made the region column reflext the actual string that represents the

region rather than the region mappings we made earlier. Figured out that
that was unnessessary.

data/MDetailedGamesOvrStats.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3befec5b96d853905bfc504c0de65565ee863a7cf1ed3e12ab6b908118989f81
-size 17447016
+oid sha256:077d7a26c588a8ebed106d4b8c91aad395646794667e48bce009bed913c6bc4a
+size 17441682

data/MTeamsAgg.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9729caff08c85e33b66e4476def7adbfa5c43067accc1cc3b7855738a6b74cd2
-size 2117343
+oid sha256:f69db045ecdba8f31abbd697f350630784714162778c7f0e020f3ead8227a763
+size 2116682

src/mens_nn.ipynb

@@ -62,8 +62,8 @@
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
       "RangeIndex: 661 entries, 0 to 660\n",
-      "Columns: 554 entries, Unnamed: 0 to Seed\n",
-      "dtypes: float64(276), int64(275), object(3)\n",
+      "Columns: 556 entries, Unnamed: 0 to Seed_Region\n",
+      "dtypes: float64(276), int64(276), object(4)\n",
       "memory usage: 2.8+ MB\n"
      ]
     }

src/mens_pre_processing.ipynb

@@ -847,7 +847,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -863,24 +863,15 @@
     "    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",
+    "    lambda row: row[\"Seed\"][0],\n",
     "    axis=1,\n",
     ")\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -890,11 +881,11 @@
       "<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"
+      "Non-Null Count  Dtype \n",
+      "--------------  ----- \n",
+      "661 non-null    object\n",
+      "dtypes: object(1)\n",
+      "memory usage: 10.3+ KB\n"
      ]
     }
    ],
@@ -963,6 +954,7 @@
        "      <th>reg_WFGM_sum</th>\n",
        "      <th>reg_WFGM_min</th>\n",
        "      <th>...</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",
@@ -972,7 +964,6 @@
        "      <th>FirstD1Season</th>\n",
        "      <th>LastD1Season</th>\n",
        "      <th>Seed_Num</th>\n",
-       "      <th>Seed_Region</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -993,12 +984,12 @@
        "      <td>661.000000</td>\n",
        "      <td>661.000000</td>\n",
        "      <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",
        "      <td>661.0</td>\n",
        "      <td>661.000000</td>\n",
-       "      <td>661.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mean</th>\n",
@@ -1013,6 +1004,7 @@
        "      <td>644.32829</td>\n",
        "      <td>19.069592</td>\n",
        "      <td>...</td>\n",
+       "      <td>18.833585</td>\n",
        "      <td>76.003026</td>\n",
        "      <td>76.003026</td>\n",
        "      <td>76.003026</td>\n",
@@ -1022,7 +1014,6 @@
        "      <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",
@@ -1037,6 +1028,7 @@
        "      <td>120.26041</td>\n",
        "      <td>2.439200</td>\n",
        "      <td>...</td>\n",
+       "      <td>4.233291</td>\n",
        "      <td>10.964128</td>\n",
        "      <td>10.964128</td>\n",
        "      <td>10.964128</td>\n",
@@ -1046,7 +1038,6 @@
        "      <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",
@@ -1061,6 +1052,7 @@
        "      <td>248.00000</td>\n",
        "      <td>12.000000</td>\n",
        "      <td>...</td>\n",
+       "      <td>7.000000</td>\n",
        "      <td>47.000000</td>\n",
        "      <td>47.000000</td>\n",
        "      <td>47.000000</td>\n",
@@ -1070,7 +1062,6 @@
        "      <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",
@@ -1085,6 +1076,7 @@
        "      <td>569.00000</td>\n",
        "      <td>17.000000</td>\n",
        "      <td>...</td>\n",
+       "      <td>16.000000</td>\n",
        "      <td>69.000000</td>\n",
        "      <td>69.000000</td>\n",
        "      <td>69.000000</td>\n",
@@ -1094,7 +1086,6 @@
        "      <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",
@@ -1109,6 +1100,7 @@
        "      <td>639.00000</td>\n",
        "      <td>19.000000</td>\n",
        "      <td>...</td>\n",
+       "      <td>19.000000</td>\n",
        "      <td>76.000000</td>\n",
        "      <td>76.000000</td>\n",
        "      <td>76.000000</td>\n",
@@ -1118,7 +1110,6 @@
        "      <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",
@@ -1133,6 +1124,7 @@
        "      <td>721.00000</td>\n",
        "      <td>21.000000</td>\n",
        "      <td>...</td>\n",
+       "      <td>22.000000</td>\n",
        "      <td>83.000000</td>\n",
        "      <td>83.000000</td>\n",
        "      <td>83.000000</td>\n",
@@ -1142,7 +1134,6 @@
        "      <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",
@@ -1157,6 +1148,7 @@
        "      <td>1025.00000</td>\n",
        "      <td>27.000000</td>\n",
        "      <td>...</td>\n",
+       "      <td>33.000000</td>\n",
        "      <td>121.000000</td>\n",
        "      <td>121.000000</td>\n",
        "      <td>121.000000</td>\n",
@@ -1166,11 +1158,10 @@
        "      <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 × 552 columns</p>\n",
+       "<p>8 rows × 551 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -1194,37 +1185,37 @@
        "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_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",
+       "       reg_WFGM_sum  reg_WFGM_min  ...  tourney_PF_mean  tourney_PA_sum  \\\n",
+       "count     661.00000    661.000000  ...       661.000000      661.000000   \n",
+       "mean      644.32829     19.069592  ...        18.833585       76.003026   \n",
+       "std       120.26041      2.439200  ...         4.233291       10.964128   \n",
+       "min       248.00000     12.000000  ...         7.000000       47.000000   \n",
+       "25%       569.00000     17.000000  ...        16.000000       69.000000   \n",
+       "50%       639.00000     19.000000  ...        19.000000       76.000000   \n",
+       "75%       721.00000     21.000000  ...        22.000000       83.000000   \n",
+       "max      1025.00000     27.000000  ...        33.000000      121.000000   \n",
        "\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",
+       "       tourney_PA_min  tourney_PA_max  tourney_PA_median  tourney_PA_std  \\\n",
+       "count      661.000000      661.000000         661.000000           661.0   \n",
+       "mean        76.003026       76.003026          76.003026             0.0   \n",
+       "std         10.964128       10.964128          10.964128             0.0   \n",
+       "min         47.000000       47.000000          47.000000             0.0   \n",
+       "25%         69.000000       69.000000          69.000000             0.0   \n",
+       "50%         76.000000       76.000000          76.000000             0.0   \n",
+       "75%         83.000000       83.000000          83.000000             0.0   \n",
+       "max        121.000000      121.000000         121.000000             0.0   \n",
        "\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",
+       "       tourney_PA_mean  FirstD1Season  LastD1Season    Seed_Num  \n",
+       "count       661.000000     661.000000         661.0  661.000000  \n",
+       "mean         76.003026    1985.512859        2024.0    1.366112  \n",
+       "std          10.964128       2.812079           0.0    3.930341  \n",
+       "min          47.000000    1985.000000        2024.0    0.000000  \n",
+       "25%          69.000000    1985.000000        2024.0    0.000000  \n",
+       "50%          76.000000    1985.000000        2024.0    0.000000  \n",
+       "75%          83.000000    1985.000000        2024.0    1.000000  \n",
+       "max         121.000000    2014.000000        2024.0   16.000000  \n",
        "\n",
-       "[8 rows x 552 columns]"
+       "[8 rows x 551 columns]"
       ]
      },
      "execution_count": 17,
@@ -1520,7 +1511,7 @@
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
        "      <td>0</td>\n",
-       "      <td>59</td>\n",
+       "      <td>Y</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
@@ -1544,7 +1535,7 @@
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
        "      <td>0</td>\n",
-       "      <td>59</td>\n",
+       "      <td>Y</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
@@ -1568,7 +1559,7 @@
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
        "      <td>0</td>\n",
-       "      <td>59</td>\n",
+       "      <td>Y</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
@@ -1592,7 +1583,7 @@
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
        "      <td>0</td>\n",
-       "      <td>59</td>\n",
+       "      <td>Y</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
@@ -1616,7 +1607,7 @@
        "      <td>big_ten</td>\n",
        "      <td>Y05</td>\n",
        "      <td>0</td>\n",
-       "      <td>59</td>\n",
+       "      <td>Y</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -1646,11 +1637,11 @@
        "4             1985            2024       big_ten     Y05           0   \n",
        "\n",
        "   Seed_Region_L  \n",
-       "0             59  \n",
-       "1             59  \n",
-       "2             59  \n",
-       "3             59  \n",
-       "4             59  \n",
+       "0              Y  \n",
+       "1              Y  \n",
+       "2              Y  \n",
+       "3              Y  \n",
+       "4              Y  \n",
        "\n",
        "[5 rows x 1146 columns]"
       ]