTTz8pJCQkxectICBAEydOVGBgoE6ePKnDhw8rKChI06dPlyR16tRJBoNBvXr10rFjx7RhwwZNnTo1xeMXLVpUpUuXNn0VLlxY0oM/Bri6uqZ4nNQitAMAAADIdIKm+6vLW001fPwXeq1Wa7XqOUx7Dx1VwXzuT9xvzOdj1LB5Q3064lM1r9Zc/kP9dSf2weyrq7urFq9brITEBPVp10dtfNto0seT5OziLCurlEevD8Z/oF1bd6l++fpqV/fB4nAjxo9QjmzZVPfdd/XWwIGqX62ayj9y/7okzZswQa65cqlht256+/331b1tWzlnyWJadM5gMGjV7NmqUaGC+owZo7LNmqnLBx/o3MWLcsuVK0W1GQwG5c6RQ3b/ulT9oRYtWmjo0KEaOHCgypcvr507d2rMmDFmfdq2bavGjRurTp06ypMnj7799ltJD2ayK1WqpI4dO6pkyZIaMWJEqv7Y8d5772n+/PkKCgpSmTJl5Ovrq+DgYFO4dnJy0tq1a3X48GH5+Pho9OjRmjx5corHzygG48ML8TOxqKgoubi46NatW09dIAH/z/PD9RldwmOdceiU0SU8VplkLtGyBN9NjM/oEh7L+6/jGV0CMgk+154Nn2upx+caXhZ3795VWFiYChcubLZ4V5q4mPrnY78oR/8Xci1NkUupi27nL11SiQYNtH7ePNWpUiWdqnrAsXTpdB3/ZfWkf0MpzaHc0w4AAAAAr4Ctu3crOjZWpYsX16Vr1zR6+nQVypdPNSpUyOjS8By4PB4AAAAAXgH34+PlHxioCq1b6+0hQ5Q7Rw5tXLAgyarrSF7fvn3l5OSU7Fffvn0zrC5m2gEAAADgFdCgenU1qF49o8t4aY0fP15+fn7JbsvI26gJ7QAAAACATM/V1TVdV4F/VlweDwAAAACAhSK0AwAAAHiiR58HDiDl0uLfDpfHAwAAAEiWnZ2drKysdPHiReXJk0d2dnYyGAxpM3i85T55OtFgmX+kiEu03HNmuHs3o0uwKEajUffu3dPVq1dlZWUlu+d4jKBFh/aEhAT5+/tryZIlunTpkjw8PNStWzd9/PHHpg8Lo9GocePGad68eYqMjFT16tU1Z84cFS9ePIOrBwAAAF5uVlZWKly4sCIiInTx4sW0HTzyatqOl4au2FhmTDJGZXQFj8cK9cnLkiWLChYsKCurZ7/I3TJ/G/9n8uTJmjNnjhYuXKhSpUpp37596t69u1xcXDR48GBJ0pQpUxQYGKiFCxeqcOHCGjNmjBo1aqRjx44leXg9AAAAgNSxs7NTwYIFFR8fr4SEhLQbeGa7tBsrjQ3J55HRJSTri//EZ3QJj1X4pw0ZXYLFsba2lo2NzXNfnWLRoX3nzp1q2bKlmjZtKkny9PTUt99+qz179kh6MMs+Y8YMffzxx2rZsqUkadGiRXJzc9Pq1av19ttvZ1jtAAAAwKvCYDDI1tY2bWdTo8+l3VhpLOJeGt0CkMasIiw3tDNhmn4seiG6atWqKTQ0VCdPnpQkHTp0SL/99puaNGkiSQoLC9OlS5dUv3590z4uLi6qXLmydu3a9dhx4+LiFBUVZfYFAAAAAIClseiZ9g8//FBRUVHy8vKStbW1EhIS9Nlnn6lz586SpEuXLkmS3NzczPZzc3MzbUvOxIkTFRAQkH6FAwAAAACQBix6pv27777T0qVLtWzZMv3xxx9auHChpk6dqoULFz7XuKNGjdKtW7dMX+fOWe6lOQAAAACAzMuiZ9o/+OADffjhh6Z708uUKaOzZ89q4sSJ6tq1q9zd3SVJly9fVt68eU37Xb58WeXLl3/suPb29rK3t0/X2gEAAAAAeF4WPdMeGxubZGl8a2tr0wPqCxcuLHd3d4WGhpq2R0VFaffu3apateoLrRUAAAAAgLRm0TPtzZs312effaaCBQuqVKlSOnDggKZPn64ePXpIerCK5fvvv69PP/1UxYsXNz3yzcPDQ61atcrY4gEAAIAM5vnh+owu4bHOsNg4kCIWHdq/+uorjRkzRv3799eVK1fk4eGhPn36aOzYsaY+I0aMUExMjHr37q3IyEjVqFFDISEhPHIAAAAAAPDSs+jQ7uzsrBkzZmjGjBmP7WMwGDR+/HiNHz/+xRUGAAAAAMALYNH3tAMAAAAAkJkR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwELZpKTTsGHDUjzg9OnTn7kYAAAAAADw/1IU2g8cOGD2+o8//lB8fLxee+01SdLJkydlbW2tChUqpH2FAAAAAABkUikK7Vu2bDF9P336dDk7O2vhwoXKkSOHJOnmzZvq3r27atasmT5VAgAAAACQCaX6nvZp06Zp4sSJpsAuSTly5NCnn36qadOmpWlxAAAAAABkZqkO7VFRUbp69WqS9qtXr+r27dtpUhQAAAAAAHiG0N66dWt1795dP/74o86fP6/z589r5cqV6tmzp9q0aZMeNQIAAAAAkCml6J72R82dO1d+fn7q1KmT7t+//2AQGxv17NlTn3/+eZoXCAAAAABAZpXq0J4lSxbNnj1bn3/+uU6dOiVJKlq0qLJmzZrmxQEAAAAAkJml+vL4hyIiIhQREaHixYsra9asMhqNaVkXAAAAAACZXqpD+/Xr11WvXj2VKFFCb775piIiIiRJPXv21PDhw9O8QAAAAAAAMqtUh/ahQ4fK1tZW4eHhypIli6m9Q4cOCgkJSdPiAAAAAADIzFJ9T/vPP/+sjRs3Kn/+/GbtxYsX19mzZ9OsMAAAAAAAMrtUz7THxMSYzbA/dOPGDdnb26dJUQAAAAAA4BlCe82aNbVo0SLTa4PBoMTERE2ZMkV16tRJ0+IAAAAAAMjMUn15/JQpU1SvXj3t27dP9+7d04gRI3T06FHduHFDO3bsSI8aAQAAAADIlFI90166dGmdPHlSNWrUUMuWLRUTE6M2bdrowIEDKlq0aHrUCAAAAABAppTqmXZJcnFx0ejRo9O6FgAAAAAA8IhnCu2RkZHas2ePrly5osTERLNtXbp0SZPCAAAAAADI7FId2teuXavOnTsrOjpa2bJlk8FgMG0zGAyEdgAAAAAA0kiq72kfPny4evTooejoaEVGRurmzZumrxs3bqRHjQAAAAAAZEqpDu0XLlzQ4MGDk31WOwAAAAAASDupDu2NGjXSvn370qMWAAAAAADwiBTd075mzRrT902bNtUHH3ygY8eOqUyZMrK1tTXr26JFi7StEAAAAACATCpFob1Vq1ZJ2saPH5+kzWAwKCEh4bmLAgAAAAAAKQzt/36sGwAAAAAASH+pvqcdAAAAAAC8GKkO7YMHD1ZgYGCS9pkzZ+r9999Pi5oAAAAAAICeIbSvXLlS1atXT9JerVo1/fDDD2lSFAAAAAAAeIbQfv36dbm4uCRpz5Ytm65du5YmRQEAAAAAgGcI7cWKFVNISEiS9p9++klFihRJk6IAAAAAAEAKV49/1LBhwzRw4EBdvXpVdevWlSSFhoZq2rRpmjFjRlrXBwAAAABAppXq0N6jRw/FxcXps88+0yeffCJJ8vT01Jw5c9SlS5c0LxAAAAAAgMwq1aFdkvr166d+/frp6tWrcnR0lJOTU1rXBQAAAABAppfqe9rr1q2ryMhISVKePHlMgT0qKsp0uTwAAAAAAHh+qQ7tW7du1b1795K03717V9u3b0+TogAAAAAAQCouj//zzz9N3x87dkyXLl0yvU5ISFBISIjy5cuXttUBAAAAAJCJpTi0ly9fXgaDQQaDIdnL4B0dHfXVV1+laXEAAAAAAGRmKQ7tYWFhMhqNKlKkiPbs2aM8efKYttnZ2cnV1VXW1tbpUiQAAAAAAJlRikN7oUKFJEmJiYnpVgwAAAAAAPh/z/TIN+nBfe3h4eFJFqVr0aLFcxcFAAAAAACeIbSfPn1arVu31uHDh2UwGGQ0GiVJBoNB0oNF6QAAAAAAwPNL9SPfhgwZosKFC+vKlSvKkiWLjh49qm3btqlixYraunVrOpQIAAAAAEDmlOqZ9l27dumXX35R7ty5ZWVlJSsrK9WoUUMTJ07U4MGDdeDAgfSoEwAAAACATCfVM+0JCQlydnaWJOXOnVsXL16U9GChuhMnTqRtdZIuXLigd955R7ly5ZKjo6PKlCmjffv2mbYbjUaNHTtWefPmlaOjo+rXr6+///47zesAAAAAAOBFS3VoL126tA4dOiRJqly5sqZMmaIdO3Zo/PjxKlKkSJoWd/PmTVWvXl22trb66aefdOzYMU2bNk05cuQw9ZkyZYoCAwM1d+5c7d69W1mzZlWjRo109+7dNK0FAAAAAIAXLdWXx3/88ceKiYmRJI0fP17NmjVTzZo1lStXLq1YsSJNi5s8ebIKFCigoKAgU1vhwoVN3xuNRs2YMUMff/yxWrZsKUlatGiR3NzctHr1ar399ttpWg8AAAAAAC9SqmfaGzVqpDZt2kiSihUrpr/++kvXrl3TlStXVLdu3TQtbs2aNapYsaLatWsnV1dX+fj4aN68eabtYWFhunTpkurXr29qc3FxUeXKlbVr167HjhsXF6eoqCizLwAAAAAALE2qQ3tycubMaXrkW1o6ffq05syZo+LFi2vjxo3q16+fBg8erIULF0qSLl26JElyc3Mz28/Nzc20LTkTJ06Ui4uL6atAgQJpXjsAAAAAAM8r1ZfH3717V1999ZW2bNmiK1euKDEx0Wz7H3/8kWbFJSYmqmLFipowYYIkycfHR0eOHNHcuXPVtWvXZx531KhRGjZsmOl1VFQUwR0AAAAAYHFSHdp79uypn3/+WW+99ZbeeOONdJlhfyhv3rwqWbKkWZu3t7dWrlwpSXJ3d5ckXb58WXnz5jX1uXz5ssqXL//Yce3t7WVvb5/2BQMAAAAAkIZSHdrXrVunDRs2qHr16ulRj5nq1asneYzcyZMnVahQIUkPFqVzd3dXaGioKaRHRUVp9+7d6tevX7rXBwAAAABAekp1aM+XL5/pOe3pbejQoapWrZomTJig9u3ba8+ePfrPf/6j//znP5Ikg8Gg999/X59++qmKFy+uwoULa8yYMfLw8FCrVq1eSI0AAAAAAKSXVC9EN23aNI0cOVJnz55Nj3rMVKpUSatWrdK3336r0qVL65NPPtGMGTPUuXNnU58RI0Zo0KBB6t27typVqqTo6GiFhITIwcEh3esDAAAAACA9pXqmvWLFirp7966KFCmiLFmyyNbW1mz7jRs30qw4SWrWrJmaNWv22O0Gg0Hjx4/X+PHj0/R9AQAAAADIaKkO7R07dtSFCxc0YcIEubm5petCdAAAAAAAZGapDu07d+7Url27VK5cufSoBwAAAAAA/E+q72n38vLSnTt30qMWAAAAAADwiFSH9kmTJmn48OHaunWrrl+/rqioKLMvAAAAAACQNlJ9eXzjxo0lSfXq1TNrNxqNMhgMSkhISJvKAAAAAADI5FId2rds2ZIedQAAAAAAgH9JdWj39fVNjzoAAAAAAMC/pPqedgAAAAAA8GIQ2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC5Xq0H7nzh3FxsaaXp89e1YzZszQzz//nKaFAQAAAACQ2aU6tLds2VKLFi2SJEVGRqpy5cqaNm2aWrZsqTlz5qR5gQAAAAAAZFapDu1//PGHatasKUn64Ycf5ObmprNnz2rRokUKDAxM8wIBAAAAAMisUh3aY2Nj5ezsLEn6+eef1aZNG1lZWalKlSo6e/ZsmhcIAAAAAEBmlerQXqxYMa1evVrnzp3Txo0b1bBhQ0nSlStXlC1btjQvEAAAAACAzCrVoX3s2LHy8/OTp6enKleurKpVq0p6MOvu4+OT5gUCAAAAAJBZ2aR2h7feeks1atRQRESEypUrZ2qvV6+eWrdunabFAQAAAACQmaU6tEuSu7u73N3dzdreeOONNCkIAAAAAAA8kKLQ3qZNmxQP+OOPPz5zMQAAAAAA4P+l6J52FxcX01e2bNkUGhqqffv2mbbv379foaGhcnFxSbdCAQAAAADIbFI00x4UFGT6fuTIkWrfvr3mzp0ra2trSVJCQoL69+/P6vEAAAAAAKShVK8ev2DBAvn5+ZkCuyRZW1tr2LBhWrBgQZoWBwAAAABAZpbq0B4fH6+//vorSftff/2lxMTENCkKAAAAAAA8w+rx3bt3V8+ePXXq1CnTivG7d+/WpEmT1L179zQvEAAAAACAzCrVoX3q1Klyd3fXtGnTFBERIUnKmzevPvjgAw0fPjzNCwQAAAAAILNKdWi3srLSiBEjNGLECEVFRUkSC9ABAAAAAJAOUh3aH0VYBwAAAAAg/aQotPv4+MhgMKRowD/++OO5CgIAAAAAAA+kKLS3atUqncsAAAAAAAD/lqLQPm7cuPSuAwAAAAAA/Msz39O+f/9+HT9+XJJUqlQp+fj4pFlRAAAAAADgGUL7lStX9Pbbb2vr1q3Knj27JCkyMlJ16tTR8uXLlSdPnrSuEQAAAACATMkqtTsMGjRIt2/f1tGjR3Xjxg3duHFDR44cUVRUlAYPHpweNQIAAAAAkCmleqY9JCREmzdvlre3t6mtZMmSmjVrlho2bJimxQEAAAAAkJmleqY9MTFRtra2SdptbW2VmJiYJkUBAAAAAIBnCO1169bVkCFDdPHiRVPbhQsXNHToUNWrVy9NiwMAAAAAIDNLdWifOXOmoqKi5OnpqaJFi6po0aIqXLiwoqKi9NVXX6VHjQAAAAAAZEqpvqe9QIEC+uOPP7R582b99ddfkiRvb2/Vr18/zYsDAAAAACAze6bntBsMBjVo0EANGjRI63oAAAAAAMD/PFNoDw0NVWhoqK5cuZJk8bkFCxakSWEAAAAAAGR2qQ7tAQEBGj9+vCpWrKi8efPKYDCkR10AAAAAAGR6qQ7tc+fOVXBwsN599930qAcAAAAAAPxPqlePv3fvnqpVq5YetQAAAAAAgEekOrS/9957WrZsWXrUAgAAAAAAHpGiy+OHDRtm+j4xMVH/+c9/tHnzZpUtW1a2trZmfadPn562FQIAAAAAkEmlKLQfOHDA7HX58uUlSUeOHDFrZ1E6AAAAAADSTopC+5YtW9K7DgAAAAAA8C+pvqf9oX/++UcbN27UnTt3JElGozHNigIAAAAAAM8Q2q9fv6569eqpRIkSevPNNxURESFJ6tmzp4YPH57mBQIAAAAAkFmlOrQPHTpUtra2Cg8PV5YsWUztHTp0UEhISJoWBwAAAABAZpaie9of9fPPP2vjxo3Knz+/WXvx4sV19uzZNCsMAAAAAIDMLtUz7TExMWYz7A/duHFD9vb2aVIUAAAAAAB4htBes2ZNLVq0yPTaYDAoMTFRU6ZMUZ06ddK0OAAAAAAAMrNUXx4/ZcoU1atXT/v27dO9e/c0YsQIHT16VDdu3NCOHTvSo0YAAAAAADKlVM+0ly5dWidPnlSNGjXUsmVLxcTEqE2bNjpw4ICKFi2aHjUCAAAAAJAppXqmXZJcXFw0evTotK4FAAAAAAA8ItUz7SEhIfrtt99Mr2fNmqXy5curU6dOunnzZpoWBwAAAABAZpbq0P7BBx8oKipKknT48GENGzZMb775psLCwjRs2LA0LxAAAAAAgMwq1ZfHh4WFqWTJkpKklStXqnnz5powYYL++OMPvfnmm2leIAAAAAAAmVWqZ9rt7OwUGxsrSdq8ebMaNmwoScqZM6dpBh4AAAAAADy/VM+016hRQ8OGDVP16tW1Z88erVixQpJ08uRJ5c+fP80LBAAAAAAgs0r1TPvMmTNlY2OjH374QXPmzFG+fPkkST/99JMaN26c5gUCAAAAAJBZpXqmvWDBglq3bl2S9i+++CJNCgIAAAAAAA+kOrSHh4c/cXvBggWfuRgAAAAAAPD/Uh3aPT09ZTAYHrs9ISHhuQoCAAAAAAAPpDq0HzhwwOz1/fv3deDAAU2fPl2fffZZmhUGAAAAAEBml+rQXq5cuSRtFStWlIeHhz7//HO1adMmTQoDAAAAACCzS/Xq8Y/z2muvae/evWk1HAAAAAAAmV6qZ9qjoqLMXhuNRkVERMjf31/FixdPs8IAAAAAAMjsUh3as2fPnmQhOqPRqAIFCmj58uVpVhgAAAAAAJldqkP7li1bzF5bWVkpT548KlasmGxsUj0cAAAAAAB4jFSnbF9f3/SoAwAAAAAA/MszTY2fOnVKM2bM0PHjxyVJJUuW1JAhQ1S0aNE0LQ4AAAAAgMws1avHb9y4USVLltSePXtUtmxZlS1bVrt371apUqW0adOm9KgRAAAAAIBMKdUz7R9++KGGDh2qSZMmJWkfOXKkGjRokGbFAQAAAACQmaV6pv348ePq2bNnkvYePXro2LFjaVIUAAAAAAB4htCeJ08eHTx4MEn7wYMH5erqmhY1AQAAAAAAPcPl8b169VLv3r11+vRpVatWTZK0Y8cOTZ48WcOGDUvzAgEAAAAAyKxSPdM+ZswYjR07Vl999ZV8fX3l6+urmTNnyt/fXx9//HF61GgyadIkGQwGvf/++6a2u3fvasCAAcqVK5ecnJzUtm1bXb58OV3rAAAAAADgRUh1aDcYDBo6dKjOnz+vW7du6datWzp//ryGDBkig8GQHjVKkvbu3auvv/5aZcuWNWsfOnSo1q5dq++//16//vqrLl68qDZt2qRbHQAAAAAAvCipDu2PcnZ2lrOzc1rV8ljR0dHq3Lmz5s2bpxw5cpjab926pW+++UbTp09X3bp1VaFCBQUFBWnnzp36/fff070uAAAAAADSU6pD++XLl/Xuu+/Kw8NDNjY2sra2NvtKDwMGDFDTpk1Vv359s/b9+/fr/v37Zu1eXl4qWLCgdu3a9djx4uLiFBUVZfYFAAAAAIClSfVCdN26dVN4eLjGjBmjvHnzpusl8ZK0fPly/fHHH9q7d2+SbZcuXZKdnZ2yZ89u1u7m5qZLly49dsyJEycqICAgrUsFAAAAACBNpTq0//bbb9q+fbvKly+fDuWYO3funIYMGaJNmzbJwcEhzcYdNWqU2Ur3UVFRKlCgQJqNDwAAAABAWkj15fEFChSQ0WhMj1qS2L9/v65cuaLXX39dNjY2srGx0a+//qrAwEDZ2NjIzc1N9+7dU2RkpNl+ly9flru7+2PHtbe3V7Zs2cy+AAAAAACwNKkO7TNmzNCHH36oM2fOpEM55urVq6fDhw/r4MGDpq+KFSuqc+fOpu9tbW0VGhpq2ufEiRMKDw9X1apV070+AAAAAADSU4ouj8+RI4fZvesxMTEqWrSosmTJIltbW7O+N27cSLPinJ2dVbp0abO2rFmzKleuXKb2nj17atiwYcqZM6eyZcumQYMGqWrVqqpSpUqa1QEAAAAAQEZIUWifMWNGOpfx7L744gtZWVmpbdu2iouLU6NGjTR79uyMLgsAAAAAgOeWotDetWvX9K4jxbZu3Wr22sHBQbNmzdKsWbMypiAAAAAAANJJqu9pBwAAAAAALwahHQAAAAAAC0VoBwAAAADAQqUotP/5559KTExM71oAAAAAAMAjUhTafXx8dO3aNUlSkSJFdP369XQtCgAAAAAApDC0Z8+eXWFhYZKkM2fOMOsOAAAAAMALkKJHvrVt21a+vr7KmzevDAaDKlasKGtr62T7nj59Ok0LBAAAAAAgs0pRaP/Pf/6jNm3a6J9//tHgwYPVq1cvOTs7p3dtAAAAAABkaikK7ZLUuHFjSdL+/fs1ZMgQQjsAAAAAAOksxaH9oaCgINP358+flyTlz58/7SoCAAAAAACSnuE57YmJiRo/frxcXFxUqFAhFSpUSNmzZ9cnn3zCAnUAAAAAAKShVM+0jx49Wt98840mTZqk6tWrS5J+++03+fv76+7du/rss8/SvEgAAAAAADKjVIf2hQsXav78+WrRooWprWzZssqXL5/69+9PaAcAAAAAII2k+vL4GzduyMvLK0m7l5eXbty4kSZFAQAAAACAZwjt5cqV08yZM5O0z5w5U+XKlUuTogAAAAAAwDNcHj9lyhQ1bdpUmzdvVtWqVSVJu3bt0rlz57Rhw4Y0LxAAAAAAgMwq1TPtvr6+OnnypFq3bq3IyEhFRkaqTZs2OnHihGrWrJkeNQIAAAAAkCmleqZdkjw8PFhwDgAAAACAdJbqmXYAAAAAAPBiENoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAv1TAvRPXTt2jXt3r1bCQkJqlSpkvLmzZtWdQEAAAAAkOk9c2hfuXKlevbsqRIlSuj+/fs6ceKEZs2ape7du6dlfQAAAAAAZFopvjw+Ojra7HVAQID27NmjPXv26MCBA/r+++81evToNC8QAAAAAIDMKsWhvUKFCvrvf/9rem1jY6MrV66YXl++fFl2dnZpWx0AAAAAAJlYii+P37hxowYMGKDg4GDNmjVLX375pTp06KCEhATFx8fLyspKwcHB6VgqAAAAAACZS4pDu6enp9avX69vv/1Wvr6+Gjx4sP755x/9888/SkhIkJeXlxwcHNKzVgAAAAAAMpVUP/KtY8eO2rt3rw4dOqTatWsrMTFR5cuXJ7ADAAAAAJDGUrV6/IYNG3T8+HGVK1dO8+fP16+//qrOnTurSZMmGj9+vBwdHdOrTgAAAAAAMp0Uz7QPHz5c3bt31969e9WnTx998skn8vX11R9//CEHBwf5+Pjop59+Ss9aAQAAAADIVFIc2oODg7VhwwYtX75ce/fu1eLFiyVJdnZ2+uSTT/Tjjz9qwoQJ6VYoAAAAAACZTYpDe9asWRUWFiZJOnfuXJJ72EuWLKnt27enbXUAAAAAAGRiKQ7tEydOVJcuXeTh4SFfX1998skn6VkXAAAAAACZXooXouvcubMaN26s06dPq3jx4sqePXs6lgUAAAAAAFK1enyuXLmUK1eu9KoFAAAAAAA8ItXPaQcAAAAAAC8GoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUBYd2idOnKhKlSrJ2dlZrq6uatWqlU6cOGHW5+7duxowYIBy5colJycntW3bVpcvX86gigEAAAAASDsWHdp//fVXDRgwQL///rs2bdqk+/fvq2HDhoqJiTH1GTp0qNauXavvv/9ev/76qy5evKg2bdpkYNUAAAAAAKQNm4wu4ElCQkLMXgcHB8vV1VX79+9XrVq1dOvWLX3zzTdatmyZ6tatK0kKCgqSt7e3fv/9d1WpUiUjygYAAAAAIE1Y9Ez7v926dUuSlDNnTknS/v37df/+fdWvX9/Ux8vLSwULFtSuXbseO05cXJyioqLMvgAAAAAAsDQvTWhPTEzU+++/r+rVq6t06dKSpEuXLsnOzk7Zs2c36+vm5qZLly49dqyJEyfKxcXF9FWgQIH0LB0AAAAAgGfy0oT2AQMG6MiRI1q+fPlzjzVq1CjdunXL9HXu3Lk0qBAAAAAAgLRl0fe0PzRw4ECtW7dO27ZtU/78+U3t7u7uunfvniIjI81m2y9fvix3d/fHjmdvby97e/v0LBkAAAAAgOdm0TPtRqNRAwcO1KpVq/TLL7+ocOHCZtsrVKggW1tbhYaGmtpOnDih8PBwVa1a9UWXCwAAAABAmrLomfYBAwZo2bJl+u9//ytnZ2fTfeouLi5ydHSUi4uLevbsqWHDhilnzpzKli2bBg0apKpVq7JyPAAAAADgpWfRoX3OnDmSpNq1a5u1BwUFqVu3bpKkL774QlZWVmrbtq3i4uLUqFEjzZ49+wVXCgAAAABA2rPo0G40Gp/ax8HBQbNmzdKsWbNeQEUAAAAAALw4Fn1POwAAAAAAmRmhHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQhHYAAAAAACwUoR0AAAAAAAtFaAcAAAAAwEIR2gEAAAAAsFCEdgAAAAAALBShHQAAAAAAC0VoBwAAAADAQhHaAQAAAACwUIR2AAAAAAAsFKEdAAAAAAALRWgHAAAAAMBCEdoBAAAAALBQr0xonzVrljw9PeXg4KDKlStrz549GV0SAAAAAADP5ZUI7StWrNCwYcM0btw4/fHHHypXrpwaNWqkK1euZHRpAAAAAAA8s1citE+fPl29evVS9+7dVbJkSc2dO1dZsmTRggULMro0AAAAAACemU1GF/C87t27p/3792vUqFGmNisrK9WvX1+7du1Kdp+4uDjFxcWZXt+6dUuSFBUVlb7FvmIS42IzuoTHijIYM7qEx0q4k5DRJSQrOsEy65L4t4kXh8+1Z8PnWurxuYYXhc+1Z8PnWurxuZZ6D8+Z0fjkfwsvfWi/du2aEhIS5ObmZtbu5uamv/76K9l9Jk6cqICAgCTtBQoUSJca8eK5ZHQBT3Q8owtI1hsZXcCTuFj2TxR4ESz7XwGfa6nG5xrA59oz4HPt1XT79m25POH8vfSh/VmMGjVKw4YNM71OTEzUjRs3lCtXLhkMhgysDK+6qKgoFShQQOfOnVO2bNkyuhwAeG58rgF41fC5hhfFaDTq9u3b8vDweGK/lz60586dW9bW1rp8+bJZ++XLl+Xu7p7sPvb29rK3tzdry549e3qVCCSRLVs2/iMA4JXC5xqAVw2fa3gRnjTD/tBLvxCdnZ2dKlSooNDQUFNbYmKiQkNDVbVq1QysDAAAAACA5/PSz7RL0rBhw9S1a1dVrFhRb7zxhmbMmKGYmBh17949o0sDAAAAAOCZvRKhvUOHDrp69arGjh2rS5cuqXz58goJCUmyOB2Q0ezt7TVu3Lgkt2cAwMuKzzUArxo+12BpDManrS8PAAAAAAAyxEt/TzsAAAAAAK8qQjsAAAAAABaK0A4AAAAAgIUitAMAAAAAYKEI7QAAAAAAWKhX4pFvgKW6du2aFixYoF27dunSpUuSJHd3d1WrVk3dunVTnjx5MrhCAAAAAJaMmXYgnezdu1clSpRQYGCgXFxcVKtWLdWqVUsuLi4KDAyUl5eX9u3bl9FlAkCaOXfunHr06JHRZQBAqty5c0e//fabjh07lmTb3bt3tWjRogyoCvh/PKcdSCdVqlRRuXLlNHfuXBkMBrNtRqNRffv21Z9//qldu3ZlUIUAkLYOHTqk119/XQkJCRldCgCkyMmTJ9WwYUOFh4fLYDCoRo0aWr58ufLmzStJunz5sjw8PPhcQ4bi8nggnRw6dEjBwcFJArskGQwGDR06VD4+PhlQGQA8mzVr1jxx++nTp19QJQCQNkaOHKnSpUtr3759ioyM1Pvvv6/q1atr69atKliwYEaXB0gitAPpxt3dXXv27JGXl1ey2/fs2SM3N7cXXBUAPLtWrVrJYDDoSRfpJfeHSgCwVDt37tTmzZuVO3du5c6dW2vXrlX//v1Vs2ZNbdmyRVmzZs3oEgFCO5Be/Pz81Lt3b+3fv1/16tUzBfTLly8rNDRU8+bN09SpUzO4SgBIubx582r27Nlq2bJlstsPHjyoChUqvOCqAODZ3blzRzY2/x+JDAaD5syZo4EDB8rX11fLli3LwOqABwjtQDoZMGCAcufOrS+++EKzZ8823QtlbW2tChUqKDg4WO3bt8/gKgEg5SpUqKD9+/c/NrQ/bRYeACzNw4WBvb29zdpnzpwpSWrRokVGlAWYYSE64AW4f/++rl27JknKnTu3bG1tM7giAEi97du3KyYmRo0bN052e0xMjPbt2ydfX98XXBkAPJuJEydq+/bt2rBhQ7Lb+/fvr7lz5yoxMfEFVwb8P0I7AAAAAAAWiue0AwAAAABgoQjtAAAAAABYKEI7AAAAAAAWitAOAAAAAICFIrQDAAAAAGChCO0AAMCi3bt3L6NLAAAgwxDaAQB4idWuXVuDBw/WiBEjlDNnTrm7u8vf31+SdObMGRkMBh08eNDUPzIyUgaDQVu3bpUkbd26VQaDQRs3bpSPj48cHR1Vt25dXblyRT/99JO8vb2VLVs2derUSbGxsSmqKTExUVOmTFGxYsVkb2+vggUL6rPPPjNtHzlypEqUKKEsWbKoSJEiGjNmjO7fv2/a7u/vr/Lly2v+/PkqXLiwHBwcJEk//PCDypQpI0dHR+XKlUv169dXTEzM851AAAAsnE1GFwAAAJ7PwoULNWzYMO3evVu7du1St27dVL16dRUvXjzFY/j7+2vmzJnKkiWL2rdvr/bt28ve3l7Lli1TdHS0Wrdura+++kojR4586lijRo3SvHnz9MUXX6hGjRqKiIjQX3/9Zdru7Oys4OBgeXh46PDhw+rVq5ecnZ01YsQIU59//vlHK1eu1I8//ihra2tFRESoY8eOmjJlilq3bq3bt29r+/btMhqNqTtZAAC8ZAxG/msHAMBLq3bt2kpISND27dtNbW+88Ybq1q2rvn37qnDhwjpw4IDKly8v6cFMe44cObRlyxbVrl1bW7duVZ06dbR582bVq1dPkvR/7dw9SCNdGIbhZ9Y1OCgBiyhWUWGUCP5AFISUQsQUVoKFpRYWFoqgSBJBEEmhjVpbx8pGUZA0FpGImEqsguOACEmpjTDIVyxfUHZds8sGJ3JfkGLmhHfOSROeOT+pVEorKysqFArq7OyUJM3Ozsq2bZ2cnPy2P4+PjwoEAtrd3dXMzExFY9jc3FQ6ndbl5aWkHy8QNjY2dH9/r0AgIEm6urpSOByWbdsKBoN/9BsBAFDLmGkHAKDG9fX1vblua2tTsVj86xqtra3lpeuv711cXHxY5+bmRs/Pz+UXAL+yv7+v7e1tFQoFPT09yXVd+f3+N98JBoPlwC5J/f39GhkZUW9vr0ZHRxWNRjUxMaHm5uY/GSYAADWHPe0AANS4+vr6N9eGYejl5UXfvv34m3+9qO713vH3ahiG8W7Nj5im+dv28/NzTU1NKRaL6fDwUPl8XvF4/KfD5hobG99c19XV6fT0VMfHx+rp6dHOzo66u7t1e3v7YZ8AAKhlhHYAAL6o/2eqHx4eyvdeH0pXDZZlyTRNZTKZX7Zns1kFg0HF43ENDg7Ksizd3d1VVNswDEUiEa2trSmfz8vn8+ng4OBfdh8AAM9heTwAAF+UaZoaHh5WKpVSR0eHisWiEolEVZ/Z0NCg5eVlLS0tyefzKRKJqFQq6fr6WtPT07IsS47jKJ1Oa2hoSEdHRxUF71wup0wmo2g0qpaWFuVyOZVKJYVCoaqOBwCAz8ZMOwAAX9je3p5c11U4HNb8/LzW19er/sxkMqnFxUWtrq4qFAppcnKyvMd+fHxcCwsLmpub08DAgLLZrJLJ5Ic1/X6/zs7OFIvF1NXVpUQioa2tLY2NjVV7OAAAfCpOjwcAAAAAwKOYaQcAAAAAwKMI7QAAoGKO46ipqendj+M4n91FAAC+FJbHAwCAirmuK9u2321vb2/X9++ccwsAwL9CaAcAAAAAwKNYHg8AAAAAgEcR2gEAAAAA8ChCOwAAAAAAHkVoBwAAAADAowjtAAAAAAB4FKEdAAAAAACPIrQDAAAAAOBRhHYAAAAAADzqP65BLM9iWuVwAAAAAElFTkSuQmCC",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "# loop over all variables in matching_dfs_dict and save a plot for each\n",
-    "for key in list(matching_dfs_dict.keys())[1:]:      # skip 1st key (hid)\n",
-    "    x = (match_coverage_1[key]\n",
-    "     .merge(match_coverage_2[key], on=matching_dfs_dict[key][0], suffixes=('_1', '_2'))\n",
-    "     .merge(match_coverage_3[key], on=matching_dfs_dict[key][0], suffixes=('_2', '_3'))\n",
-    "     .merge(match_coverage_4[key], on=matching_dfs_dict[key][0], suffixes=('_3', '_4')))\n",
-    "    # keep % columns only \n",
-    "    x = x[[col for col in x.columns if 'Percentage' in col]]\n",
-    "    # plot bar chart of Percentage of households matched for each category\n",
-    "    fig, ax = plt.subplots(1, 1, figsize=(12, 6))\n",
-    "    x.plot(kind='bar', ax=ax)\n",
-    "    plt.ylabel('% of households matched')\n",
-    "    plt.title('Matching coverage for ' + key)\n",
-    "    plt.show()\n",
-    "    # save the plot\n",
-    "    fig.savefig(f'../data/interim/matching/plots/matching_coverage_hh_{key}.png')\n",
-    "    \n",
-    "\n",
-    "    \n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Treat different households differently\n",
-    "\n",
-    "Salary is a useful matching variable, so it's a shame not to use it all. We can try to:\n",
-    "- match on salary for households with 0 pensioners\n",
-    "- match without salary for households with one or more pensioners "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 44,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "493 households in the SPC had no match\n",
-      "7.3 % of households in the SPC had no match\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "# match on different subset of column depending on yearly_income value\n",
-    "keys = ['yearly_income', 'number_adults', 'number_children', 'num_pension_age', \n",
-    "        'employment_status', 'number_cars', 'tenure_status', 'rural_urban_2_categories']\n",
-    "# remove yearly income from the list\n",
-    "# new list without yearly income, without modifying the original list\n",
-    "keys_no_salary = keys.copy()\n",
-    "keys_no_salary.remove('yearly_income')\n",
-    "\n",
-    "\n",
-    "#### ------ Split the two datasets into households with no salary and households with a salary\n",
-    "\n",
-    "# get spc column name that matches yearly_income in matching_dfs_dict\n",
-    "spc_col = matching_dfs_dict['num_pension_age'][0]\n",
-    "nts_col = matching_dfs_dict['num_pension_age'][1]\n",
-    "\n",
-    "# dfs: households with no salary\n",
-    "spc_matching_no_salary = spc_matching[spc_matching[spc_col] > 0]\n",
-    "nts_matching_no_salary = nts_matching[nts_matching[nts_col] > 0]\n",
-    "\n",
-    "# dfs: households with a salary\n",
-    "spc_matching_salary = spc_matching[spc_matching[spc_col] != 0]\n",
-    "nts_matching_salary = nts_matching[nts_matching[nts_col] != 0]\n",
-    "\n",
-    "\n",
-    "#### ------ Match the two datasets separately\n",
-    "\n",
-    "# extract equivalent column names from dictionary\n",
-    "spc_cols = [matching_dfs_dict[key][0] for key in keys]\n",
-    "nts_cols = [matching_dfs_dict[key][1] for key in keys]\n",
-    "\n",
-    "# extract equivalent column names from dictionary\n",
-    "spc_cols_no_salary = [matching_dfs_dict[key][0] for key in keys_no_salary]\n",
-    "nts_cols_no_salary = [matching_dfs_dict[key][1] for key in keys_no_salary]\n",
-    "\n",
-    "# match\n",
-    "spc_nts_no_salary = spc_matching_no_salary.merge(nts_matching_no_salary,\n",
-    "                                                 left_on= spc_cols_no_salary,\n",
-    "                                                 right_on= nts_cols_no_salary,\n",
-    "                                                 how = 'left')\n",
-    "\n",
-    "spc_nts_salary = spc_matching_salary.merge(nts_matching_salary,\n",
-    "                                           left_on= spc_cols,\n",
-    "                                           right_on= nts_cols,\n",
-    "                                           how = 'left')\n",
-    "\n",
-    "# bind the rows of the two dataframes\n",
-    "spc_nts_x = pd.concat([spc_nts_no_salary, spc_nts_salary])\n",
-    "\n",
-    "\n",
-    "# Calculate how many rows from nts_matching are matched onto each hid in spc_matching,\n",
-    "spc_nts_x['count'] = spc_nts_x.groupby('hid')['HouseholdID'].transform('count')\n",
-    "\n",
-    "spc_nts_x_hist = spc_nts_x.drop_duplicates(subset='hid')\n",
-    "\n",
-    "\n",
-    "# plot a histogram of the counts and label the axis and title\n",
-    "plt.hist(spc_nts_x_hist['count'], bins=50)\n",
-    "plt.xlabel('Number of matches per household')\n",
-    "plt.ylabel('Number of households')\n",
-    "plt.title('Categorical Matching')\n",
-    "\n",
-    "\n",
-    "print(spc_nts_x_hist[spc_nts_x_hist['count'] == 0].shape[0], \"households in the SPC had no match\")\n",
-    "print(round((spc_nts_x_hist[spc_nts_x_hist['count'] == 0].shape[0] / spc_matching['hid'].unique().shape[0]) * 100, 1), \"% of households in the SPC had no match\")\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Store the results in a dictionary, \n",
-    "\n",
-    "- Key: SPC hid\n",
-    "- Value: List of NTS Household IDs\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Each hid in spc_matching is joined onto multiple HouseholdID in nts_matching.\n",
-    "# Create a dictionary to store the hid to HouseholdID matches\n",
-    "\n",
-    "def extract_matching_results(df: pd.DataFrame, key_col: str, value_col: str) -> dict:\n",
-    "    '''\n",
-    "    Extracts a dictionary where each key can be associated with multiple values\n",
-    "\n",
-    "    Parameters\n",
-    "    ----------\n",
-    "    df : DataFrame\n",
-    "        The DataFrame to extract the matching results from\n",
-    "    key_col : str\n",
-    "        The name of the column to use as the key\n",
-    "    value_col : str\n",
-    "        The name of the column to use as the value\n",
-    "\n",
-    "    Returns\n",
-    "    -------\n",
-    "    dict\n",
-    "        A dictionary where each key can be associated with multiple values\n",
-    "    '''\n",
-    "    matching_results = df.groupby(key_col)[value_col].apply(list).to_dict()\n",
-    "    return matching_results"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "matches_hh_level = extract_matching_results(df = spc_nts_4,\n",
-    "                                            key_col = 'hid',\n",
-    "                                            value_col = 'HouseholdID')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "('E02002183_0091', [2019001902.0, 2019004101.0, 2019004092.0, 2019004108.0, 2019004125.0, 2019004121.0, 2019001719.0, 2019001714.0, 2019001119.0, 2019001130.0, 2019001148.0, 2019000880.0, 2019003240.0, 2019002767.0, 2019002775.0, 2019002769.0, 2019005597.0, 2019002770.0, 2019003252.0, 2019005438.0, 2019006462.0, 2019006475.0, 2019003208.0, 2019004196.0, 2019004191.0, 2019004200.0, 2019004197.0, 2019000839.0, 2019000350.0, 2019000855.0, 2019001091.0, 2019001721.0, 2019001716.0, 2019000813.0, 2019004159.0, 2019000823.0, 2019004177.0, 2019001167.0, 2019000633.0, 2019000536.0, 2019005323.0, 2019005356.0, 2019004637.0, 2019005612.0, 2019002547.0, 2019005638.0, 2019001816.0, 2019002329.0, 2019002894.0, 2019001865.0, 2019003329.0, 2019002919.0, 2019002929.0, 2019005553.0, 2019000307.0, 2019004714.0, 2019002980.0, 2019001202.0, 2019001205.0, 2019001210.0, 2019001782.0, 2019001788.0, 2019002721.0, 2019005579.0, 2019000863.0, 2019001896.0, 2019001909.0, 2019000589.0, 2019000701.0, 2019002368.0, 2019002369.0, 2019002374.0, 2019002378.0, 2019002376.0, 2019002366.0, 2019001012.0, 2019002405.0, 2019002392.0, 2019002712.0, 2019002711.0, 2019001044.0, 2019001066.0, 2019001084.0, 2019001268.0, 2019003070.0, 2019004770.0, 2019002288.0, 2019001949.0, 2019002312.0, 2019000961.0, 2019003385.0, 2019003394.0, 2019000244.0, 2019003381.0, 2019003384.0, 2019001373.0, 2019006564.0, 2019001450.0, 2019006569.0, 2019001371.0, 2019006568.0, 2019005410.0, 2019005415.0, 2019005417.0, 2019000491.0, 2019000187.0, 2019003333.0, 2019002952.0, 2019005752.0, 2019002951.0, 2019000199.0, 2019004994.0, 2019004997.0, 2019005174.0, 2019005909.0, 2019005185.0, 2019005177.0, 2019005914.0, 2019005558.0, 2019001437.0, 2019005574.0, 2019004547.0, 2019000074.0, 2019006080.0, 2019006090.0, 2019005020.0, 2019005024.0, 2019000088.0, 2019006273.0, 2019002705.0, 2019002203.0, 2019000762.0, 2019000759.0, 2019000655.0, 2019000661.0, 2019000662.0, 2019004035.0, 2019000660.0, 2019000767.0, 2019000529.0, 2019005311.0, 2019005342.0, 2019005501.0, 2019002739.0, 2019001245.0, 2019001286.0, 2019001255.0, 2019001246.0, 2019004776.0, 2019001261.0, 2019001259.0, 2019001295.0, 2019003022.0, 2019003023.0, 2019001269.0, 2019003725.0, 2019003726.0, 2019003737.0, 2019006300.0, 2019003738.0, 2019000518.0, 2019000523.0, 2019000525.0, 2019000212.0, 2019003411.0, 2019005772.0, 2019005779.0, 2019001284.0, 2019005849.0, 2019001596.0, 2019002044.0, 2019002039.0, 2019003127.0, 2019001490.0, 2019001493.0, 2019005972.0, 2019003150.0, 2019001959.0, 2019001964.0, 2019001966.0, 2019001543.0, 2019001983.0, 2019001524.0, 2019006505.0, 2019001350.0, 2019001349.0, 2019001352.0, 2019001355.0, 2019006549.0, 2019001367.0, 2019001400.0, 2019004598.0, 2019003484.0, 2019005143.0, 2019005152.0, 2019005172.0, 2019005810.0, 2019005039.0, 2019003494.0, 2019000052.0, 2019000056.0, 2019000081.0, 2019003540.0, 2019000134.0, 2019003554.0, 2019006630.0, 2019003560.0, 2019004432.0, 2019002492.0, 2019002518.0, 2019005498.0, 2019002519.0, 2019001670.0, 2019005821.0, 2019005869.0, 2019005116.0, 2019002058.0, 2019005864.0, 2019002061.0, 2019005069.0, 2019001826.0, 2019002872.0, 2019005708.0, 2019005693.0, 2019003294.0, 2019003297.0, 2019003273.0, 2019005654.0, 2019000907.0, 2019000913.0, 2019000904.0, 2019001823.0, 2019001839.0, 2019002861.0, 2019003365.0, 2019004669.0, 2019004660.0, 2019000293.0, 2019003910.0, 2019003911.0, 2019003921.0, 2019003801.0, 2019002075.0, 2019005823.0, 2019005218.0, 2019005226.0, 2019003630.0, 2019004305.0, 2019003648.0, 2019004314.0, 2019004315.0, 2019004291.0, 2019004303.0, 2019000247.0, 2019004579.0, 2019006669.0, 2019003730.0, 2019003713.0, 2019003618.0, 2019006291.0, 2019000021.0, 2019006077.0, 2019006110.0, 2019000030.0, 2019000041.0, 2019000025.0, 2019006127.0, 2019006764.0, 2019005947.0, 2019005959.0, 2019005812.0, 2019003831.0, 2019006755.0, 2019006754.0, 2019004601.0, 2019003077.0, 2019003104.0, 2019001320.0, 2019000452.0, 2019006436.0, 2019006446.0, 2019006425.0, 2019000459.0, 2019001318.0, 2019003125.0, 2019006375.0, 2019000329.0, 2019006406.0, 2019006409.0, 2019003164.0, 2019003220.0, 2019002599.0, 2019004341.0, 2019004327.0, 2019004349.0, 2019003683.0, 2019004334.0, 2019004343.0, 2019004354.0, 2019004854.0, 2019003777.0, 2019004802.0, 2019003968.0, 2019003944.0, 2019003962.0, 2019003754.0, 2019000038.0, 2019003699.0, 2019003694.0, 2019003704.0, 2019004385.0, 2019003706.0, 2019004367.0, 2019004379.0, 2019004387.0, 2019004819.0, 2019006822.0, 2019006239.0, 2019003571.0, 2019006642.0, 2019006229.0, 2019003586.0, 2019006248.0, 2019006663.0, 2019006677.0, 2019005784.0, 2019005793.0, 2019000224.0, 2019004485.0, 2019004981.0, 2019003821.0, 2019003852.0, 2019004508.0, 2019004515.0, 2019003858.0, 2019003864.0, 2019003889.0, 2021003917.0, 2021003873.0, 2021003878.0, 2021003879.0, 2021003008.0, 2021003874.0, 2021003880.0, 2021003633.0, 2021003020.0, 2021003914.0, 2021002626.0, 2021002635.0, 2021002656.0, 2021002664.0, 2021003779.0, 2021002082.0, 2021002092.0, 2021002220.0, 2021003126.0, 2021002234.0, 2021002531.0, 2021002249.0, 2021002546.0, 2021002959.0, 2021002954.0, 2021002968.0, 2021002844.0, 2021002595.0, 2021002598.0, 2021002858.0, 2021003704.0, 2021004011.0, 2021003082.0, 2021003707.0, 2021004022.0, 2021004025.0, 2021003745.0, 2021004057.0, 2021003800.0, 2021004098.0, 2021004102.0, 2021004100.0, 2021004110.0, 2021002538.0, 2021003180.0, 2021001152.0, 2021001179.0, 2021004549.0, 2021004176.0, 2021000529.0, 2021004303.0, 2021004567.0, 2021001893.0, 2021004313.0, 2021000557.0, 2021000523.0, 2021004209.0, 2021000563.0, 2021001900.0, 2021004572.0, 2021000556.0, 2021001203.0, 2021003945.0, 2021000172.0, 2021004792.0, 2021004791.0, 2021004794.0, 2021000165.0, 2021000159.0, 2021001661.0, 2021001907.0, 2021000199.0, 2021001724.0, 2021001954.0, 2021001736.0, 2021001721.0, 2021001967.0, 2021000464.0, 2021004234.0, 2021000514.0, 2021000987.0, 2021000997.0, 2021000976.0, 2021000775.0, 2021000804.0, 2021000797.0, 2021000801.0, 2021000789.0, 2021004514.0, 2021004260.0, 2021003028.0, 2021003746.0, 2021003027.0, 2021002703.0, 2021002706.0, 2021002394.0, 2021002159.0, 2021002379.0, 2021002147.0, 2021004317.0, 2021001450.0, 2021001242.0, 2021001435.0, 2021001429.0, 2021001456.0, 2021004591.0, 2021001224.0, 2021001499.0, 2021000582.0, 2021004371.0, 2021004375.0, 2021004373.0, 2021004379.0, 2021001036.0, 2021001305.0, 2021004397.0, 2021001083.0, 2021001100.0, 2021001335.0, 2021001081.0, 2021003792.0, 2021002083.0, 2021002210.0, 2021002525.0, 2021002353.0, 2021002511.0, 2021003061.0, 2021003694.0, 2021003685.0, 2021003978.0, 2021003692.0, 2021003500.0, 2021000307.0, 2021004668.0, 2021000072.0, 2021004703.0, 2021003511.0, 2021003529.0, 2021000372.0, 2021001979.0, 2021001983.0, 2021001978.0, 2021001552.0, 2021002003.0, 2021000634.0, 2021000638.0, 2021000629.0, 2021000491.0, 2021000632.0, 2021000649.0, 2021000296.0, 2021003478.0, 2021000064.0, 2021003362.0, 2021004673.0, 2021003360.0, 2021004676.0, 2021003371.0, 2021003377.0, 2021002406.0, 2021000222.0, 2021001692.0, 2021000422.0, 2021000414.0, 2021000418.0, 2021001707.0, 2021001955.0, 2021001911.0, 2021000206.0, 2021001680.0, 2021000020.0, 2021000225.0, 2021000226.0, 2021000025.0, 2021002482.0, 2021001802.0, 2021004223.0, 2021001803.0, 2021004641.0, 2021001809.0, 2021001800.0, 2021004642.0, 2021000736.0, 2021000745.0, 2021004233.0, 2021001820.0, 2021000945.0, 2021000972.0, 2021004666.0, 2021000969.0, 2021003546.0, 2021003554.0, 2021000371.0, 2021000388.0, 2021000826.0, 2021003855.0, 2021002073.0, 2021000814.0, 2021000816.0, 2021000850.0, 2021004137.0, 2021004533.0, 2021004144.0, 2021000835.0, 2021004526.0, 2021001400.0, 2021003417.0, 2021002259.0, 2021003242.0, 2021003269.0, 2021002286.0, 2021003281.0, 2021000599.0, 2021001274.0, 2021003603.0, 2021001590.0, 2021000501.0, 2021000881.0, 2021000889.0, 2021001562.0, 2021001595.0, 2021000879.0, 2021000887.0, 2021001612.0, 2021001594.0, 2021003270.0, 2021003282.0, 2021002294.0, 2021002293.0, 2021003307.0, 2021003308.0, 2021002297.0, 2021003467.0, 2021001356.0, 2021001347.0, 2021001326.0, 2021001114.0, 2021004441.0, 2021004445.0, 2021004430.0, 2021004460.0, 2021001132.0, 2021004436.0, 2021001128.0, 2021003096.0, 2021003097.0, 2021000130.0, 2021004781.0, 2021004776.0, 2021004785.0, 2021004772.0, 2022001047.0, 2022001062.0, 2022001110.0, 2022001120.0, 2022001123.0, 2022001176.0, 2022001215.0, 2022001217.0, 2022001223.0, 2022001228.0, 2022001255.0, 2022001300.0, 2022001301.0, 2022001310.0, 2022001375.0, 2022001376.0, 2022001381.0, 2022001402.0, 2022001410.0, 2022001415.0, 2022001419.0, 2022001429.0, 2022001434.0, 2022001449.0, 2022001549.0, 2022001552.0, 2022000006.0, 2022000010.0, 2022000014.0, 2022000064.0, 2022000107.0, 2022000110.0, 2022000116.0, 2022000123.0, 2022000126.0, 2022000181.0, 2022000218.0, 2022002651.0, 2022002676.0, 2022002688.0, 2022002698.0, 2022002707.0, 2022002722.0, 2022002757.0, 2022002777.0, 2022002778.0, 2022002787.0, 2022002848.0, 2022003170.0, 2022003226.0, 2022003247.0, 2022003274.0, 2022003279.0, 2022003295.0, 2022003300.0, 2022003315.0, 2022003324.0, 2022003340.0, 2022003388.0, 2022003394.0, 2022003414.0, 2022003423.0, 2022003427.0, 2022003430.0, 2022003476.0, 2022003515.0, 2022003525.0, 2022003536.0, 2022003539.0, 2022003579.0, 2022003600.0, 2022003627.0, 2022000552.0, 2022000556.0, 2022000579.0, 2022000596.0, 2022000624.0, 2022000633.0, 2022000653.0, 2022000659.0, 2022000662.0, 2022000668.0, 2022000695.0, 2022000718.0, 2022000719.0, 2022000720.0, 2022000735.0, 2022000758.0, 2022000815.0, 2022000816.0, 2022000823.0, 2022000844.0, 2022000867.0, 2022000874.0, 2022000887.0, 2022000918.0, 2022001652.0, 2022001663.0, 2022001669.0, 2022001678.0, 2022001681.0, 2022001682.0, 2022001684.0, 2022001685.0, 2022001708.0, 2022001734.0, 2022001745.0, 2022001759.0, 2022001765.0, 2022001767.0, 2022001828.0, 2022001856.0, 2022001934.0, 2022001937.0, 2022001944.0, 2022001953.0, 2022001988.0, 2022001998.0, 2022002009.0, 2022002098.0, 2022002136.0, 2022002140.0, 2022002166.0, 2022002174.0, 2022002197.0, 2022002211.0, 2022002256.0, 2022002336.0, 2022002346.0, 2022002356.0, 2022002358.0, 2022002363.0, 2022002364.0, 2022002380.0, 2022002429.0, 2022002435.0, 2022002460.0, 2022002509.0, 2022002522.0, 2022002525.0, 2022002531.0, 2022002571.0, 2022002582.0, 2022002590.0, 2022003660.0, 2022003669.0, 2022003720.0, 2022003727.0, 2022003759.0, 2022003808.0, 2022003813.0, 2022003817.0, 2022003841.0, 2022003844.0, 2022003872.0, 2022003881.0, 2022003890.0, 2022003892.0, 2022003904.0, 2022003912.0, 2022003913.0, 2022003916.0, 2022003921.0, 2022003932.0, 2022003935.0, 2022003937.0, 2022003940.0, 2022003945.0, 2022003961.0, 2022003976.0, 2022003978.0, 2022003984.0, 2022004015.0, 2022004048.0, 2022004075.0, 2022004078.0, 2022004096.0, 2022004130.0, 2022000262.0, 2022000268.0, 2022000269.0, 2022000284.0, 2022000357.0, 2022000439.0, 2022000444.0, 2022000461.0, 2022000484.0, 2022000485.0, 2022000517.0, 2022002869.0, 2022002872.0, 2022002878.0, 2022002897.0, 2022002907.0, 2022002908.0, 2022002931.0, 2022002937.0, 2022002967.0, 2022002974.0, 2022002987.0, 2022003004.0, 2022003042.0, 2022003049.0, 2022003056.0, 2022003058.0, 2022003065.0, 2022003067.0, 2022003104.0, 2022003106.0, 2022003114.0, 2022003116.0, 2022004222.0, 2022004240.0, 2022004255.0, 2022004305.0, 2022004329.0, 2022004359.0])\n"
-     ]
-    }
-   ],
-   "source": [
-    "# print the 6th key, value in the matches_hh_level dictionary\n",
-    "print(list(matches_hh_level.items())[90])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
@@ -4257,7 +3651,7 @@
        "4                      1.0  [2019001923.0, 2019003253.0, 2019001755.0, 201...  "
       ]
      },
-     "execution_count": 48,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -4280,7 +3674,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4303,14 +3697,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "('E02002183_0595', 2019004263.0)\n"
+      "('E02002183_0595', 2019003190.0)\n"
      ]
     }
    ],
@@ -4327,7 +3721,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4350,7 +3744,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# random sample \n",
+    "# random sample\n",
     "with open('../data/interim/matching/matches_hh_level_categorical_random_sample.pkl', 'wb') as f:\n",
     "    pkl.dump(matches_hh_level_sample, f)\n",
     "\n",
@@ -4372,7 +3766,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# # for each hid in spc_edited, sample a value from the nts_hh_id col. \n",
+    "# # for each hid in spc_edited, sample a value from the nts_hh_id col.\n",
     "# spc_edited['nts_hh_id_sample'] = spc_edited['nts_hh_id'].apply(lambda x: np.random.choice(x) if x is not np.nan else np.nan)\n",
     "# # All rows with the same 'hid' should have the same value for 'nts_hh_id_sample'. Group by hid and assign the first value to all rows in the group\n",
     "# spc_edited['nts_hh_id_sample'] = spc_edited.groupby('hid')['nts_hh_id_sample'].transform('first')\n",
@@ -4395,7 +3789,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [
     {
@@ -4672,13 +4066,13 @@
        "340876            -9             -9            -9          -10  "
       ]
      },
-     "execution_count": 52,
+     "execution_count": 43,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "nts_individuals_filtered.head()"
+    "nts_individuals.head()"
    ]
   },
   {
@@ -4690,7 +4084,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -4722,25 +4116,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 45,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_375225/400388732.py:3: SettingWithCopyWarning: \n",
-      "A value is trying to be set on a copy of a slice from a DataFrame\n",
-      "\n",
-      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
-      "  nts_individuals_filtered.rename(columns={'Age_B04ID': 'age_group', 'Sex_B01ID': 'sex'}, inplace=True)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# rename nts columns in preparation for matching\n",
     "\n",
-    "nts_individuals_filtered.rename(columns={'Age_B04ID': 'age_group', 'Sex_B01ID': 'sex'}, inplace=True)"
+    "nts_individuals.rename(columns={'Age_B04ID': 'age_group', 'Sex_B01ID': 'sex'}, inplace=True)"
    ]
   },
   {
@@ -4757,38 +4139,38 @@
    "outputs": [],
    "source": [
     "matches_ind = match_individuals(\n",
-    "    df1 = spc_edited, \n",
-    "    df2 = nts_individuals_filtered,\n",
+    "    df1 = spc_edited,\n",
+    "    df2 = nts_individuals,\n",
     "    matching_columns = ['age_group', 'sex'],\n",
-    "    df1_id = 'hid', \n",
+    "    df1_id = 'hid',\n",
     "    df2_id = 'HouseholdID',\n",
     "    matches_hh = matches_hh_level_sample,\n",
-    "    show_progress = False)\n",
+    "    show_progress = True)\n",
     "\n",
     "#matches_ind"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{0: 374874,\n",
-       " 1: 364538,\n",
-       " 2: 364539,\n",
-       " 3: 381654,\n",
-       " 4: 381655,\n",
-       " 5: 366116,\n",
-       " 9: 382246,\n",
+       "{0: 349184,\n",
+       " 1: 368506,\n",
+       " 2: 368505,\n",
+       " 3: 355607,\n",
+       " 4: 355606,\n",
+       " 5: 344330,\n",
+       " 9: 352777,\n",
        " 10: 354879,\n",
        " 11: 354878,\n",
        " 12: 354880}"
       ]
      },
-     "execution_count": 58,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -4802,20 +4184,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 48,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Add matches_ind values to spc_edited using map\n",
     "spc_edited['nts_ind_id'] = spc_edited.index.map(matches_ind)\n",
     "\n",
-    "# add the nts_individuals_filtered.IndividualID to spc_edit. The current nts_ind_id is the row index of nts_individuals_filtered\n",
-    "spc_edited['nts_ind_id'] = spc_edited['nts_ind_id'].map(nts_individuals_filtered['IndividualID'])\n"
+    "# add the nts_individuals.IndividualID to spc_edit. The current nts_ind_id is the row index of nts_individuals\n",
+    "spc_edited['nts_ind_id'] = spc_edited['nts_ind_id'].map(nts_individuals['IndividualID'])\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [
     {
@@ -4933,7 +4315,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
        "      <td>9</td>\n",
-       "      <td>2.022000e+09</td>\n",
+       "      <td>2.019009e+09</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
@@ -4981,7 +4363,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019004130.0, 2019004126.0, 2019004144.0, 201...</td>\n",
        "      <td>9</td>\n",
-       "      <td>2.021006e+09</td>\n",
+       "      <td>2.021011e+09</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
@@ -5029,7 +4411,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019004130.0, 2019004126.0, 2019004144.0, 201...</td>\n",
        "      <td>9</td>\n",
-       "      <td>2.021006e+09</td>\n",
+       "      <td>2.021011e+09</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
@@ -5077,7 +4459,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019001923.0, 2019003253.0, 2019001755.0, 201...</td>\n",
        "      <td>5</td>\n",
-       "      <td>2.022001e+09</td>\n",
+       "      <td>2.019010e+09</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
@@ -5125,7 +4507,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019001923.0, 2019003253.0, 2019001755.0, 201...</td>\n",
        "      <td>5</td>\n",
-       "      <td>2.022001e+09</td>\n",
+       "      <td>2.019010e+09</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -5203,14 +4585,14 @@
        "4                      1.0  [2019001923.0, 2019003253.0, 2019001755.0, 201...   \n",
        "\n",
        "   age_group    nts_ind_id  \n",
-       "0          9  2.022000e+09  \n",
-       "1          9  2.021006e+09  \n",
-       "2          9  2.021006e+09  \n",
-       "3          5  2.022001e+09  \n",
-       "4          5  2.022001e+09  "
+       "0          9  2.019009e+09  \n",
+       "1          9  2.021011e+09  \n",
+       "2          9  2.021011e+09  \n",
+       "3          5  2.019010e+09  \n",
+       "4          5  2.019010e+09  "
       ]
      },
-     "execution_count": 60,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5228,7 +4610,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 50,
    "metadata": {},
    "outputs": [
     {
@@ -5346,7 +4728,7 @@
        "      <td>2.0</td>\n",
        "      <td>[2019000929.0, 2019003194.0, 2019003199.0, 201...</td>\n",
        "      <td>9</td>\n",
-       "      <td>2021007939.0</td>\n",
+       "      <td>2022001198.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>118</th>\n",
@@ -5394,7 +4776,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019001923.0, 2019003253.0, 2019001755.0, 201...</td>\n",
        "      <td>6</td>\n",
-       "      <td>2019013980.0</td>\n",
+       "      <td>2019007422.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>119</th>\n",
@@ -5442,7 +4824,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019001923.0, 2019003253.0, 2019001755.0, 201...</td>\n",
        "      <td>5</td>\n",
-       "      <td>2019013979.0</td>\n",
+       "      <td>2019007423.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>120</th>\n",
@@ -5490,7 +4872,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019001902.0, 2019004101.0, 2019004092.0, 201...</td>\n",
        "      <td>7</td>\n",
-       "      <td>2022005303.0</td>\n",
+       "      <td>2022006066.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>121</th>\n",
@@ -5538,7 +4920,7 @@
        "      <td>1.0</td>\n",
        "      <td>[2019001902.0, 2019004101.0, 2019004092.0, 201...</td>\n",
        "      <td>7</td>\n",
-       "      <td>2022005304.0</td>\n",
+       "      <td>2022006067.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>122</th>\n",
@@ -5586,7 +4968,7 @@
        "      <td>2.0</td>\n",
        "      <td>[2019000933.0, 2019001918.0, 2019001705.0, 201...</td>\n",
        "      <td>8</td>\n",
-       "      <td>2022007601.0</td>\n",
+       "      <td>2022004957.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -5674,15 +5056,15 @@
        "122                             3                     2.0   \n",
        "\n",
        "                                             nts_hh_id age_group    nts_ind_id  \n",
-       "117  [2019000929.0, 2019003194.0, 2019003199.0, 201...         9  2021007939.0  \n",
-       "118  [2019001923.0, 2019003253.0, 2019001755.0, 201...         6  2019013980.0  \n",
-       "119  [2019001923.0, 2019003253.0, 2019001755.0, 201...         5  2019013979.0  \n",
-       "120  [2019001902.0, 2019004101.0, 2019004092.0, 201...         7  2022005303.0  \n",
-       "121  [2019001902.0, 2019004101.0, 2019004092.0, 201...         7  2022005304.0  \n",
-       "122  [2019000933.0, 2019001918.0, 2019001705.0, 201...         8  2022007601.0  "
+       "117  [2019000929.0, 2019003194.0, 2019003199.0, 201...         9  2022001198.0  \n",
+       "118  [2019001923.0, 2019003253.0, 2019001755.0, 201...         6  2019007422.0  \n",
+       "119  [2019001923.0, 2019003253.0, 2019001755.0, 201...         5  2019007423.0  \n",
+       "120  [2019001902.0, 2019004101.0, 2019004092.0, 201...         7  2022006066.0  \n",
+       "121  [2019001902.0, 2019004101.0, 2019004092.0, 201...         7  2022006067.0  \n",
+       "122  [2019000933.0, 2019001918.0, 2019001705.0, 201...         8  2022004957.0  "
       ]
      },
-     "execution_count": 61,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5702,7 +5084,7 @@
     "\n",
     "    # get rows from spc and nts dfs that match spc_ind and nts_ind\n",
     "    spc_row = spc_edited.loc[spc_ind]\n",
-    "    nts_row = nts_individuals_filtered.loc[nts_ind]\n",
+    "    nts_row = nts_individuals.loc[nts_ind]\n",
     "\n",
     "    # convert to df and append\n",
     "    spc_rows.append(spc_row.to_frame().transpose())\n",
@@ -5710,14 +5092,14 @@
     "# convert individual dfs to one df\n",
     "spc_rows_df = pd.concat(spc_rows)\n",
     "nts_rows_df = pd.concat(nts_rows)\n",
-    "    \n",
+    "\n",
     "\n",
     "spc_rows_df\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 51,
    "metadata": {},
    "outputs": [
     {
@@ -6019,49 +5401,49 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>374350</th>\n",
-       "      <td>2.021008e+09</td>\n",
-       "      <td>2.021003e+09</td>\n",
-       "      <td>20.0</td>\n",
+       "      <th>375894</th>\n",
+       "      <td>2.022001e+09</td>\n",
+       "      <td>2.022001e+09</td>\n",
+       "      <td>18.0</td>\n",
        "      <td>9.0</td>\n",
-       "      <td>2.0</td>\n",
        "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>356778</th>\n",
-       "      <td>2.019014e+09</td>\n",
-       "      <td>2.019006e+09</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
+       "      <th>351919</th>\n",
+       "      <td>2.019007e+09</td>\n",
+       "      <td>2.019003e+09</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>9.0</td>\n",
        "      <td>1.0</td>\n",
        "      <td>2.0</td>\n",
        "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>356777</th>\n",
-       "      <td>2.019014e+09</td>\n",
-       "      <td>2.019006e+09</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2.0</td>\n",
+       "      <th>351920</th>\n",
+       "      <td>2.019007e+09</td>\n",
+       "      <td>2.019003e+09</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>9.0</td>\n",
        "      <td>1.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>3.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>375791</th>\n",
-       "      <td>2.022005e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
+       "      <th>380675</th>\n",
+       "      <td>2.022006e+09</td>\n",
+       "      <td>2.022003e+09</td>\n",
        "      <td>14.0</td>\n",
        "      <td>7.0</td>\n",
        "      <td>1.0</td>\n",
        "      <td>2.0</td>\n",
-       "      <td>3.0</td>\n",
+       "      <td>1.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>375792</th>\n",
-       "      <td>2.022005e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
+       "      <th>380676</th>\n",
+       "      <td>2.022006e+09</td>\n",
+       "      <td>2.022003e+09</td>\n",
        "      <td>14.0</td>\n",
        "      <td>7.0</td>\n",
        "      <td>2.0</td>\n",
@@ -6069,14 +5451,14 @@
        "      <td>3.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>377525</th>\n",
-       "      <td>2.022008e+09</td>\n",
-       "      <td>2.022003e+09</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
+       "      <th>378401</th>\n",
+       "      <td>2.022005e+09</td>\n",
+       "      <td>2.022002e+09</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>9.0</td>\n",
        "      <td>2.0</td>\n",
        "      <td>2.0</td>\n",
-       "      <td>3.0</td>\n",
+       "      <td>1.0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -6084,20 +5466,20 @@
       ],
       "text/plain": [
        "        IndividualID   HouseholdID  Age_B01ID  age_group  sex  OfPenAge_B01ID  \\\n",
-       "374350  2.021008e+09  2.021003e+09       20.0        9.0  2.0             1.0   \n",
-       "356778  2.019014e+09  2.019006e+09       15.0        8.0  1.0             2.0   \n",
-       "356777  2.019014e+09  2.019006e+09       15.0        8.0  2.0             2.0   \n",
-       "375791  2.022005e+09  2.022002e+09       14.0        7.0  1.0             2.0   \n",
-       "375792  2.022005e+09  2.022002e+09       14.0        7.0  2.0             2.0   \n",
-       "377525  2.022008e+09  2.022003e+09       15.0        8.0  2.0             2.0   \n",
+       "375894  2.022001e+09  2.022001e+09       18.0        9.0  1.0             1.0   \n",
+       "351919  2.019007e+09  2.019003e+09       16.0        9.0  1.0             2.0   \n",
+       "351920  2.019007e+09  2.019003e+09       16.0        9.0  1.0             2.0   \n",
+       "380675  2.022006e+09  2.022003e+09       14.0        7.0  1.0             2.0   \n",
+       "380676  2.022006e+09  2.022003e+09       14.0        7.0  2.0             2.0   \n",
+       "378401  2.022005e+09  2.022002e+09       17.0        9.0  2.0             2.0   \n",
        "\n",
        "        IndIncome2002_B02ID  \n",
-       "374350                  2.0  \n",
-       "356778                  1.0  \n",
-       "356777                  1.0  \n",
-       "375791                  3.0  \n",
-       "375792                  3.0  \n",
-       "377525                  3.0  "
+       "375894                  1.0  \n",
+       "351919                  1.0  \n",
+       "351920                  3.0  \n",
+       "380675                  1.0  \n",
+       "380676                  3.0  \n",
+       "378401                  1.0  "
       ]
      },
      "metadata": {},
@@ -6108,8 +5490,8 @@
     "from IPython.display import display\n",
     "\n",
     "display(spc_rows_df[['id', 'household', 'pwkstat', 'salary_yearly', 'salary_hourly', 'hid',\n",
-    "       'tenure', 'num_cars', 'sex', 'age_years','age_group', 'nssec8', 'salary_yearly_hh', \n",
-    "       'salary_yearly_hh_cat', 'is_adult','is_child', 'is_pension_age','pwkstat_FT_hh', 'pwkstat_PT_hh', \n",
+    "       'tenure', 'num_cars', 'sex', 'age_years','age_group', 'nssec8', 'salary_yearly_hh',\n",
+    "       'salary_yearly_hh_cat', 'is_adult','is_child', 'is_pension_age','pwkstat_FT_hh', 'pwkstat_PT_hh',\n",
     "       'pwkstat_NTS_match', 'Settlement2011EW_B03ID_spc',\n",
     "       'Settlement2011EW_B04ID_spc', 'Settlement2011EW_B03ID_spc_CD', 'Settlement2011EW_B04ID_spc_CD']])\n",
     "\n",
@@ -6140,20 +5522,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# iterate over all items in the matches_hh_level_sample_list and apply the match_individuals function to each \n",
+    "# iterate over all items in the matches_hh_level_sample_list and apply the match_individuals function to each\n",
     "\n",
     "matches_list_of_dict = []\n",
     "for i in range(len(matches_hh_level_sample_list)):\n",
     "    print(f'Processing item {i}')\n",
     "    # apply match_individuals function to each item in the list\n",
     "    matches_ind = match_individuals(\n",
-    "        df1 = spc_edited, \n",
-    "        df2 = nts_individuals_filtered,\n",
+    "        df1 = spc_edited,\n",
+    "        df2 = nts_individuals,\n",
     "        matching_columns = ['age_group', 'sex'],\n",
-    "        df1_id = 'hid', \n",
+    "        df1_id = 'hid',\n",
     "        df2_id = 'HouseholdID',\n",
     "        matches_hh = matches_hh_level_sample_list[i],\n",
-    "        show_progress= False)\n",
+    "        show_progress= True)\n",
     "\n",
     "    matches_list_of_dict.append(matches_ind)"
    ]
@@ -6171,7 +5553,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# random sample \n",
+    "# random sample\n",
     "with open('../data/interim/matching/matches_ind_level_categorical_random_sample.pkl', 'wb') as f:\n",
     "    pkl.dump(matches_ind, f)\n",
     "\n",
@@ -6190,7 +5572,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 54,
    "metadata": {},
    "outputs": [
     {
@@ -6600,13 +5982,13 @@
        "4659592  0.870854  1.071548  "
       ]
      },
-     "execution_count": 63,
+     "execution_count": 54,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "nts_trips_filtered.head(10)"
+    "nts_trips.head(10)"
    ]
   },
   {
@@ -6620,7 +6002,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 55,
    "metadata": {},
    "outputs": [
     {
@@ -7018,13 +6400,13 @@
        "4659592  1.071548  "
       ]
      },
-     "execution_count": 64,
+     "execution_count": 55,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "nts_trips_filtered = nts_trips_filtered.rename(\n",
+    "nts_trips = nts_trips.rename(\n",
     "    columns={  # rename data\n",
     "        \"JourSeq\": \"seq\",\n",
     "        \"TripOrigGOR_B02ID\": \"ozone\",\n",
@@ -7037,12 +6419,12 @@
     "    }\n",
     ")\n",
     "\n",
-    "nts_trips_filtered.head(10)"
+    "nts_trips.head(10)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -7093,16 +6475,16 @@
     "}\n",
     "\n",
     "\n",
-    "nts_trips_filtered[\"mode\"] = nts_trips_filtered[\"mode\"].map(mode_mapping)\n",
+    "nts_trips[\"mode\"] = nts_trips[\"mode\"].map(mode_mapping)\n",
     "\n",
-    "nts_trips_filtered[\"oact\"] = nts_trips_filtered[\"oact\"].map(purp_mapping)\n",
+    "nts_trips[\"oact\"] = nts_trips[\"oact\"].map(purp_mapping)\n",
     "\n",
-    "nts_trips_filtered[\"dact\"] = nts_trips_filtered[\"dact\"].map(purp_mapping)"
+    "nts_trips[\"dact\"] = nts_trips[\"dact\"].map(purp_mapping)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 57,
    "metadata": {},
    "outputs": [
     {
@@ -7500,34 +6882,20 @@
        "4659592  0.870854  1.071548  "
       ]
      },
-     "execution_count": 66,
+     "execution_count": 57,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "nts_trips_filtered.head(10)"
+    "nts_trips.head(10)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_375225/3883540079.py:5: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
-      "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
-      "\n",
-      "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
-      "\n",
-      "\n",
-      "  spc_edited_copy['nts_ind_id'].fillna(-1, inplace=True)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# create an independant copy of spc_edited\n",
     "spc_edited_copy = spc_edited.copy()\n",
@@ -7537,1032 +6905,17 @@
     "# convert the nts_ind_id column to int for merging\n",
     "spc_edited_copy['nts_ind_id'] = spc_edited_copy['nts_ind_id'].astype(int)\n",
     "\n",
-    "# merge the copy with nts_trips_filtered using IndividualID \n",
-    "spc_edited_copy = spc_edited_copy.merge(nts_trips_filtered, \n",
-    "                                        left_on='nts_ind_id', right_on='IndividualID', \n",
+    "# merge the copy with nts_trips using IndividualID\n",
+    "spc_edited_copy = spc_edited_copy.merge(nts_trips,\n",
+    "                                        left_on='nts_ind_id', right_on='IndividualID',\n",
     "                                        how='left')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>id</th>\n",
-       "      <th>household</th>\n",
-       "      <th>location</th>\n",
-       "      <th>pid_hs</th>\n",
-       "      <th>msoa</th>\n",
-       "      <th>oa</th>\n",
-       "      <th>members</th>\n",
-       "      <th>sic1d2007</th>\n",
-       "      <th>sic2d2007</th>\n",
-       "      <th>pwkstat</th>\n",
-       "      <th>salary_yearly</th>\n",
-       "      <th>salary_hourly</th>\n",
-       "      <th>hid</th>\n",
-       "      <th>accommodation_type</th>\n",
-       "      <th>communal_type</th>\n",
-       "      <th>num_rooms</th>\n",
-       "      <th>central_heat</th>\n",
-       "      <th>tenure</th>\n",
-       "      <th>num_cars</th>\n",
-       "      <th>sex</th>\n",
-       "      <th>age_years</th>\n",
-       "      <th>ethnicity</th>\n",
-       "      <th>nssec8</th>\n",
-       "      <th>salary_yearly_hh</th>\n",
-       "      <th>salary_yearly_hh_cat</th>\n",
-       "      <th>is_adult</th>\n",
-       "      <th>num_adults</th>\n",
-       "      <th>is_child</th>\n",
-       "      <th>num_children</th>\n",
-       "      <th>is_pension_age</th>\n",
-       "      <th>num_pension_age</th>\n",
-       "      <th>pwkstat_FT_hh</th>\n",
-       "      <th>pwkstat_PT_hh</th>\n",
-       "      <th>pwkstat_NTS_match</th>\n",
-       "      <th>OA11CD</th>\n",
-       "      <th>RUC11</th>\n",
-       "      <th>RUC11CD</th>\n",
-       "      <th>Settlement2011EW_B03ID_spc</th>\n",
-       "      <th>Settlement2011EW_B04ID_spc</th>\n",
-       "      <th>Settlement2011EW_B03ID_spc_CD</th>\n",
-       "      <th>Settlement2011EW_B04ID_spc_CD</th>\n",
-       "      <th>tenure_spc_for_matching</th>\n",
-       "      <th>nts_hh_id</th>\n",
-       "      <th>age_group</th>\n",
-       "      <th>nts_ind_id</th>\n",
-       "      <th>TripID</th>\n",
-       "      <th>DayID</th>\n",
-       "      <th>IndividualID</th>\n",
-       "      <th>HouseholdID</th>\n",
-       "      <th>PSUID</th>\n",
-       "      <th>PersNo</th>\n",
-       "      <th>TravDay</th>\n",
-       "      <th>seq</th>\n",
-       "      <th>ShortWalkTrip_B01ID</th>\n",
-       "      <th>NumStages</th>\n",
-       "      <th>MainMode_B03ID</th>\n",
-       "      <th>mode</th>\n",
-       "      <th>oact</th>\n",
-       "      <th>dact</th>\n",
-       "      <th>TripPurpose_B04ID</th>\n",
-       "      <th>tst</th>\n",
-       "      <th>tet</th>\n",
-       "      <th>TripDisIncSW</th>\n",
-       "      <th>TripDisExSW</th>\n",
-       "      <th>TripTotalTime</th>\n",
-       "      <th>TripTravTime</th>\n",
-       "      <th>ozone</th>\n",
-       "      <th>dzone</th>\n",
-       "      <th>W5</th>\n",
-       "      <th>W5xHH</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>car</td>\n",
-       "      <td>home</td>\n",
-       "      <td>visit</td>\n",
-       "      <td>7.0</td>\n",
-       "      <td>570.0</td>\n",
-       "      <td>585.0</td>\n",
-       "      <td>6.00</td>\n",
-       "      <td>6.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.609670</td>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>car</td>\n",
-       "      <td>visit</td>\n",
-       "      <td>home</td>\n",
-       "      <td>7.0</td>\n",
-       "      <td>660.0</td>\n",
-       "      <td>680.0</td>\n",
-       "      <td>6.00</td>\n",
-       "      <td>6.0</td>\n",
-       "      <td>20.0</td>\n",
-       "      <td>20.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.609670</td>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>walk</td>\n",
-       "      <td>home</td>\n",
-       "      <td>shop</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>900.0</td>\n",
-       "      <td>920.0</td>\n",
-       "      <td>0.75</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>20.0</td>\n",
-       "      <td>20.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.621353</td>\n",
-       "      <td>1.019163</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>walk</td>\n",
-       "      <td>shop</td>\n",
-       "      <td>home</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>935.0</td>\n",
-       "      <td>950.0</td>\n",
-       "      <td>0.75</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.621353</td>\n",
-       "      <td>1.019163</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>car</td>\n",
-       "      <td>home</td>\n",
-       "      <td>other</td>\n",
-       "      <td>7.0</td>\n",
-       "      <td>600.0</td>\n",
-       "      <td>615.0</td>\n",
-       "      <td>1.50</td>\n",
-       "      <td>1.5</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.654143</td>\n",
-       "      <td>1.072946</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>walk</td>\n",
-       "      <td>other</td>\n",
-       "      <td>other</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>615.0</td>\n",
-       "      <td>652.0</td>\n",
-       "      <td>1.00</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>37.0</td>\n",
-       "      <td>37.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.654143</td>\n",
-       "      <td>1.072946</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>walk</td>\n",
-       "      <td>other</td>\n",
-       "      <td>other</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>652.0</td>\n",
-       "      <td>690.0</td>\n",
-       "      <td>1.00</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>38.0</td>\n",
-       "      <td>38.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.654143</td>\n",
-       "      <td>1.072946</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>car</td>\n",
-       "      <td>other</td>\n",
-       "      <td>home</td>\n",
-       "      <td>7.0</td>\n",
-       "      <td>690.0</td>\n",
-       "      <td>705.0</td>\n",
-       "      <td>1.50</td>\n",
-       "      <td>1.5</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.654143</td>\n",
-       "      <td>1.072946</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>car</td>\n",
-       "      <td>home</td>\n",
-       "      <td>other</td>\n",
-       "      <td>7.0</td>\n",
-       "      <td>1095.0</td>\n",
-       "      <td>1110.0</td>\n",
-       "      <td>1.50</td>\n",
-       "      <td>1.5</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.609670</td>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9</th>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>{'x': -1.7892179489135742, 'y': 53.91915130615...</td>\n",
-       "      <td>2905399</td>\n",
-       "      <td>E02002183</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>[0]</td>\n",
-       "      <td>J</td>\n",
-       "      <td>58.0</td>\n",
-       "      <td>6</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>E02002183_0001</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1</td>\n",
-       "      <td>86</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>E00053954</td>\n",
-       "      <td>Urban city and town</td>\n",
-       "      <td>C1</td>\n",
-       "      <td>Urban</td>\n",
-       "      <td>Urban City and Town</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>[2019004064.0, 2019000229.0, 2019002914.0, 201...</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2022000302</td>\n",
-       "      <td>2.022004e+09</td>\n",
-       "      <td>2.022002e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>2.022000e+09</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>6.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>car</td>\n",
-       "      <td>other</td>\n",
-       "      <td>home</td>\n",
-       "      <td>7.0</td>\n",
-       "      <td>1305.0</td>\n",
-       "      <td>1320.0</td>\n",
-       "      <td>1.50</td>\n",
-       "      <td>1.5</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>15.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>8.0</td>\n",
-       "      <td>0.609670</td>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   id  household                                           location   pid_hs  \\\n",
-       "0   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "1   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "2   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "3   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "4   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "5   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "6   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "7   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "8   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "9   0          0  {'x': -1.7892179489135742, 'y': 53.91915130615...  2905399   \n",
-       "\n",
-       "        msoa         oa members sic1d2007  sic2d2007  pwkstat  salary_yearly  \\\n",
-       "0  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "1  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "2  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "3  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "4  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "5  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "6  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "7  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "8  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "9  E02002183  E00053954     [0]         J       58.0        6            NaN   \n",
-       "\n",
-       "   salary_hourly             hid  accommodation_type  communal_type  \\\n",
-       "0            NaN  E02002183_0001                 1.0            NaN   \n",
-       "1            NaN  E02002183_0001                 1.0            NaN   \n",
-       "2            NaN  E02002183_0001                 1.0            NaN   \n",
-       "3            NaN  E02002183_0001                 1.0            NaN   \n",
-       "4            NaN  E02002183_0001                 1.0            NaN   \n",
-       "5            NaN  E02002183_0001                 1.0            NaN   \n",
-       "6            NaN  E02002183_0001                 1.0            NaN   \n",
-       "7            NaN  E02002183_0001                 1.0            NaN   \n",
-       "8            NaN  E02002183_0001                 1.0            NaN   \n",
-       "9            NaN  E02002183_0001                 1.0            NaN   \n",
-       "\n",
-       "   num_rooms  central_heat  tenure  num_cars  sex  age_years  ethnicity  \\\n",
-       "0        2.0          True     2.0         2    1         86          1   \n",
-       "1        2.0          True     2.0         2    1         86          1   \n",
-       "2        2.0          True     2.0         2    1         86          1   \n",
-       "3        2.0          True     2.0         2    1         86          1   \n",
-       "4        2.0          True     2.0         2    1         86          1   \n",
-       "5        2.0          True     2.0         2    1         86          1   \n",
-       "6        2.0          True     2.0         2    1         86          1   \n",
-       "7        2.0          True     2.0         2    1         86          1   \n",
-       "8        2.0          True     2.0         2    1         86          1   \n",
-       "9        2.0          True     2.0         2    1         86          1   \n",
-       "\n",
-       "   nssec8  salary_yearly_hh  salary_yearly_hh_cat  is_adult  num_adults  \\\n",
-       "0     1.0               0.0                     1         1           1   \n",
-       "1     1.0               0.0                     1         1           1   \n",
-       "2     1.0               0.0                     1         1           1   \n",
-       "3     1.0               0.0                     1         1           1   \n",
-       "4     1.0               0.0                     1         1           1   \n",
-       "5     1.0               0.0                     1         1           1   \n",
-       "6     1.0               0.0                     1         1           1   \n",
-       "7     1.0               0.0                     1         1           1   \n",
-       "8     1.0               0.0                     1         1           1   \n",
-       "9     1.0               0.0                     1         1           1   \n",
-       "\n",
-       "   is_child  num_children  is_pension_age  num_pension_age  pwkstat_FT_hh  \\\n",
-       "0         0             0               1                1              0   \n",
-       "1         0             0               1                1              0   \n",
-       "2         0             0               1                1              0   \n",
-       "3         0             0               1                1              0   \n",
-       "4         0             0               1                1              0   \n",
-       "5         0             0               1                1              0   \n",
-       "6         0             0               1                1              0   \n",
-       "7         0             0               1                1              0   \n",
-       "8         0             0               1                1              0   \n",
-       "9         0             0               1                1              0   \n",
-       "\n",
-       "   pwkstat_PT_hh  pwkstat_NTS_match     OA11CD                RUC11 RUC11CD  \\\n",
-       "0              0                  1  E00053954  Urban city and town      C1   \n",
-       "1              0                  1  E00053954  Urban city and town      C1   \n",
-       "2              0                  1  E00053954  Urban city and town      C1   \n",
-       "3              0                  1  E00053954  Urban city and town      C1   \n",
-       "4              0                  1  E00053954  Urban city and town      C1   \n",
-       "5              0                  1  E00053954  Urban city and town      C1   \n",
-       "6              0                  1  E00053954  Urban city and town      C1   \n",
-       "7              0                  1  E00053954  Urban city and town      C1   \n",
-       "8              0                  1  E00053954  Urban city and town      C1   \n",
-       "9              0                  1  E00053954  Urban city and town      C1   \n",
-       "\n",
-       "  Settlement2011EW_B03ID_spc Settlement2011EW_B04ID_spc  \\\n",
-       "0                      Urban        Urban City and Town   \n",
-       "1                      Urban        Urban City and Town   \n",
-       "2                      Urban        Urban City and Town   \n",
-       "3                      Urban        Urban City and Town   \n",
-       "4                      Urban        Urban City and Town   \n",
-       "5                      Urban        Urban City and Town   \n",
-       "6                      Urban        Urban City and Town   \n",
-       "7                      Urban        Urban City and Town   \n",
-       "8                      Urban        Urban City and Town   \n",
-       "9                      Urban        Urban City and Town   \n",
-       "\n",
-       "   Settlement2011EW_B03ID_spc_CD  Settlement2011EW_B04ID_spc_CD  \\\n",
-       "0                              1                              2   \n",
-       "1                              1                              2   \n",
-       "2                              1                              2   \n",
-       "3                              1                              2   \n",
-       "4                              1                              2   \n",
-       "5                              1                              2   \n",
-       "6                              1                              2   \n",
-       "7                              1                              2   \n",
-       "8                              1                              2   \n",
-       "9                              1                              2   \n",
-       "\n",
-       "   tenure_spc_for_matching                                          nts_hh_id  \\\n",
-       "0                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "1                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "2                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "3                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "4                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "5                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "6                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "7                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "8                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "9                      1.0  [2019004064.0, 2019000229.0, 2019002914.0, 201...   \n",
-       "\n",
-       "   age_group  nts_ind_id        TripID         DayID  IndividualID  \\\n",
-       "0          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "1          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "2          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "3          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "4          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "5          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "6          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "7          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "8          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "9          9  2022000302  2.022004e+09  2.022002e+09  2.022000e+09   \n",
-       "\n",
-       "    HouseholdID         PSUID  PersNo  TravDay  seq  ShortWalkTrip_B01ID  \\\n",
-       "0  2.022000e+09  2.022000e+09     1.0      1.0  1.0                  2.0   \n",
-       "1  2.022000e+09  2.022000e+09     1.0      1.0  2.0                  2.0   \n",
-       "2  2.022000e+09  2.022000e+09     1.0      1.0  3.0                  1.0   \n",
-       "3  2.022000e+09  2.022000e+09     1.0      1.0  4.0                  1.0   \n",
-       "4  2.022000e+09  2.022000e+09     1.0      2.0  1.0                  2.0   \n",
-       "5  2.022000e+09  2.022000e+09     1.0      2.0  2.0                  2.0   \n",
-       "6  2.022000e+09  2.022000e+09     1.0      2.0  3.0                  2.0   \n",
-       "7  2.022000e+09  2.022000e+09     1.0      2.0  4.0                  2.0   \n",
-       "8  2.022000e+09  2.022000e+09     1.0      2.0  5.0                  2.0   \n",
-       "9  2.022000e+09  2.022000e+09     1.0      2.0  6.0                  2.0   \n",
-       "\n",
-       "   NumStages  MainMode_B03ID  mode   oact   dact  TripPurpose_B04ID     tst  \\\n",
-       "0        1.0             5.0   car   home  visit                7.0   570.0   \n",
-       "1        1.0             5.0   car  visit   home                7.0   660.0   \n",
-       "2        1.0             1.0  walk   home   shop                4.0   900.0   \n",
-       "3        1.0             1.0  walk   shop   home                4.0   935.0   \n",
-       "4        1.0             8.0   car   home  other                7.0   600.0   \n",
-       "5        1.0             2.0  walk  other  other                8.0   615.0   \n",
-       "6        1.0             2.0  walk  other  other                8.0   652.0   \n",
-       "7        1.0             8.0   car  other   home                7.0   690.0   \n",
-       "8        1.0             5.0   car   home  other                7.0  1095.0   \n",
-       "9        1.0             5.0   car  other   home                7.0  1305.0   \n",
-       "\n",
-       "      tet  TripDisIncSW  TripDisExSW  TripTotalTime  TripTravTime  ozone  \\\n",
-       "0   585.0          6.00          6.0           15.0          15.0    8.0   \n",
-       "1   680.0          6.00          6.0           20.0          20.0    8.0   \n",
-       "2   920.0          0.75          0.0           20.0          20.0    8.0   \n",
-       "3   950.0          0.75          0.0           15.0          15.0    8.0   \n",
-       "4   615.0          1.50          1.5           15.0          15.0    8.0   \n",
-       "5   652.0          1.00          1.0           37.0          37.0    8.0   \n",
-       "6   690.0          1.00          1.0           38.0          38.0    8.0   \n",
-       "7   705.0          1.50          1.5           15.0          15.0    8.0   \n",
-       "8  1110.0          1.50          1.5           15.0          15.0    8.0   \n",
-       "9  1320.0          1.50          1.5           15.0          15.0    8.0   \n",
-       "\n",
-       "   dzone        W5     W5xHH  \n",
-       "0    8.0  0.609670  1.000000  \n",
-       "1    8.0  0.609670  1.000000  \n",
-       "2    8.0  0.621353  1.019163  \n",
-       "3    8.0  0.621353  1.019163  \n",
-       "4    8.0  0.654143  1.072946  \n",
-       "5    8.0  0.654143  1.072946  \n",
-       "6    8.0  0.654143  1.072946  \n",
-       "7    8.0  0.654143  1.072946  \n",
-       "8    8.0  0.609670  1.000000  \n",
-       "9    8.0  0.609670  1.000000  "
-      ]
-     },
-     "execution_count": 68,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "spc_edited_copy.head(10)"
    ]
diff --git a/src/acbm/matching.py b/src/acbm/matching.py
index 4516954..eb233d9 100644
--- a/src/acbm/matching.py
+++ b/src/acbm/matching.py
@@ -2,6 +2,82 @@
 import pandas as pd
 from sklearn.neighbors import NearestNeighbors
 
+# categorical (exact) matching
+
+
+def match_categorical(
+    df_pop: pd.DataFrame,
+    df_pop_cols: list,
+    df_pop_id: str,
+    df_sample: pd.DataFrame,
+    df_sample_cols: list,
+    df_sample_id: str,
+    chunk_size: int,
+    show_progress=True,
+) -> dict:
+    """
+    Match the rows in two DataFrames based on specified columns.
+    The function matches the rows in df_pop to the rows in df_sample based
+    on the columns in df_pop_cols and df_sample_cols. The matching is done
+    in chunks to avoid memory issues.
+
+    Parameters
+    ----------
+    df_pop: pandas DataFrame
+        The DataFrame to be matched on
+    df_pop_cols: list
+        The columns to be used for matching in df_pop
+    df_pop_id: str
+        The column name that contains the unique identifier in df_pop
+        It is the key in the final dictionary
+    df_sample: pandas DataFrame
+        The DataFrame to be matched with
+    df_sample_cols: list
+        The columns to be used for matching in df_sample
+    df_sample_id: str
+        The column name that contains the unique identifier in df_sample
+        It is the value in the final dictionary
+    chunk_size: int
+        The number of rows to process at a time
+    show_progress: bool
+        Whether to print the progress of the matching to the console
+
+    Returns
+    -------
+    results: dict
+        A dictionary with the matched rows {df_pop_id: [df_sample_id]}
+
+    """
+
+    # dictionary to store results
+    results = {}
+
+    # loop over the df_pop DataFrame in chunks
+    for i in range(0, df_pop.shape[0], chunk_size):
+        # filter the df_pop DataFrame to the current chunk
+        j = i + chunk_size
+        if show_progress:
+            print("matching rows ", i, "to", j, " out of ", df_pop.shape[0])
+
+        df_pop_chunk = df_pop.iloc[i:j]
+
+        # merge the df_pop_chunk with the df_sample DataFrame
+        df_matched_chunk = df_pop_chunk.merge(
+            df_sample, left_on=df_pop_cols, right_on=df_sample_cols, how="left"
+        )
+
+        # convert the matched df to a dictionary:
+        df_matched_dict_i = (
+            df_matched_chunk.groupby(df_pop_id)[df_sample_id].apply(list).to_dict()
+        )
+
+        # add the dictionary to results{}
+        results.update(df_matched_dict_i)
+    return results
+
+
+# propensity score matching
+
 
 def match_psm(df1: pd.DataFrame, df2: pd.DataFrame, matching_columns: list) -> dict:
     """
@@ -58,6 +134,8 @@ def match_psm(df1: pd.DataFrame, df2: pd.DataFrame, matching_columns: list) -> d
     return matches
 
 
+# TODO: parallelize the matching process. See this stackoverflow suggestion
+# for iterating over dict keys https://stackoverflow.com/a/30075659
 def match_individuals(
     df1: pd.DataFrame,
     df2: pd.DataFrame,
@@ -97,7 +175,7 @@ def match_individuals(
     """
     # Initialize an empty dic to store the matches
     matches = {}
-    # Remove all unmateched households 
+    # Remove all unmateched households
     matches_hh = {key: value for key, value in matches_hh.items() if not pd.isna(value)}
 
     # loop over all rows in the matches_hh dictionary