diff --git a/src/analysis/surival_01.ipynb b/src/analysis/surival_01.ipynb
index 0111215..4cef3db 100644
--- a/src/analysis/surival_01.ipynb
+++ b/src/analysis/surival_01.ipynb
@@ -75,13 +75,6 @@
     "# df_tooth_surface_procedures.head() # good"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -111,13 +104,6 @@
     "len(df_patients_teeth) # 1,231,726"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 8,
@@ -159,13 +145,6 @@
     "plt.show()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -234,225 +213,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 198,
    "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>tooth_id</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>tooth_num</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>953</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2098</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1831</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1373</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>1226</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>624</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>842</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>740</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9</th>\n",
-       "      <td>772</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>817</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>603</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>12</th>\n",
-       "      <td>1226</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>1354</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>1819</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>15</th>\n",
-       "      <td>2275</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>16</th>\n",
-       "      <td>962</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>17</th>\n",
-       "      <td>898</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18</th>\n",
-       "      <td>2055</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19</th>\n",
-       "      <td>1941</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>20</th>\n",
-       "      <td>1022</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21</th>\n",
-       "      <td>551</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>22</th>\n",
-       "      <td>236</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>23</th>\n",
-       "      <td>321</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>24</th>\n",
-       "      <td>336</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25</th>\n",
-       "      <td>368</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>26</th>\n",
-       "      <td>316</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>27</th>\n",
-       "      <td>240</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>28</th>\n",
-       "      <td>598</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>29</th>\n",
-       "      <td>1051</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>30</th>\n",
-       "      <td>1968</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31</th>\n",
-       "      <td>2186</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>32</th>\n",
-       "      <td>875</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "           tooth_id\n",
-       "tooth_num          \n",
-       "1               953\n",
-       "2              2098\n",
-       "3              1831\n",
-       "4              1373\n",
-       "5              1226\n",
-       "6               624\n",
-       "7               842\n",
-       "8               740\n",
-       "9               772\n",
-       "10              817\n",
-       "11              603\n",
-       "12             1226\n",
-       "13             1354\n",
-       "14             1819\n",
-       "15             2275\n",
-       "16              962\n",
-       "17              898\n",
-       "18             2055\n",
-       "19             1941\n",
-       "20             1022\n",
-       "21              551\n",
-       "22              236\n",
-       "23              321\n",
-       "24              336\n",
-       "25              368\n",
-       "26              316\n",
-       "27              240\n",
-       "28              598\n",
-       "29             1051\n",
-       "30             1968\n",
-       "31             2186\n",
-       "32              875"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "df_extracted = df_obs[df_obs.extract_date.notnull()][['tooth_id','tooth_num']]\n",
     "# df_extracted = df_obs[df_obs.extract_date.notna()][['tooth_id','tooth_num']]\n",
     "df_extracted.tooth_num = pds.to_numeric(df_extracted.tooth_num)\n",
     "df_extracted.drop_duplicates(inplace=True)\n",
-    "df_extracted.head()\n",
-    "df_extracted.groupby('tooth_num').count()\n",
+    "# df_extracted.head()\n",
+    "# df_extracted.groupby('tooth_num').count()\n",
     "# len(df_extracted) # isnull -> 1,617,783; isna -> 1,617,783; notnull -> 41,331; notna -> 41,331"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 199,
    "metadata": {},
    "outputs": [
     {
@@ -472,48 +248,6 @@
       "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
       "  # Remove the CWD from sys.path while we load stuff.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "15    2275\n",
-       "31    2186\n",
-       "2     2098\n",
-       "18    2055\n",
-       "30    1968\n",
-       "19    1941\n",
-       "3     1831\n",
-       "14    1819\n",
-       "4     1373\n",
-       "13    1354\n",
-       "5     1226\n",
-       "12    1226\n",
-       "29    1051\n",
-       "20    1022\n",
-       "16     962\n",
-       "1      953\n",
-       "17     898\n",
-       "32     875\n",
-       "7      842\n",
-       "10     817\n",
-       "9      772\n",
-       "8      740\n",
-       "6      624\n",
-       "11     603\n",
-       "28     598\n",
-       "21     551\n",
-       "25     368\n",
-       "24     336\n",
-       "23     321\n",
-       "26     316\n",
-       "27     240\n",
-       "22     236\n",
-       "Name: tooth_num, dtype: int64"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -527,7 +261,7 @@
     "print(len(temp3))\n",
     "# temp3.groupby('tooth_num').size()\n",
     "temp3.drop_duplicates(inplace=True)\n",
-    "temp3.tooth_num.value_counts()\n",
+    "# temp3.tooth_num.value_counts()\n",
     "# print(len(temp3))\n",
     "# temp2.head()\n",
     "# temp3.groupby('tooth_num').size()\n",
@@ -539,100 +273,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 200,
    "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>tooth_num</th>\n",
-       "      <th>tooth_id</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>275</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_1_1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1084</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_149_1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8836</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_2946_1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13571</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_3302_1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>15481</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_3046_1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "      tooth_num      tooth_id\n",
-       "275           1     A_1_1_1_1\n",
-       "1084          1   A_1_1_149_1\n",
-       "8836          1  A_1_1_2946_1\n",
-       "13571         1  A_1_1_3302_1\n",
-       "15481         1  A_1_1_3046_1"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "temp4 = temp3.query(\"tooth_num == '1'\")\n",
-    "temp4.head()"
+    "# temp4 = temp3.query(\"tooth_num == '1'\")\n",
+    "# temp4.head()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 201,
    "metadata": {},
    "outputs": [
     {
@@ -642,7 +293,7 @@
       "Index(['practice', 'patient_id', 'gender', 'dob', 'first_visit', 'last_visit',\n",
       "       'tooth_id', 'tooth_num', 'first_PCR', 'first_RCT', 'extract_date',\n",
       "       'missing_date', 'event_id', 'event_name', 'event_date', 'ada_code', 'm',\n",
-      "       'o', 'd', 'b', 'l', 'f', 'i'],\n",
+      "       'o', 'd', 'b', 'l', 'f', 'i', 'patient_age', 'missing_flag'],\n",
       "      dtype='object')\n"
      ]
     }
@@ -726,27 +377,6 @@
     "# df_demographics.head()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 23,
@@ -858,161 +488,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 202,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/usr/local/anaconda3/lib/python3.6/site-packages/pandas/core/generic.py:4405: SettingWithCopyWarning: \n",
-      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
-      "Try using .loc[row_indexer,col_indexer] = value instead\n",
-      "\n",
-      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
-      "  self[name] = value\n"
-     ]
-    },
-    {
-     "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>tooth_id</th>\n",
-       "      <th>tooth_num</th>\n",
-       "      <th>ada_code</th>\n",
-       "      <th>event_name</th>\n",
-       "      <th>m</th>\n",
-       "      <th>o</th>\n",
-       "      <th>d</th>\n",
-       "      <th>b</th>\n",
-       "      <th>l</th>\n",
-       "      <th>f</th>\n",
-       "      <th>i</th>\n",
-       "      <th>num_restored_surfaces</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>A_1_1_155_15</td>\n",
-       "      <td>15</td>\n",
-       "      <td>D2150</td>\n",
-       "      <td>amalgam filling restoration procedure</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>A_1_1_155_31</td>\n",
-       "      <td>31</td>\n",
-       "      <td>D2391</td>\n",
-       "      <td>resin filling restoration procedure</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18</th>\n",
-       "      <td>A_1_1_155_30</td>\n",
-       "      <td>30</td>\n",
-       "      <td>D2391</td>\n",
-       "      <td>resin filling restoration procedure</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>26</th>\n",
-       "      <td>A_1_1_155_20</td>\n",
-       "      <td>20</td>\n",
-       "      <td>D2150</td>\n",
-       "      <td>amalgam filling restoration procedure</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>27</th>\n",
-       "      <td>A_1_1_155_8</td>\n",
-       "      <td>8</td>\n",
-       "      <td>D2330</td>\n",
-       "      <td>resin filling restoration procedure</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>1.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "        tooth_id tooth_num ada_code                             event_name  \\\n",
-       "10  A_1_1_155_15        15    D2150  amalgam filling restoration procedure   \n",
-       "14  A_1_1_155_31        31    D2391    resin filling restoration procedure   \n",
-       "18  A_1_1_155_30        30    D2391    resin filling restoration procedure   \n",
-       "26  A_1_1_155_20        20    D2150  amalgam filling restoration procedure   \n",
-       "27   A_1_1_155_8         8    D2330    resin filling restoration procedure   \n",
-       "\n",
-       "      m    o    d    b    l    f    i  num_restored_surfaces  \n",
-       "10  1.0  1.0  0.0  0.0  0.0  0.0  0.0                    2.0  \n",
-       "14  0.0  1.0  0.0  0.0  0.0  0.0  0.0                    1.0  \n",
-       "18  0.0  1.0  0.0  0.0  0.0  0.0  0.0                    1.0  \n",
-       "26  0.0  1.0  1.0  0.0  0.0  0.0  0.0                    2.0  \n",
-       "27  0.0  0.0  0.0  0.0  0.0  0.0  1.0                    1.0  "
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "df_fillings.num_restored_surfaces = pds.to_numeric(df_fillings.num_restored_surfaces)\n",
     "df_fillings = df_fillings[df_fillings.num_restored_surfaces > 0]\n",
-    "df_fillings.head()"
+    "# df_fillings.head()"
    ]
   },
   {
@@ -1026,53 +508,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 204,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "tooth_num\n",
-       "1      5557\n",
-       "2     70930\n",
-       "3     83304\n",
-       "4     47524\n",
-       "5     41943\n",
-       "6     26819\n",
-       "7     31896\n",
-       "8     41835\n",
-       "9     40930\n",
-       "10    31771\n",
-       "11    27314\n",
-       "12    41213\n",
-       "13    45505\n",
-       "14    82109\n",
-       "15    73201\n",
-       "16     5720\n",
-       "17     8883\n",
-       "18    77981\n",
-       "19    80683\n",
-       "20    44953\n",
-       "21    27576\n",
-       "22    13604\n",
-       "23    10007\n",
-       "24    12255\n",
-       "25    11986\n",
-       "26     9916\n",
-       "27    13670\n",
-       "28    27844\n",
-       "29    45195\n",
-       "30    82534\n",
-       "31    77107\n",
-       "32     8840\n",
-       "Name: tooth_num, dtype: int64"
-      ]
-     },
-     "execution_count": 29,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# find number of procedures per tooth\n",
     "# tooth_counts = pds.DataFrame(df_fillings.groupby('tooth_num')['tooth_num'].count())\n",
@@ -1081,12 +519,12 @@
     "tooth_counts.columns = ['count']\n",
     "tooth_counts.index = pds.to_numeric(tooth_counts.index)\n",
     "tooth_counts.sort_index(inplace=True) # sort data by tooth number 1 -> 32\n",
-    "tooth_counts"
+    "# tooth_counts"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 205,
    "metadata": {},
    "outputs": [
     {
@@ -1202,97 +640,22 @@
     "# note the use of engine=\"python\"\n",
     "# df_extracted = df_obs[df_obs.extract_date.notnull()]\n",
     "df_extracted = df_obs[~np.isnat(df_obs.extract_date)][['tooth_id','tooth_num','extract_date']]\n",
-    "# df_extracted = df_obs[~np.isnat(df_obs.extract_date)][['tooth_id','tooth_num']]\n",
-    "df_extracted.tooth_num = pds.to_numeric(df_extracted.tooth_num)\n",
-    "df_extracted.drop_duplicates(inplace=True)\n",
-    "df_extracted.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "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>tooth_num</th>\n",
-       "      <th>tooth_id</th>\n",
-       "      <th>extract_date</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_1_1</td>\n",
-       "      <td>2003-05-16T00:00:00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_2946_1</td>\n",
-       "      <td>2012-01-30T00:00:00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_149_1</td>\n",
-       "      <td>2015-01-06T00:00:00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_3046_1</td>\n",
-       "      <td>2014-11-26T00:00:00</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1</td>\n",
-       "      <td>A_1_1_3302_1</td>\n",
-       "      <td>2010-08-30T00:00:00</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   tooth_num      tooth_id         extract_date\n",
-       "0          1     A_1_1_1_1  2003-05-16T00:00:00\n",
-       "1          1  A_1_1_2946_1  2012-01-30T00:00:00\n",
-       "2          1   A_1_1_149_1  2015-01-06T00:00:00\n",
-       "3          1  A_1_1_3046_1  2014-11-26T00:00:00\n",
-       "4          1  A_1_1_3302_1  2010-08-30T00:00:00"
-      ]
-     },
-     "execution_count": 32,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+    "# df_extracted = df_obs[~np.isnat(df_obs.extract_date)][['tooth_id','tooth_num']]\n",
+    "df_extracted.tooth_num = pds.to_numeric(df_extracted.tooth_num)\n",
+    "df_extracted.drop_duplicates(inplace=True)\n",
+    "df_extracted.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 206,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# query results from triplestore\n",
     "df_tooth1 = pds.read_csv('extracted_tooth_1_no_es.csv')\n",
     "df_tooth1.drop_duplicates(inplace=True)\n",
-    "df_tooth1.head()"
+    "# df_tooth1.head()"
    ]
   },
   {
@@ -1318,7 +681,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 207,
    "metadata": {},
    "outputs": [
     {
@@ -1328,80 +691,6 @@
       "/usr/local/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:3: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
       "  This is separate from the ipykernel package so we can avoid doing imports until\n"
      ]
-    },
-    {
-     "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>tooth_id</th>\n",
-       "      <th>tooth_num</th>\n",
-       "      <th>extract_date</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>275</th>\n",
-       "      <td>A_1_1_1_1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2003-05-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1084</th>\n",
-       "      <td>A_1_1_149_1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2015-01-06</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8836</th>\n",
-       "      <td>A_1_1_2946_1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2012-01-30</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13571</th>\n",
-       "      <td>A_1_1_3302_1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2010-08-30</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>15481</th>\n",
-       "      <td>A_1_1_3046_1</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2014-11-26</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "           tooth_id tooth_num extract_date\n",
-       "275       A_1_1_1_1         1   2003-05-16\n",
-       "1084    A_1_1_149_1         1   2015-01-06\n",
-       "8836   A_1_1_2946_1         1   2012-01-30\n",
-       "13571  A_1_1_3302_1         1   2010-08-30\n",
-       "15481  A_1_1_3046_1         1   2014-11-26"
-      ]
-     },
-     "execution_count": 34,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -1409,7 +698,7 @@
     "temp = df_obs.query(\"tooth_num == '1'\")\n",
     "extract = temp[df_obs.extract_date.notnull()][['tooth_id','tooth_num', 'extract_date']]\n",
     "extract.drop_duplicates(inplace=True)\n",
-    "extract.head()"
+    "# extract.head()"
    ]
   },
   {
@@ -1770,20 +1059,6 @@
     "df_missing[df_missing.missing_flag == 0].head() # should be none ..."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 49,
@@ -1839,7 +1114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 208,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1852,7 +1127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 210,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1877,7 +1152,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 211,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1895,7 +1170,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 90,
+   "execution_count": 212,
    "metadata": {},
    "outputs": [
     {
@@ -1925,7 +1200,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 213,
    "metadata": {},
    "outputs": [
     {
@@ -1958,7 +1233,129 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 95,
+   "execution_count": 188,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# add some meta information about teeth\n",
+    "# tooth_info = pds.read_csv(\"tooth_numbers_and_labels.csv\")\n",
+    "# tooth_info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 190,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# add meta info about tooth type and region in mouth\n",
+    "# posterior_tooth = [1, 2, 3, 4, 5, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 28, 29, 30, 31, 32]\n",
+    "# anterior_tooth = [6, 7, 8, 9, 10, 11, 22, 23, 24, 25, 26, 27]\n",
+    "\n",
+    "# tooth_info['molar'] =  tooth_info.tooth_label.map(lambda label: 1 if \" molar \" in label else 0)\n",
+    "# tooth_info['premolar'] =  tooth_info.tooth_label.map(lambda label: 1 if \" premolar \" in label else 0)\n",
+    "# tooth_info['canine'] =  tooth_info.tooth_label.map(lambda label: 1 if \" canine \" in label else 0)\n",
+    "# tooth_info['incisor'] =  tooth_info.tooth_label.map(lambda label: 1 if \" incisor \" in label else 0)\n",
+    "# tooth_info['upper'] =  tooth_info.tooth_label.map(lambda label: 1 if \" upper \" in label else 0)\n",
+    "# tooth_info['lower'] =  tooth_info.tooth_label.map(lambda label: 1 if \" lower \" in label else 0)\n",
+    "# tooth_info['right'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Right \" in label else 0)\n",
+    "# tooth_info['right upper'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Right upper \" in label else 0)\n",
+    "# tooth_info['right lower'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Right lower \" in label else 0)\n",
+    "# tooth_info['left'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Left \" in label else 0)\n",
+    "# tooth_info['left upper'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Left upper \" in label else 0)\n",
+    "# tooth_info['left lower'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Left lower \" in label else 0)\n",
+    "# tooth_info['posterior'] = tooth_info.tooth.map(lambda tooth: 1 if tooth in posterior_tooth else 0)\n",
+    "# tooth_info['anterior'] = tooth_info.tooth.map(lambda tooth: 1 if tooth in anterior_tooth else 0)\n",
+    "# tooth_info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 214,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# tooth_info.to_csv(\"tooth_meta_info.csv\", index=False) # save tooth info dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 192,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# tooth_info = pds.read_csv(\"tooth_meta_info.csv\", index_col='tooth')\n",
+    "# tooth_info = pds.read_csv(\"tooth_meta_info.csv\")\n",
+    "# tooth_info.set_index('tooth', inplace=True)\n",
+    "# tooth_info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 222,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# restored_surface_counts.reset_index(inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 228,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# restored_surface_counts.drop(columns='index', inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 231,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# restored_surface_counts.columns.name = None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 235,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# restored_surface_counts.tooth_num = restored_surface_counts.tooth_num.astype(int)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 239,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# restored_surface_counts = restored_surface_counts.merge(tooth_info, left_on='tooth_num', right_on='tooth', how='left')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 241,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# restored_surface_counts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 245,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "incisor_surface_counts = restored_surface_counts.query('incisor == 1')[['tooth_num', '1', '2', '3', '4', '5', '6']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 249,
    "metadata": {},
    "outputs": [
     {
@@ -1982,256 +1379,161 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>tooth</th>\n",
-       "      <th>tooth_label</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>Right upper third secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
+       "      <th>tooth_num</th>\n",
        "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>Right upper second secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>3</td>\n",
-       "      <td>Right upper first secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>4</td>\n",
-       "      <td>Right upper second secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>5</td>\n",
-       "      <td>Right upper first secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
        "      <th>5</th>\n",
-       "      <td>6</td>\n",
-       "      <td>Right upper secondary canine tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
        "      <th>6</th>\n",
-       "      <td>7</td>\n",
-       "      <td>Right upper lateral secondary incisor tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>8</td>\n",
-       "      <td>Right upper central secondary incisor tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>9</td>\n",
-       "      <td>Left upper central secondary incisor tooth</td>\n",
        "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
        "    <tr>\n",
-       "      <th>9</th>\n",
+       "      <th>1</th>\n",
        "      <td>10</td>\n",
-       "      <td>Left upper lateral secondary incisor tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>11</td>\n",
-       "      <td>Left upper secondary canine tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>12</td>\n",
-       "      <td>Left upper first secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>12</th>\n",
-       "      <td>13</td>\n",
-       "      <td>Left upper second secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>14</td>\n",
-       "      <td>Left upper first secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>15</td>\n",
-       "      <td>Left upper second secondary molar tooth</td>\n",
+       "      <td>11438</td>\n",
+       "      <td>10234</td>\n",
+       "      <td>6438</td>\n",
+       "      <td>3140</td>\n",
+       "      <td>521</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>15</th>\n",
-       "      <td>16</td>\n",
-       "      <td>Left upper third secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>16</th>\n",
-       "      <td>17</td>\n",
-       "      <td>Left lower third secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>17</th>\n",
-       "      <td>18</td>\n",
-       "      <td>Left lower second secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18</th>\n",
-       "      <td>19</td>\n",
-       "      <td>Left lower first secondary molar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19</th>\n",
-       "      <td>20</td>\n",
-       "      <td>Left lower second secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>20</th>\n",
-       "      <td>21</td>\n",
-       "      <td>Left lower first secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21</th>\n",
-       "      <td>22</td>\n",
-       "      <td>Left lower secondary canine tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>22</th>\n",
        "      <td>23</td>\n",
-       "      <td>Left lower lateral secondary incisor tooth</td>\n",
+       "      <td>4365</td>\n",
+       "      <td>3089</td>\n",
+       "      <td>1720</td>\n",
+       "      <td>727</td>\n",
+       "      <td>106</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>23</th>\n",
+       "      <th>16</th>\n",
        "      <td>24</td>\n",
-       "      <td>Left lower central secondary incisor tooth</td>\n",
+       "      <td>5125</td>\n",
+       "      <td>3697</td>\n",
+       "      <td>2083</td>\n",
+       "      <td>1109</td>\n",
+       "      <td>240</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>24</th>\n",
+       "      <th>17</th>\n",
        "      <td>25</td>\n",
-       "      <td>Right lower central secondary incisor tooth</td>\n",
+       "      <td>4806</td>\n",
+       "      <td>3808</td>\n",
+       "      <td>2087</td>\n",
+       "      <td>1082</td>\n",
+       "      <td>203</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>25</th>\n",
+       "      <th>18</th>\n",
        "      <td>26</td>\n",
-       "      <td>Right lower lateral secondary incisor tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>26</th>\n",
-       "      <td>27</td>\n",
-       "      <td>Right lower secondary canine tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>27</th>\n",
-       "      <td>28</td>\n",
-       "      <td>Right lower first secondary premolar tooth</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>28</th>\n",
-       "      <td>29</td>\n",
-       "      <td>Right lower second secondary premolar tooth</td>\n",
+       "      <td>4194</td>\n",
+       "      <td>3247</td>\n",
+       "      <td>1695</td>\n",
+       "      <td>665</td>\n",
+       "      <td>115</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>29</th>\n",
-       "      <td>30</td>\n",
-       "      <td>Right lower first secondary molar tooth</td>\n",
+       "      <td>7</td>\n",
+       "      <td>11249</td>\n",
+       "      <td>10399</td>\n",
+       "      <td>6536</td>\n",
+       "      <td>3214</td>\n",
+       "      <td>498</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>30</th>\n",
-       "      <td>31</td>\n",
-       "      <td>Right lower second secondary molar tooth</td>\n",
+       "      <td>8</td>\n",
+       "      <td>12742</td>\n",
+       "      <td>13514</td>\n",
+       "      <td>8559</td>\n",
+       "      <td>6064</td>\n",
+       "      <td>956</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>31</th>\n",
-       "      <td>32</td>\n",
-       "      <td>Right lower third secondary molar tooth</td>\n",
+       "      <td>9</td>\n",
+       "      <td>12488</td>\n",
+       "      <td>13227</td>\n",
+       "      <td>8316</td>\n",
+       "      <td>5976</td>\n",
+       "      <td>923</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "    tooth                                  tooth_label\n",
-       "0       1      Right upper third secondary molar tooth\n",
-       "1       2     Right upper second secondary molar tooth\n",
-       "2       3      Right upper first secondary molar tooth\n",
-       "3       4  Right upper second secondary premolar tooth\n",
-       "4       5   Right upper first secondary premolar tooth\n",
-       "5       6           Right upper secondary canine tooth\n",
-       "6       7  Right upper lateral secondary incisor tooth\n",
-       "7       8  Right upper central secondary incisor tooth\n",
-       "8       9   Left upper central secondary incisor tooth\n",
-       "9      10   Left upper lateral secondary incisor tooth\n",
-       "10     11            Left upper secondary canine tooth\n",
-       "11     12    Left upper first secondary premolar tooth\n",
-       "12     13   Left upper second secondary premolar tooth\n",
-       "13     14       Left upper first secondary molar tooth\n",
-       "14     15      Left upper second secondary molar tooth\n",
-       "15     16       Left upper third secondary molar tooth\n",
-       "16     17       Left lower third secondary molar tooth\n",
-       "17     18      Left lower second secondary molar tooth\n",
-       "18     19       Left lower first secondary molar tooth\n",
-       "19     20   Left lower second secondary premolar tooth\n",
-       "20     21    Left lower first secondary premolar tooth\n",
-       "21     22            Left lower secondary canine tooth\n",
-       "22     23   Left lower lateral secondary incisor tooth\n",
-       "23     24   Left lower central secondary incisor tooth\n",
-       "24     25  Right lower central secondary incisor tooth\n",
-       "25     26  Right lower lateral secondary incisor tooth\n",
-       "26     27           Right lower secondary canine tooth\n",
-       "27     28   Right lower first secondary premolar tooth\n",
-       "28     29  Right lower second secondary premolar tooth\n",
-       "29     30      Right lower first secondary molar tooth\n",
-       "30     31     Right lower second secondary molar tooth\n",
-       "31     32      Right lower third secondary molar tooth"
+       "    tooth_num      1      2     3     4    5  6\n",
+       "1          10  11438  10234  6438  3140  521  0\n",
+       "15         23   4365   3089  1720   727  106  0\n",
+       "16         24   5125   3697  2083  1109  240  1\n",
+       "17         25   4806   3808  2087  1082  203  0\n",
+       "18         26   4194   3247  1695   665  115  0\n",
+       "29          7  11249  10399  6536  3214  498  0\n",
+       "30          8  12742  13514  8559  6064  956  0\n",
+       "31          9  12488  13227  8316  5976  923  0"
       ]
      },
-     "execution_count": 95,
+     "execution_count": 249,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# add some meta information about teeth\n",
-    "tooth_info = pds.read_csv(\"tooth_numbers_and_labels.csv\")\n",
-    "tooth_info"
+    "incisor_surface_counts"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 109,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 252,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# add meta info about tooth type and region in mouth\n",
-    "posterior_tooth = [1, 2, 3, 4, 5, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 28, 29, 30, 31, 32]\n",
-    "anterior_tooth = [6, 7, 8, 9, 10, 11, 22, 23, 24, 25, 26, 27]\n",
-    "\n",
-    "tooth_info['molar'] =  tooth_info.tooth_label.map(lambda label: 1 if \" molar \" in label else 0)\n",
-    "tooth_info['premolar'] =  tooth_info.tooth_label.map(lambda label: 1 if \" premolar \" in label else 0)\n",
-    "tooth_info['canine'] =  tooth_info.tooth_label.map(lambda label: 1 if \" canine \" in label else 0)\n",
-    "tooth_info['incisor'] =  tooth_info.tooth_label.map(lambda label: 1 if \" incisor \" in label else 0)\n",
-    "tooth_info['upper'] =  tooth_info.tooth_label.map(lambda label: 1 if \" upper \" in label else 0)\n",
-    "tooth_info['lower'] =  tooth_info.tooth_label.map(lambda label: 1 if \" lower \" in label else 0)\n",
-    "tooth_info['right'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Right \" in label else 0)\n",
-    "tooth_info['right upper'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Right upper \" in label else 0)\n",
-    "tooth_info['right lower'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Right lower \" in label else 0)\n",
-    "tooth_info['left'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Left \" in label else 0)\n",
-    "tooth_info['left upper'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Left upper \" in label else 0)\n",
-    "tooth_info['left lower'] =  tooth_info.tooth_label.map(lambda label: 1 if \"Left lower \" in label else 0)\n",
-    "tooth_info['posterior'] = tooth_info.tooth.map(lambda tooth: 1 if tooth in posterior_tooth else 0)\n",
-    "tooth_info['anterior'] = tooth_info.tooth.map(lambda tooth: 1 if tooth in anterior_tooth else 0)\n",
-    "# tooth_info"
+    "incisor_surface_counts.set_index('tooth_num', inplace=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 253,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1    66407\n",
+       "2    61215\n",
+       "3    37434\n",
+       "4    21977\n",
+       "5     3562\n",
+       "6        1\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 253,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "tooth_info.to_csv(\"tooth_meta_info.csv\", index=False) # save tooth info dataframe"
+    "incisor_surface_counts.sum()"
    ]
   },
   {