Commit
•
fbeeea5
1
Parent(s):
9c0cc03
working through aggregating the regular season data, deleted the data
Browse files- data/MTeamsAgg.csv +0 -3
- src/pre_processing.ipynb +569 -0
data/MTeamsAgg.csv
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f69db045ecdba8f31abbd697f350630784714162778c7f0e020f3ead8227a763
|
3 |
-
size 2116682
|
|
|
|
|
|
|
|
src/pre_processing.ipynb
CHANGED
@@ -986,6 +986,575 @@
|
|
986 |
"\n",
|
987 |
"team_reg_agg.sample(10, random_state=1)"
|
988 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
989 |
}
|
990 |
],
|
991 |
"metadata": {
|
|
|
986 |
"\n",
|
987 |
"team_reg_agg.sample(10, random_state=1)"
|
988 |
]
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"cell_type": "markdown",
|
992 |
+
"metadata": {},
|
993 |
+
"source": [
|
994 |
+
"## Join Aggregated w/ Attributes"
|
995 |
+
]
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"cell_type": "code",
|
999 |
+
"execution_count": 24,
|
1000 |
+
"metadata": {},
|
1001 |
+
"outputs": [
|
1002 |
+
{
|
1003 |
+
"data": {
|
1004 |
+
"text/html": [
|
1005 |
+
"<div>\n",
|
1006 |
+
"<style scoped>\n",
|
1007 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
1008 |
+
" vertical-align: middle;\n",
|
1009 |
+
" }\n",
|
1010 |
+
"\n",
|
1011 |
+
" .dataframe tbody tr th {\n",
|
1012 |
+
" vertical-align: top;\n",
|
1013 |
+
" }\n",
|
1014 |
+
"\n",
|
1015 |
+
" .dataframe thead th {\n",
|
1016 |
+
" text-align: right;\n",
|
1017 |
+
" }\n",
|
1018 |
+
"</style>\n",
|
1019 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
1020 |
+
" <thead>\n",
|
1021 |
+
" <tr style=\"text-align: right;\">\n",
|
1022 |
+
" <th></th>\n",
|
1023 |
+
" <th>Season</th>\n",
|
1024 |
+
" <th>TeamID</th>\n",
|
1025 |
+
" <th>ConfAbbrev</th>\n",
|
1026 |
+
" <th>League</th>\n",
|
1027 |
+
" <th>Seed</th>\n",
|
1028 |
+
" <th>TeamName</th>\n",
|
1029 |
+
" <th>FirstD1Season</th>\n",
|
1030 |
+
" <th>LastD1Season</th>\n",
|
1031 |
+
" </tr>\n",
|
1032 |
+
" </thead>\n",
|
1033 |
+
" <tbody>\n",
|
1034 |
+
" <tr>\n",
|
1035 |
+
" <th>507</th>\n",
|
1036 |
+
" <td>2016</td>\n",
|
1037 |
+
" <td>1292</td>\n",
|
1038 |
+
" <td>cusa</td>\n",
|
1039 |
+
" <td>M</td>\n",
|
1040 |
+
" <td>X15</td>\n",
|
1041 |
+
" <td>MTSU</td>\n",
|
1042 |
+
" <td>1985</td>\n",
|
1043 |
+
" <td>2024</td>\n",
|
1044 |
+
" </tr>\n",
|
1045 |
+
" <tr>\n",
|
1046 |
+
" <th>1174</th>\n",
|
1047 |
+
" <td>1994</td>\n",
|
1048 |
+
" <td>1438</td>\n",
|
1049 |
+
" <td>acc</td>\n",
|
1050 |
+
" <td>M</td>\n",
|
1051 |
+
" <td>Z07</td>\n",
|
1052 |
+
" <td>Virginia</td>\n",
|
1053 |
+
" <td>1985</td>\n",
|
1054 |
+
" <td>2024</td>\n",
|
1055 |
+
" </tr>\n",
|
1056 |
+
" <tr>\n",
|
1057 |
+
" <th>1158</th>\n",
|
1058 |
+
" <td>1998</td>\n",
|
1059 |
+
" <td>1428</td>\n",
|
1060 |
+
" <td>wac</td>\n",
|
1061 |
+
" <td>M</td>\n",
|
1062 |
+
" <td>X03</td>\n",
|
1063 |
+
" <td>Utah</td>\n",
|
1064 |
+
" <td>1985</td>\n",
|
1065 |
+
" <td>2024</td>\n",
|
1066 |
+
" </tr>\n",
|
1067 |
+
" <tr>\n",
|
1068 |
+
" <th>638</th>\n",
|
1069 |
+
" <td>1988</td>\n",
|
1070 |
+
" <td>1328</td>\n",
|
1071 |
+
" <td>big_eight</td>\n",
|
1072 |
+
" <td>M</td>\n",
|
1073 |
+
" <td>Y01</td>\n",
|
1074 |
+
" <td>Oklahoma</td>\n",
|
1075 |
+
" <td>1985</td>\n",
|
1076 |
+
" <td>2024</td>\n",
|
1077 |
+
" </tr>\n",
|
1078 |
+
" <tr>\n",
|
1079 |
+
" <th>404</th>\n",
|
1080 |
+
" <td>1999</td>\n",
|
1081 |
+
" <td>1268</td>\n",
|
1082 |
+
" <td>acc</td>\n",
|
1083 |
+
" <td>M</td>\n",
|
1084 |
+
" <td>Y02</td>\n",
|
1085 |
+
" <td>Maryland</td>\n",
|
1086 |
+
" <td>1985</td>\n",
|
1087 |
+
" <td>2024</td>\n",
|
1088 |
+
" </tr>\n",
|
1089 |
+
" <tr>\n",
|
1090 |
+
" <th>1797</th>\n",
|
1091 |
+
" <td>2007</td>\n",
|
1092 |
+
" <td>1308</td>\n",
|
1093 |
+
" <td>wac</td>\n",
|
1094 |
+
" <td>M</td>\n",
|
1095 |
+
" <td>W13</td>\n",
|
1096 |
+
" <td>New Mexico St</td>\n",
|
1097 |
+
" <td>1985</td>\n",
|
1098 |
+
" <td>2024</td>\n",
|
1099 |
+
" </tr>\n",
|
1100 |
+
" <tr>\n",
|
1101 |
+
" <th>1471</th>\n",
|
1102 |
+
" <td>1988</td>\n",
|
1103 |
+
" <td>1185</td>\n",
|
1104 |
+
" <td>mac</td>\n",
|
1105 |
+
" <td>M</td>\n",
|
1106 |
+
" <td>X15</td>\n",
|
1107 |
+
" <td>E Michigan</td>\n",
|
1108 |
+
" <td>1985</td>\n",
|
1109 |
+
" <td>2024</td>\n",
|
1110 |
+
" </tr>\n",
|
1111 |
+
" <tr>\n",
|
1112 |
+
" <th>1313</th>\n",
|
1113 |
+
" <td>2021</td>\n",
|
1114 |
+
" <td>1196</td>\n",
|
1115 |
+
" <td>sec</td>\n",
|
1116 |
+
" <td>M</td>\n",
|
1117 |
+
" <td>Z07</td>\n",
|
1118 |
+
" <td>Florida</td>\n",
|
1119 |
+
" <td>1985</td>\n",
|
1120 |
+
" <td>2024</td>\n",
|
1121 |
+
" </tr>\n",
|
1122 |
+
" <tr>\n",
|
1123 |
+
" <th>881</th>\n",
|
1124 |
+
" <td>1987</td>\n",
|
1125 |
+
" <td>1424</td>\n",
|
1126 |
+
" <td>pcaa</td>\n",
|
1127 |
+
" <td>M</td>\n",
|
1128 |
+
" <td>Z01</td>\n",
|
1129 |
+
" <td>UNLV</td>\n",
|
1130 |
+
" <td>1985</td>\n",
|
1131 |
+
" <td>2024</td>\n",
|
1132 |
+
" </tr>\n",
|
1133 |
+
" <tr>\n",
|
1134 |
+
" <th>1998</th>\n",
|
1135 |
+
" <td>2006</td>\n",
|
1136 |
+
" <td>1203</td>\n",
|
1137 |
+
" <td>a_ten</td>\n",
|
1138 |
+
" <td>M</td>\n",
|
1139 |
+
" <td>W08</td>\n",
|
1140 |
+
" <td>G Washington</td>\n",
|
1141 |
+
" <td>1985</td>\n",
|
1142 |
+
" <td>2024</td>\n",
|
1143 |
+
" </tr>\n",
|
1144 |
+
" </tbody>\n",
|
1145 |
+
"</table>\n",
|
1146 |
+
"</div>"
|
1147 |
+
],
|
1148 |
+
"text/plain": [
|
1149 |
+
" Season TeamID ConfAbbrev League Seed TeamName FirstD1Season \\\n",
|
1150 |
+
"507 2016 1292 cusa M X15 MTSU 1985 \n",
|
1151 |
+
"1174 1994 1438 acc M Z07 Virginia 1985 \n",
|
1152 |
+
"1158 1998 1428 wac M X03 Utah 1985 \n",
|
1153 |
+
"638 1988 1328 big_eight M Y01 Oklahoma 1985 \n",
|
1154 |
+
"404 1999 1268 acc M Y02 Maryland 1985 \n",
|
1155 |
+
"1797 2007 1308 wac M W13 New Mexico St 1985 \n",
|
1156 |
+
"1471 1988 1185 mac M X15 E Michigan 1985 \n",
|
1157 |
+
"1313 2021 1196 sec M Z07 Florida 1985 \n",
|
1158 |
+
"881 1987 1424 pcaa M Z01 UNLV 1985 \n",
|
1159 |
+
"1998 2006 1203 a_ten M W08 G Washington 1985 \n",
|
1160 |
+
"\n",
|
1161 |
+
" LastD1Season \n",
|
1162 |
+
"507 2024 \n",
|
1163 |
+
"1174 2024 \n",
|
1164 |
+
"1158 2024 \n",
|
1165 |
+
"638 2024 \n",
|
1166 |
+
"404 2024 \n",
|
1167 |
+
"1797 2024 \n",
|
1168 |
+
"1471 2024 \n",
|
1169 |
+
"1313 2024 \n",
|
1170 |
+
"881 2024 \n",
|
1171 |
+
"1998 2024 "
|
1172 |
+
]
|
1173 |
+
},
|
1174 |
+
"execution_count": 24,
|
1175 |
+
"metadata": {},
|
1176 |
+
"output_type": "execute_result"
|
1177 |
+
}
|
1178 |
+
],
|
1179 |
+
"source": [
|
1180 |
+
"conference_df = pd.concat([\n",
|
1181 |
+
" pd.read_csv(os.path.join(DATA_DIR, \"MTeamConferences.csv\")).assign(League=\"M\"),\n",
|
1182 |
+
" pd.read_csv(os.path.join(DATA_DIR, \"WTeamConferences.csv\")).assign(League=\"W\"),\n",
|
1183 |
+
"])\n",
|
1184 |
+
"\n",
|
1185 |
+
"team_conf_seeds_df = (\n",
|
1186 |
+
" conference_df.merge(\n",
|
1187 |
+
" right=(pd.concat([\n",
|
1188 |
+
" pd.read_csv(os.path.join(DATA_DIR, \"MNCAATourneySeeds.csv\")).assign(League=\"M\"),\n",
|
1189 |
+
" pd.read_csv(os.path.join(DATA_DIR, \"WNCAATourneySeeds.csv\")).assign(League=\"W\"),\n",
|
1190 |
+
" ])),\n",
|
1191 |
+
" on=[\"League\", \"Season\", \"TeamID\"],\n",
|
1192 |
+
" )\n",
|
1193 |
+
" .merge(right=pd.read_csv(os.path.join(DATA_DIR, \"MTeams.csv\")), on=\"TeamID\")\n",
|
1194 |
+
")\n",
|
1195 |
+
"\n",
|
1196 |
+
"team_conf_seeds_df.sample(10, random_state=10)"
|
1197 |
+
]
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"cell_type": "code",
|
1201 |
+
"execution_count": 27,
|
1202 |
+
"metadata": {},
|
1203 |
+
"outputs": [
|
1204 |
+
{
|
1205 |
+
"data": {
|
1206 |
+
"text/html": [
|
1207 |
+
"<div>\n",
|
1208 |
+
"<style scoped>\n",
|
1209 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
1210 |
+
" vertical-align: middle;\n",
|
1211 |
+
" }\n",
|
1212 |
+
"\n",
|
1213 |
+
" .dataframe tbody tr th {\n",
|
1214 |
+
" vertical-align: top;\n",
|
1215 |
+
" }\n",
|
1216 |
+
"\n",
|
1217 |
+
" .dataframe thead th {\n",
|
1218 |
+
" text-align: right;\n",
|
1219 |
+
" }\n",
|
1220 |
+
"</style>\n",
|
1221 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
1222 |
+
" <thead>\n",
|
1223 |
+
" <tr style=\"text-align: right;\">\n",
|
1224 |
+
" <th></th>\n",
|
1225 |
+
" <th>TeamID</th>\n",
|
1226 |
+
" <th>Season</th>\n",
|
1227 |
+
" <th>League</th>\n",
|
1228 |
+
" <th>TeamScore min</th>\n",
|
1229 |
+
" <th>TeamScore max</th>\n",
|
1230 |
+
" <th>TeamScore std</th>\n",
|
1231 |
+
" <th>TeamScore median</th>\n",
|
1232 |
+
" <th>TeamScore mean</th>\n",
|
1233 |
+
" <th>OppScore min</th>\n",
|
1234 |
+
" <th>OppScore max</th>\n",
|
1235 |
+
" <th>...</th>\n",
|
1236 |
+
" <th>Win min</th>\n",
|
1237 |
+
" <th>Win max</th>\n",
|
1238 |
+
" <th>Win std</th>\n",
|
1239 |
+
" <th>Win median</th>\n",
|
1240 |
+
" <th>Win mean</th>\n",
|
1241 |
+
" <th>ConfAbbrev</th>\n",
|
1242 |
+
" <th>Seed</th>\n",
|
1243 |
+
" <th>TeamName</th>\n",
|
1244 |
+
" <th>FirstD1Season</th>\n",
|
1245 |
+
" <th>LastD1Season</th>\n",
|
1246 |
+
" </tr>\n",
|
1247 |
+
" </thead>\n",
|
1248 |
+
" <tbody>\n",
|
1249 |
+
" <tr>\n",
|
1250 |
+
" <th>976</th>\n",
|
1251 |
+
" <td>1387</td>\n",
|
1252 |
+
" <td>2012</td>\n",
|
1253 |
+
" <td>M</td>\n",
|
1254 |
+
" <td>58</td>\n",
|
1255 |
+
" <td>86</td>\n",
|
1256 |
+
" <td>7.354612</td>\n",
|
1257 |
+
" <td>68.0</td>\n",
|
1258 |
+
" <td>69.096774</td>\n",
|
1259 |
+
" <td>35</td>\n",
|
1260 |
+
" <td>79</td>\n",
|
1261 |
+
" <td>...</td>\n",
|
1262 |
+
" <td>0</td>\n",
|
1263 |
+
" <td>1</td>\n",
|
1264 |
+
" <td>0.425024</td>\n",
|
1265 |
+
" <td>1.0</td>\n",
|
1266 |
+
" <td>0.774194</td>\n",
|
1267 |
+
" <td>a_ten</td>\n",
|
1268 |
+
" <td>Z09</td>\n",
|
1269 |
+
" <td>St Louis</td>\n",
|
1270 |
+
" <td>1985</td>\n",
|
1271 |
+
" <td>2024</td>\n",
|
1272 |
+
" </tr>\n",
|
1273 |
+
" <tr>\n",
|
1274 |
+
" <th>834</th>\n",
|
1275 |
+
" <td>1332</td>\n",
|
1276 |
+
" <td>2019</td>\n",
|
1277 |
+
" <td>M</td>\n",
|
1278 |
+
" <td>47</td>\n",
|
1279 |
+
" <td>84</td>\n",
|
1280 |
+
" <td>11.186577</td>\n",
|
1281 |
+
" <td>72.0</td>\n",
|
1282 |
+
" <td>70.485714</td>\n",
|
1283 |
+
" <td>46</td>\n",
|
1284 |
+
" <td>90</td>\n",
|
1285 |
+
" <td>...</td>\n",
|
1286 |
+
" <td>0</td>\n",
|
1287 |
+
" <td>1</td>\n",
|
1288 |
+
" <td>0.481594</td>\n",
|
1289 |
+
" <td>1.0</td>\n",
|
1290 |
+
" <td>0.657143</td>\n",
|
1291 |
+
" <td>pac_twelve</td>\n",
|
1292 |
+
" <td>Z12</td>\n",
|
1293 |
+
" <td>Oregon</td>\n",
|
1294 |
+
" <td>1985</td>\n",
|
1295 |
+
" <td>2024</td>\n",
|
1296 |
+
" </tr>\n",
|
1297 |
+
" <tr>\n",
|
1298 |
+
" <th>305</th>\n",
|
1299 |
+
" <td>1199</td>\n",
|
1300 |
+
" <td>2011</td>\n",
|
1301 |
+
" <td>M</td>\n",
|
1302 |
+
" <td>44</td>\n",
|
1303 |
+
" <td>97</td>\n",
|
1304 |
+
" <td>13.496634</td>\n",
|
1305 |
+
" <td>69.0</td>\n",
|
1306 |
+
" <td>69.322581</td>\n",
|
1307 |
+
" <td>38</td>\n",
|
1308 |
+
" <td>89</td>\n",
|
1309 |
+
" <td>...</td>\n",
|
1310 |
+
" <td>0</td>\n",
|
1311 |
+
" <td>1</td>\n",
|
1312 |
+
" <td>0.475191</td>\n",
|
1313 |
+
" <td>1.0</td>\n",
|
1314 |
+
" <td>0.677419</td>\n",
|
1315 |
+
" <td>acc</td>\n",
|
1316 |
+
" <td>Z10</td>\n",
|
1317 |
+
" <td>Florida St</td>\n",
|
1318 |
+
" <td>1985</td>\n",
|
1319 |
+
" <td>2024</td>\n",
|
1320 |
+
" </tr>\n",
|
1321 |
+
" <tr>\n",
|
1322 |
+
" <th>124</th>\n",
|
1323 |
+
" <td>1139</td>\n",
|
1324 |
+
" <td>2016</td>\n",
|
1325 |
+
" <td>M</td>\n",
|
1326 |
+
" <td>55</td>\n",
|
1327 |
+
" <td>144</td>\n",
|
1328 |
+
" <td>16.508128</td>\n",
|
1329 |
+
" <td>78.0</td>\n",
|
1330 |
+
" <td>80.580645</td>\n",
|
1331 |
+
" <td>52</td>\n",
|
1332 |
+
" <td>88</td>\n",
|
1333 |
+
" <td>...</td>\n",
|
1334 |
+
" <td>0</td>\n",
|
1335 |
+
" <td>1</td>\n",
|
1336 |
+
" <td>0.475191</td>\n",
|
1337 |
+
" <td>1.0</td>\n",
|
1338 |
+
" <td>0.677419</td>\n",
|
1339 |
+
" <td>big_east</td>\n",
|
1340 |
+
" <td>X09</td>\n",
|
1341 |
+
" <td>Butler</td>\n",
|
1342 |
+
" <td>1985</td>\n",
|
1343 |
+
" <td>2024</td>\n",
|
1344 |
+
" </tr>\n",
|
1345 |
+
" <tr>\n",
|
1346 |
+
" <th>1305</th>\n",
|
1347 |
+
" <td>1458</td>\n",
|
1348 |
+
" <td>2019</td>\n",
|
1349 |
+
" <td>M</td>\n",
|
1350 |
+
" <td>46</td>\n",
|
1351 |
+
" <td>101</td>\n",
|
1352 |
+
" <td>12.044032</td>\n",
|
1353 |
+
" <td>69.0</td>\n",
|
1354 |
+
" <td>69.060606</td>\n",
|
1355 |
+
" <td>45</td>\n",
|
1356 |
+
" <td>84</td>\n",
|
1357 |
+
" <td>...</td>\n",
|
1358 |
+
" <td>0</td>\n",
|
1359 |
+
" <td>1</td>\n",
|
1360 |
+
" <td>0.466694</td>\n",
|
1361 |
+
" <td>1.0</td>\n",
|
1362 |
+
" <td>0.696970</td>\n",
|
1363 |
+
" <td>big_ten</td>\n",
|
1364 |
+
" <td>Z05</td>\n",
|
1365 |
+
" <td>Wisconsin</td>\n",
|
1366 |
+
" <td>1985</td>\n",
|
1367 |
+
" <td>2024</td>\n",
|
1368 |
+
" </tr>\n",
|
1369 |
+
" <tr>\n",
|
1370 |
+
" <th>1174</th>\n",
|
1371 |
+
" <td>1433</td>\n",
|
1372 |
+
" <td>2019</td>\n",
|
1373 |
+
" <td>M</td>\n",
|
1374 |
+
" <td>49</td>\n",
|
1375 |
+
" <td>90</td>\n",
|
1376 |
+
" <td>10.441658</td>\n",
|
1377 |
+
" <td>70.5</td>\n",
|
1378 |
+
" <td>71.437500</td>\n",
|
1379 |
+
" <td>36</td>\n",
|
1380 |
+
" <td>87</td>\n",
|
1381 |
+
" <td>...</td>\n",
|
1382 |
+
" <td>0</td>\n",
|
1383 |
+
" <td>1</td>\n",
|
1384 |
+
" <td>0.420013</td>\n",
|
1385 |
+
" <td>1.0</td>\n",
|
1386 |
+
" <td>0.781250</td>\n",
|
1387 |
+
" <td>a_ten</td>\n",
|
1388 |
+
" <td>W08</td>\n",
|
1389 |
+
" <td>VCU</td>\n",
|
1390 |
+
" <td>1985</td>\n",
|
1391 |
+
" <td>2024</td>\n",
|
1392 |
+
" </tr>\n",
|
1393 |
+
" <tr>\n",
|
1394 |
+
" <th>567</th>\n",
|
1395 |
+
" <td>1272</td>\n",
|
1396 |
+
" <td>2004</td>\n",
|
1397 |
+
" <td>M</td>\n",
|
1398 |
+
" <td>60</td>\n",
|
1399 |
+
" <td>94</td>\n",
|
1400 |
+
" <td>10.228604</td>\n",
|
1401 |
+
" <td>73.0</td>\n",
|
1402 |
+
" <td>73.571429</td>\n",
|
1403 |
+
" <td>48</td>\n",
|
1404 |
+
" <td>85</td>\n",
|
1405 |
+
" <td>...</td>\n",
|
1406 |
+
" <td>0</td>\n",
|
1407 |
+
" <td>1</td>\n",
|
1408 |
+
" <td>0.440959</td>\n",
|
1409 |
+
" <td>1.0</td>\n",
|
1410 |
+
" <td>0.750000</td>\n",
|
1411 |
+
" <td>cusa</td>\n",
|
1412 |
+
" <td>Y07</td>\n",
|
1413 |
+
" <td>Memphis</td>\n",
|
1414 |
+
" <td>1985</td>\n",
|
1415 |
+
" <td>2024</td>\n",
|
1416 |
+
" </tr>\n",
|
1417 |
+
" <tr>\n",
|
1418 |
+
" <th>665</th>\n",
|
1419 |
+
" <td>1292</td>\n",
|
1420 |
+
" <td>2013</td>\n",
|
1421 |
+
" <td>M</td>\n",
|
1422 |
+
" <td>45</td>\n",
|
1423 |
+
" <td>97</td>\n",
|
1424 |
+
" <td>11.877053</td>\n",
|
1425 |
+
" <td>72.0</td>\n",
|
1426 |
+
" <td>71.242424</td>\n",
|
1427 |
+
" <td>41</td>\n",
|
1428 |
+
" <td>82</td>\n",
|
1429 |
+
" <td>...</td>\n",
|
1430 |
+
" <td>0</td>\n",
|
1431 |
+
" <td>1</td>\n",
|
1432 |
+
" <td>0.364110</td>\n",
|
1433 |
+
" <td>1.0</td>\n",
|
1434 |
+
" <td>0.848485</td>\n",
|
1435 |
+
" <td>sun_belt</td>\n",
|
1436 |
+
" <td>Y11a</td>\n",
|
1437 |
+
" <td>MTSU</td>\n",
|
1438 |
+
" <td>1985</td>\n",
|
1439 |
+
" <td>2024</td>\n",
|
1440 |
+
" </tr>\n",
|
1441 |
+
" <tr>\n",
|
1442 |
+
" <th>271</th>\n",
|
1443 |
+
" <td>1186</td>\n",
|
1444 |
+
" <td>2004</td>\n",
|
1445 |
+
" <td>M</td>\n",
|
1446 |
+
" <td>49</td>\n",
|
1447 |
+
" <td>100</td>\n",
|
1448 |
+
" <td>12.568700</td>\n",
|
1449 |
+
" <td>70.0</td>\n",
|
1450 |
+
" <td>70.250000</td>\n",
|
1451 |
+
" <td>52</td>\n",
|
1452 |
+
" <td>104</td>\n",
|
1453 |
+
" <td>...</td>\n",
|
1454 |
+
" <td>0</td>\n",
|
1455 |
+
" <td>1</td>\n",
|
1456 |
+
" <td>0.503953</td>\n",
|
1457 |
+
" <td>1.0</td>\n",
|
1458 |
+
" <td>0.571429</td>\n",
|
1459 |
+
" <td>big_sky</td>\n",
|
1460 |
+
" <td>Y15</td>\n",
|
1461 |
+
" <td>E Washington</td>\n",
|
1462 |
+
" <td>1985</td>\n",
|
1463 |
+
" <td>2024</td>\n",
|
1464 |
+
" </tr>\n",
|
1465 |
+
" <tr>\n",
|
1466 |
+
" <th>325</th>\n",
|
1467 |
+
" <td>1207</td>\n",
|
1468 |
+
" <td>2011</td>\n",
|
1469 |
+
" <td>M</td>\n",
|
1470 |
+
" <td>46</td>\n",
|
1471 |
+
" <td>111</td>\n",
|
1472 |
+
" <td>14.956568</td>\n",
|
1473 |
+
" <td>69.0</td>\n",
|
1474 |
+
" <td>71.032258</td>\n",
|
1475 |
+
" <td>51</td>\n",
|
1476 |
+
" <td>102</td>\n",
|
1477 |
+
" <td>...</td>\n",
|
1478 |
+
" <td>0</td>\n",
|
1479 |
+
" <td>1</td>\n",
|
1480 |
+
" <td>0.475191</td>\n",
|
1481 |
+
" <td>1.0</td>\n",
|
1482 |
+
" <td>0.677419</td>\n",
|
1483 |
+
" <td>big_east</td>\n",
|
1484 |
+
" <td>Z06</td>\n",
|
1485 |
+
" <td>Georgetown</td>\n",
|
1486 |
+
" <td>1985</td>\n",
|
1487 |
+
" <td>2024</td>\n",
|
1488 |
+
" </tr>\n",
|
1489 |
+
" </tbody>\n",
|
1490 |
+
"</table>\n",
|
1491 |
+
"<p>10 rows × 163 columns</p>\n",
|
1492 |
+
"</div>"
|
1493 |
+
],
|
1494 |
+
"text/plain": [
|
1495 |
+
" TeamID Season League TeamScore min TeamScore max TeamScore std \\\n",
|
1496 |
+
"976 1387 2012 M 58 86 7.354612 \n",
|
1497 |
+
"834 1332 2019 M 47 84 11.186577 \n",
|
1498 |
+
"305 1199 2011 M 44 97 13.496634 \n",
|
1499 |
+
"124 1139 2016 M 55 144 16.508128 \n",
|
1500 |
+
"1305 1458 2019 M 46 101 12.044032 \n",
|
1501 |
+
"1174 1433 2019 M 49 90 10.441658 \n",
|
1502 |
+
"567 1272 2004 M 60 94 10.228604 \n",
|
1503 |
+
"665 1292 2013 M 45 97 11.877053 \n",
|
1504 |
+
"271 1186 2004 M 49 100 12.568700 \n",
|
1505 |
+
"325 1207 2011 M 46 111 14.956568 \n",
|
1506 |
+
"\n",
|
1507 |
+
" TeamScore median TeamScore mean OppScore min OppScore max ... \\\n",
|
1508 |
+
"976 68.0 69.096774 35 79 ... \n",
|
1509 |
+
"834 72.0 70.485714 46 90 ... \n",
|
1510 |
+
"305 69.0 69.322581 38 89 ... \n",
|
1511 |
+
"124 78.0 80.580645 52 88 ... \n",
|
1512 |
+
"1305 69.0 69.060606 45 84 ... \n",
|
1513 |
+
"1174 70.5 71.437500 36 87 ... \n",
|
1514 |
+
"567 73.0 73.571429 48 85 ... \n",
|
1515 |
+
"665 72.0 71.242424 41 82 ... \n",
|
1516 |
+
"271 70.0 70.250000 52 104 ... \n",
|
1517 |
+
"325 69.0 71.032258 51 102 ... \n",
|
1518 |
+
"\n",
|
1519 |
+
" Win min Win max Win std Win median Win mean ConfAbbrev Seed \\\n",
|
1520 |
+
"976 0 1 0.425024 1.0 0.774194 a_ten Z09 \n",
|
1521 |
+
"834 0 1 0.481594 1.0 0.657143 pac_twelve Z12 \n",
|
1522 |
+
"305 0 1 0.475191 1.0 0.677419 acc Z10 \n",
|
1523 |
+
"124 0 1 0.475191 1.0 0.677419 big_east X09 \n",
|
1524 |
+
"1305 0 1 0.466694 1.0 0.696970 big_ten Z05 \n",
|
1525 |
+
"1174 0 1 0.420013 1.0 0.781250 a_ten W08 \n",
|
1526 |
+
"567 0 1 0.440959 1.0 0.750000 cusa Y07 \n",
|
1527 |
+
"665 0 1 0.364110 1.0 0.848485 sun_belt Y11a \n",
|
1528 |
+
"271 0 1 0.503953 1.0 0.571429 big_sky Y15 \n",
|
1529 |
+
"325 0 1 0.475191 1.0 0.677419 big_east Z06 \n",
|
1530 |
+
"\n",
|
1531 |
+
" TeamName FirstD1Season LastD1Season \n",
|
1532 |
+
"976 St Louis 1985 2024 \n",
|
1533 |
+
"834 Oregon 1985 2024 \n",
|
1534 |
+
"305 Florida St 1985 2024 \n",
|
1535 |
+
"124 Butler 1985 2024 \n",
|
1536 |
+
"1305 Wisconsin 1985 2024 \n",
|
1537 |
+
"1174 VCU 1985 2024 \n",
|
1538 |
+
"567 Memphis 1985 2024 \n",
|
1539 |
+
"665 MTSU 1985 2024 \n",
|
1540 |
+
"271 E Washington 1985 2024 \n",
|
1541 |
+
"325 Georgetown 1985 2024 \n",
|
1542 |
+
"\n",
|
1543 |
+
"[10 rows x 163 columns]"
|
1544 |
+
]
|
1545 |
+
},
|
1546 |
+
"execution_count": 27,
|
1547 |
+
"metadata": {},
|
1548 |
+
"output_type": "execute_result"
|
1549 |
+
}
|
1550 |
+
],
|
1551 |
+
"source": [
|
1552 |
+
"# merge the team_conf_seeds_df with team attributes into the aggregated data\n",
|
1553 |
+
"\n",
|
1554 |
+
"team_reg_agg_df = team_reg_agg.merge(right=team_conf_seeds_df, on=[\"TeamID\", \"Season\", \"League\"])\n",
|
1555 |
+
"\n",
|
1556 |
+
"team_reg_agg_df.sample(10, random_state=10)"
|
1557 |
+
]
|
1558 |
}
|
1559 |
],
|
1560 |
"metadata": {
|