making new columns Seed_Num and Region_Num so that the model can train

withe seed in mind (if it explains any variance) without having to make
a crap load of dummy variables

data/MDetailedGamesOvrStats.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bddd55618ad48a70efd2f8de4626867b640529be8a9735710fb6e4dbc36d312
-size 17420050
+oid sha256:3befec5b96d853905bfc504c0de65565ee863a7cf1ed3e12ab6b908118989f81
+size 17447016

data/MTeamsAgg.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333ca074666b0857fe15a49d55dc32d3a87778568467bcdb84e839a1a75a5e2d
-size 2113961
+oid sha256:9729caff08c85e33b66e4476def7adbfa5c43067accc1cc3b7855738a6b74cd2
+size 2117343

src/mens_pre_processing.ipynb

@@ -73,6 +73,7 @@
     }
    ],
    "source": [
+    "# read in the tournament games data\n",
     "tourney_games_df = pd.read_csv(\n",
     "    os.path.join(DATA_DIR, \"MNCAATourneyDetailedResults.csv\")\n",
     ")\n",
@@ -146,6 +147,7 @@
     }
    ],
    "source": [
+    "# read in regular season games data\n",
     "reg_games_df = pd.read_csv(\n",
     "    os.path.join(DATA_DIR, \"MRegularSeasonDetailedResults.csv\")\n",
     ")\n",
@@ -847,209 +849,86 @@
    "cell_type": "code",
    "execution_count": 14,
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "def seed_to_num(seed: str) -> int:\n",
+    "    chars = [char for char in seed]\n",
+    "    all_nums = all([char.isnumeric() for char in chars])\n",
+    "    if not all_nums:\n",
+    "        return int(seed[1:-1])\n",
+    "    return int(seed[1:])\n",
+    "\n",
+    "tms_conf_seeds[\"Seed_Num\"] = tms_conf_seeds.apply(\n",
+    "    lambda row: seed_to_num(row[\"Seed\"]),\n",
+    "    axis=1,\n",
+    ")\n",
+    "\n",
+    "\n",
+    "region_mappings = {seed[0]: idx for idx, seed in enumerate(sorted(tms_conf_seeds[\"Seed\"].unique()))}\n",
+    "\n",
+    "def region_to_num(region: str) -> int:\n",
+    "    r_num = region_mappings.get(region, None)\n",
+    "    if not r_num:\n",
+    "        raise KeyError(f\"Invalid Region '{region}'\")\n",
+    "    return r_num\n",
+    "\n",
+    "tms_conf_seeds[\"Seed_Region\"] = tms_conf_seeds.apply(\n",
+    "    lambda row: region_to_num(row[\"Seed\"][0]),\n",
+    "    axis=1,\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "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>Season</th>\n",
-       "      <th>DayNum</th>\n",
-       "      <th>WTeamID</th>\n",
-       "      <th>WScore</th>\n",
-       "      <th>LTeamID</th>\n",
-       "      <th>LScore</th>\n",
-       "      <th>WLoc</th>\n",
-       "      <th>NumOT</th>\n",
-       "      <th>WFGM</th>\n",
-       "      <th>WFGA</th>\n",
-       "      <th>...</th>\n",
-       "      <th>LDR</th>\n",
-       "      <th>LAst</th>\n",
-       "      <th>LTO</th>\n",
-       "      <th>LStl</th>\n",
-       "      <th>LBlk</th>\n",
-       "      <th>LPF</th>\n",
-       "      <th>GameType</th>\n",
-       "      <th>WPA</th>\n",
-       "      <th>LPA</th>\n",
-       "      <th>LLoc</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2003</td>\n",
-       "      <td>10</td>\n",
-       "      <td>1104</td>\n",
-       "      <td>68</td>\n",
-       "      <td>1328</td>\n",
-       "      <td>62</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>27</td>\n",
-       "      <td>58</td>\n",
-       "      <td>...</td>\n",
-       "      <td>22</td>\n",
-       "      <td>8</td>\n",
-       "      <td>18</td>\n",
-       "      <td>9</td>\n",
-       "      <td>2</td>\n",
-       "      <td>20</td>\n",
-       "      <td>reg</td>\n",
-       "      <td>62</td>\n",
-       "      <td>68</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2003</td>\n",
-       "      <td>10</td>\n",
-       "      <td>1272</td>\n",
-       "      <td>70</td>\n",
-       "      <td>1393</td>\n",
-       "      <td>63</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>26</td>\n",
-       "      <td>62</td>\n",
-       "      <td>...</td>\n",
-       "      <td>25</td>\n",
-       "      <td>7</td>\n",
-       "      <td>12</td>\n",
-       "      <td>8</td>\n",
-       "      <td>6</td>\n",
-       "      <td>16</td>\n",
-       "      <td>reg</td>\n",
-       "      <td>63</td>\n",
-       "      <td>70</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2003</td>\n",
-       "      <td>11</td>\n",
-       "      <td>1266</td>\n",
-       "      <td>73</td>\n",
-       "      <td>1437</td>\n",
-       "      <td>61</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>24</td>\n",
-       "      <td>58</td>\n",
-       "      <td>...</td>\n",
-       "      <td>22</td>\n",
-       "      <td>9</td>\n",
-       "      <td>12</td>\n",
-       "      <td>2</td>\n",
-       "      <td>5</td>\n",
-       "      <td>23</td>\n",
-       "      <td>reg</td>\n",
-       "      <td>61</td>\n",
-       "      <td>73</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2003</td>\n",
-       "      <td>11</td>\n",
-       "      <td>1296</td>\n",
-       "      <td>56</td>\n",
-       "      <td>1457</td>\n",
-       "      <td>50</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>18</td>\n",
-       "      <td>38</td>\n",
-       "      <td>...</td>\n",
-       "      <td>20</td>\n",
-       "      <td>9</td>\n",
-       "      <td>19</td>\n",
-       "      <td>4</td>\n",
-       "      <td>3</td>\n",
-       "      <td>23</td>\n",
-       "      <td>reg</td>\n",
-       "      <td>50</td>\n",
-       "      <td>56</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2003</td>\n",
-       "      <td>11</td>\n",
-       "      <td>1400</td>\n",
-       "      <td>77</td>\n",
-       "      <td>1208</td>\n",
-       "      <td>71</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>30</td>\n",
-       "      <td>61</td>\n",
-       "      <td>...</td>\n",
-       "      <td>15</td>\n",
-       "      <td>12</td>\n",
-       "      <td>10</td>\n",
-       "      <td>7</td>\n",
-       "      <td>1</td>\n",
-       "      <td>14</td>\n",
-       "      <td>reg</td>\n",
-       "      <td>71</td>\n",
-       "      <td>77</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>5 rows × 38 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   Season  DayNum  WTeamID  WScore  LTeamID  LScore  WLoc  NumOT  WFGM  WFGA  \\\n",
-       "0    2003      10     1104      68     1328      62     1      0    27    58   \n",
-       "1    2003      10     1272      70     1393      63     1      0    26    62   \n",
-       "2    2003      11     1266      73     1437      61     1      0    24    58   \n",
-       "3    2003      11     1296      56     1457      50     1      0    18    38   \n",
-       "4    2003      11     1400      77     1208      71     1      0    30    61   \n",
-       "\n",
-       "   ...  LDR  LAst  LTO  LStl  LBlk  LPF  GameType  WPA  LPA  LLoc  \n",
-       "0  ...   22     8   18     9     2   20       reg   62   68     1  \n",
-       "1  ...   25     7   12     8     6   16       reg   63   70     1  \n",
-       "2  ...   22     9   12     2     5   23       reg   61   73     1  \n",
-       "3  ...   20     9   19     4     3   23       reg   50   56     1  \n",
-       "4  ...   15    12   10     7     1   14       reg   71   77     1  \n",
-       "\n",
-       "[5 rows x 38 columns]"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.series.Series'>\n",
+      "Int64Index: 661 entries, 0 to 660\n",
+      "Series name: Seed_Region\n",
+      "Non-Null Count  Dtype\n",
+      "--------------  -----\n",
+      "661 non-null    int64\n",
+      "dtypes: int64(1)\n",
+      "memory usage: 10.3 KB\n"
+     ]
     }
    ],
    "source": [
-    "# get a dataframe of all games regardless of wether or not it was a tournament game or not\n",
-    "all_games_df = pd.concat([reg_games_df, tourney_games_df])\n",
-    "all_games_df.head()"
+    "tms_conf_seeds[\"Seed_Region\"].info()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.series.Series'>\n",
+      "Int64Index: 661 entries, 0 to 660\n",
+      "Series name: Seed_Num\n",
+      "Non-Null Count  Dtype\n",
+      "--------------  -----\n",
+      "661 non-null    int64\n",
+      "dtypes: int64(1)\n",
+      "memory usage: 10.3 KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "tms_conf_seeds[\"Seed_Num\"].info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -1084,8 +963,6 @@
        "      <th>reg_WFGM_sum</th>\n",
        "      <th>reg_WFGM_min</th>\n",
        "      <th>...</th>\n",
-       "      <th>tourney_PF_std</th>\n",
-       "      <th>tourney_PF_mean</th>\n",
        "      <th>tourney_PA_sum</th>\n",
        "      <th>tourney_PA_min</th>\n",
        "      <th>tourney_PA_max</th>\n",
@@ -1094,6 +971,8 @@
        "      <th>tourney_PA_mean</th>\n",
        "      <th>FirstD1Season</th>\n",
        "      <th>LastD1Season</th>\n",
+       "      <th>Seed_Num</th>\n",
+       "      <th>Seed_Region</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -1110,8 +989,6 @@
        "      <td>661.00000</td>\n",
        "      <td>661.000000</td>\n",
        "      <td>...</td>\n",
-       "      <td>661.0</td>\n",
-       "      <td>661.000000</td>\n",
        "      <td>661.000000</td>\n",
        "      <td>661.000000</td>\n",
        "      <td>661.000000</td>\n",
@@ -1120,6 +997,8 @@
        "      <td>661.000000</td>\n",
        "      <td>661.000000</td>\n",
        "      <td>661.0</td>\n",
+       "      <td>661.000000</td>\n",
+       "      <td>661.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mean</th>\n",
@@ -1134,8 +1013,6 @@
        "      <td>644.32829</td>\n",
        "      <td>19.069592</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>18.833585</td>\n",
        "      <td>76.003026</td>\n",
        "      <td>76.003026</td>\n",
        "      <td>76.003026</td>\n",
@@ -1144,6 +1021,8 @@
        "      <td>76.003026</td>\n",
        "      <td>1985.512859</td>\n",
        "      <td>2024.0</td>\n",
+       "      <td>1.366112</td>\n",
+       "      <td>49.022693</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>std</th>\n",
@@ -1158,8 +1037,6 @@
        "      <td>120.26041</td>\n",
        "      <td>2.439200</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>4.233291</td>\n",
        "      <td>10.964128</td>\n",
        "      <td>10.964128</td>\n",
        "      <td>10.964128</td>\n",
@@ -1168,6 +1045,8 @@
        "      <td>10.964128</td>\n",
        "      <td>2.812079</td>\n",
        "      <td>0.0</td>\n",
+       "      <td>3.930341</td>\n",
+       "      <td>22.835534</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>min</th>\n",
@@ -1182,8 +1061,6 @@
        "      <td>248.00000</td>\n",
        "      <td>12.000000</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>7.000000</td>\n",
        "      <td>47.000000</td>\n",
        "      <td>47.000000</td>\n",
        "      <td>47.000000</td>\n",
@@ -1192,6 +1069,8 @@
        "      <td>47.000000</td>\n",
        "      <td>1985.000000</td>\n",
        "      <td>2024.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>19.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>25%</th>\n",
@@ -1206,8 +1085,6 @@
        "      <td>569.00000</td>\n",
        "      <td>17.000000</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>16.000000</td>\n",
        "      <td>69.000000</td>\n",
        "      <td>69.000000</td>\n",
        "      <td>69.000000</td>\n",
@@ -1216,6 +1093,8 @@
        "      <td>69.000000</td>\n",
        "      <td>1985.000000</td>\n",
        "      <td>2024.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>19.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50%</th>\n",
@@ -1230,8 +1109,6 @@
        "      <td>639.00000</td>\n",
        "      <td>19.000000</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>19.000000</td>\n",
        "      <td>76.000000</td>\n",
        "      <td>76.000000</td>\n",
        "      <td>76.000000</td>\n",
@@ -1240,6 +1117,8 @@
        "      <td>76.000000</td>\n",
        "      <td>1985.000000</td>\n",
        "      <td>2024.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>39.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>75%</th>\n",
@@ -1254,8 +1133,6 @@
        "      <td>721.00000</td>\n",
        "      <td>21.000000</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>22.000000</td>\n",
        "      <td>83.000000</td>\n",
        "      <td>83.000000</td>\n",
        "      <td>83.000000</td>\n",
@@ -1264,6 +1141,8 @@
        "      <td>83.000000</td>\n",
        "      <td>1985.000000</td>\n",
        "      <td>2024.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>59.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
@@ -1278,8 +1157,6 @@
        "      <td>1025.00000</td>\n",
        "      <td>27.000000</td>\n",
        "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>33.000000</td>\n",
        "      <td>121.000000</td>\n",
        "      <td>121.000000</td>\n",
        "      <td>121.000000</td>\n",
@@ -1288,10 +1165,12 @@
        "      <td>121.000000</td>\n",
        "      <td>2014.000000</td>\n",
        "      <td>2024.0</td>\n",
+       "      <td>16.000000</td>\n",
+       "      <td>80.000000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>8 rows × 550 columns</p>\n",
+       "<p>8 rows × 552 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -1315,40 +1194,40 @@
        "75%        105.000000          80.000000       11.584882        80.541667   \n",
        "max        144.000000          91.500000       16.534890        91.689655   \n",
        "\n",
-       "       reg_WFGM_sum  reg_WFGM_min  ...  tourney_PF_std  tourney_PF_mean  \\\n",
-       "count     661.00000    661.000000  ...           661.0       661.000000   \n",
-       "mean      644.32829     19.069592  ...             0.0        18.833585   \n",
-       "std       120.26041      2.439200  ...             0.0         4.233291   \n",
-       "min       248.00000     12.000000  ...             0.0         7.000000   \n",
-       "25%       569.00000     17.000000  ...             0.0        16.000000   \n",
-       "50%       639.00000     19.000000  ...             0.0        19.000000   \n",
-       "75%       721.00000     21.000000  ...             0.0        22.000000   \n",
-       "max      1025.00000     27.000000  ...             0.0        33.000000   \n",
+       "       reg_WFGM_sum  reg_WFGM_min  ...  tourney_PA_sum  tourney_PA_min  \\\n",
+       "count     661.00000    661.000000  ...      661.000000      661.000000   \n",
+       "mean      644.32829     19.069592  ...       76.003026       76.003026   \n",
+       "std       120.26041      2.439200  ...       10.964128       10.964128   \n",
+       "min       248.00000     12.000000  ...       47.000000       47.000000   \n",
+       "25%       569.00000     17.000000  ...       69.000000       69.000000   \n",
+       "50%       639.00000     19.000000  ...       76.000000       76.000000   \n",
+       "75%       721.00000     21.000000  ...       83.000000       83.000000   \n",
+       "max      1025.00000     27.000000  ...      121.000000      121.000000   \n",
        "\n",
-       "       tourney_PA_sum  tourney_PA_min  tourney_PA_max  tourney_PA_median  \\\n",
-       "count      661.000000      661.000000      661.000000         661.000000   \n",
-       "mean        76.003026       76.003026       76.003026          76.003026   \n",
-       "std         10.964128       10.964128       10.964128          10.964128   \n",
-       "min         47.000000       47.000000       47.000000          47.000000   \n",
-       "25%         69.000000       69.000000       69.000000          69.000000   \n",
-       "50%         76.000000       76.000000       76.000000          76.000000   \n",
-       "75%         83.000000       83.000000       83.000000          83.000000   \n",
-       "max        121.000000      121.000000      121.000000         121.000000   \n",
+       "       tourney_PA_max  tourney_PA_median  tourney_PA_std  tourney_PA_mean  \\\n",
+       "count      661.000000         661.000000           661.0       661.000000   \n",
+       "mean        76.003026          76.003026             0.0        76.003026   \n",
+       "std         10.964128          10.964128             0.0        10.964128   \n",
+       "min         47.000000          47.000000             0.0        47.000000   \n",
+       "25%         69.000000          69.000000             0.0        69.000000   \n",
+       "50%         76.000000          76.000000             0.0        76.000000   \n",
+       "75%         83.000000          83.000000             0.0        83.000000   \n",
+       "max        121.000000         121.000000             0.0       121.000000   \n",
        "\n",
-       "       tourney_PA_std  tourney_PA_mean  FirstD1Season  LastD1Season  \n",
-       "count           661.0       661.000000     661.000000         661.0  \n",
-       "mean              0.0        76.003026    1985.512859        2024.0  \n",
-       "std               0.0        10.964128       2.812079           0.0  \n",
-       "min               0.0        47.000000    1985.000000        2024.0  \n",
-       "25%               0.0        69.000000    1985.000000        2024.0  \n",
-       "50%               0.0        76.000000    1985.000000        2024.0  \n",
-       "75%               0.0        83.000000    1985.000000        2024.0  \n",
-       "max               0.0       121.000000    2014.000000        2024.0  \n",
+       "       FirstD1Season  LastD1Season    Seed_Num  Seed_Region  \n",
+       "count     661.000000         661.0  661.000000   661.000000  \n",
+       "mean     1985.512859        2024.0    1.366112    49.022693  \n",
+       "std         2.812079           0.0    3.930341    22.835534  \n",
+       "min      1985.000000        2024.0    0.000000    19.000000  \n",
+       "25%      1985.000000        2024.0    0.000000    19.000000  \n",
+       "50%      1985.000000        2024.0    0.000000    39.000000  \n",
+       "75%      1985.000000        2024.0    1.000000    59.000000  \n",
+       "max      2014.000000        2024.0   16.000000    80.000000  \n",
        "\n",
-       "[8 rows x 550 columns]"
+       "[8 rows x 552 columns]"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1358,9 +1237,220 @@
     "tms_conf_seeds.describe()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Extra Dataset with Games and Team Data mapped together"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 18,
+   "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>Season</th>\n",
+       "      <th>DayNum</th>\n",
+       "      <th>WTeamID</th>\n",
+       "      <th>WScore</th>\n",
+       "      <th>LTeamID</th>\n",
+       "      <th>LScore</th>\n",
+       "      <th>WLoc</th>\n",
+       "      <th>NumOT</th>\n",
+       "      <th>WFGM</th>\n",
+       "      <th>WFGA</th>\n",
+       "      <th>...</th>\n",
+       "      <th>LDR</th>\n",
+       "      <th>LAst</th>\n",
+       "      <th>LTO</th>\n",
+       "      <th>LStl</th>\n",
+       "      <th>LBlk</th>\n",
+       "      <th>LPF</th>\n",
+       "      <th>GameType</th>\n",
+       "      <th>WPA</th>\n",
+       "      <th>LPA</th>\n",
+       "      <th>LLoc</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2003</td>\n",
+       "      <td>10</td>\n",
+       "      <td>1104</td>\n",
+       "      <td>68</td>\n",
+       "      <td>1328</td>\n",
+       "      <td>62</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>27</td>\n",
+       "      <td>58</td>\n",
+       "      <td>...</td>\n",
+       "      <td>22</td>\n",
+       "      <td>8</td>\n",
+       "      <td>18</td>\n",
+       "      <td>9</td>\n",
+       "      <td>2</td>\n",
+       "      <td>20</td>\n",
+       "      <td>reg</td>\n",
+       "      <td>62</td>\n",
+       "      <td>68</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2003</td>\n",
+       "      <td>10</td>\n",
+       "      <td>1272</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1393</td>\n",
+       "      <td>63</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>26</td>\n",
+       "      <td>62</td>\n",
+       "      <td>...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>7</td>\n",
+       "      <td>12</td>\n",
+       "      <td>8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>16</td>\n",
+       "      <td>reg</td>\n",
+       "      <td>63</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2003</td>\n",
+       "      <td>11</td>\n",
+       "      <td>1266</td>\n",
+       "      <td>73</td>\n",
+       "      <td>1437</td>\n",
+       "      <td>61</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>24</td>\n",
+       "      <td>58</td>\n",
+       "      <td>...</td>\n",
+       "      <td>22</td>\n",
+       "      <td>9</td>\n",
+       "      <td>12</td>\n",
+       "      <td>2</td>\n",
+       "      <td>5</td>\n",
+       "      <td>23</td>\n",
+       "      <td>reg</td>\n",
+       "      <td>61</td>\n",
+       "      <td>73</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2003</td>\n",
+       "      <td>11</td>\n",
+       "      <td>1296</td>\n",
+       "      <td>56</td>\n",
+       "      <td>1457</td>\n",
+       "      <td>50</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>18</td>\n",
+       "      <td>38</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20</td>\n",
+       "      <td>9</td>\n",
+       "      <td>19</td>\n",
+       "      <td>4</td>\n",
+       "      <td>3</td>\n",
+       "      <td>23</td>\n",
+       "      <td>reg</td>\n",
+       "      <td>50</td>\n",
+       "      <td>56</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2003</td>\n",
+       "      <td>11</td>\n",
+       "      <td>1400</td>\n",
+       "      <td>77</td>\n",
+       "      <td>1208</td>\n",
+       "      <td>71</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>30</td>\n",
+       "      <td>61</td>\n",
+       "      <td>...</td>\n",
+       "      <td>15</td>\n",
+       "      <td>12</td>\n",
+       "      <td>10</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14</td>\n",
+       "      <td>reg</td>\n",
+       "      <td>71</td>\n",
+       "      <td>77</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 38 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Season  DayNum  WTeamID  WScore  LTeamID  LScore  WLoc  NumOT  WFGM  WFGA  \\\n",
+       "0    2003      10     1104      68     1328      62     1      0    27    58   \n",
+       "1    2003      10     1272      70     1393      63     1      0    26    62   \n",
+       "2    2003      11     1266      73     1437      61     1      0    24    58   \n",
+       "3    2003      11     1296      56     1457      50     1      0    18    38   \n",
+       "4    2003      11     1400      77     1208      71     1      0    30    61   \n",
+       "\n",
+       "   ...  LDR  LAst  LTO  LStl  LBlk  LPF  GameType  WPA  LPA  LLoc  \n",
+       "0  ...   22     8   18     9     2   20       reg   62   68     1  \n",
+       "1  ...   25     7   12     8     6   16       reg   63   70     1  \n",
+       "2  ...   22     9   12     2     5   23       reg   61   73     1  \n",
+       "3  ...   20     9   19     4     3   23       reg   50   56     1  \n",
+       "4  ...   15    12   10     7     1   14       reg   71   77     1  \n",
+       "\n",
+       "[5 rows x 38 columns]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# get a dataframe of all games regardless of wether or not it was a tournament game or not\n",
+    "all_games_df = pd.concat([reg_games_df, tourney_games_df])\n",
+    "all_games_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -1395,8 +1485,6 @@
        "      <th>WFGM</th>\n",
        "      <th>WFGA</th>\n",
        "      <th>...</th>\n",
-       "      <th>tourney_PA_min_L</th>\n",
-       "      <th>tourney_PA_max_L</th>\n",
        "      <th>tourney_PA_median_L</th>\n",
        "      <th>tourney_PA_std_L</th>\n",
        "      <th>tourney_PA_mean_L</th>\n",
@@ -1405,6 +1493,8 @@
        "      <th>LastD1Season_L</th>\n",
        "      <th>ConfAbbrev_L</th>\n",
        "      <th>Seed_L</th>\n",
+       "      <th>Seed_Num_L</th>\n",
+       "      <th>Seed_Region_L</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -1421,8 +1511,6 @@
        "      <td>24</td>\n",
        "      <td>46</td>\n",
        "      <td>...</td>\n",
-       "      <td>62</td>\n",
-       "      <td>62</td>\n",
        "      <td>62.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>62.0</td>\n",
@@ -1431,6 +1519,8 @@
        "      <td>2024</td>\n",
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
+       "      <td>0</td>\n",
+       "      <td>59</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
@@ -1445,8 +1535,6 @@
        "      <td>23</td>\n",
        "      <td>51</td>\n",
        "      <td>...</td>\n",
-       "      <td>62</td>\n",
-       "      <td>62</td>\n",
        "      <td>62.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>62.0</td>\n",
@@ -1455,6 +1543,8 @@
        "      <td>2024</td>\n",
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
+       "      <td>0</td>\n",
+       "      <td>59</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
@@ -1469,8 +1559,6 @@
        "      <td>25</td>\n",
        "      <td>50</td>\n",
        "      <td>...</td>\n",
-       "      <td>62</td>\n",
-       "      <td>62</td>\n",
        "      <td>62.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>62.0</td>\n",
@@ -1479,6 +1567,8 @@
        "      <td>2024</td>\n",
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
+       "      <td>0</td>\n",
+       "      <td>59</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
@@ -1493,8 +1583,6 @@
        "      <td>24</td>\n",
        "      <td>49</td>\n",
        "      <td>...</td>\n",
-       "      <td>62</td>\n",
-       "      <td>62</td>\n",
        "      <td>62.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>62.0</td>\n",
@@ -1503,6 +1591,8 @@
        "      <td>2024</td>\n",
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
+       "      <td>0</td>\n",
+       "      <td>59</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
@@ -1517,8 +1607,6 @@
        "      <td>33</td>\n",
        "      <td>61</td>\n",
        "      <td>...</td>\n",
-       "      <td>62</td>\n",
-       "      <td>62</td>\n",
        "      <td>62.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>62.0</td>\n",
@@ -1527,10 +1615,12 @@
        "      <td>2024</td>\n",
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
+       "      <td>0</td>\n",
+       "      <td>59</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>5 rows × 1142 columns</p>\n",
+       "<p>5 rows × 1146 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -1541,31 +1631,31 @@
        "3    2003     143     1246      63     1458      57     1      0    24    49   \n",
        "4    2003      30     1448      90     1458      80     1      0    33    61   \n",
        "\n",
-       "   ...  tourney_PA_min_L  tourney_PA_max_L  tourney_PA_median_L  \\\n",
-       "0  ...                62                62                 62.0   \n",
-       "1  ...                62                62                 62.0   \n",
-       "2  ...                62                62                 62.0   \n",
-       "3  ...                62                62                 62.0   \n",
-       "4  ...                62                62                 62.0   \n",
+       "   ...  tourney_PA_median_L  tourney_PA_std_L  tourney_PA_mean_L  TeamName_L  \\\n",
+       "0  ...                 62.0               0.0               62.0   Wisconsin   \n",
+       "1  ...                 62.0               0.0               62.0   Wisconsin   \n",
+       "2  ...                 62.0               0.0               62.0   Wisconsin   \n",
+       "3  ...                 62.0               0.0               62.0   Wisconsin   \n",
+       "4  ...                 62.0               0.0               62.0   Wisconsin   \n",
        "\n",
-       "   tourney_PA_std_L  tourney_PA_mean_L  TeamName_L  FirstD1Season_L  \\\n",
-       "0               0.0               62.0   Wisconsin             1985   \n",
-       "1               0.0               62.0   Wisconsin             1985   \n",
-       "2               0.0               62.0   Wisconsin             1985   \n",
-       "3               0.0               62.0   Wisconsin             1985   \n",
-       "4               0.0               62.0   Wisconsin             1985   \n",
+       "   FirstD1Season_L  LastD1Season_L  ConfAbbrev_L  Seed_L  Seed_Num_L  \\\n",
+       "0             1985            2024       big_ten     Y05           0   \n",
+       "1             1985            2024       big_ten     Y05           0   \n",
+       "2             1985            2024       big_ten     Y05           0   \n",
+       "3             1985            2024       big_ten     Y05           0   \n",
+       "4             1985            2024       big_ten     Y05           0   \n",
        "\n",
-       "   LastD1Season_L  ConfAbbrev_L  Seed_L  \n",
-       "0            2024       big_ten     Y05  \n",
-       "1            2024       big_ten     Y05  \n",
-       "2            2024       big_ten     Y05  \n",
-       "3            2024       big_ten     Y05  \n",
-       "4            2024       big_ten     Y05  \n",
+       "   Seed_Region_L  \n",
+       "0             59  \n",
+       "1             59  \n",
+       "2             59  \n",
+       "3             59  \n",
+       "4             59  \n",
        "\n",
-       "[5 rows x 1142 columns]"
+       "[5 rows x 1146 columns]"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1592,7 +1682,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [