Data Reference

This page serves as a dataset reference. It currently shows a header for each dataset, but I'll update it with notes as I uncover important aspects of the data.

Original source: https://www.kaggle.com/c/mens-machine-learning-competition-2019/data

Data Section 1 - The Basics
Data Section 2 - Team Box Scores
- RegularSeasonDetailedResults
- NCAATourneyDetailedResults
Data Section 3 - Geography
- Cities
- GameCities
Data Section 4 - Public Rankings
- MasseyOrdinals
Data Section 5 - Play by Play
- Events_2015
- Players_2015
Data Section 6 - Supplements

Data Section 1 - The Basics

import pandas as pd
import numpy as np
from tabulate import tabulate
import os
def print_df(df):
    print(tabulate(df, headers="keys",tablefmt="html"))
print(os.listdir('../input/datafiles/'))

['SecondaryTourneyTeams.csv', 'Players_2012.csv', 'GameCities.csv', 'Events_2010.csv', 'Players_2013.csv', 'Players_2017.csv', 'Events_2011.csv', 'Events_2017.csv', 'Players_2014.csv', 'Events_2018.csv', 'NCAATourneySlots.csv', 'MasseyOrdinals.csv', 'TeamConferences.csv', 'NCAATourneyDetailedResults.csv', 'NCAATourneySeedRoundSlots.csv', 'NCAATourneySeeds.csv', 'NCAATourneyCompactResults.csv', 'TeamCoaches.csv', 'Players_2015.csv', 'Seasons.csv', 'Cities.csv', 'Players_2016.csv', 'Events_2014.csv', 'Players_2018.csv', 'Events_2012.csv', 'Events_2013.csv', 'SecondaryTourneyCompactResults.csv', 'Players_2011.csv', 'RegularSeasonCompactResults.csv', 'Events_2016.csv', 'Events_2015.csv', 'Teams.csv', 'Players_2010.csv', 'Conferences.csv', 'ConferenceTourneyGames.csv', 'TeamSpellings.csv', 'RegularSeasonDetailedResults.csv']

RegularSeasonCompactResults

RegularSeasonCompactResults = pd.read_csv('../input/datafiles/RegularSeasonCompactResults.csv')
print("size = ", RegularSeasonCompactResults.shape)
print_df(RegularSeasonCompactResults.head())

size = (156089, 8)

	Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc
0	1985	20	1228	81	1328	64	N
1	1985	25	1106	77	1354	70	H
2	1985	25	1112	63	1223	56	H
3	1985	25	1165	70	1432	54	H
4	1985	25	1192	86	1447	74	H

NCAATourneyCompactResults

NCAATourneyCompactResults = pd.read_csv('../input/datafiles/NCAATourneyCompactResults.csv')
print("size = ", NCAATourneyCompactResults.shape)
print_df(NCAATourneyCompactResults.head())

size = (2184, 8)

	Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc
0	1985	136	1116	63	1234	54	N
1	1985	136	1120	59	1345	58	N
2	1985	136	1207	68	1250	43	N
3	1985	136	1229	58	1425	55	N
4	1985	136	1242	49	1325	38	N

NCAATourneySeeds

NCAATourneySeeds = pd.read_csv('../input/datafiles/NCAATourneySeeds.csv')
print("size = ", NCAATourneySeeds.shape)
print_df(NCAATourneySeeds.head())

size = (2218, 3)

	Season	Seed	TeamID
0	1985	W01	1207
1	1985	W02	1210
2	1985	W03	1228
3	1985	W04	1260
4	1985	W05	1374

Seasons

Seasons = pd.read_csv('../input/datafiles/Seasons.csv')
print("size = ", Seasons.shape)
print_df(Seasons.head())

size = (35, 6)

	Season	DayZero	RegionW	RegionX	RegionY	RegionZ
0	1985	10/29/1984	East	West	Midwest	Southeast
1	1986	10/28/1985	East	Midwest	Southeast	West
2	1987	10/27/1986	East	Southeast	Midwest	West
3	1988	11/2/1987	East	Midwest	Southeast	West
4	1989	10/31/1988	East	West	Midwest	Southeast

Teams

Teams = pd.read_csv('../input/datafiles/Teams.csv')
print("size = ", Teams.shape)
print_df(Teams.head())

size = (366, 4)

	TeamID	TeamName	FirstD1Season	LastD1Season
0	1101	Abilene Chr	2014	2019
1	1102	Air Force	1985	2019
2	1103	Akron	1985	2019
3	1104	Alabama	1985	2019
4	1105	Alabama A&M	2000	2019

SampleSubmissionStage1

SampleSubmissionStage1 = pd.read_csv('../input/SampleSubmissionStage1.csv')
print("size = ", SampleSubmissionStage1.shape)
print_df(SampleSubmissionStage1.head())

size = (11390, 2)

	ID	Pred
0	2014_1107_1110	0.5
1	2014_1107_1112	0.5
2	2014_1107_1113	0.5
3	2014_1107_1124	0.5
4	2014_1107_1140	0.5

Data Section 2 - Team Box Scores

Variables:

WFGM - field goals made (by the winning team)
WFGA - field goals attempted (by the winning team)
WFGM3 - three pointers made (by the winning team)
WFGA3 - three pointers attempted (by the winning team)
WFTM - free throws made (by the winning team)
WFTA - free throws attempted (by the winning team)
WOR - offensive rebounds (pulled by the winning team)
WDR - defensive rebounds (pulled by the winning team)
WAst - assists (by the winning team)
WTO - turnovers committed (by the winning team)
WStl - steals (accomplished by the winning team)
WBlk - blocks (accomplished by the winning team)
WPF - personal fouls committed (by the winning team)

RegularSeasonDetailedResults

RegularSeasonDetailedResults = pd.read_csv('../input/datafiles/RegularSeasonDetailedResults.csv')
print("size = ", RegularSeasonDetailedResults.shape)
print_df(RegularSeasonDetailedResults.head())

size = (82041, 34)

	Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc	WFGM	WFGA	WFGM3	WFGA3	WFTM	WFTA	WOR	WDR	WAst	WTO	WStl	WBlk	WPF	LFGM	LFGA	LFGM3	LFGA3	LFTM	LFTA	LOR	LDR	LAst	LTO	LStl	LBlk	LPF
0	2003	10	1104	68	1328	62	N	27	58	3	14	11	18	14	24	13	23	7	1	22	22	53	2	10	16	22	10	22	8	18	9	2	20
1	2003	10	1272	70	1393	63	N	26	62	8	20	10	19	15	28	16	13	4	4	18	24	67	6	24	9	20	20	25	7	12	8	6	16
2	2003	11	1266	73	1437	61	N	24	58	8	18	17	29	17	26	15	10	5	2	25	22	73	3	26	14	23	31	22	9	12	2	5	23
3	2003	11	1296	56	1457	50	N	18	38	3	9	17	31	6	19	11	12	14	2	18	18	49	6	22	8	15	17	20	9	19	4	3	23
4	2003	11	1400	77	1208	71	N	30	61	6	14	11	13	17	22	12	14	4	4	20	24	62	6	16	17	27	21	15	12	10	7	1	14

NCAATourneyDetailedResults

NCAATourneyDetailedResults = pd.read_csv('../input/datafiles/NCAATourneyDetailedResults.csv')
print("size = ", NCAATourneyDetailedResults.shape)
print_df(NCAATourneyDetailedResults.head())

size = (1048, 34)

	Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc	NumOT	WFGM	WFGA	WFGM3	WFGA3	WFTM	WFTA	WOR	WDR	WAst	WTO	WStl	WBlk	WPF	LFGM	LFGA	LFGM3	LFGA3	LFTM	LFTA	LOR	LDR	LAst	LTO	LStl	LBlk	LPF
0	2003	134	1421	92	1411	84	N	1	32	69	11	29	17	26	14	30	17	12	5	3	22	29	67	12	31	14	31	17	28	16	15	5	0	22
1	2003	136	1112	80	1436	51	N	0	31	66	7	23	11	14	11	36	22	16	10	7	8	20	64	4	16	7	7	8	26	12	17	10	3	15
2	2003	136	1113	84	1272	71	N	0	31	59	6	14	16	22	10	27	18	9	7	4	19	25	69	7	28	14	21	20	22	11	12	2	5	18
3	2003	136	1141	79	1166	73	N	0	29	53	3	7	18	25	11	20	15	18	13	1	19	27	60	7	17	12	17	14	17	20	21	6	6	21
4	2003	136	1143	76	1301	74	N	1	27	64	7	20	15	23	18	20	17	13	8	2	14	25	56	9	21	15	20	10	26	16	14	5	8	19

Data Section 3 - Geography

Cities

Cities = pd.read_csv('../input/datafiles/Cities.csv')
print("size = ", Cities.shape)
print_df(Cities.head())

size = (421, 3)

	CityID	City	State
0	4001	Abilene	TX
1	4002	Akron	OH
2	4003	Albany	NY
3	4004	Albuquerque	NM
4	4005	Allentown	PA

GameCities

GameCities = pd.read_csv('../input/datafiles/GameCities.csv')
print("size = ", GameCities.shape)
print_df(GameCities.head())

size = (49235, 6)

	Season	DayNum	WTeamID	LTeamID	CRType	CityID
0	2010	7	1143	1293	Regular	4027
1	2010	7	1314	1198	Regular	4061
2	2010	7	1326	1108	Regular	4080
3	2010	7	1393	1107	Regular	4340
4	2010	9	1143	1178	Regular	4027

Data Section 4 - Public Rankings

MasseyOrdinals

MasseyOrdinals = pd.read_csv('../input/datafiles/MasseyOrdinals.csv')
print("size = ", MasseyOrdinals.shape)
print_df(MasseyOrdinals.head())

size = (3492320, 5)

	Season	RankingDayNum	SystemName	TeamID	OrdinalRank
0	2003	35	SEL	1102	159
1	2003	35	SEL	1103	229
2	2003	35	SEL	1104	12
3	2003	35	SEL	1105	314
4	2003	35	SEL	1106	260

Data Section 5 - Play by Play

Events_2015

Events_2015 = pd.read_csv('../input/datafiles/Events_2015.csv')
print("size = ", Events_2015.shape)
print_df(Events_2015.head())

size = (2548633, 11)

	EventID	Season	DayNum	WTeamID	LTeamID	WPoints	LPoints	ElapsedSeconds	EventTeamID	EventPlayerID	EventType
0	12703749	2015	11	1103	1420	0	0	19	1103	626476	miss3_jump
1	12703750	2015	11	1103	1420	0	0	19	1420	631228	reb_def
2	12703751	2015	11	1103	1420	0	0	27	1420	631233	assist
3	12703752	2015	11	1103	1420	0	2	27	1420	631230	made2_dunk
4	12703753	2015	11	1103	1420	2	2	59	1103	626468	made2_jump

Players_2015

Players_2015 = pd.read_csv('../input/datafiles/Players_2015.csv')
print("size = ", Players_2015.shape)
print_df(Players_2015.head())

size = (5442, 4)

	PlayerID	Season	TeamID	PlayerName
0	626432	2015	1101	ALBRIGHT_CHRISTIAN
1	626433	2015	1101	COOKE_AUSTIN
2	626434	2015	1101	GRANT_MICHAEL
3	626435	2015	1101	GREEN_DRAKE
4	626436	2015	1101	HANSON_DAVID

Data Section 6 - Supplements

ConferenceTourneyGames

Conference Tourney Games = pd.read_csv('../input/datafiles/ConferenceTourneyGames.csv')
print("size = ", Conference Tourney Games.shape)
print_df(Conference Tourney Games.head())

Traceback (most recent call last): File "", line 1, in File "/tmp/babel-7PnAYV/python-KdmXXV", line 1 Conference Tourney Games = pd.read_csv('../input/datafiles/ConferenceTourneyGames.csv') ^ SyntaxError: invalid syntax

TeamCoaches

TeamCoaches = pd.read_csv('../input/datafiles/TeamCoaches.csv')
print("size = ", TeamCoaches.shape)
print_df(TeamCoaches.head())

size = (10994, 5)

	Season	TeamID	LastDayNum	CoachName
0	1985	1102	154	reggie_minton
1	1985	1103	154	bob_huggins
2	1985	1104	154	wimp_sanderson
3	1985	1106	154	james_oliver
4	1985	1108	154	davey_whitney

Conferences

Conferences = pd.read_csv('../input/datafiles/Conferences.csv')
print("size = ", Conferences.shape)
print_df(Conferences.head())

size = (51, 2)

	ConfAbbrev	Description
0	a_sun	Atlantic Sun Conference
1	a_ten	Atlantic 10 Conference
2	aac	American Athletic Conference
3	acc	Atlantic Coast Conference
4	aec	America East Conference

TeamConferences

TeamConferences = pd.read_csv('../input/datafiles/TeamConferences.csv')
print("size = ", TeamConferences.shape)
print_df(TeamConferences.head())

size = (11241, 3)

	Season	TeamID	ConfAbbrev
0	1985	1114	a_sun
1	1985	1147	a_sun
2	1985	1204	a_sun
3	1985	1209	a_sun
4	1985	1215	a_sun

SecondaryTourneyTeams

SecondaryTourneyTeams = pd.read_csv('../input/datafiles/SecondaryTourneyTeams.csv')
print("size = ", SecondaryTourneyTeams.shape)
print_df(SecondaryTourneyTeams.head())

size = (1568, 3)

	Season	SecondaryTourney	TeamID
0	1985	NIT	1108
1	1985	NIT	1133
2	1985	NIT	1139
3	1985	NIT	1145
4	1985	NIT	1151

SecondaryTourneyCompactResults

SecondaryTourneyCompactResults = pd.read_csv('../input/datafiles/SecondaryTourneyCompactResults.csv')
print("size = ", SecondaryTourneyCompactResults.shape)
print_df(SecondaryTourneyCompactResults.head())

size = (1551, 9)

	Season	DayNum	WTeamID	WScore	LTeamID	LScore	WLoc	SecondaryTourney
0	1985	136	1151	67	1155	65	H	NIT
1	1985	136	1153	77	1245	61	H	NIT
2	1985	136	1201	79	1365	76	H	NIT
3	1985	136	1231	79	1139	57	H	NIT
4	1985	136	1249	78	1222	71	H	NIT

NCAATourneySlots

NCAATourneySlots = pd.read_csv('../input/datafiles/NCAATourneySlots.csv')
print("size = ", NCAATourneySlots.shape)
print_df(NCAATourneySlots.head())

size = (2184, 4)

	Season	Slot	StrongSeed	WeakSeed
0	1985	R1W1	W01	W16
1	1985	R1W2	W02	W15
2	1985	R1W3	W03	W14
3	1985	R1W4	W04	W13
4	1985	R1W5	W05	W12

NCAATourneySeedRoundSlots

NCAATourneySeedRoundSlots = pd.read_csv('../input/datafiles/NCAATourneySeedRoundSlots.csv')
print("size = ", NCAATourneySeedRoundSlots.shape)
print_df(NCAATourneySeedRoundSlots.head())

size = (720, 5)

	Seed	GameRound	GameSlot	EarlyDayNum	LateDayNum
0	W01	1	R1W1	136	137
1	W01	2	R2W1	138	139
2	W01	3	R3W1	143	144
3	W01	4	R4W1	145	146
4	W01	5	R5WX	152	152

Table of Contents